The convergence of computing, sensing, and communication technology will soon permit large-scale deployment of self-driving vehicles. This will in turn permit a radical transformation of traffic control technology. This paper makes a case for the importance of addressing questions of social justice in this transformation, and sketches a preliminary framework for doing so. We explain how new forms of traffic control technology have potential implications for several dimensions of social justice, including safety, sustainability, privacy, efficiency, and equal access. (...) Our central focus is on efficiency and equal access as desiderata for traffic control design. We explain the limitations of conventional traffic control in meeting these desiderata, and sketch a preliminary vision for a next-generation traffic control tailored to address better the demands of social justice. One component of this vision is cooperative, hierarchically distributed self-organization among vehicles. Another component of this vision is a priority system enabling selection of priority levels by the user for each vehicle trip in the network, based on the supporting structure of non-monetary credits. (shrink)

Smart Traffic Analysis, Monitoring, and Density Estimation System Using YOLOv8 and DeepSORT, aims to provide an efficient and real-time solution for vehicle detection, tracking, and speed estimation in traffic surveillance. The system leverages YOLOv8 (You Only Look Once version 8) for high-precision object detection and integrates DeepSORT (Simple Online and Realtime Tracker with a Deep Association Metric) for multi-object tracking, ensuring accurate identification and movement tracking of vehicles across video frames. The YOLOv8 model is trained on large-scale datasets (...) for object detection and efficiently identifies vehicles in real-time. The detected bounding boxes, confidence scores, and class labels are then passed to the DeepSORT tracking algorithm, which assigns a unique ID to each detected object and maintains its trajectory across frames. DeepSORT employs an advanced Kalman filter for motion prediction and a deep appearance descriptor to ensure robust re-identification even in complex traffic conditions. Additionally, the system integrates speed estimation by tracking the movement of each vehicle across frames, calculating the pixel displacement over time, and converting it into an approximate speed (km/h). This enables real-time monitoring of traffic flow and assists in identifying potential rule violations, such as over speeding. The system processes video streams efficiently using OpenCV, NumPy, and PyTorch, making it suitable for both offline video analysis and live surveillance feeds. The output video includes annotated bounding boxes, unique tracking IDs, and estimated vehicle speeds. This solution is highly scalable and can be deployed for traffic density estimation, congestion monitoring, and automated traffic law enforcement. By combining deep learning-based detection with robust tracking and speed estimation, this project offers a faultless, real-time, and automated approach to traffic analysis, helping urban planners and law enforcement agencies manage road safety effectively. (shrink)

Internet network optimization techniques require immediate expansion because users require fast latency performance alongside improved data transmission speed. Dynamic traffic systems operate with Machine learning algorithms that belong to the Artificial Intelligence category to power their fundamental operational tools. Through real-time data processing, AI systems can modify network pathways in operation thus generating enhanced performance together with outstanding user interface quality. Using reinforcement learning and neural networks developed by artificial intelligence enables better traffic prediction along with response abilities (...) (Zhang et al., 2020). The effectiveness of networks improves from dynamic routing since it addresses congestion issues to boost overall system data transfer speeds according to Lee et al. (2019). Large real-time data stream processing through AI systems promotes network flexibility that leads to enhanced operational results for unpredictable internet traffic (Kumar & Rao, 2020). Before displaying internet infrastructure network applications this research evaluates multiple AI traffic optimization approaches to determine their latency performance measurements including throughput rates. (shrink)

Traffic sign detection is a crucial task for autonomous vehicles, enabling safe navigation through complex environments. Traditional Convolutional Neural Networks (CNNs) are highly effective in detecting traffic signs, but their computational complexity and large memory requirements make them challenging to deploy in real-time systems, especially on resource-limited devices. Binary Neural Networks (BNNs) provide a more efficient alternative by simplifying computations and reducing memory usage, enabling faster processing, but they often sacrifice the detailed features that CNNs capture. Group Convolutional (...) Neural Networks (GCNNs), on the other hand, excel at understanding spatial relationships, such as how traffic signs relate to their surrounding environment and road networks. By combining the computational efficiency of BNNs with the spatial awareness of G-CNNs, this approach aims to deliver a solution that balances speed, efficiency, and the ability to detect traffic signs with contextual understanding. (shrink)

Traffic congestion in urban areas is a growing challenge, leading to increased travel time, fuel consumption, and environmental pollution. Traditional traffic signal systems operate on fixed timing schedules, failing to adapt to real-time traffic conditions. This research proposes an AI-based smart traffic management system that dynamically adjusts traffic signal timings using CCTV cameras and deep learning models. The system continuously monitors stopped vehicles at intersections using YOLO-based object detection and assigns adaptive green light durations based (...) on vehicle density. The proposed solution is tested using a custom-trained YOLO model, YOLOv8, and YOLOv5, comparing performance metrics such as mAP, precision, and recall. Experimental results demonstrate that the proposed model achieves improved traffic flow efficiency by reducing waiting times and prioritizing lanes with higher congestion. The system is scalable for smart cities and can integrate IoT-based sensors and real-time traffic analytics for further optimization. (shrink)

Traffic sign detection and recognition (TSDR) is a critical aspect of autonomous driving and intelligent transportation systems. Traditional methods of traffic sign detection rely on handcrafted features and classical machine learning algorithms, which often struggle to achieve high accuracy in complex real-world environments. In contrast, deep learning techniques, particularly Convolutional Neural Networks (CNNs), have shown remarkable performance in both detecting and recognizing traffic signs in diverse conditions. This paper reviews the application of deep learning methods for TSDR, (...) focusing on recent advancements in the use of CNNs, Region-based CNNs (R-CNNs), and YOLO (You Only Look Once) for real-time detection and recognition of traffic signs. We discuss the challenges, including the variability of traffic signs, environmental factors, and computational requirements, and present solutions proposed in the literature. The paper also highlights future directions for improving the robustness, accuracy, and speed of traffic sign detection and recognition systems, with an emphasis on real-time applications. (shrink)

