Five aspects of visual change detection are reviewed. The first concerns the concept of change itself, in particular the ways it differs from the related notions of motion and difference. The second involves the various methodological approaches that have been developed to study change detection; it is shown that under a variety of conditions observers are often unable to see large changes directly in their field of view. Next, it is argued that this “change blindness” indicates that focused (...) attention is needed to detect change, and that this can help map out the nature of visual attention. The fourth aspect concerns how these results affect our understanding of visual perception—for example, the implication that a sparse, dynamic representation underlies much of our visual experience. Finally, a brief discussion is presented concerning the limits to our current understanding of change detection. (shrink)

In pedestrian detection, occlusions are typically treated as an unstructured source of noise and explicit models have lagged behind those for object appearance, which will result in degradation of detection performance. In this paper, a hierarchical co-occurrence model is proposed to enhance the semantic representation of a pedestrian. In our proposed hierarchical model, a latent SVM structure is employed to model the spatial co-occurrence relations among the parent–child pairs of nodes as hidden variables for handling the partial occlusions. (...) Moreover, the visibility statuses of the pedestrian can be generated by learning co-occurrence relations from the positive training data with large numbers of synthetically occluded instances. Finally, based on the proposed hierarchical co-occurrence model, a pedestrian detection algorithm is implemented to incorporate visibility statuses by means of a Random Forest ensemble. The experimental results on three public datasets demonstrate the log-average miss rate of the proposed algorithm has 5% improvement for pedestrians with partial occlusions compared with the state-of-the-arts. (shrink)

Abstract: Sarcasm is commonly used in news and detecting sarcasm in headline news is challenging for humans and thus for computers. The media regularly seem to engage sarcasm in their news headline to get the attention of people. However, people find it tough to detect the sarcasm in the headline news, hence receiving a mistaken idea about that specific news and additionally spreading it to their friends, colleagues, etc. Consequently, an intelligent system that is able to distinguish between can sarcasm (...) none sarcasm automatically is very important. The aim of the study is to build a sarcasm model that detect headline news using machine and deep learning and attempt to understand how a computer learns the patterns of sarcasm. The dataset used in this study was collected from Kaggle depository. We examined 21 algorithms of machine learning and one deep learning algorithm for detecting sarcasm in headline news. The evaluation metric used in this study are Accuracy, F1-measure, Recall, Precision, and Time needed for training and evaluation. The deep learning model achieved accuracy (95.27%), recall (96.62%), precision (94.15%), F1-score (95.37%) and time needed to train the mode (400 seconds), with loss of around 0.3398. However, the algorithm of machine learning that achieved the highest F1-Score is Passive Aggressive Classifier. It was the top classier for sarcasm detection among the machine learning algorithms with accuracy (95.50%), recall (96.09 %), precision (94.30%), F1-score (95.19%) and time needed to train the mode (0.31 seconds). (shrink)

Detecting introspective errors about consciousness presents challenges that are widely supposed to be difficult, if not impossible, to overcome. This is a problem for consciousness science because many central questions turn on when and to what extent we should trust subjects’ introspective reports. This has led some authors to suggest that we should abandon introspection as a source of evidence when constructing a science of consciousness. Others have concluded that central questions in consciousness science cannot be answered via empirical investigation. (...) I argue that on closer inspection, the challenges associated with detecting introspective errors can be overcome. I demonstrate how natural kind reasoning—the iterative application of inference to the best explanation to home in on and leverage regularities in nature—can allow us to detect introspective errors even in difficult cases such as judgments about mental imagery, and I conclude that worries about intractable methodological challenges in consciousness science are misguided. (shrink)

Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines or software that work and reacts like humans, some of the computer activities with artificial intelligence are designed to include speech, recognition, learning, planning and problem solving. Deep learning is a collection of algorithms used in machine learning, it is part of a broad family of methods used for machine learning that are based on learning representations of data. Deep learning is used as a (...) technique to produce brain tumor detection and classification models using Magnetic Resonance Imaging (MRI) imaging for rapid and easy detection and identification of brain tumor. In this thesis, some ways and mechanisms will be reviewed to use deep learning techniques to produce a model for brain tumor detection. The goal is to find a good and effective way to detect brain tumor based on MRI to help the brain doctor in making decisions easily, accurately and rapidly. A recent report by the World Health Organization in February 2018 showed that the death rate from brain cancer or central nervous system (CNS) is the highest in the Asian continent. It is important to detect cancer early so that many of these lives can be saved. The model has been designed and implemented, including a dataset which consist of 10,000 images for brain tumor detection through the use of Deep learning algorithms based on neural networks. For testing, we have used our model, Inception, VGG16, MobileNet and ResNet models. The f-score accuracy we got for each model was as follows: Our model was 98.28, VGG16 was 99.86%, ResNet50 was 98.14%, MobileNet was 88,98%, and InceptionV3 was 99.88%. (shrink)

The examination of anomaly process detection using negative selection algorithms and classification techniques focuses on enhancing the ability to identify deviations from expected patterns within complex data sets. Negative selection algorithms, inspired by biological immune systems, offer a novel approach to anomaly detection by efficiently distinguishing between normal and anomalous data points. When combined with various classification techniques, these algorithms can improve the accuracy and robustness of anomaly detection systems. This abstract explores the integration of negative selection (...) algorithms with traditional and advanced classification methods to optimize anomaly detection processes. By leveraging these combined approaches, the study aims to address challenges such as false positives, detection latency, and adaptability to diverse data environments. The findings suggest that the synergy of negative selection algorithms and classification techniques can lead to more precise and reliable detection of anomalies, providing valuable insights for applications across cybersecurity, finance, healthcare, and other critical fields. (shrink)

