We recall, "a priori," numeric energy expression: -/- Energy Numbers -/- $\begin{gathered}\mathcal{V}=\left\{f \mid \exists\left\{e_1, e_2, \ldots, e_n\right\} \in E \cup R\right\} \\ \mathcal{V}=\left\{f \mid \exists\left\{e_1, e_2, \ldots, e_n\right\} \in E, \text { and }: E \mapsto r \in R\right\} \\ \mathcal{V}=\left\{E \mid \exists\left\{a_1, \ldots, a_n\right\} \in E, E \not \neg r \in R\right\}\end{gathered}$ -/- We now introduce the set of optimized energy numbers: -/- ($H_a \in \mathcal{H}$ or $P^n = NP$ or $(P,\mathcal{L},F) = NP$). -/- Based on our formulation (...) of the bi-objective optimization task, we can make the following mathematical inferences: -/- 1. If the optimized energy numbers set $\mathcal{N}_H$ is equal to the original energy numbers set $\mathcal{E}$, i.e. $\mathcal{N}_H = \mathcal{E}$, then the maximum optimization score is achieved, i.e. the bi-objective optimization task is solved. This implies that there exists at least one solution to the optimization problem and $H_a \in \mathcal{H}$, where $H_a$ is the hypothesis that states the existence of an efficient algorithm to solve the problem. -/- 2. If the optimized energy numbers set $\mathcal{N}_H$ is a subset of the original energy numbers set $\mathcal{E}$, i.e. $\mathcal{N}_H \subset \mathcal{E}$, then the optimization score is less than the maximum score. This indicates that there may exist more efficient algorithms to solve the problem, and the hypothesis $H_a$ is still possible. -/- 3. If the optimized energy numbers set $\mathcal{N}_H$ is a superset of the original energy numbers set $\mathcal{E}$, i.e. $\mathcal{N}_H \supset \mathcal{E}$, then the optimization score is higher than the maximum score. This implies that the optimization problem may be easier than initially thought, and $P^n = NP$, or at least some form of $NP$-completeness. -/- 4. If the optimized energy numbers set $\mathcal{N}_H$ is a strict subset of the original energy numbers set $\mathcal{E}$, i.e. $\mathcal{N}_H \subsetneq \mathcal{E}$, and $P^n \neq NP$, then it can be concluded that the optimization problem is complex but there may exist algorithms that can efficiently approximate the solution. -/- 5. If the optimized energy numbers set $\mathcal{N}_H$ is empty, i.e. $\mathcal{N}_H = \emptyset$, then it can be inferred that the optimization problem is infeasible, i.e. no efficient algorithm exists to solve it, and $H_a$ is false. -/- 6. Comparing the two objectives in the bi-objective optimization task, we can make the following statements: -/- - The first objective, $\frac{\delta_{v(f)}(\mathbf{v}, \mathbf{w_{max}})} {\langle \mathbf{v_f}, \mathbf{1_f}\rangle}$, measures the efficiency of the algorithm and its ability to find low energy numbers. - The second objective, $\rho(\mathcal{N}_H)$, measures the accuracy of the algorithm in terms of loss and perplexity on the HyperLanguageModel. - Therefore, by optimizing both objectives simultaneously, we aim to find an efficient algorithm that also minimizes the loss and perplexities on the HyperLanguageModel. - If the optimization task is successfully solved, then the algorithm achieves both high efficiency and high accuracy. This would imply that the algorithm is able to find low energy numbers effectively and also generalize well on the HyperLanguageModel. -/- The optimized energy numbers aim to find a set of numbers $\mathbf{v}$ that maximize the bi-objective optimization task, while also minimizing the loss and perplexity of the HyperLanguageModel. This is achieved by finding the set of numbers that have the highest delta value and the lowest perplexity, resulting in a more optimized and efficient set of energy numbers. -/- By comparing the optimized energy numbers to the original set, we can see that the optimized set may have a higher delta value and a lower perplexity, indicating that it is a better set of numbers for the given task. This shows that the optimized energy numbers have successfully achieved their goal of maximizing efficiency while minimizing loss and perplexity. (shrink)

Underwater Wireless Sensor Networks (UWSNs) are pivotal for various applications, including oceanographic data collection, environmental monitoring, and naval operations. However, the harsh underwater environment poses challenges in designing efficient routing protocols, especially concerning energy consumption and data transmission reliability. This paper proposes an optimized depth-based routing protocol for energy-aware data transmission in UWSNs, focusing on minimizing energy usage while ensuring robust data delivery. The protocol dynamically adjusts transmission power based on node depth and residual energy, reducing communication overhead and (...) prolonging network lifetime. (shrink)