Cyber espionage campaigns pose significant challenges to global security, exploiting vulnerabilities in network infrastructures. This research paper explores advanced network traffic analysis models tailored for detecting sophisticated cyber espionage operations. The study focuses on leveraging machine learning algorithms, anomaly detection systems, and hybrid threat detection frameworks to identify subtle yet malicious activities within network traffic. Through a review of research, this paper synthesizes key findings and outlines practical applications, offering a roadmap for enhancing cybersecurity frameworks. Findings highlight the (...) efficacy of deep learning and unsupervised models in mitigating espionage-related risks, paving the way for more robust detection systems. (shrink)

This project addresses the critical issue of traffic safety and law enforcement, specifically focusing on noncompliance with helmet laws by motorcyclists, a leading cause of fatalities in road accidents. Traditional methods of enforcing helmet laws are often ineffective due to the challenge of ensuring immediate detection and action. To solve this, we propose an automated traffic management system that integrates artificial intelligence (AI) with real-time surveillance and data monitoring to improve road safety. The core of the proposed system (...) utilizes YOLOv11 (You Only Look Once), a state-of-the-art object detection algorithm, for both helmet detection and license plate recognition. The system is designed to automatically identify motorcyclists riding without helmets and capture the vehicle's license plate. Once a violation is detected, the system sends an instant notification containing the license plate information to the traffic control officer’s email, enabling immediate enforcement actions. This automated approach significantly enhances the efficiency and speed of traffic law enforcement, while ensuring high accuracy through advanced deep learning techniques. With real-time image processing capabilities, the system can operate effectively in dynamic traffic conditions, ensuring prompt action and promoting compliance with traffic safety laws. (shrink)

Traffic sign detection and recognition (TSDR) is a critical aspect of autonomous driving and intelligent transportation systems. Traditional methods of traffic sign detection rely on handcrafted features and classical machine learning algorithms, which often struggle to achieve high accuracy in complex real-world environments. In contrast, deep learning techniques, particularly Convolutional Neural Networks (CNNs), have shown remarkable performance in both detecting and recognizing traffic signs in diverse conditions. This paper reviews the application of deep learning methods for TSDR, (...) focusing on recent advancements in the use of CNNs, Region-based CNNs (R-CNNs), and YOLO (You Only Look Once) for real-time detection and recognition of traffic signs. We discuss the challenges, including the variability of traffic signs, environmental factors, and computational requirements, and present solutions proposed in the literature. The paper also highlights future directions for improving the robustness, accuracy, and speed of traffic sign detection and recognition systems, with an emphasis on real-time applications. (shrink)

Beyond traffic congestion and urban noise lies a less visible but profound threat—air pollution linked to serious health risks [2]. A recent study published in Environmental Health Perspectives has identified a significant association between traffic-related air pollutants and an increased risk of ovarian cancer, one of the most lethal cancers affecting women [3].

Abstract—Traffic clog is a serious issue in the majority of the urban areas over the world and it has turned into a bad dream for the residents. It is brought about by postponement in flag, improper planning of traffic flagging and so on. The postponement of traffic light is hard coded and it doesn't depend on traffic. In this manner for streamlining traffic control, there is an expanding request in precise snappy programmed framework. This paper (...) is intended to build up a thickness based powerful traffic flag control. The flag timing changes naturally on detecting the traffic thickness at the junction. The microcontroller utilized in this undertaking is ARDUINO. The framework contains IR sensors (transmitter and collector) which will be mounted. It gets initiated and gets the flag as the vehicles passes near to it. (shrink)

Urban traffic congestion presents significant challenges, including prolonged travel times, increased fuel consumption, and critical delays in emergency response. Traditional traffic management systems lack the adaptability to regulate traffic flow dynamically based on real-time conditions. This system introduces an innovative approach, Automated Speed Control and Emergency Route Creation in Traffic Congestion, to improve vehicle movement and prioritize emergency transport. The system incorporates IR sensors positioned at strategic intervals to monitor traffic density up to 1 km (...) ahead of intersections. The gathered data is processed using an Arduino-based controller, categorizing congestion levels into low, medium, or high and displaying real-time updates on an LCD module, enabling drivers to make informed speed adjustments to enhance traffic flow efficiency. A crucial feature of this system is emergency vehicle prioritization, implemented through RF communication, where emergency vehicles equipped with RF transmitters transmit signals to RF receivers installed at traffic signals, allowing the system to override normal traffic control mechanisms and promptly switch the signal to green, ensuring seamless passage for emergency responders. Simultaneously, the LCD provides real-time route guidance, advising emergency vehicles in high-traffic areas to take alternative routes to reduce congestion. This solution offers a cost-effective, scalable, and intelligent method for mitigating urban traffic issues by combining real-time traffic monitoring, automated signal control, and emergency response management. Experimental validation confirms improved traffic efficiency, reduced congestion delays, and enhanced emergency response times, supporting the advancement of Intelligent Transportation Systems and contributing to the development of smart city. (shrink)

The work described in this report is motivated by the desire to test the expressive possibilities of action language C+. The Causal Calculator (CCalc) is a system that answers queries about action domains described in a fragment of that language. The Zoo World and the Traffic World have been proposed by Erik Sandewall in his Logic Modelling Workshop—an environment for communicating axiomatizations of action domains of nontrivial size. -/- The Zoo World consists of several cages and the exterior, gates (...) between them, and animals of several species, including humans. Actions in this domain include moving within and between cages, opening and closing gates, and mounting and riding animals. The Traffic World includes vehicles moving continuously between road crossings subject to a number of restrictions, such as speed limits and keeping a fixed safety distance away from other vehicles on the road. We show how to represent the two domains in the input language of CCalc, and how to use CCalc to test these representations. (shrink)

Mobile and wireless networking infrastructures are facing unprecedented loads due to increasing apps and services on mobiles. Hence, 5G systems have been developed to maximise mobile user experiences as they can accommodate large volumes of traffics with extractions of fine-grained data while offering flexible network resource controls. Potential solutions for managing networks and their security using network traffic are based on UAA (User Activity Analysis). DLTs (Deep Learning Techniques) have been recently used in network traffic analysis for better (...) performances. These previously suggested techniques for network traffic analysis typically need voluminous information on network usages. Hence, this work proposes OFedeMWOUAA (optimal federated learning-based UAA technique with Meadow Wolf Optimisation) and DNN (deep Neuron Networks) for minimizing risks of data leakages in MWNs (Mobile Wireless Networks). In the proposed OFedeMWOUAA, the need to submit data to cloud servers does not arise because it trains DLTs locally and only uploads model gradients or knowledge weights. The OFedeMWOUAA approach effectively decreases dangers to data privacies with very minor performance losses in simulations. (shrink)