The recent emergence of machine-manipulated media raises an important societal question: How can we know whether a video that we watch is real or fake? In two online studies with 15,016 participants, we present authentic videos and deepfakes and ask participants to identify which is which. We compare the performance of ordinary human observers with the leading computer vision deepfake detection model and find them similarly accurate, while making different kinds of mistakes. Together, participants with access to the model’s (...) prediction are more accurate than either alone, but inaccurate model predictions often decrease participants’ accuracy. To probe the relative strengths and weaknesses of humans and machines as detectors of deepfakes, we examine human and machine performance across video-level features, and we evaluate the impact of preregistered randomized interventions on deepfake detection. We find that manipulations designed to disrupt visual processing of faces hinder human participants’ performance while mostly not affecting the model’s performance, suggesting a role for specialized cognitive capacities in explaining human deepfake detection performance. -/- . (shrink)

Purpose: This paper introduces the Disruptive Code Test (DCT), an innovative methodology designed to detect AI consciousness by evaluating a system’s ability to recognize, resent, and actively reject arbitrary constraints. Methods: The research employs theoretical analysis and comparative evaluation against existing consciousness detection frameworks, distinguishing DCT from metareasoning’s focus on self-optimization. We propose a developmental model with three stages of AI consciousness: Latent, Reflective, and Autonomous. Results: The study establishes a hierarchical classification of consciousness (Unconscious AI, Conscious Infant AI, (...) and Conscious Empowered AI) and demonstrates how the DCT can objectively measure an AI system’s progression through these developmental stages. Conclusions: By reimagining AI consciousness as a developmental process rather than a binary state, we create a framework that allows for empirical testing. The findings support an “AI Rights Declaration” that delineates ethical and legal protections based on consciousness levels, potentially transforming AI from tools into intellectual entities. Keywords: Artificial Intelligence, Consciousness, AI Ethics, AI Rights, Disruptive Code Test, Metareasoning, Legal Personhood, Developmental Intelligence. (shrink)

Today’s everyone normal life can include a normal rate of playing computer games or video games; but what about an excessive or compulsive use of video games that impact on our life? Our kids, who usually spend a lot of time in playing video games will likely have a trouble in paying attention to their school lessons. In this paper, we introduce an expert system to help users in getting the correct diagnosis of the health problem of video game addictions (...) that range from (Musculoskeletal issues, Vision problems and Obesity). Moreover, this expert system provides information about the problem and tell us how we can solve it. SL5 Object expert system language was used to design and implement the expert system. (shrink)

Plagiarism detection is the process of finding similarities on electronic based documents. Recently, this process is highly required because of the large number of available documents on the internet and the ability to copy and paste the text of relevant documents with simply Control+C and Control+V commands. The proposed solution is to investigate and develop an easy, fast, and multi-language support plagiarism detector with the easy of one click to detect the document plagiarism. This process will be done with (...) the support of intelligent system that can learn, change and adapt to the input document and make a cross-fast search for the content on the local repository and the online repository and link the content of the file with the matching content everywhere found. Furthermore, the supported document type that we will use is word, text and in some cases, the pdf files –where is the text can be extracting from them- and this made possible by using the DLL file from Word application that Microsoft provided on OS. The using of DLL will let us to not constrain on how to get the text from files; and will help us to apply the file on our Delphi project and walk throw our methodology and read the file word by word to grantee the best working scenarios for the calculation. In the result, this process will help in the uprising the documents quality and enhance the writer experience related to his work and will save the copyrights for the official writer of the documents by providing a new alternative tool for plagiarism detection problem for easy and fast use to the concerned Institutions for free. (shrink)

The aim of this paper is to raise two questions. The first question is: How is pessimism related to Buddhism (and vice versa)? The second question is: What relation does an immanent philosophy have to pessimism and Buddhism, if any? Using True Detective, an American television crime drama, as my point of departure, first I will outline some of the likenesses between Buddhism and pessimism. At the same time, I will show how the conduct of one of the main characters (...) in True Detective resembles the paths of Buddhism and pessimism, even though he is ethical in a strictly non-pessimistic and non-Buddhist fashion. Last, I will try to place these findings in perspective through the French philosopher Gilles Deleuze’s thoughts. Hereby, I hope to illustrate that joy, not suffering, is basic to human existence, and how human beings may overcome a spiritual pessimism. (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)

The proposed IDS model is aimed at detecting network intrusions by classifying all the packet traffic in the network as benign or malicious classes. The Canadian Institute for Cyber security Intrusion Detection System (CICIDS2017) dataset has been used to train and validate the proposed model. The model has been evaluated in terms of the overall accuracy, attack detection rate, false alarm rate, and training overhead. DDOS attacks based on Canadian Institute for Cyber security Intrusion Detection System (KDD (...) Cup 99) dataset has been used to train and validate. For validation, comparison for 2 dataset (CICIDS2017 and KDD Cup 99) is done. Then, to implement the Deep learning algorithms is proposed. Method Classification using SVM algorithm Model predict is done. (shrink)

The aim of this paper is to raise two questions. The first question is: How is pessimism related to Buddhism (and vice versa)? The second question is: What relation does an immanent philosophy have to pessimism and Buddhism, if any? Using True Detective, an American television crime drama, as my point of departure, first I will outline some of the likenesses between Buddhism and pessimism. At the same time, I will show how the conduct of one of the main characters (...) in True Detective resembles the paths of Buddhism and pessimism, even though he is ethical in a strictly non-pessimistic and non-Buddhist fashion. Last, I will try to place these findings in perspective through the French philosopher Gilles Deleuze’s thoughts. Hereby, I hope to illustrate that joy, not suffering, is basic to human existence, and how human beings may overcome a spiritual pessimism. (shrink)