In this paper, we explore the properties and optimization techniques related to polyhedral cones and energy numbers with a focus on the cone of positive semidefinite matrices and efficient computation strategies for kernels. In Part (a), we examine the polyhedral nature of the cone of positive semidefinite matrices, , establishing that it does not form a polyhedral cone for due to its infinite dimensional characteristics. In Part (b), we present an algorithm for efficiently computing the kernel function on-the-fly, leveraging a (...) polyhedral description of the convex hull generated by the feature mappings and . By restructuring the problem and using gradient-based optimization techniques, our approach minimizes memory usage and computational overhead, thus enabling scalable computation. Through examples and visualizations, we demonstrate the practical applications and efficiency of the proposed algorithm in optimizing these kernel computations. (shrink)

The ever-evolving landscape of cyber threats necessitates robust and adaptable intrusion detection systems (IDS) capable of identifying both known and emerging attacks. Traditional IDS models often struggle with detecting novel threats, leading to significant security vulnerabilities. This paper proposes an optimized intrusion detection model using Support Vector Machine (SVM) algorithms tailored to detect known and innovative cyberattacks with high accuracy and efficiency. The model integrates feature selection and dimensionality reduction techniques to enhance detection performance while reducing computational overhead. By (...) leveraging advanced optimization techniques such as Grid Search and Particle Swarm Optimization (PSO), the proposed SVM-based IDS achieves superior classification results. (shrink)

he Sensor-Integrated IoT Solution for Precision Farming is designed to optimize agricultural water usage and enhance crop productivity through real-time monitoring and automated control. The system uses an Arduino and NodeMCU to collect and process data from various sensors, including a pH sensor for water quality, a DHT11 sensor for temperature and humidity, and a soil moisture sensor to assess soil conditions. Sensor data is displayed on an LCD and uploaded to the ThingSpeak platform for remote monitoring. When the pH (...) value deviates from the optimal range, the system activates two water pumps—first, the outlet pump to remove poorquality water, followed by the inlet pump to introduce fresh water. Relays control the operation of the pumps, ensuring efficient water management. By integrating IoT technology, this system enhances water conservation, reduces manual intervention, and improves overall agricultural efficiency, making precision farming more sustainable and effective. (shrink)

Driver drowsiness is a significant factor contributing to road accidents, resulting in severe injuries and fatalities. This study presents an optimized approach for detecting driver drowsiness using machine learning techniques. The proposed system utilizes real-time data to analyze driver behavior and physiological signals to identify signs of fatigue. Various machine learning algorithms, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Random Forest, are explored for their efficacy in detecting drowsiness. The system incorporates an optimization technique—such as Genetic (...) Algorithms (GA) or Particle Swarm Optimization (PSO)—to enhance the accuracy and response time of the detection process. The integration of optimization methods ensures that the model adapts to various driving conditions and individual differences, providing a more reliable and robust detection mechanism. (shrink)

Cardiovascular diseases (CVD) represent a significant cause of morbidity and mortality worldwide, necessitating early detection for effective intervention. This research explores the application of machine learning (ML) algorithms in predicting cardiovascular diseases with enhanced accuracy by integrating optimization techniques. By leveraging data-driven approaches, ML models can analyze vast datasets, identifying patterns and risk factors that traditional methods might overlook. This study focuses on implementing various ML algorithms, such as Decision Trees, Random Forest, Support Vector Machines, and Neural Networks, optimized (...) through techniques like hyperparameter tuning, cross-validation, and feature selection to improve prediction accuracy. (shrink)

In the modern digital era, cloud storage has become an indispensable service due to its scalability, accessibility, and cost-effectiveness. However, with the vast amount of sensitive information stored on cloud platforms, ensuring data security and privacy remains a critical challenge. Traditional encryption techniques, while secure, often hinder efficient data retrieval, especially when using keyword searches. To address this, attribute-based keyword search (ABKS) offers a promising solution by allowing secure, fine-grained access control and efficient keyword searches over encrypted data. This paper (...) delves into the integration of optimization techniques within ABKS to enhance search efficiency and data security in cloud storage environments. We explore various optimization strategies, such as index compression, query processing enhancement, and encryption optimization, which aim to reduce computational overhead while maintaining robust security measures. Through a comprehensive analysis, the paper illustrates how these techniques can significantly improve the performance of cloud storage systems, ensuring both security and usability. Experimental results demonstrate that optimized ABKS not only accelerates search queries but also reduces storage costs, making it a viable solution for modern cloud storage challenges. Future research directions include exploring advanced machine learning algorithms for predictive search optimizations and further improving the resilience of ABKS against emerging security threats. (shrink)