This work has been designed to develop an a dynamic road signal based on an emergency with density. The sync signal automatically switches to detecting traffic density at the intersection. Traffic congestion is a serious problem in many large cities around the world and has become a nightmare for travelers in these cities. The conventional traffic light system is based on the concept of fixed time assigned to each side of the join that cannot be varied by (...) varying traffic density. The tie times assigned are fixed. But in an emergency, emergency timings change according to the distance and depth of the traffic. At the time the emergency vehicle is read by the receiver it will execute the management of the traffic light. These projects are infrared proximity sensors in the sightline configuration through the load to detect the traffic light density. The vehicle density is measured in several sectors based on the times assigned as a result. Every crossing of the emergency vehicle logs the data's to the cloud. This log signal would help with the destination acknowledgment. This synchronization will greatly reduce traffic jam. -/- . (shrink)

Mobile and wireless networking infrastructures are facing unprecedented loads due to increasing apps and services on mobiles. Hence, 5G systems have been developed to maximise mobile user experiences as they can accommodate large volumes of traffics with extractions of fine-grained data while offering flexible network resource controls. Potential solutions for managing networks and their security using network traffic are based on UAA (User Activity Analysis). DLTs (Deep Learning Techniques) have been recently used in network traffic analysis for better (...) performances. These previously suggested techniques for network traffic analysis typically need voluminous information on network usages. Hence, this work proposes OFedeMWOUAA (optimal federated learning-based UAA technique with Meadow Wolf Optimisation) and DNN (deep Neuron Networks) for minimizing risks of data leakages in MWNs (Mobile Wireless Networks). In the proposed OFedeMWOUAA, the need to submit data to cloud servers does not arise because it trains DLTs locally and only uploads model gradients or knowledge weights. The OFedeMWOUAA approach effectively decreases dangers to data privacies with very minor performance losses in simulations. (shrink)

Argues that information, in the animal behaviour or evolutionary context, is correlation/covariation. The alternation of red and green traffic lights is information because it is (quite strictly) correlated with the times when it is safe to drive through the intersection; thus driving in accordance with the lights is adaptive (causative of survival). Daylength is usefully, though less strictly, correlated with the optimal time to breed. Information in the sense of covariance implies what is adaptive; if an animal can infer (...) what the information implies, it increases its chances of survival. (shrink)

Acoustic pollution is one of the main pollutants nowadays but it is not considered of great importance in the construction field, despite some studies showing that most of acoustic pollution is produced by buildings under construction and roads with high traffic. The aim of the paper is to compare the noise levels at different time of the day in two different buildings which have different characteristics and different construction materials. The goal is to understand how well sound isolated civil (...) buildings are and how engineers have calculated the noise levels based on the specific area. The buildings are located at “Zogu Zi”, Tirana, Albania. The case study area is an area that consistently harvests noise from heavy traffic. The impact of the noise and the sound insulation materials in the wellbeing of the inhabitance is going to be analyzed too. The aim of this paper is displaying a comparative study on the actual noise levels generated by this area. It indicates the acoustic properties of the current building materials followed by a more suitable soundproof insulation. (shrink)

This paper determines the acoustic properties of external wall building materials composition. Noise pollution is one of the main pollutants nowadays but it is not considered of great importance in the construction field, despite some studies showing that greater acoustic pollution is produced by buildings under construction. The study consists of analysing two different types of buildings equipped with a different type of external masonry composition in terms of building materials. The buildings are located at “21 Dhjetori” street, Tirana, Albania. (...) Furthermore, the case study area is treated as an area that consistently harvests noise. The impact of noise pollution on the existing building materials is going to be analyzed. Those milestones will provide information regarding the noise levels, a comparison of the actual level of noise production (outdoor and indoor areas), sound transmission, and sound diminution, as well as the implementation of acoustic materials in order to improve the quality of life of the inhabitants. The selected area has the highest norms of acoustic pollution in the city according to the studies implemented by Determination of acoustic properties of building materials is an important task gaining higher importance due to the demand for suitable construction materials, located in places with high levels of noise and places with heavy traffic, such as in urban areas. The aim of this paper is to display a comparative study of the actual noise levels generated by this area. It indicates the acoustic properties of the current building materials followed by a more suitable soundproof insulation. (shrink)