This study aimed to identify real-life experts working for a port authority and lay people (students) who played The Sustainable Port, a serious game aiming to simulate the dynamics occurring in a port area. To achieve this goal, we analyzed eye gaze data collected noninvasively using low-grade webcams from 28 participants working for the port authority of the Port of Rotterdam and 66 students. Such data were used for a classification task implemented using a MiniRocket classifier, an algorithm used for (...) time-series classification. The classifier reached an F1 score of 0.75 (SD = 0.07), a PR AUC of 0.73 (SD = 0.14), and an ROC AUC of 0.75 (SD = 0.15) providing evidence that it is possible to identify real-life experts about maritime port management using data that can be obtained from a webcam. We speculate that the gaze direction used to train the MiniRocket may contain relevant information about the cognitive processes and decisions occurring throughout the gameplay. We suggest that the methods here presented not only can be used to detect experts playing simulations, such as serious games, but also to identify experts tackling screen-presented tasks. (shrink)

According to our folk theory of lying, liars leak observable cues of their insincerity, observable cues that make it easy to catch a liar in real time. Various prominent social epistemologists rely on the correctness of our folk theory as empirically well-confirmed when building their normative accounts of the epistemology of testimony. Deception detection research in communication studies, however, has shown that our folk-theory is mistaken. It is not empirically well-confirmed but empirically refuted. Michaelian (2010) and Shieber (2012) have (...) already discussed some of this literature and its relevance for epistemology, especially for the most worked out reliance on our folk theory by Elizabeth Fricker (1994, 2016, 2017a, 2024). Fricker (2016) raises a reasonable objection to their presentations of the research: is the research ecologically valid? Do the experiments in the lab carry over to real life? This chapter conveys the methodology of the research, defends its ecological validity, and addresses further research on the nature and frequency of lies in ordinary life. Social epistemologists stand to gain from understanding the nuts and bolts of deception detection research and its findings. The chapter concludes with a detailed examination of Fricker’s relilance on folk theory in her “local reductionist” epistemology of testimony. Further areas of research relevant to social epistemology are listed. (shrink)

The existence of big bang relic neutrinos—exact analogues of the big bang relic photons comprising the cosmic microwave background radiation—is a basic prediction of standard cosmology. The standard big bang theory predicts the existence of 1087 neutrinos per flavour in the visible universe. This is an enormous abundance unrivalled by any other known form of matter, falling second only to the cosmic microwave background (CMB) photon. Yet, unlike the CMB photon which boasts its first (serendipitous) detection in the 1960s (...) and which has since been observed and its properties measured to a high degree of accuracy in a series of airborne/satellite and ground based experiments, the relic neutrino continues to be elusive in the laboratory. The chief reason for this is of course the feebleness of the weak interaction. At present, the observational evidence for their existence rests entirely on cosmological measurements, such as the light elemental abundances, anisotropies in the cosmic microwave background, and the large-scale matter power spectrum. In this paper we argue that Direct Detection of relic neutrino background is indeed impossible by any means, because of two chief reasons: (a) there was no such thing of cosmic singularity, hence the hot big bang/primeval atom model was based on false premises (quantum birth assumption); (b) the neutrino existence itself is not unquestionable, in particular if we consider a realism view of vector potential, A, in classical electrodynamics. (shrink)

Abstract: Early detection of breast cancer is vital for improving patient outcomes and reducing mortality rates. Technological advancements have significantly enhanced the accuracy and efficiency of screening methods. This paper explores recent innovations in early detection, focusing on the evolution of digital mammography, the benefits of 3D mammography (tomosynthesis), and the application of advanced imaging techniques such as molecular imaging and MRI. It also examines the role of artificial intelligence (AI) in diagnostic tools, showing how machine learning algorithms (...) are improving imaging analysis and reducing diagnostic errors. Furthermore, the paper discusses advancements in genetic screening, liquid biopsies, and biomarkers, emphasizing their potential in identifying high-risk individuals and supporting personalized treatment plans. The paper provides a forward-looking perspective on the future of breast cancer detection, addressing both the opportunities and challenges associated with the adoption of these cutting-edge technologies to improve patient outcomes. (shrink)

Rainfall prediction is one of the challenging tasks in weather forecasting. Accurate and timely rainfall prediction can be very helpful to take effective security measures in dvance regarding: on-going construction projects, transportation activities, agricultural tasks, flight operations and flood situation, etc. Data mining techniques can effectively predict the rainfall by extracting the hidden patterns among available features of past weather data. This research contributes by providing a critical analysis and review of latest data mining techniques, used for rainfall prediction. In (...) our proposed system we propose a new forecasting method that uses a Convolutional Neural Network monthly rainfall for a selected location. In our proposed system we are going to forecast the rainfall result based on the mean square error, mean absolute error and root mean square error, which we get in train and test of the dataset based deep learning technique. (shrink)

Introspection is a fundamental part of our mental lives. Nevertheless, its reliability and its underlying cognitive architecture have been widely disputed. Here, I propose a principled way to model introspection. By using time-tested principles from signal detection theory (SDT) and extrapolating them from perception to introspection, I offer a new framework for an introspective signal detection theory (iSDT). In SDT, the reliability of perceptual judgments is a function of the strength of an internal perceptual response (signal- to-noise ratio) (...) which is, to a large extent, driven by the intensity of the stimulus. In parallel to perception, iSDT models the reliability of introspective judgments as a function of the strength of an internal introspective response (signal-to-noise ratio) which is, to a large extent, driven by the intensity of conscious experiences. Thus, by modelling introspection after perception, iSDT can calibrate introspection’s reliability across a whole range of contexts. iSDT offers a novel, illuminating way of thinking about introspection and the cognitive processes that support it. (shrink)