The exponential growth of cloud storage has necessitated advanced security measures to protect sensitive data from unauthorized access. Traditional encryption methods provide a layer of security, but they often lack the robustness needed to address emerging threats. This paper introduces an optimized framework for secure cloud storage that integrates data encryption, decryption, and dispersion using cutting-edge optimization techniques. The proposed model enhances data security by first encrypting the data, then dispersing it across multiple cloud servers, ensuring that no single (...) server holds the complete dataset. Decryption occurs only when the dispersed data fragments are reassembled, which adds an additional layer of security. We also explore various optimization algorithms to improve the efficiency of encryption and dispersion processes, thereby reducing computational overhead while maintaining high security. The implementation of this framework is evaluated on multiple cloud platforms, demonstrating its effectiveness in safeguarding data with minimal performance impact. Future enhancements may include integrating machine learning algorithms to predict and adapt to new security threats in real time, further solidifying the reliability of cloud storage solutions. (shrink)

Urban green spaces are vital for mitigating climate change, enhancing biodiversity, and improving citizen well-being. However, traditional methods of designing and managing these spaces often lack the precision and scalability needed to address modern urban challenges. This paper explores how Artificial Intelligence (AI) and IoT technologies can optimize urban green spaces in smart cities. By integrating satellite imagery, soil sensors, and machine learning models, cities can dynamically monitor plant health, predict ecological impacts, and design green zones that maximize biodiversity and (...) sustainability. Experimental results demonstrate improvements in air quality, heat island reduction, and community engagement, offering a blueprint for AI-driven ecological urban planning. (shrink)

As the Internet of Things (IoT) continues to expand, ensuring secure and efficient data storage and retrieval becomes a critical challenge. IoT devices, often constrained by limited computational resources, require lightweight encryption protocols that balance security and performance. This paper presents an optimized encryption protocol designed specifically for lightweight, searchable data in IoT environments. The proposed protocol utilizes advanced optimization techniques to enhance the efficiency and security of searchable encryption, enabling rapid data retrieval without compromising the integrity and confidentiality (...) of the data. The protocol leverages a hybrid cryptographic approach, combining symmetric and asymmetric encryption, to ensure robust protection against unauthorized access while maintaining low computational overhead. Furthermore, the implementation of an optimized keyword indexing mechanism facilitates fast and accurate search operations, making the protocol well-suited for real-time IoT applications. Extensive experiments were conducted using various IoT datasets to evaluate the performance of the proposed protocol in terms of encryption speed, search efficiency, and overall security. The results demonstrate that the optimized encryption protocol significantly outperforms existing methods, offering a scalable solution that meets the stringent requirements of IoT systems. This research contributes to the field by providing a practical and secure encryption solution that addresses the unique challenges of IoT environments, paving the way for more secure and efficient IoT networks. (shrink)

The project offers a text summarization tool that can handle content from PDFs, DOCX, and plain text. It incorporates extractive and abstractive summarization methods for creating abridged summaries. The extractive method applies sentence tokenization in the selection of important sentences, whereas the abstractive method utilizes a pre-trained Hugging Face model. The tool also has a Streamlit-based user interface for handling multiple file uploads and direct input of text. Strong error handling and text cleansing improve dependability and summarization accuracy, so the (...) tool is useful for applications needing effective text analysis like in healthcare, research, and legal arenas. (shrink)

Electrocardiogram (ECG) signal analysis is a critical task in healthcare for diagnosing cardiovascular conditions such as arrhythmias, heart attacks, and other heart-related diseases. With the growth of Internet of Things (IoT) networks, real-time ECG monitoring has become possible through wearable devices and sensors, providing continuous patient health monitoring. However, real-time ECG signal analysis in IoT environments poses several challenges, including data latency, limited computational power of IoT devices, and energy constraints. This paper proposes a framework for Optimized Machine Learning (...) Algorithms designed to analyze ECG signals in real time within IoT networks. The proposed system leverages lightweight machine learning models, including support vector machines (SVM) and convolutional neural networks (CNNs), optimized to run efficiently on low-power IoT devices while maintaining high accuracy. The system addresses the computational limitations of IoT devices by employing edge computing techniques that distribute the processing load between IoT devices and edge servers. Additionally, data compression and feature extraction techniques are applied to reduce the size of the data transmitted over the network, thereby minimizing latency and bandwidth usage. This paper reviews the current advancements in real-time ECG analysis, explores the challenges posed by IoT environments, and presents the optimized machine learning algorithms that enhance real-time monitoring of heart health. The system is evaluated for its performance in terms of accuracy, energy efficiency, and data transmission speed, showing promising results in improving real-time ECG signal analysis in resource-constrained IoT networks. (shrink)

Hybrid Electric Vehicles (HEVs) are rapidly gaining popularity due to their potential to reduce greenhouse gas emissions and fuel consumption. However, the high-power density of HEV motors and batteries generates substantial heat during operation, which, if not effectively managed, can reduce system efficiency and shorten component lifespans. Efficient thermal management is critical for ensuring the optimal performance of HEV powertrains, specifically motors and batteries. Liquid cooling systems, with their superior heat transfer capabilities, have emerged as an effective solution for managing (...) the thermal loads in HEV systems. (shrink)

The integration and security of healthcare data are crucial challenges in the modern healthcare system, driven by the increasing digitization of medical records, diagnostic data, and patient health information. The need for secure, interoperable, and efficient data management systems has become essential, especially as healthcare providers strive to offer better care and reduce operational inefficiencies. Traditional systems often suffer from issues like data breaches, lack of interoperability, and inefficient data handling processes, resulting in compromised data integrity and patient privacy.