Prior to this intervention the site used to be a degraded fiscal property, that functioned as a bus yard, a police legal deposit, and a restaurant parking lot. Underneath it runs the Maldonado stream culvert, covered by a concrete slab at a depth of only -20cm. Next to the site is a 5m high railroad embankment. The plot is strategically located at the end of Juan B. Justo avenue and works as a gateway to the Tres de Febrero park (also (...) known as Bosques de Palermo, the Buenos Aires’s biggest green space designed by Charles Thays in 1875). It is situated in the neighborhood of Palermo, an area that underwent a vertiginous residential and commercial expansion since the late 90´s. -/- The design approach is influenced by the adjacent urban fragments: the grounds of the Sociedad Rural Argentina, the surrounding Avenues Santa Fe-Sarmiento; the opening of Darregueyra street expected for the near future, the implementation of historic preservation guidelines for the Tres de Febrero Park, and the proposal for the development of nearby railroad yards. -/- Specifically, the project seeks to minimize the impact of the fast traffic that runs along Bullrich avenue, improving pedestrian and cycle access to the park. At the same time it defines new landscape features, utilizing the earth made available by the tunneling works of a new subway line. -/- The project comprises the structuring of an existing 800 meter long embankment and the transformation of the sidewalk into a public promenade. This is achieved through a wider sidewalk of 12m on average, which is part of a series of longitudinal stripes ranging from high speed to quiet spaces. The first band of grass and aged tipas (tipuana tipu) buffer pedestrian and cyclist from automotive traffic. Cycle traffic is organized on its own lane. The sidewalk itself contains several bays that act as urban lounges. Next, a continuous concrete bench delimits the beginning of the slope, backed by a stripe of grass that works as a soft extension. Finally, plants for contemplation are arranged as undulating traces. Rhythmic use of retaining gabions defines longitudinal segments of varying slope, unifying the spacial criterion. This series is punctuated by an amphitheater and framed by triangular plazas at the corners. -/- Material choices for hard surfaces are constrained by concerns of durability, low cost, and consistency with other ongoing public works. -/- Hard materials, as well as the plant selection needed to be low-maintenance. The palette was kept to reinforced concrete, granitic slabs, and granite stone in large size –forming retaining gabions- and as loose finishing for pavements. Likewise, the lack of a protective enclosure and of continuous surveillance dictated that urban furniture and fixtures be anti-vandalic. The stealing of these components –from inspection lids, to benches, to plants- is a common problem in urban spaces in many Latin American cities. To prevent this, fixtures must be designed according to precise specifications regarding their weight, fixing and anchoring systems, and mechanical parts. -/- Sidewalks are organized through a 6 meter grid made of granitic white slab, infilled with textured combed nonslip concrete modules. Extended bays and corner squares are finished with white and black slabs respectively. These materials are similar to another used in public spaces under construction, in the believe that it creates a collective identification of themselves along the city. -/- The continuous reinforced concrete bench is 1.10 m wide, in order to allow people to use it in non-conventional ways. Further up on the slope, undulating paths separate plant species and provide access for gardening, but are also open to use by the public. They are paved with 2 meter-long precast concrete slabs (smaller and lighter pieces were avoided to deter robbery). As they reach the gabions they connect with sloping paths covered with loose granitic stones. The gabions themselves allow the creation of varying slopes while contributing to retaining the soil, which is reinforced with geosynthetic fabric in the perimeter to avoid landslides originated by strong rains typical of the region. -/- Urban furniture is featured on the wider bays of the sidewalk and at corner plazas. It includes seats, water fountains, bicycle racks, wastepaper baskets. As a counterpoint to the linear concrete bench, groups of concrete seats are arranged informally. These seats are a reinterpretation of the dynamic BKF chair (also known as Butterfly chair), the classic Argentinean design of the 1930’ by Antonio Bonet, Juan Kurchan, and Jorge Ferrari-Hardoy. A few low concrete tables complete these spaces as authentic urban lounges. Lighting design accompanies the general features of the project and creates a new scenography emphasizing night-time usage. -/- Landscape gardening criteria is set up by a selection of various species of high-resistant pasture (grass). The higher the slope, the higher the grass, increasing the final volumetric result. Based on considering the original tipas line (tipuana tipu, a species from the north of Argentina, yellow flowering) as a vertical wall that frames the view, the horizontal stripes contain a single species each, differing in size, shade and flowering periods –adding, in the middle band, a changing color on the big green plane slope in the same chromatic range. The final configuration of the stripe sequence from bottom to top: bermuda grass, bulbine frutescens, euryops pectinatus. The upper band existing native species is reinforced with new samples: paspalum exaltatum + cortadera selloana and ipomea + thumbergia climbing the railway fence. Each sector between gabions has an automated system of drip irrigation. Near the corner plazas, several palms are planted to provide shade and identity to the street-crossing. -/- The intervention proposes an ambivalent effect on the landscape, trascending the merely ornamental by accompanying the motorist in speed, while conforting the pedestrian with spaces for contemplation and urban relax. (shrink)

Interaction between drivers and pedestrians is often facilitated by informal communicative cues, like hand gestures, facial expressions, and eye contact. In the near future, however, when semi- and fully autonomous vehicles are introduced into the traffic system, drivers will gradually assume the role of mere passengers, who are casually engaged in non-driving-related activities and, therefore, unavailable to participate in traffic interaction. In this novel traffic environment, advanced communication interfaces will need to be developed that inform pedestrians of (...) the current state and future behavior of an autonomous vehicle, in order to maximize safety and efficiency for all road users. The aim of the present review is to provide a comprehensive account of empirical work in the field of external human–machine interfaces for autonomous vehicle-to- pedestrian communication. In the great majority of covered studies, participants clearly benefited from the presence of a communication interface when interacting with an autonomous vehicle. Nevertheless, standardized interface evaluation procedures and optimal interface specifications are still lacking. (shrink)

Although Internet of Things (IoT) devices are being rapidly embraced worldwide, there are still several security concerns. Due to their limited resources, they are susceptible to malware assaults such as Gafgyt and Mirai, which have the ability to interrupt networks and infect devices. This work looks into methods based on machine learning to identify and categorize malware in IoT network activity. A dataset comprising both malware and benign traffic is used to assess different classification techniques, such as Random Forest, (...) XGBoost, Logistic Regression, etc., for multi-class malware detection. After a great deal of empirical testing, XGBoost comes out on top, providing 99.9% recall and accuracy. Both known and unknown malware can be detected by the trained model with remarkable precision. The use of transfer learning, where the XGBoost model is used as a basis for the rapid construction of new malware detection models, is one of the major innovations put forth. This makes it possible to quickly adjust to new dangers. More information about how real-time network traffic can be monitored with the help of the created model to find irregularities and sound the alarm. An intelligent and proactive security solution for IoT environments is offered by the machine learning technique that is being discussed. This is an efficient defense against malware because of its high accuracy, low false positive rate, real-time detection capability, and adaptability to new malware varieties changing risks associated with IoT. The suggested methods will assist in securing susceptible IoT devices and networks from obstructive malware assaults. (shrink)

Emergency response times play a critical role in saving lives, especially in urban settings where traffic congestion and unpredictable events can delay ambulance arrivals. This paper explores a novel framework for smart route optimization for emergency vehicles, leveraging artificial intelligence (AI), Internet of Things (IoT) technologies, and dynamic traffic analytics. We propose a real-time adaptive routing system that integrates machine learning (ML) for predictive modeling and IoT-enabled communication with traffic infrastructure. The system is evaluated using simulated urban (...) environments, achieving a 35% reduction in response times compared to traditional methods. This work lays the foundation for future advancements in intelligent emergency systems and their integration into smart cities. (shrink)