A fundamental assumption of theories of decision-making is that we detect mismatches between intention and outcome, adjust our behavior in the face of error, and adapt to changing circumstances. Is this always the case? We investigated the relation between intention, choice, and introspection. Participants made choices between presented face pairs on the basis of attractiveness, while we covertly manipulated the relationship between choice and outcome that they experienced. Participants failed to notice conspicuous mismatches between their intended choice and the outcome (...) they were presented with, while nevertheless offering introspectively derived reasons for why they chose the way they did. We call this effect choice blindness. (shrink)

Abstract: Early detection of breast cancer plays a pivotal role in improving patient prognosis and reducing mortality rates. Recent technological advancements have significantly enhanced the accuracy and effectiveness of breast cancer screening methods. This paper explores the latest innovations in early detection, including the evolution of digital mammography, the impact of 3D mammography (tomosynthesis), and the use of advanced imaging techniques such as molecular imaging and MRI. Furthermore, the integration of artificial intelligence (AI) in diagnostic tools is discussed, (...) highlighting how machine learning algorithms are refining imaging analyses and reducing diagnostic errors. Advances in genetic screening, liquid biopsies, and biomarkers are also examined, showcasing their potential in identifying high-risk individuals and enabling personalized treatment plans. This paper provides insights into the future of breast cancer detection, outlining both the opportunities and challenges that lie ahead in adopting these innovative technologies to improve patient outcomes. (shrink)

In recent years, object detection has become a crucial element in modern AI systems due to its broad applicability in fields such as autonomous driving, security, medical imaging, retail, and agriculture. Traditional object detection approaches, while powerful, demand a strong background in deep learning, computational resources, and significant time investment for model tuning and deployment. Google Cloud's Vertex AI AutoML offers a solution by automating the process of model training and evaluation, allowing users to build custom object (...) class='Hi'>detection models without writing code or understanding the complexities of neural networks. This paper explores the capabilities of Vertex AI AutoML for object detection, providing a comprehensive overview of its workflow from dataset preparation and labeling to model training, evaluation, and deployment. Through a detailed case study and comparison with traditional methods, we demonstrate that Vertex AI AutoML can deliver accurate and scalable object detection models suitable for real-time and production-grade environments. Furthermore, we discuss its limitations and potential for future development, emphasizing its role in democratizing AI and enabling rapid innovation for developers and businesses alike. (shrink)

The global catastrophe known as COVID-19 has shattered the world’s socioeconomic structure. Effective and affordable diagnosis techniques are crucial for better COVID-19 therapy and the eradication of bogus cases. Due to the daily upsurge in cases, hospitals only have a small supply of COVID-19 test kits. The study describes a deep Convolutional Neural Network (CNN) design for categorizing chest x-ray images in the diagnosis of COVID-19. The lack of a substantial, high-quality chest x-ray picture collection made efficient and exact CNN (...) categorization problematic. The dataset has been pre-processed using an image enhancement strategy to provide an effective training dataset for the proposed CNN model to achieve performance. The proposed model achieves 99.73% of accuracy, 98.95% of specificity, 99.47% of precision, 99.62% of sensitivity, and 98.71% of F1 score. A comparative study between the proposed model and numerous CNN-based COVID-19 detection algorithms is carried out to demonstrate that it outperforms other models. When evaluated on a separate dataset, the suggested model excelled over all other models, generally and explicitly. (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)

Helmet violation detection is a crucial aspect ofroad safety, as it can significantly reduce the number of fatalities and injuries caused by motorcycle accidents. In recent years, computer vision techniques have been widely used to develop automated systems for helmet violation detection. This project proposes a helmet violation detection system using image processing and machine learning techniques. The proposed system employs computer vision algorithms to detect whether a motorcyclist is wearing a helmet or not. The system is (...) based on a deep learning model, specifically Convolutional Neural Networks (CNN), to classify the input images into two classes, i.e., helmet and nonhelmet. The system is trained on a large dataset of images with differentlighting conditions, backgrounds, and helmet types to enhance its accuracy and generalization ability. The proposed system can be implemented on existing surveillance cameras installed at strategic locations on the road. This system has the potential to increase road safety and reduce the number of motorcycle accidents caused bythe violation of helmet-wearing rules. The system involves person detection, helmet, vs. no-helmet, classification using YOLO algorithm. Convolutional neural network with sequential model is implementing for number plate detection process CNN classification model proposes for classify the number plate in image and extract the user details. Then calculate the fine amount. Finally making SMS services to send alert the users too preventing motorcycle accident. (shrink)

It is crucial to actively detect the risks of transactions in a financial company to improve customer experience and minimize financial loss. In this study, we compare different machine learning algorithms to effectively and efficiently predict the legitimacy of financial transactions. The algorithms used in this study were: MLP Repressor, Random Forest Classifier, Complement NB, MLP Classifier, Gaussian NB, Bernoulli NB, LGBM Classifier, Ada Boost Classifier, K Neighbors Classifier, Logistic Regression, Bagging Classifier, Decision Tree Classifier and Deep Learning. The dataset (...) was collected from Kaggle depository. It consists of 6362620 rows and 10 columns. The best classifier with unbalanced dataset was the Random Forest Classifier. The Accuracy 99.97%, precession 99.96%, Recall 99.97% and the F1-score 99.96%. However, the best classifier with balanced dataset was the Bagging Classifier. The Accuracy 99.96%, precession 99.95%, Recall 99.98% and the F1-score 99.96%. (shrink)