Our findings reveal that implementing accelerated computing can achieve substantial improvements, often reducing computation times by more than 60% compared to traditional sequential methods. This paper details the experimental setup, including algorithm selection and parallelization techniques, and discusses the role of memory bandwidth and latency in achieving optimal performance. Based on the analysis, we propose a streamlined methodology to guide the deployment of accelerated computing frameworks in various industries. Concluding with a discussion on future directions, we highlight potential advancements in (...) hardware architectures and software optimizations that could further augment computational efficiency and scalability in accelerated computing. (shrink)

The accuracy levels of VGG19 and 3D CNN are compared using the performance metrics. This comparison helps in identifying which model performs better in the task of facial reconstruction from distorted images. Visualizing the results in the form of a graph provides a clear and concise way to understand the comparative performance of the algorithms. The ultimate goal of this project is to develop a system that can accurately reconstruct distorted faces, which can be invaluable in identifying accident victims or (...) assisting in medical treatments. By providing a reliable method for facial reconstruction, this technology can potentially save lives and improve outcomes for individuals involved in accidents. (shrink)

Hybrid Electric Vehicles (HEVs) have gained significant popularity due to their reduced environmental impact and fuel efficiency. However, the complex integration of electrical and mechanical systems in HEVs presents significant cooling challenges. A robust cooling system is essential to maintain optimal performance and extend the lifespan of powertrains and battery systems. This paper explores the development of an advanced cooling system designed specifically for HEV powertrains, leveraging modern technologies such as heat exchangers, liquid cooling, and smart thermal management systems. The (...) proposed system uses adaptive cooling mechanisms that adjust based on real-time vehicle operating conditions to maximize efficiency and reduce energy consumption. Additionally, machine learning algorithms are integrated into the cooling system for predictive maintenance, identifying potential issues before they arise. By optimizing thermal management, the system ensures higher efficiency, improved vehicle performance, and a longer life for HEV components. This paper presents an analysis of the current cooling technologies in HEVs, identifies gaps in their functionality, and proposes a novel cooling framework that addresses these limitations, making HEVs more viable for long-term sustainability and performance. Keywords: Hybrid Electric Vehicle (HEV), Powertrain. (shrink)

Binary addition forms the backbone of computational arithmetic, serving as a core operation in Digital Signal Processing, arithmetic and logic units, microprocessors, and microcontrollers. As adders are integral to these applications, ongoing research aims to optimize their performance. The propagation of the carry bit significantly affects an adder's delay, making its design critical. In this paper, we propose and evaluate an efficient design for a 64-bit parallel prefix adder (PPA), a high-speed adder that balances performance with resource utilization. Unlike ripple (...) carry adders (RCA), which suffer from serial delay issues, and carry look-ahead adders (CLA), which mitigate delay at the cost of increased complexity, PPAs leverage prefix operations for fast and efficient addition. Our proposed PPA achieves a critical path delay of 23.21 ns, demonstrating high-speed performance with low power consumption and reduced area overhead. The design was developed using Verilog HDL, simulated, and synthesized using the Xilinx ISE tool. These results highlight the PPA's suitability for VLSI designs, offering an optimal trade off between speed, area, and power for modern computational systems. (shrink)

The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify and classify cyberbullying (...) behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. T. (shrink)

The EdTech revolution in India has emerged as a transformative force, particularly during and after the COVID-19 pandemic, when traditional education systems faced unprecedented disruptions. While digital technologies have unlocked new opportunities for teaching and learning, they have also exposed systemic inequities and deepened the existing digital divide. This paper examines how EdTech is reshaping India's education landscape by addressing these challenges, with a focus on both the opportunities it presents and the barriers it creates.

The world's leading cause of morbidity and death is cardiovascular diseases (CVD), which makes early detection essential for successful treatments. This study investigates how optimization techniques can be used with machine learning (ML) algorithms to forecast cardiovascular illnesses more accurately. ML models can evaluate enormous datasets by utilizing data-driven techniques, finding trends and risk factors that conventional methods can miss. In order to increase prediction accuracy, this study focuses on adopting different machine learning algorithms, including Decision Trees, Random Forest, Support (...) Vector Machines, and Neural Networks, that have been tuned using strategies including hyper parameter selection, crossvalidation, and feature selection. (shrink)

In the modern digital era, cloud storage has become an indispensable service due to its scalability, accessibility, and cost-effectiveness. However, with the vast amount of sensitive information stored on cloud platforms, ensuring data security and privacy remains a critical challenge. Traditional encryption techniques, while secure, often hinder efficient data retrieval, especially when using keyword searches. To address this, attribute-based keyword search (ABKS) offers a promising solution by allowing secure, fine-grained access control and efficient keyword searches over encrypted data.

t: Wireless Sensor Networks (WSNs) have become increasingly prevalent in various applications, ranging from environmental monitoring to smart cities. However, the limited energy resources of sensor nodes pose significant challenges in maintaining network longevity and data transmission efficiency. Duty-cycled WSNs, where sensor nodes alternate between active and sleep states to conserve energy, offer a solution to these challenges but introduce new complexities in data transmission.