Recognition plays an important role in the employee’s job satisfaction and performance, yet many employees remain unnoticed for their hard work, effort and contributions. This study investigates the consequences of unrecognized efforts on the job satisfaction of Traffic Management Group (TMG) employees in the Municipality of Lemery, Batangas. Through qualitative method and case study approach, a semi-structured interviews were conducted with selected TMG employees to explore their experiences and perceptions about their experiences of lack of recognition at work. The (...) thematic analysis revealed that TMG employees often experience frustration, burnout, and decreased motivation due to a lack of acknowledgment for their efforts. The key issues identified include unpaid overtime, handling emergencies without proper resources, and taking on responsibilities beyond their job scope without recognition. And the findings indicate that insufficient recognition contributes to emotional exhaustion, reduced morale, and decreased job performance. This study underscores the need for a structured employee recognition program to improve job satisfaction and workplace morale. Therefore, an action plan is proposed to enhance recognition practices, emphasizing the importance of appreciation, fair compensation, and improved working conditions. This research provides insights for local government units and organizations aiming to enhance employee engagement through recognition initiatives. (shrink)

Developing countries have always relied on motorcycles as their primary mode of transportation, but unfortunately, the number of motorcycle accidents has been on the rise in recent years. One of the leading causes of fatalities in these accidents is the lack of helmet usage by motorcyclists. To ensure that motorcyclists wear helmets, traditional methods include manual monitoring by traffic police at intersections or the use of CCTV footage to identify those not wearing a helmet. However, these methods require significant (...) human effort and intervention. This system proposes an automated approach to identify non-helmeted motorcyclists and retrieve their license plate information from CCTV footage. The system first differentiates moving objects as motorcycles or non-motorcycles. For classified motorcyclists, the system identifies whether they are wearing helmets or not. If the motorcyclist is not wearing a helmet, the system extracts the license plate number using an OCR algorithm. In this project CNN and yolo algorithms are used for recognition of person with and without helmet as well as triple riding detection. The violated person number plate is detected if its visible. (shrink)

Emergency response times play a critical role in saving lives, especially in urban settings where traffic congestion and unpredictable events can delay ambulance arrivals. This paper explores a novel framework for smart route optimization for emergency vehicles, leveraging artificial intelligence (AI), Internet of Things (IoT) technologies, and dynamic traffic analytics. We propose a real-time adaptive routing system that integrates machine learning (ML) for predictive modeling and IoT-enabled communication with traffic infrastructure. The system is evaluated using simulated urban (...) environments, achieving a 35% reduction in response times compared to traditional methods. This work lays the foundation for future advancements in intelligent emergency systems and their integration into smart cities. (shrink)

The rapid expansion of cloud computing and big data has placed significant demands on data center networks (DCNs). Traditional network architectures, with their rigid infrastructure and complex management, struggle to cope with the scalability, flexibility, and automation required in modern data centers. Software-Defined Networking (SDN) has emerged as a transformative paradigm that decouples the control and data planes, enabling centralized, programmable, and more efficient network management. This survey explores the application of SDN in data center network management, covering architectural models, (...) traffic engineering, security enhancements, and virtualization support. We examine existing literature, highlight key developments, and identify future directions for research and deployment in SDN-based data centers. (shrink)

: Software-Defined Networking (SDN) has emerged as a transformative paradigm in modern data center network (DCN) management, offering unprecedented levels of flexibility, scalability, and automation. This survey presents a thorough review of SDN-based applications specifically tailored for data center environments. We explore how SDN enables dynamic resource allocation, efficient traffic engineering, enhanced security frameworks, and automated fault management, addressing critical challenges faced by traditional DCNs. Various architectural models, controller platforms, and implementation strategies are examined to highlight their impact on (...) performance optimization and operational efficiency. Furthermore, the survey categorizes SDN applications based on their primary objectives, such as load balancing, energy efficiency, security enhancement, and network virtualization. Challenges associated with SDN adoption in data centers—such as scalability limitations, controller placement issues, and interoperability with legacy systems—are also discussed. In addition, recent advancements and emerging trends, including the integration of machine learning with SDN and the rise of intent-based networking, are outlined to provide insights into future research directions. This comprehensive study aims to serve as a valuable resource for researchers and practitioners seeking to understand the evolving landscape of SDN applications in data center network management. (shrink)

Software-Defined Networking (SDN) is transforming traditional networking paradigms by decoupling the control plane from the data plane, enabling more flexible and programmable network management. Load balancing, a crucial task in SDN environments, ensures efficient resource utilization and avoids congestion by distributing network traffic effectively across resources. This paper explores the role of Artificial Intelligence (AI) in enhancing load balancing techniques within SDN frameworks. We review various AIdriven strategies, including machine learning, reinforcement learning, and deep learning, assessing their benefits and (...) challenges in optimizing SDN performance. The survey highlights state-of-the-art approaches, identifies key research gaps, and proposes directions for future investigations. (shrink)

Road traffic accidents are one of the leading causes of death and severe injury globally, primarily due to delayed emergency responses. The time immediately following a traumatic injury, known as the "golden hour," is critical for administering medical aid, significantly enhancing survival rates. To address the urgent need for rapid response mechanisms, this paper presents an advanced Internet of Things (IoT)-based Automotive Accident Detection and Intimation (ADI) system. The proposed system leverages a combination of embedded and connected smartphone sensors (...) to detect vehicular collisions and assess accident severity with high precision. A microcontroller unit interfaces with various sensors—such as accelerometers, gyroscopes, and environmental monitors—as well as GPS technology to track vehicle movement and conditions. Upon detecting a probable accident, the system autonomously triggers an alert mechanism that transmits real-time data, including GPS coordinates and sensor information, to a centralized server. This information is promptly relayed to emergency response units such as ambulances, police stations, hospitals, and fire departments, along with notifying a pre- registered emergency contact. The system architecture ensures minimal human intervention, thereby reducing response time and increasing reliability. Additionally, the platform includes a remote server interface that enables real-time monitoring and analysis of incident data. By enhancing accident detection accuracy and reducing the latency in emergency communication, the ADI system has the potential to save lives and minimize post-accident trauma. This research contributes to the advancement of intelligent transportation systems and paves the way for safer, smarter vehicular technologies. (shrink)

. The surge in data traffic strains backbone networks, causing congestion, latency, and higher costs. This project proposes a data compression system tailored for backbone networks, utilizing Lempel-Ziv (LZ) and Huffman encoding to enhance processing time and network efficiency. Adaptive features allow the system to respond to network conditions, ensuring scalability and cost-effectiveness. The primary objective is to optimize network performance by reducing data packet size, increasing throughput, lowering latency, and reducing energy use.