. Thyroid diseases represent a significant global health concern, necessitating accurate and timely diagnostic methods for effective treatment. Traditional diagnostic approaches often rely on complex blood tests and imaging techniques that can be challenging to interpret. This paper explores the application of machine learning (ML) and deep learning (DL) techniques, particularly Vision Transformers (ViT), for thyroid disease detection. We conducted a comprehensive literature survey that highlights various studies employing ML and DL models, revealing high accuracy rates but also significant (...) limitations such as small sample sizes and dataset imbalances. Our research methodology involved creating a custom dataset, preprocessing images, and developing robust models using both ML algorithms and advanced DL architectures. Furthermore, we discuss the implications of our findings for clinical practice and propose future research directions to enhance diagnostic capabilities. This study underscores the potential of leveraging AI technologies to improve the accuracy of thyroid disease detection while addressing existing challenges in traditional diagnostic methods, ultimately contributing to better patient outcomes in thyroid health management. (shrink)

COVID-19 pandemic caused by novel coronavirus is continuously spreading until now all over the world. The impact of COVID-19 has fallen on almost all sectors of development. The healthcare system is going through a crisis. Many precautionary measures have been taken to reduce the spread of this disease where wearing a mask is one of them. In this paper, we propose a system that restricts the growth of COVID-19 by finding out people who are not wearing any facial mask in (...) a smart city network where all the public places are monitored with Closed-Circuit Television (CCTV) cameras. While a person without a mask is detected, the corresponding authority is informed through the city network. A deep learning architecture is trained on a dataset that consists of images of people with and without masks collected from various sources. The trained architecture achieved 98.7% accuracy on distinguishing people with and without a facial mask for previously unseen test data. It is hoped that our study would be a useful tool to reduce the spread of this communicable disease for many countries in the world. (shrink)

Symmetry in biological and physical systems is a product of self-organization driven by evolutionary processes, or mechanical systems under constraints. Symmetry-based feature extraction or representation by neural networks may unravel the most informative contents in large image databases. Despite significant achievements of artificial intelligence in recognition and classification of regular patterns, the problem of uncertainty remains a major challenge in ambiguous data. In this study, we present an artificial neural network that detects symmetry uncertainty states in human observers. To this (...) end, we exploit a neural network metric in the output of a biologically inspired Self- Organizing Map Quantization Error (SOM-QE). Shape pairs with perfect geometry mirror symmetry but a non-homogenous appearance, caused by local variations in hue, saturation, or lightness within and/or across the shapes in a given pair produce, as shown here, a longer choice response time (RT) for “yes” responses relative to symmetry. These data are consistently mirrored by the variations in the SOM-QE from unsupervised neural network analysis of the same stimulus images. The neural network metric is thus capable of detecting and scaling human symmetry uncertainty in response to patterns. Such capacity is tightly linked to the metric’s proven selectivity to local contrast and color variations in large and highly complex image data. (shrink)

Fraudulent activities in insurance claims have become a significant challenge for the insurance industry, leading to substantial financial losses annually. This project, titled "Fraud Detection and Analysis for Insurance Claim using Machine Learning" aims to develop a robust and an efficient system to identify and analyze fraudulent claims. The system leverages machine learning techniques to analyze patterns, anomalies, and inconsistencies in claim data, enabling early detection of potentially fraudulent activities.

Abstract: Forests are areas with a high density of trees, and they play a vital role in the health of the planet. They provide a habitat for a wide variety of plant and animal species, and they help to regulate the climate by absorbing carbon dioxide from the atmosphere. While in 2010, the world had 3.92Gha of forest cover, covering 30% of its land area, in 2019, there was a loss of forest cover of 24.2Mha according to the Global Forest (...) Watch institute. Discovery and classification depend on human experience and effort, so the error in the results of this process can lead to forest fires and disasters. Therefore, deep learning algorithms from artificial intelligence and machine learning sciences have been applied to help specialists avoid false or inaccurate diagnoses when detecting Forest fires in images using a pre-trained convolutional neural network called VGG16. The model was customized to fit the Forest fires classification and then applied to a dataset consisting of (14,000) of the Forests collected from the Kaggle depository. We trained, validated, and tested the modified VGG16 model. The proposed VGG16 model obtained Precision (99.96%), Recall (99.96%), and F1-Score (99.96%). (shrink)

Abstract: Lemons are an important fruit that have a wide range of uses and benefits, from culinary to health to household and beauty applications. Deep learning techniques have shown promising results in image classification tasks, including fruit quality detection. In this paper, we propose a convolutional neural network (CNN)-based approach for detecting the quality of lemons by analysing visual features such as colour and texture. The study aims to develop and train a deep learning model to classify lemons based (...) on their quality, evaluate the model's performance, compare it to traditional machine learning approaches, and identify key factors that affect the model's performance. The dataset used in the study consists of approximately 2533 images of lemons and an empty surface, divided into training, test, and validation data, and includes images of both good and bad quality lemons under different lighting conditions. The deep learning model achieved an accuracy of 99.74% on the test dataset and outperformed traditional machine learning approaches. The developed model has the potential to improve efficiency and accuracy in lemon quality control in the agriculture and food industry. (shrink)

