Search

Understanding the intellectual structure of geosciences is crucial for identifying emerging topics, which can guide future research and funding strategies. This study employs Latent Dirichlet Allocation (LDA) topic modeling and co-word network analysis to explore the intellectual landscape of highly cited geoscientific papers. Through empirical analysis, the study identifies 15 research areas, including climate change, geological processes, environmental impacts, and advancements in data analysis and remote sensing. These findings highlight the prominent role of big data analysis and machine learning methods across various geoscientific domains. Additionally, a notable gap has been identified in the integration of these computational methods with research on organic chemistry and formation processes, suggesting a potential direction for future exploration and innovation. [ABSTRACT FROM AUTHOR]

This paper reflects the research to design and application the complex method to evaluate the quality of the paper written in the IMRaD format. As a field we choose Russian segment of the financial technologies area since we had interest to use multilingual language model. The method covers paper's relevance to the chosen field and internal topics, the actuality, relation between parts, text borrowing, and experiment part. The clustering and classifying algorithms, and language machine learning model were used. The experimental part based on corpus of Russian papers shows the deviation of method's recommendations from expert opinion not more than 20%. The results may be interested not only reviewers but student as authors of futures papers to avoid common mistakes during paper's writing. [ABSTRACT FROM AUTHOR]

Machine learning (ML) and artificial intelligence (AI) have emerged as pivotal tools for enhancing network security in the 21st century, offering innovative approaches that surpass traditional methods. This paper conducts a comprehensive literature review to explore how AI and ML contribute to advancing network security. The findings underscore the critical role of these technologies in detecting and mitigating cyber threats, automating threat responses, and predicting future vulnerabilities. The research highlights how AI and ML can significantly enhance the accuracy and efficiency of security processes, thereby bolstering an organization's overall cybersecurity posture. Additionally, the study emphasizes the importance of seamlessly integrating AI and ML with existing security architectures to maximize their benefits. Despite the significant potential of these technologies, the study identifies several gaps in the literature, such as the need for more empirical research on the effectiveness of AI and ML-based security solutions and the practical challenges of implementing these technologies in real-world scenarios. Finally, this paper discusses the limitations of the current research and suggests future research directions to further explore the convergence of network security, AI, and ML. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is now used in many sectors but its transformative impact on cybersecurity is unmatched. Cybersecurity is seen to rely heavily on artificial intelligence (AI), which has brought about automation of responses, detection of network threats and security consciousness. This paper examines various modern techniques involving deep learning, machine learning and behavior analysis among others that are used in dealing with the increasing number and complexity of cyber threats. The research also looks at how automated cybersecurity response and decision-making capacities have been transformed through AI. It also investigates into security intelligence modeling as a means of offering actionable insights towards strengthening organizational resilience. Additionally, the goal of this paper is to provide a nuanced understanding of how AI is reshaping cybersecurity and to outline future pathways for research and development in this dynamic field. [ABSTRACT FROM AUTHOR]

In today's rapidly developing chemical industry, safety production and equipment management have become the primary tasks of enterprises. However, the complexity and unpredictability of chemical equipment make safety management(SM) face many challenges and difficulties. Therefore, the demand for chemical enterprises to apply computer information(CI) technology to improve the level of equipment SM has become increasingly prominent. Based on the investigation of a chemical enterprise, this paper verifies that the application of new technologies such as artificial intelligence and Internet of Things can effectively improve the level of equipment SM. In the past five years, the number of safety accidents in equipment management in chemical enterprises has decreased year by year, and the accuracy of fault prediction has increased from 60% to 80%, which shows that the application of new technology can effectively improve the safety performance and operation efficiency of equipment, and at the same time improve the economic benefits of enterprises. On this basis, this paper puts forward some related strategies to improve the level of equipment SM by using CI technology. [ABSTRACT FROM AUTHOR]

Computer geometric graphics modeling refers to the restoration of the target graphics in the computer graphics environment, and the visual presentation of users, which has been applied in the fields of graphics, virtual reality and computer-aided design. However, the traditional modeling system has some problems, such as low precision and low efficiency, so this paper proposes to use the point cloud data to extract the geometric features of the target graph. In this paper, the Particle swarm optimization-Extreme learning machine (PSO-ELM) algorithm is proposed later, and its principle and operation process are analyzed, and then the algorithm is used to improve the performance of the modeling system. In the comparative experiment of modeling accuracy in this paper, the average modeling accuracy of the intelligent modeling system using the proposed method is 96.97%, while that of the basic system is 94.70%. It is not difficult to see that the experimental results fully reflect the improvement of the modeling accuracy of the modeling system brought by the method in this paper, which is helpful to the application of computer geometric graphics modeling system in practical work. [ABSTRACT FROM AUTHOR]

Cold chain logistics has become a core link in ensuring drug quality and safety, especially for temperature sensitive drugs such as vaccines and biologics. This paper aims to develop a drug cold chain transportation risk assessment and early warning system based on big data, utilizing advanced technologies such as big data analysis and machine learning to achieve real-time monitoring, intelligent analysis, and early warning of various risk factors in the drug cold chain transportation process. This paper proposes a comprehensive architecture that includes data collection layer, data transmission layer, data processing and storage layer, analysis engine, warning and response module, user interface, and system integration interface. This paper collects key environmental data in real-time through sensors, such as temperature and humidity, and uses a secure data transmission layer to transmit the data to the central processing system. The construction of the risk assessment model is based on a series of quantifiable risk indicators, including temperature deviation, humidity deviation, location deviation, etc., and through data standardization and weight allocation, combined with a machine learning model to perform risk scoring and grading. The early warning mechanism implementation part includes early warning rules and threshold settings as well as real-time monitoring and dynamic warning to ensure that the system can respond to potential risks in a timely manner. The results of the system performance evaluation show that the risk evolution prediction deviation rate remains at a very low level, with a maximum of 1.4%, the false alarm rate is very low, with a maximum of 0.15% and a minimum of 0.03%, and the risk situational awareness sensitivity coefficient remains at a high level, with a minimum of 0.8. These results indicate that the developed system performs well in terms of risk prediction accuracy, warning timeliness and risk perception sensitivity. [ABSTRACT FROM AUTHOR]