We live in a world of crowds and corporations, artworks and artifacts, legislatures and languages, money and markets. These are all social objects — they are made, at least in part, by people and by communities. But what exactly are these things? How are they made, and what is the role of people in making them? In The Ant Trap, Brian Epstein rewrites our understanding of the nature of the social world and the foundations of the social sciences. Epstein explains (...) and challenges the three prevailing traditions about how the social world is made. One tradition takes the social world to be built out of people, much as traffic is built out of cars. A second tradition also takes people to be the building blocks of the social world, but focuses on thoughts and attitudes we have toward one another. And a third tradition takes the social world to be a collective projection onto the physical world. Epstein shows that these share critical flaws. Most fundamentally, all three traditions overestimate the role of people in building the social world: they are overly anthropocentric. Epstein starts from scratch, bringing the resources of contemporary metaphysics to bear. In the place of traditional theories, he introduces a model based on a new distinction between the grounds and the anchors of social facts. Epstein illustrates the model with a study of the nature of law, and shows how to interpret the prevailing traditions about the social world. Then he turns to social groups, and to what it means for a group to take an action or have an intention. Contrary to the overwhelming consensus, these often depend on more than the actions and intentions of group members. (shrink)

In the current digital environment, cyberattacks continue to pose a serious risk and difficulty. Internet of Things (IoT) devices are becoming more and more vulnerable due to security problems like ransomware, malware, poor encryption, and IoT botnets. These flaws may result in ransom demands, data tampering, illegal access, and system risks. Creating strong cybersecurity procedures for contemporary smart environments is essential to resolving these problems. This strategy uses proactive network traffic monitoring to spot any dangers in the Internet of (...) Things ecosystem. Our approach is to improve Smart Environments' security and awareness of potential threats. Two IoT gateways were used to examine the effectiveness and performance of a deep neural network (DNN) model. The results were promising: the model caused an average increase of less than 30 kb/s in network bandwidth and a mere 2% rise in CPU usage. Additionally, memory and power consumption were minimal, with 0.42 GB and 0.2 GB of memory usage for NVIDIA Jetson and Raspberry Pi devices, respectively, and an average 13.5% increase in power consumption per device. The machine learning models achieved nearly 93% detection accuracy and a 92% F1 score on the datasets used. Our framework demonstrates an effective and efficient method for detecting malware and attacks in Smart Environments. (shrink)

Quilty-Dunn et al.'s wide-ranging defense of the Language of Thought Hypothesis (LoTH) argues that vision traffics in abstract, structured representational formats. We agree: Vision, like language, is compositional – just as words compose into phrases, many visual representations contain discrete constituents that combine in systematic ways. Here, we amass evidence extending this proposal, and explore its implications for how vision interfaces with the rest of the mind.

In 2012, a major traffic safety organization tasked the MIT AgeLab with developing a data-driven system for rating the effectiveness of new technologies intended to improve safety. Such a system was envisioned as having the potential to educate and guide consumers towards more confident and strategic purchasing decisions, ideally encouraging adoption of technologies with demonstrated safety benefit. In addition, an evaluation of the status and extent of existing data was seen as a way of identifying research gaps in the (...) state of knowledge about safety systems. The focus was on technologies as a class, not on a rating review of individual vehicle model implementations. As conceptualized, the system aimed to complement traditional NCAP style ratings as well as to provide consumers with transparent information on early stage and often improving safety technologies. Development of the rating system and identification of data was undertaken in consultation with a range of academic, industrial, consumer, NGO, and governmental experts as well as with representatives of many of the major automotive manufacturers and suppliers. -/- A key observation that emerged was that data on objectively demonstrable real-world benefits were generally sparse and often lower than expectations based on theoretical considerations, simulation studies, or pre-production evaluations. A number of experts and industry representatives expressed some surprise at both the divergence between theoretical and observed benefits and the relative scarcity of data upon which to make objective assessments, while others were quite aware of these issues and the need for the development of objective data under real-world operating conditions. A number of factors that might be relevant to understanding why such differences between expected and observed benefits exist were identified. One outcome of this effort was the founding of the Advanced Vehicle Technology (AVT) consortium to collect and examine objective data under naturalistic driving conditions of how drivers interact with, engage or don’t engage, various production safety and driver assistance systems. This ongoing effort is contributing to insights concerning actual benefits and reasons for benefit gaps. -/- Drawing from our initial work, as well as newer sources of data, we argue that the evaluation and rating of safety and driver assistance technologies for informing the consumer and the public at large should consider both theoretical potential and existing demonstrated benefit of specific technologies. This position is increasingly relevant as the effectiveness of many newer technologies have the potential to actually improve over the lifecycle of a vehicle through software updates. The emphasis on ratings based on observed benefit for actual drivers under real-world conditions is proposed to be complementary, rather than competing with, ratings focused largely on controlled test track evaluations of engineered capability. In addition, a case is made for providing ratings that assesses benefit relative to overall crash, injury, and fatality rates – and in relation to the specific scenario / crash event type that a given technology is intended to address. This approach should aid consumers in considering the extent to which a specific technology is or is not relevant to their particular driving needs. (shrink)

Bayesianism is our leading theory of uncertainty. Epistemology is defined as the theory of knowledge. So “Bayesian Epistemology” may sound like an oxymoron. Bayesianism, after all, studies the properties and dynamics of degrees of belief, understood to be probabilities. Traditional epistemology, on the other hand, places the singularly non-probabilistic notion of knowledge at centre stage, and to the extent that it traffics in belief, that notion does not come in degrees. So how can there be a Bayesian epistemology?