The ever-evolving landscape of cyber threats necessitates robust and adaptable intrusion detection systems (IDS) capable of identifying both known and emerging attacks. Traditional IDS models often struggle with detecting novel threats, leading to significant security vulnerabilities. This paper proposes an optimized intrusion detection model using Support Vector Machine (SVM) algorithms tailored to detect known and innovative cyberattacks with high accuracy and efficiency. The model integrates feature selection and dimensionality reduction techniques to enhance detection performance while reducing computational overhead.

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)

We propose a systematic workflow for automating the storage and retrieval process, starting from the identification of the stock to its precise placement and retrieval within the storage facility. The design also addresses potential challenges such as robot mobility, collision avoidance, and space optimization. Performance metrics, including accuracy, time efficiency, and system scalability, are measured using simulation-based experiments in a controlled environment. The results show significant improvements in operational efficiency compared to traditional stock management approaches. This integration paves the way (...) for future advancements in fully automated warehouses, reducing the need for human labor and increasing reliability. Finally, we discuss potential enhancements, including AI-based decision-making algorithms, multi-robot collaboration, and integration with Internet of Things (IoT) for real-time data analysis and continuous system improvement. (shrink)

The framework leverages a hybrid cloud architecture, combining the scalability of public clouds with the security of private clouds. By employing a combination of client-side hashing, metadata indexing, and machine learning-based duplicate detection, the framework achieves significant storage savings without compromising data integrity. Real-time testing on a hybrid cloud setup demonstrated a 65% reduction in storage needs and a 40% improvement in data retrieval times. Additionally, the system employs blockchain for immutable logging of deduplication activities, enhancing transparency and traceability. This (...) study concludes with an evaluation of the deduplication framework's impact on cost efficiency, system performance, and potential scalability. Future enhancements aim to integrate multi-cloud interoperability and advanced compression algorithms to further refine storage management. (shrink)

Monitoring soil pH levels forms the backbone of precision agriculture with regard to maximizing crop health and yield. The paper discusses an IoT-based solution, specifically designed for continuous soil pH testing in digital farming. It has pH sensors placed strategically around the agricultural fields such that the information regarding the acidity or alkalinity of the soil is available in real-time. The pH information will be transmitted to the central IoT gateway. Here, the information is processed, and via communication of cloud-based (...) platforms, it is further stored and analyzed. So, by checking variations in soil pH, the system provides actionable information to farmers. Thus, by adjusting soil treatments like lime or fertilizers better, it enhances crop performance. The response uses mobile and web interfaces that support automated pH testing with automatically designed data visualization. This allows farmers the chance to decide from remote sites about imminent and proper fluctuations in soil pH by the use of historical data analysis and models from machine learning. One part of the effectuality of this proactive approach would be that soil quality is improved while unnecessary chemical use is avoided, therefore reducing the resulting costs of farming with sustainability considerations. By limiting itself to pH value testing, this solution increases the farmland's productivity with less wastage of resources. (shrink)

Cloud storage's scalability, accessibility, and affordability have made it essential in the digital age. Data security and privacy remain a major issue due to the large volume of sensitive data kept on cloud services. Traditional encryption is safe but slows data recovery, especially for keyword searches. Secure, fine-grained access control and quick keyword searches over encrypted data are possible using attribute-based keyword search (ABKS). This study examines how ABKS might optimize search efficiency and data security in cloud storage systems. We (...) examine index compression, query processing improvement, and encryption optimization to decrease computational cost and preserve security. (shrink)

Computed tomography (CT) films are used to construct cross-sectional pictures of a particular region of the body by using many x-ray readings that were obtained at various angles. There is a general agreement in the medical community at this time that chest CT is the most accurate approach for identifying COVID-19 disease. It was demonstrated that chest CT had a higher sensitivity than reverse transcription polymerase chain reaction (RT-PCR) for the detection of COVID-19 illness. This article presents gray-level co-occurrence matrix (...) (GLCM) texture feature extraction and convolutional neural network (CNN)-enabled optimized diagnostic model for COVID-19 detection. In this diagnostic model, CT scan images of patients are given as input. Firstly, GLCM algorithm is used to extract texture features from the CT scan images. This feature extraction helps in achieving higher classification accuracy. Classification is performed using CNN. It achieves higher accuracy than the k-nearest neighbors (KNN) algorithm and multi-layer preceptor (MLP). The accuracy of GLCM based CNN is 99%, F1 score is 99% and the recall rate is also 98%. CNN has achieved better results than MLP and KNN algorithms for COVID-19 detection. (shrink)