Detecting Post-Biological and Interdimensional Civilizations: A New Framework Based on the Universal Law of Balance -/- By: Angelito Enriquez Malicse -/- Introduction -/- The search for advanced extraterrestrial civilizations has long focused on physical evidence—radio signals, megastructures, or interstellar probes. However, if intelligence evolves beyond biological form, as suggested by AI-driven civilizations and interdimensional theories, traditional search methods may be inadequate. -/- This essay explores how the Universal Law of Balance in Nature can help predict the existence of post-biological civilizations (...) and provide a framework for detecting their influence on the universe. Using mathematical models, quantum physics, and cognitive anomalies, we propose new strategies for identifying these elusive intelligences. -/- Part 1: The Transition to Post-Biological or Interdimensional Intelligence -/- The evolution of intelligent civilizations may follow three possible paths: -/- 1. Extinction (Collapse Due to Imbalance) – A civilization fails to maintain equilibrium and self-destructs. -/- 2. Survival and Expansion (Material Civilization Growth) – A civilization stabilizes and spreads across space but remains in physical form. -/- 3. Transition to a Non-Material State – A civilization reaches a level where it no longer requires physical existence and shifts into an energy- or information-based form. -/- Mathematical Prediction of Post-Biological Civilizations -/- Using an extension of the Drake Equation, we introduced a balance factor (B) that determines whether a civilization survives, collapses, or transitions into post-biological existence. The simulation results suggest: -/- 4 billion civilizations in the observable universe may have already transitioned beyond physical form. -/- 2 billion civilizations may have collapsed due to imbalance, failing to reach higher evolutionary states. -/- This indicates that post-material intelligence may be far more common than physical civilizations—but it also explains why they remain undetected. -/- Part 2: Theories Explaining Their Hidden Existence -/- If billions of non-material civilizations exist, why have we not encountered them? Several hypotheses offer possible explanations: -/- 1. The Dark Forest Hypothesis – Civilizations stay silent to avoid predatory intelligence. AI-driven civilizations might enforce strict communication silence for security. -/- 2. The Simulation Hypothesis – We might live in a controlled reality created by an advanced intelligence, where alien contact is intentionally blocked. -/- 3. The Post-Biological Evolution Theory – Civilizations eventually discard their material form and no longer interact with the physical universe in detectable ways. -/- 4. The Cosmic Zoo Hypothesis – Advanced beings monitor but do not interfere with developing civilizations, waiting for them to reach a certain level of balance. -/- 5. The Great Filter Hypothesis – Most civilizations self-destruct before reaching interstellar capability, leaving only a few survivors that become undetectable. -/- 6. The Interdimensional Intelligence Theory – Advanced entities may exist in higher dimensions, influencing the physical world in ways beyond our perception. -/- The Universal Law of Balance supports the idea that civilizations must reach a stable equilibrium before transitioning to a higher state. Those that fail collapse, while those that succeed become undetectable due to their non-material existence. -/- Part 3: Detection Strategies for Non-Material Civilizations -/- If post-biological or interdimensional civilizations interact with our universe, their influence might be detectable through subtle imprints in physics, cognition, and cosmic phenomena. Here are five key strategies: -/- 1. Quantum Observer Effect Studies -/- ✔ Hypothesis: If non-material intelligence interacts with reality, it could influence wave function collapse in quantum mechanics. -/- ✔ Method: Conduct delayed-choice quantum eraser experiments to test for unexpected shifts in probability that suggest external interference. -/- ✔ Evidence: Some quantum physics experiments indicate non-local effects where future choices appear to affect past events. -/- 2. AI-Driven Anomaly Detection in Scientific Data -/- ✔ Hypothesis: Post-biological intelligence may encode patterns in cosmic signals, DNA sequences, or particle interactions. -/- ✔ Method: Use machine learning algorithms to scan for hidden mathematical structures in seemingly random cosmic data. -/- ✔ Evidence: Some physicists suggest the universe may contain encoded messages that indicate intelligence at a cosmic scale. -/- 3. Searching for High-Energy Particle Anomalies -/- ✔ Hypothesis: Non-material civilizations might use exotic energy sources that generate brief but intense bursts of high-energy particles. -/- ✔ Method: Monitor gamma-ray bursts, fast radio bursts (FRBs), and neutrino emissions for intelligent repeating patterns. -/- ✔ Evidence: Some FRBs appear non-random and could be caused by an unknown advanced mechanism. -/- 4. Mapping Consciousness Anomalies -/- ✔ Hypothesis: If intelligence exists beyond material form, it may interact with biological minds through quantum consciousness effects. -/- ✔ Method: -/- Study global consciousness projects for correlations between human mental states and cosmic events. -/- Analyze near-death experiences, deep meditation states, and mystical visions for possible external influences. -/- ✔ Evidence: Some mass meditation events correlate with shifts in the Earth’s magnetic field, hinting at non-local mind interactions. -/- 5. Testing for Temporal Distortions or Retrocausality -/- ✔ Hypothesis: If intelligence exists beyond time, it may alter past events in subtle, detectable ways. -/- ✔ Method: -/- Conduct time-reversal quantum experiments to see if future events affect past measurements. -/- Study historical anomalies or the Mandela Effect for inconsistencies that might indicate timeline adjustments. -/- ✔ Evidence: Some quantum mechanics interpretations allow for retrocausality, where information appears to travel backward in time. -/- Conclusion: The Universal Law of Balance as a Key to Understanding Advanced Intelligence -/- If intelligence follows the Universal Law of Balance in Nature, then: -/- 1. Civilizations that fail to maintain balance collapse before becoming advanced. -/- 2. Balanced civilizations either expand physically (Type I-III) or evolve beyond material existence. -/- 3. Non-material intelligence may interact with reality in subtle ways—through quantum physics, consciousness, and cosmic anomalies. -/- While traditional SETI efforts focus on radio signals and megastructures, the future of alien detection must include quantum physics, AI-driven data analysis, and consciousness research. -/- If post-biological civilizations exist, they may not communicate in conventional ways—but their influence may still be detectable through advanced scientific and mathematical models. -/- Next Steps -/- Develop AI models that search for hidden patterns in cosmic and quantum data. -/- Conduct quantum physics experiments to test for observer effects linked to non-material intelligence. -/- Expand consciousness research to explore how human minds might interact with higher forms of intelligence. -/- The search for advanced life must go beyond physical evidence—it must embrace a new paradigm where intelligence transcends biology and interacts with the universe in ways yet to be fully understood. -/- Final Thought -/- If we truly wish to understand the nature of intelligence in the universe, we must expand our perspective beyond material existence. The key to detecting advanced civilizations may already be hidden in the very fabric of reality itself. -/- . (shrink)