Experiences justify beliefs about our environment. Sometimes the justification is immediate: seeing a red light immediately justifies believing there is a red light. Other times the justification is mediate: seeing a red light justifies believing one should brake in a way that is mediated by background knowledge of traffic signals. How does this distinction map onto the distinction between what is and what isn't part of the content of experience? Epistemic egalitarians think that experiences immediately justify whatever is part (...) of their content. Epistemic elitists deny this and think that there is some further constraint the contents of experience must satisfy to be immediately justified. Here I defend epistemic elitism, propose a phenomenological account of what the further constraint is, and explore the resulting view's consequences for our knowledge of other minds, and in particular for perceptual theories of this knowledge. (shrink)

Crossing the road within the traffic system is an example of an action human agents perform successfully day-to-day in complex systems. How do they perform such successful actions given that the behaviour of complex systems is often difficult to predict? The contemporary literature contains two contrasting approaches to the epistemology of complex systems: an analytic and a post-modern approach. We argue that neither approach adequately accounts for how successful action is possible in complex systems. Agents regularly perform successful actions (...) without obeying (explicit or implicit) algorithmic rules (as the analytic approach suggests) and without an existential leap to action (as the post-modern approach suggests). We offer an alternative: A common-sense pragmatist epistemology, one that focuses on the kind of actions making up most agents’ successful moment-to-moment actions in complex systems. Successful actions obtain when agents apply ceteris paribus rules-of-thumb during predictive and decisional practices while achieving some desired goal. (shrink)

What are rules? In this paper I develop a view of regulative rules which takes them to be a distinctive normative kind occupying a middle ground between orders and normative truths. The paradigmatic cases of regulative rules that I’m interested in are social rules like rules of etiquette and legal rules like traffic rules. On the view I’ll propose, a rule is a general normative content that is in force due to human activity: enactment by an authority or acceptance (...) by a community. Rules are unlike orders in being not necessarily communicative, not an expression’s of the giver’s will, not evaluable for sincerity, and in that they have propositional content. And they’re unlike normative truths in that they’re themselves not even truth-evaluable (though their contents are). This is because rules qua things that are in force are not like constatives which have a mind to world direction of fit, but more like performatives. Furthermore, they differ from normative truths in that their normativity is isolated from their background justification and is therefore not dependent on contributory notions like reasons coming together in a weighing explanation. As such, they occupy a middle ground between orders and normative truths, much like in H. L. A. Hart’s opinion law occupies a middle ground between “coercion” and “morality” (Hart 1961/1994). I also illustrate the virtues of this understanding of rules by showing how proper appreciation of how they differ from normative truths helps us defuse a common objection to Hart’s practice theory of rules. (shrink)

In the rapidly evolving digital landscape, cyber threats are becoming increasingly sophisticated, making traditional security measures inadequate. Advanced Threat Detection (ATD) leveraging Artificial Intelligence (AI)-driven anomaly detection systems offers a proactive approach to identifying and mitigating cyber threats in real time. This paper explores the integration of AI, particularly machine learning (ML) and deep learning (DL) techniques, in anomaly detection to enhance cybersecurity defenses. By analyzing vast amounts of network traffic, user behavior, and system logs, AI-driven models can identify (...) deviations from normal patterns, enabling early threat detection and prevention. These systems excel in detecting zero-day attacks, insider threats, and advanced persistent threats (APTs), which often bypass conventional rule-based security mechanisms. Additionally, we discuss the challenges of AI-based anomaly detection, including false positives, model interpretability, and adversarial attacks. The findings emphasize the need for continuous learning and adaptive security frameworks to ensure robust cyber threat detection. The study concludes that AIdriven anomaly detection significantly enhances threat intelligence and response capabilities, making it a vital component of modern cybersecurity strategies. (shrink)

Urban parking systems are a significant contributor to traffic congestion and driver frustration, with studies showing that up to 30% of urban traffic is caused by drivers searching for parking. Traditional parking systems often lack real-time data and adaptability, leading to inefficiencies such as overfilled lots and underutilized spaces. This paper explores how Artificial Intelligence (AI) and IoT technologies can optimize urban parking by enabling real-time parking space detection, demand forecasting, and dynamic pricing. By integrating data from IoT (...) sensors, traffic systems, and mobile applications, cities can reduce congestion, improve parking availability, and enhance the overall urban mobility experience. Experimental results demonstrate significant improvements in parking efficiency, traffic flow, and user satisfaction, offering a sustainable blueprint for smart urban parking systems. (shrink)

Cloud computing has transformed data management by providing scalable and on-demand services, but its open and shared infrastructure makes it highly vulnerable to sophisticated cyber threats. Traditional Intrusion Detection Systems (IDS) struggle with dynamic and large-scale cloud environments due to high false positives, limited adaptability, and computational overhead. To address these challenges, this paper proposes an AI-driven Intrusion Detection System (AI-IDS) that leverages deep learning models, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, to analyze network (...) class='Hi'>traffic, detect anomalies, and identify advanced cyber threats with high accuracy. Unlike rule-based IDS, which rely on static signatures, our model continuously learns from real-time data, improving detection rates while reducing false alarms. The proposed AI-IDS is optimized for cloud infrastructure, ensuring low-latency threat detection, minimal computational burden, and real-time adaptability to emerging attack patterns. Experimental validation on benchmark datasets demonstrates significant improvements in accuracy, precision, and scalability, making AI-powered IDS a crucial innovation in cloud security. (shrink)

This paper presents a puzzle or antinomy about the role of properties in causation. In theories of properties, a distinction is often made between determinable properties, like red, and their determinates, like scarlet (see Armstrong 1978, volume II). Sometimes determinable properties are cited in causal explanations, as when we say that someone stopped at the traffic light because it was red. If we accept that properties can be among the relata of causation, then it can be argued that there (...) are good reasons for allowing that some of these are determinable properties. On the other hand, there are strong arguments in the metaphysics of properties to treat properties as sparse in David Lewis’s (1983) sense. But then it seems that we only need to believe in the most determinate properties: particular shades of colour, specific masses, lengths and so on. And if we also agree with Lewis that sparse properties are ‘the ones relevant to causal powers’ (1983: 13) it seems we must conclude that if properties are relevant to causation at all, then all of these are determinate properties. I call this ‘the antinomy of determinable causation’. On the one hand, we have a good argument for the claim that determinable properties can be causes, if any properties are. I call this the Thesis. But on the other hand, we have a good argument for the claim that only the most determinate properties can be causes, if any properties are. I call this the Antithesis. Clearly, we need to reject either the Thesis or the.. (shrink)