Driver drowsiness is a significant factor contributing to road accidents, resulting in severe injuries and fatalities. This study presents an optimized approach for detecting driver drowsiness using machine learning techniques. The proposed system utilizes real-time data to analyze driver behavior and physiological signals to identify signs of fatigue. Various machine learning algorithms, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Random Forest, are explored for their efficacy in detecting drowsiness. The system incorporates an optimization technique—such as Genetic (...) Algorithms (GA) or Particle Swarm Optimization (PSO)—to enhance the accuracy and response time of the detection process. The integration of optimization methods ensures that the model adapts to various driving conditions and individual differences, providing a more reliable and robust detection mechanism. Data from multiple sources, including camera feeds and wearable sensors, are used to train and validate the models, ensuring a comprehensive understanding of drowsiness indicators. (shrink)

: Driver drowsiness is a significant factor contributing to road accidents, resulting in severe injuries and fatalities. This study presents an optimized approach for detecting driver drowsiness using machine learning techniques. The proposed system utilizes real-time data to analyze driver behavior and physiological signals to identify signs of fatigue. Various machine learning algorithms, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Random Forest, are explored for their efficacy in detecting drowsiness. The system incorporates an optimization technique—such as (...) Genetic Algorithms (GA) or Particle Swarm Optimization (PSO)—to enhance the accuracy and response time of the detection process. The integration of optimization methods ensures that the model adapts to various driving conditions and individual differences, providing a more reliable and robust detection mechanism. Data from multiple sources, including camera feeds and wearable sensors, are used to train and validate the models, ensuring a comprehensive understanding of drowsiness indicators. (shrink)

The rapid expansion of artificial intelligence (AI) and machine learning (ML) workloads has created an urgent demand for high-performance, low-latency network architectures capable of handling massive data transfers with minimal congestion. Traditional Ethernet solutions often struggle with inefficiencies, packet loss, and network congestion, limiting AI scalability and performance. Arista’s Etherlink AI platform introduces an advanced AIoptimized Ethernet architecture designed to enhance congestion avoidance, maximize bandwidth utilization, and provide lossless data transmission for high-performance computing environments. By integrating real-time telemetry, intelligent packet (...) scheduling, and adaptive routing mechanisms, Etherlink AI ensures optimal network efficiency, enabling seamless AI workload execution. This paper examines the platform’s core architectural components, congestion control strategies, and impact on next-generation AI infrastructure, highlighting its role in addressing the critical challenges of modern AI-driven networking. (shrink)

The framework leverages a hybrid cloud architecture, combining the scalability of public clouds with the security of private clouds. By employing a combination of client-side hashing, metadata indexing, and machine learning-based duplicate detection, the framework achieves significant storage savings without compromising data integrity. Real-time testing on a hybrid cloud setup demonstrated a 65% reduction in storage needs and a 40% improvement in data retrieval times. Additionally, the system employs blockchain for immutable logging of deduplication activities, enhancing transparency and traceability. This (...) study concludes with an evaluation of the deduplication framework's impact on cost efficiency, system performance, and potential scalability. Future enhancements aim to integrate multi-cloud interoperability and advanced compression algorithms to further refine storage management. (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)

The world's leading cause of morbidity and death is cardiovascular diseases (CVD), which makes early detection essential for successful treatments. This study investigates how optimization techniques can be used with machine learning (ML) algorithms to forecast cardiovascular illnesses more accurately. ML models can evaluate enormous datasets by utilizing data-driven techniques, finding trends and risk factors that conventional methods can miss. In order to increase prediction accuracy, this study focuses on adopting different machine learning algorithms, including Decision Trees, Random Forest, Support (...) Vector Machines, and Neural Networks, that have been tuned using strategies including hyper parameter selection, crossvalidation, and feature selection. (shrink)

This study examines how ABKS might optimize search efficiency and data security in cloud storage systems. We examine index compression, query processing improvement, and encryption optimization to decrease computational cost and preserve security. After a thorough investigation, the article shows how these methods may boost cloud storage system performance, security, and usability. Tests show that improved ABKS speeds up search searches and lowers storage costs, making it a viable cloud storage alternative. Exploring sophisticated machine learning algorithms for predictive search improvements (...) a. (shrink)

Data preparation, feature engineering, model training, and performance evaluation are all part of the study methodology. To ensure reliable and broadly applicable models, we utilize optimization techniques like Grid Search and Genetic Algorithms to precisely adjust model parameters. Features including age, blood pressure, cholesterol levels, and lifestyle choices are employed as inputs for the machine learning models in the dataset, which consists of patient medical information. The predictive capacity of the model is evaluated using evaluation measures, such as accuracy, precision, (...) recall, F1-score, and the area under the ROC curve (AUC-ROC). Our findings show that improved machine learning models perform better than conventional methods, offering trustworthy forecasts that can help medical practitioners with early diagnosis and individualized treatment planning. (shrink)