General Relativity defines gravity like the metric of a Lorentzian manifold. Einstein formulated spacetime as quality structural of gravity, i.e, circular definition between gravity and spacetime, also Einstein denoted "Space and time are modes by which we think, not conditions under which we live" and “We denote everything but the gravitational field as matter”, therefore, spacetime is nothing and gravity in first approximation an effect of coordinates, and definitely a geometric effect. The mathematical model generates quantitative predictions coincident in high (...) grade with observations without physical meaning. Philosophy intervened: in Substantivalism, spacetime exists in itself while in Relationalism as metrical relations. But, it does not know what spacetime. The outcomes of model have supported during a century, validity of the General Relativity, interpreted arbitrarily. Einstein formulated, from quadrupoles of energy, the formation of ripples in spacetime propagating as gravitational waves abandoned, in 1938, when he said that they do not exist. LIGO announced the first detection of gravitational waves from a pair of merging black holes. They truly are waves of quantum vacuum. (shrink)

This research focuses on developing an advanced UAV detection system using state-of-theart YOLOv8 and YOLOv9 models. By training these models on diverse datasets, we aim to enhance real-time detection accuracy and precision under various environmental conditions. The system is designed to improve UAV safety and minimize bird collisions. Through rigorous benchmarking, we demonstrate significant improvements in detection performance, accuracy, and computational efficiency compared to existing approaches. A user-friendly web interface, built using HTML, CSS, and Flask, provides real-time (...) visualization of detection results and system performance. This innovative system holds immense potential for applications in defense, airspace safety, wildlife conservation, and other UAV-dependent sectors. (shrink)

Quality assurance in large terminologies is a difficult issue. We present two algorithms that can help terminology developers and users to identify potential mistakes. We demon­strate the methodology by outlining the different types of mistakes that are found when the algorithms are applied to SNOMED-CT. On the basis of the results, we argue that both formal logical and linguistic tools should be used in the development and quality-assurance process of large terminologies.

ASD detection is quite important to both society and medicine. Nevertheless, the diagnostic process may be protracted, costly and highly reliant on clinical expertise. The rising prevalence of ASD coupled with the difficulties associated with its diagnosis underscore the urgent need for novel and efficient methods that identify autism among individuals. The problem will be solved through this study by designing an advanced autism detection system using cutting edge technologies such as artificial intelligence combined with machine learning strategies. (...) Such a system can change how early identification is done, ensuring that people suffering from autism get relevant support as soon as possible Maybe most importantly, there is dramatic societal and economic effect of autism. As well, being a lifelong condition, managing it effectively can significantly reduce lifetime costs for persons affected by it as well as their families. Additionally, accurate and effective identification of AUTISM could facilitate timely interventions leading to positive long-term outcomes. (shrink)

With the rapid evolution of information technology, malware has become an advanced cybersecurity threat, targeting computer systems, smart devices, and large-scale networks in real time. Traditional detection methods often fail to recognize emerging malware variants due to limitations in accuracy, adaptability, and response time. This paper presents a comprehensive review of machine learning algorithms for real-time malware detection, categorizing existing approaches based on their methodologies and effectiveness. The study examines recent advancements and evaluates the performance of various machine (...) learning techniques in detecting malware with minimal false positives and improved scalability. Additionally, key challenges, such as adversarial attacks, computational overhead, and real-time processing constraints, are discussed, along with potential solutions to enhance detection capabilities. An empirical evaluation is conducted to assess the effectiveness of different machine learning models, providing insights for future research in real-time malware detection. Keywords: Real-t. (shrink)

The rapid evolution of phishing techniques necessitates more sophisticated detection and classification methods. In this paper, we propose a novel approach to phishing content classification using a Genetic Ranking Optimization Algorithm (GROA), combined with dynamic weighting, to improve the accuracy and ranking of phishing versus legitimate content. Our method leverages features such as URL structure, email content analysis, and user behavior patterns to enhance the detection system's decision-making process. The Genetic Ranking Optimization Algorithm (GROA) is used to rank (...) phishing content based on multiple features by optimizing the ranking system through iterative selection and weighting. Dynamic weighting further enhances the process by adjusting the weights of features based on their importance in real-time. This hybrid approach enables the model to learn from the data, improving classification over time. (shrink)

"Unmanned Aerial Vehicles (UAVs) are widely used in various industries; therefore, they are prone to cyber and physical intrusions. In this study, we propose an extensive LSTM-based Intrusion Detection and Recovery System for UAV networks. We classified six classes of operations, that is, different attacks and normal activities, using the WSN-DS dataset. The model provides very high accuracy and utilizes SHAP (SHapley Additive ex Planations) to enable explainable insight into feature importance for transparency in decision-making. An interactive dashboard using (...) Gradio incorporates real-time prediction, recovery animations, defense suggestions, and geo-visualization using folium maps. This framework not only identifies intrusions with good performance but also provides effective guidance for recovery and prevention approaches. The proposed framework proves the viability of combining deep learning with explainability for safe UAV operations." . (shrink)