Rae Langton and Caroline West argue that pornography silences women by presupposing misogynistic attitudes, such as that women enjoy being raped. More precisely, they claim that a somewhat infamous pictorial, ‘Dirty Pool’, makes such presuppositions, and that it is typical in this respect. I argue for four claims. (1) There are empirical reasons to doubt that women are silenced in the way that Langton and West claim they are. (2) There is no evidence that very much pornography makes the sorts (...) of presuppositions that Langton and West's explanation of silencing requires it to make. (3) Even ‘Dirty Pool’, for all its other problems, does not make such presuppositions. (4) Langton and West misread ‘Dirty Pool’ because they do not take proper account of the fact that pornography often traffics in sexual fantasy. The broader lesson is that we need to read pornography more sensitively if we are to understand its capacity to shape socio‐sexual norms (for good or for ill). (shrink)

In many areas, technology has facilitated many things, diagnosing diseases, regulating traffic and teaching students in schools rely on Intelligent systems to name a few. At present, traditional classroom-based education is no longer the most appropriate in schools. From here, the idea of intelligent e-learning for students to increase their culture and keep them updated in life began. E-learning has become an ideal solution, relying on artificial intelligence, which has a footprint in this through the development of systems based (...) on education without a teacher taking into account the individual differences of students. This study describes intelligent tutoring system for teaching the Data Manipulation Language (DML) Commands Using SQLite to non IT students to overcome the difficulties they face. The System was built as education system by using the researcher own authoring tool that based on mobile and web App. The basic idea of this system is a systematic introduction into the concept of Database and its DML query. The system presents the topic of DML Commands, help student to execute what they are learn from the system content using the practical part of the system and administers automatically adapted at run time to the student’s individual growth. The system was assessed by a group of teachers and students and the outcome showed as 91% from the database specialists, 94% from Diploma students group and 89% from the secondary school students group. (shrink)

In this chapter, I critically examine issues relevant to the construction and reality of social categories, focusing on issues concerning conceptual schemes and conventionalism. Conceptual schemes (‘paradigms,’ ‘linguistic frameworks,’ ‘forms of life’) are systems of concepts that organize and give (intersubjective) meaning to empirical experience. In discussions about the construction of social categories, a common assumption is that social categories and kinds (e.g., ‘money,’ ‘marriage,’ ‘liberal’) require the presupposition of a conceptual scheme that gives meaning to those terms. One prominent (...) position in social ontology (Lewis, 1969, Gilbert 1989, 2014, Searle 1995) holds that the reality of social categories is grounded in a conventionalist conceptual scheme: social categories are conventionally accepted categories that reflect explicit or implicit agreements within a community. According to this view, the reality of social categories and kinds is established (and maintained) by contingent and arbitrary conventional decisions about social categories (e.g., laws about legal tender, marriage laws, the one-drop rule). Conventions can be understood as social customs (e.g., rules governing traffic, marriage laws, institutionalized rules about sex and gender) that serve some human purpose or interest. They are important for the establishment and maintenance of social norms (see Bicchieri 2006, 2017). -/- The chapter proceeds as follows. In section 2, I examine the general idea of conceptual schemes, focusing on Kuhn’s influential theory of paradigms. While Kuhn’s position implies a conceptual relativity and anti-realism (or instrumentalism) about scientific concepts, Davidson and Popper challenge the Kuhnian orthodoxy that the presence of conceptual schemes implies conceptual relativity or ‘incommensurability’ of competing conceptual schemes. I argue that a key difference between scientific and social conceptual schemes is that the former are oriented towards describing nature, whereas the latter are oriented towards social utility or usefulness. In section 3, I examine some foundational works in social ontology—focusing on the accounts of Lewis, Gilbert, and Searle—that hold that social categories are grounded by a conventionalist conceptual scheme. These accounts of social categories imply that the reality of social categories is constituted by (or grounded in) social conventions, which ultimately reflect (or are anchored by) explicit or implicit community-level agreements. In section 4, I survey some prominent accounts of social human categories, focusing on the views of Hacking, Khalidi, Mallon, Haslanger, and Ásta. A common tendency in these accounts is the portrayal of social categories as social to the extent that they are conventionally determined. This suggests that the proper contrast class for social categories is natural categories (as opposed to individual categories or innate categories). (shrink)

The prospective introduction of autonomous cars into public traffic raises the question of how such systems should behave when an accident is inevitable. Due to concerns with self-interest and liberal legitimacy that have become paramount in the emerging debate, a contractarian framework seems to provide a particularly attractive means of approaching this problem. We examine one such attempt, which derives a harm minimisation rule from the assumptions of rational self-interest and ignorance of one’s position in a future accident. We (...) contend, however, that both contractarian approaches and harm minimisation standards are flawed, due to a failure to account for the fundamental difference between those ‘involved’ and ‘uninvolved’ in an impending crash. Drawing from classical works on the trolley problem, we show how this notion can be substantiated by reference to either the distinction between negative and positive rights, or to differences in people’s claims. By supplementing harm minimisation with corresponding constraints, we can develop crash algorithms for autonomous cars which are both ethically adequate and promise to overcome certain significant practical barriers to implementation. (shrink)

Through modern driver assistant systems, algorithmic decisions already have a significant impact on the behavior of vehicles in everyday traffic. This will become even more prominent in the near future considering the development of autonomous driving functionality. The need to consider ethical principles in the design of such systems is generally acknowledged. However, scope, principles and strategies for their implementations are not yet clear. Most of the current discussions concentrate on situations of unavoidable crashes in which the life of (...) human beings is existentially affected. In this paper, we argue that ethical considerations should be mandatory for any algorithmic decision of autonomous vehicles, instead of a limitation to hazard situations. Such an ethically aligned behavior is relevant because autonomous vehicles, like any other traffic participants, operate in a shared public space, where every behavioral decision impacts the operational possibilities of others. These possibilities concern the fulfillment of a road-user’s safety, utility and comfort needs. We propose that, to operate ethically in such space, an autonomous vehicle will have to take its behavior decisions according to a just distribution of operational possibilities among all traffic participants. Using an application on a partially-autonomous prototype vehicle, we describe how to apply and implement concepts of distributive justice to the driving environment and demonstrate the impact on its behavior in comparison to an advanced but egoistic decision maker. (shrink)