The predictive capacity of the model is evaluated using evaluation measures, such as accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC). Our findings show that improved machine learning models perform better than conventional methods, offering trustworthy forecasts that can help medical practitioners with early diagnosis and individualized treatment planning. In order to achieve even higher predicted accuracy, the study's conclusion discusses the significance of its findings for clinical practice as well as future improvements that might be (...) made, like adding wearable device data in real-time or investigating deep learning techniques. (shrink)

AI can be leveraged to shape and promote community commitments to interdisciplinary responsibility and ethics across three domains: humans, the environment, and technology.

In today’s fast moving insurance environment, efficient claim management is a vital business practice to improve operational effectiveness and provide an exceptional customer experience. Based on the first notice of loss (FNOL), Guidewire Claim Center, the leading claims management platform, gives insurers the thorough, scalable, and customizable option to accelerate the claims process from FNOL to final resolution. In this paper, we explore how insurers adapt Guidewire Claim Center to enable effective utilization of Guidewire Claim Center to optimize and transform (...) their claim management process, making better decisions, and delivering better customer experience. Advanced automation features, their role in reducing manual footprint, and the integration of the platform with external systems for a smooth data flow and analytics driven insights are key things covered. Finally we see real world case studies detailing where Guidewire's predictive analytics are in use for fraud detection, expedited claims processing and building proactive relationships between the claimant and the Carrier. We also look at best practices for implementation and ways to work around typical problems, including change management, system customization, and others. Framed around the dual aims of operational efficiency and customer satisfaction, this blueprint offers practical advice for insurers navigating a more and more digitalized industry. Guidewire Claim Center is agile, flexible foundations that can help insurers transform their claims operations, while also creating lasting trust and loyalty with policyholders. (shrink)

The concept of a sales pipeline has gone through major changes due to the use of machine learning (ML) in managing sales pipelines. Analyzing intelligent sales pipelines that utilize ML algorithms for maximizing the deal closure in Salesforce environments constitutes the focus of this paper. The following discussion extends our prior work by specifically considering how the present approach of predictive modeling, NLP, and clustering contribute to more accurate predictions, better customer understanding, and enhanced targeting. To assess the performance of (...) the proposed approach we consider history data analysis, technological background of Salesforce platforms and proper integration of machine learning tools. This we illustrate with hypothetical business cases where the net deals closure rates have been achieved with an improvement in customer satisfaction by 30%. It also provides challenges like data quality, algorithms bias and scalability that have been discussed in this paper as well. Inferences made lay the foundation for organizations to employ intelligent pipelines to support credible sales development. (shrink)

In the privacy preserving data mining, the utility mining casts a very vital part. The objective of the suggested technique is performed by concealing the high sensitive item sets with the help of the hiding maximum utility item first (HMUIF) algorithm, which effectively evaluates the sensitive item sets by effectively exploiting the user defined utility threshold value. It successfully attempts to estimate the sensitive item sets by utilising optimal threshold value, by means of the grey wolf optimisation (GWO) algorithm. The (...) optimised threshold value is then checked for its performance analysis by employing several constraints like the HF, MC and DIS. The novel technique is performed and the optimal threshold resultant item sets are assessed and contrasted with those of diverse optimisation approaches. The novel HMUIF considerably cuts down the calculation complication, thereby paving the way for the enhancement in hiding performance of the item sets. (shrink)

Plastic waste is a significant environmental problem for almost all countries; therefore, protecting the environment from the problem is crucial. The most sensible solution to these problems is substituting the natural aggregates with substantial plastic waste in various building materials. This study aimed to optimise the mixed design ratio of cement brick containing plastic waste as aggregate replacement. Plastic cement brick mixtures were prepared by the incorporation of four different types of plastic waste such as polyethylene terephthalate (PET), high-density polyethylene, (...) low-density polyethylene and polypropylene into cement bricks with different cement contents (150, 300 and 450 g) and plastic replacement percentages (0, 3 and 6%). Compressive strength and water absorption of the plastic cement bricks were analysed using a statistical model through the response surface methodology. It revealed the optimum cement brick mixed design is C3-1% PET with the compressive strength of 27.50 MPa and water absorption of 1.16%. The optimised plastic cement brick also satisfied the general ASTM C62-17 requirements for building bricks despite the higher porosity observed by the scanning electron microscopy. The results from Fourier transform infrared spectroscopy analysis also showed that the addition of the plastic waste into cement brick was unlikely to modify the chemical compound within the cement brick mixtures. Thus, the proposed mathematical model can predict the required hardened properties of plastic cement bricks and could lead to greater utilisation of plastic waste in building materials. (shrink)