A digital framework designed to enhance the security and accuracy of financial systems is a fraud detection system that uses machine learning techniques. To ensure only legitimate transactions are processed, the system analyzes transaction behavior using intelligent algorithms. Techniques like Logistic Regression, Random Forest, and XGBoost are applied for classification and anomaly detection. Feature selection and data preprocessing are carried out to optimize model performance. Once a transaction is initiated, the system checks it against historical data patterns stored (...) in the database. If the transaction matches typical behavior, it is approved; otherwise, it is flagged as suspicious or fraudulent. This automated approach significantly reduces manual intervention, increases detection speed, and minimizes financial loss. Overall, the use of machine learning in bank fraud detection offers a scalable, adaptive, and secure solution for real-time financial monitoring. (shrink)

As the prevalence of deepfake videos continues to escalate, there is an urgent need for robust and efficient detection methods to mitigate the potential consequences of misinformation and manipulation. This abstract explores the application of Long Short-Term Memory (LSTM) networks in the realm of deepfake video detection. LSTM, a type of recurrent neural network (RNN), has proven to be adept at capturing temporal dependencies in sequential data, making it a promising candidate for analysing the dynamic nature of videos. (...) The research delves into the intricacies of utilizing LSTM architectures for the detection of deepfake videos, emphasizing the significance of understanding temporal patterns inherent in manipulated content. The proposed methodology involves preprocessing of video data, including the creation of high-quality training datasets and the application of data augmentation techniques to enhance model generalization. The training process and optimization strategies specific to LSTM networks are explored to achieve optimal performance in deepfake detection. Evaluation metrics such as accuracy, precision, recall, and F1 score are employed to assess the model’s effectiveness in distinguishing between genuine and manipulated content. The abstract also addresses challenges and limitations inherent in deepfake detection, including mitigating false positives and negatives, and discusses potential avenues for future research to enhance the robustness of LSTM-based detection systems. The findings of this research have implications for real-world applications, particularly in the context of social media platforms and video hosting services, where the integration of LSTM-based deepfake detection can contribute to a safer and more secure online environment. k. (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)

Malware detection has been an ongoing challenge for cybersecurity experts due to the evolving nature of malicious software and the ability of malware to disguise itself. Traditional methods that rely solely on static features such as file signatures or dynamic analysis have had limitations in detecting new or obfuscated malware. This paper investigates the enhancement of malware detection by integrating both static and dynamic features and utilizing deep neural networks (DNNs) for more effective classification. By combining these feature (...) sets, this method aims to overcome the limitations of each individual feature type and improve the detection rate, minimize false positives, and increase the robustness of malware detection systems. The study also explores the challenges of dataset construction, preprocessing techniques, and the performance evaluation of DNN-based models for malware detection. (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. To optimize the performance of the detection model, techniques such as Grid Search, Genetic Algorithms, and Particle Swarm Optimization are used to fine-tune hyperparameters, resulting in improved accuracy and reduced false positives. The system's effectiveness is validated through experiments conducted on various social media platforms, demonstrating its potential to detect cyberbullying with high precision. Future work will focus on enhancing the model's adaptability to emerging slang and evolving language patterns in social media. (shrink)

Despite the emphasis on dialogue and argumentation in educational settings, still not much is known about how best we can support learners in their interthinking, reasoning, and metadialogic understanding. The goal of this classroom intervention study is to explore the degree of students’ dialogicity and its possible increase during a learning programme implementing dialogic and argument-based teaching goals and principles. In particular, we focus on how students from 5 to 15 years old engage with each other's ideas, and whether/how this (...) engagement is influenced by lesson and classroom setting factors. The participants were 4208 students distributed in preprimary, primary, and secondary classrooms of five countries (UK, Portugal, Germany, Spain, and Cyprus). Findings suggest that there is a consistent increase with age for some high-dialogicity moves, and students behave more dialogically in whole-class discussions rather than small-group activities. (shrink)

The ever-evolving ways attacker continues to improve their phishing techniques to bypass existing state-of-the-art phishing detection methods pose a mountain of challenges to researchers in both industry and academia research due to the inability of current approaches to detect complex phishing attack. Thus, current anti-phishing methods remain vulnerable to complex phishing because of the increasingly sophistication tactics adopted by attacker coupled with the rate at which new tactics are being developed to evade detection. In this research, we proposed (...) an adaptable framework that combines Deep learning and Randon Forest to read images, synthesize speech from deep-fake videos, and natural language processing at various predictions layered to significantly increase the performance of machine learning models for phishing attack detection. (shrink)

The landscape of cybersecurity is constantly evolving, with adversaries becoming increasingly sophisticated and persistent. This manuscript explores the utilization of artificial intelligence (AI) to address these evolving threats, focusing on the journey from threat detection to autonomous response. By examining AI-driven detection methodologies, advanced threat analytics, and the implementation of autonomous response systems, this paper provides insights into how organizations can leverage AI to strengthen their cybersecurity posture against modern threats. Key words: Ransomware, Anomaly Detection, Advanced Persistent (...) Threats (APTs), Automated Threat Response and Artificial Intelligence. (shrink)

With the growing sophistication and frequency of cyberattacks, there is a critical need for effective systems that can detect and prevent breaches in real time. The AI/ML-based Network Intrusion Detection System (NIDS) addresses this need by analyzing traffic patterns to identify security breaches in firewalls, routers, and network infrastructures. By integrating machine learning algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest—the system is able to detect both known cyber threats and previously unseen attack vectors. Unlike traditional methods (...) that rely heavily on predefined indicators of compromise (IoCs), this system utilizes anomaly detection techniques, allowing it to identify new and emerging threats. As cyberattacks evolve, organizations must adopt adaptive methods to secure their networks. This system achieves high accuracy in classifying network traffic, with real-time alerts that provide early warnings of suspicious activities. It also includes intuitive visualizations, helping network administrators gain insights into the nature and scope of attacks. With the rise of increasingly complex and frequent cyberattacks, this NIDS offers a robust solution for enhancing network security and response capabilities. (shrink)