The environmental costs and energy constraints have become emerging issues for the future development of Machine Learning (ML) and Artificial Intelligence (AI). So far, the discussion on environmental impacts of ML/AI lacks a perspective reaching beyond quantitative measurements of the energy-related research costs. Building on the foundations laid down by Schwartz et al., 2019 in the GreenAI initiative, our argument considers two interlinked phenomena, the gratuitous generalisation capability and the future where ML/AI performs the majority of quantifiable inductive inferences. The (...) gratuitous generalisation capability refers to a discrepancy between the cognitive demands of a task to be accomplished and the performance (accuracy) of a used ML/AI model. If the latter exceeds the former because the model was optimised to achieve the best possible accuracy, it becomes inefficient and its operation harmful to the environment. The future dominated by the non-anthropic induction describes a use of ML/AI so all-pervasive that most of the inductive inferences become furnished by ML/AI generalisations. The paper argues that the present debate deserves an expansion connecting the environmental costs of research and ineffective ML/AI uses (the issue of gratuitous generalisation capability) with the (near) future marked by the all-pervasive Human-Artificial Intelligence Nexus. (shrink)

Humans are uncontroversially better than other species at learning from their peers. A key example of this is imitation, the ability to reproduce both the means and ends of others’ behaviours. Imitation is critical to the acquisition of a number of uniquely human cultural and cognitive traits. However, while authors largely agree on the importance of imitation, they disagree about the origins of imitation in humans. Some argue that imitation is an adaptation, connected to the ‘Mirror Neuron System’ that evolved (...) to facilitate action understanding and the learning of social behaviours. Others argue that imitation is a cultural practice learned in childhood, and that there is no evidence that it evolved genetically. We offer a third alternative that is consistent with both data that the human brain is optimised for imitation, and consistent with its being substantially learned. We hypothesise that at some point in human history humans underwent natural selection for two imitation-relevant abilities – specifically, (i) the tendency to be more attentive to our peers, and (ii) fine motor skill in the manual and oro-facial domains. These changes enabled us to excel at both learning to imitate, and learning by imitating. (shrink)

We address the most fundamental yet routinely ignored issue in economics today: that of distributive impact of the monetary system on the real economy. By re-examining the logical implications of token re-presentation of value and Irving Fisher’s theory of exchange, we argue that producers of value incur incidental expropriation of wealth associated with the deflationary effect that new value supply has on the purchasing power of money. In order to remedy the alleged inequity we propose a value-added negative tax (VANT) (...) based on net individual contribution to the economic output, which is structured as a negative tax function geared to profits derived from eligible productive activities in consideration of their estimated deflationary impact. We show that an adequately optimised VANT can be non-inflationary and have zero net cost to the public. Furthermore, economic output stands to improve due to direct incentivisation of value creation, making the proposed scheme not only politically feasible but economically desirable. The proposal advances the principle of ‘fair money’, where all forms of economic value are attributed to their rightful owners prior to any positive taxation. (shrink)

YouTube has been implicated in the transformation of users into extremists and conspiracy theorists. The alleged mechanism for this radicalizing process is YouTube’s recommender system, which is optimized to amplify and promote clips that users are likely to watch through to the end. YouTube optimizes for watch-through for economic reasons: people who watch a video through to the end are likely to then watch the next recommended video as well, which means that more advertisements can be served to them. (...) This is a seemingly innocuous design choice, but it has a troubling side-effect. Critics of YouTube have alleged that the recommender system tends to recommend extremist content and conspiracy theories, as such videos are especially likely to capture and keep users’ attention. To date, the problem of radicalization via the YouTube recommender system has been a matter of speculation. The current study represents the first systematic, pre-registered attempt to establish whether and to what extent the recommender system tends to promote such content. We begin by contextualizing our study in the framework of technological seduction. Next, we explain our methodology. After that, we present our results, which are consistent with the radicalization hypothesis. Finally, we discuss our findings, as well as directions for future research and recommendations for users, industry, and policy-makers. (shrink)

Detailed examinations of scientific practice have revealed that the use of idealized models in the sciences is pervasive. These models play a central role in not only the investigation and prediction of phenomena, but in their received scientific explanations as well. This has led philosophers of science to begin revising the traditional philosophical accounts of scientific explanation in order to make sense of this practice. These new model-based accounts of scientific explanation, however, raise a number of key questions: Can the (...) fictions and falsehoods inherent in the modeling practice do real explanatory work? Do some highly abstract and mathematical models exhibit a noncausal form of scientific explanation? How can one distinguish an exploratory "how-possibly" model explanation from a genuine "how-actually" model explanation? Do modelers face tradeoffs such that a model that is optimized for yielding explanatory insight, for example, might fail to be the most predictively accurate, and vice versa? This chapter explores the various answers that have been given to these questions. (shrink)