Under the background of digitalization and networking, the fashion industry is undergoing unprecedented changes. In such a big environment, online clothing design based on artificial intelligence technology is a brand-new innovation and development direction. In this paper, the online fashion design is taken as the research object, and the latest artificial intelligence algorithm is combined to discuss the fashion design automation and personalized design method based on AI(Artificial Intelligence). The online clothing design system based on artificial intelligence uses deep learning, image recognition and machine learning methods to analyze user preferences, historical data and fashion trends, and automatically generate personalized and innovative clothing design schemes. In addition, this study also compares the differences between artificial intelligence-driven clothing design and traditional clothing design in creativity, cost-effectiveness and user satisfaction. In the AI design method, the design cycle is generally shorter, in which the automatic primary, intermediate and advanced design takes 8 days, 6 days and 4 days respectively, while the expert-aided design and fully customized design cycle takes 5 days and 7 days respectively. The research results of this paper will promote the automation and personalization of fashion design, and open up a brand-new working mode for the development of fashion industry. [ABSTRACT FROM AUTHOR]

This paper presents a comparison of the classification performance of a fuzzy clustering based support vector machine (SVM) with reinforcement learning and the previously developed fuzzy clustering based SVM for autocoding. While SVM is a machine leaning method known for high classification performance, there is an issue that SVM requires a large amount of processing time for large complex data. Therefore, in this study, we develop a classification method of fuzzy clustering based SVM with reinforcement learning to reduce the processing time for SVM. The purpose of this paper is comparing both classification performance and processing time of the developed fuzzy clustering based SVM with reinforcement learning and the ordinary fuzzy clustering based SVM. Numerical examples with governmental survey data, the Family Income and Expenditure survey data, show a better performance of the fuzzy clustering based SVM with reinforcement learning. [ABSTRACT FROM AUTHOR]

Data Centres (DCs), the core of the ever-increasing economic and societal activities, are experiencing high energy consumption due to the rapidly growing demand for digital services, which leads to the largest DCs' operational costs and significant environmental and power security impacts. Hence, optimising their energy efficiency is a critical and top priority to ensure economic and environmentally sustainable DC management. However, prior heuristics and engineering-based solutions are inadequate due to the increasing physical complexity and sheer number of possible configurations, non-linear system interactions, and the growing monitoring of operational management data. Therefore, this paper develops a six-layered hybrid Convolutional Neural Network (CNN) and Long-Short-Term Memory (LSTM), called CNN-LSTM, a suitable data-driven Deep Learning (DL) model inspired by the human brain for effectively modelling the complex and plant performance and optimising DC efficiency. The proposed model uses CNN to capture complex parameter interactions and spatial pattern recognition and LSTM to capture temporal dependencies of the time series operational data to predict the next energy consumption value and optimise it using a cooling system fan speed controllable variable. The model was extensively trained and tested using actual operational management data obtained from the Enea High-Performance Computing (HPC) CRESCO6 cluster, Italy. 80% of the data was used for training, and the rest 20% for testing. According to the experimental results, it accurately predicts energy consumption every 15 minutes with an average Mean Absolute Error (MAE) of 0.0043. A sensitivity analysis optimisation strategy is also implemented using various cooling system fan speed set points. When the fan speed optimal set-point is automatically reduced by 50%, the energy consumption is optimised by an average of 0.0029 kWh with a 0.0039 MAE over the last 15 minutes of the testing set. Hence, this paper found that the proposed CNN-LSTM deep learning predictive model can effectively mimic actual DC operations and optimise efficiency. By simulating this model, DC operators can effectively manage and optimise their DC energy efficiency while reducing energy and environmental costs. [ABSTRACT FROM AUTHOR]

The paper aims to create an understanding of the importance of remote sensing data and its efficient analysis. The authors show the benefits that the combination of unmanned aerial vehicles and deep learning algorithms can create. The focus of the paper is on a practical example: using a semi-supervised neural network and remote sensing data to distinguish between healthy and unhealthy trees. This scenario occurs in similar contexts in the real world and can provide added value for the observation of fruit trees and forest stands. Particularly in view of climate change and its effects, it is extremely important to ensure good health monitoring of ecosystems in order to initiate appropriate measures at an early stage. An Open-Source-framework serves as the basis. It is based on a semi-supervised approach and promises to create a good neural network with comparatively little annotated data. This work shows how Deepforest can be extended from simple tree detection to multi-class health monitoring. [ABSTRACT FROM AUTHOR]

Considerable and high-quality scientific research papers play a crucial role in acquiring knowledge across various fields. Extracting information from the full text of these papers presents a challenging task. Named Entity Recognition (NER) stands out as a key step in information extraction. This recognition is indispensable for many tasks and applications requiring direct access to relevant information, such as knowledge discovery and document retrieval. However, effectively processing important contextual information remains a challenge in the literature. In our work, we introduce a supervised NER method named N-AMES (Named entity recognition using contextual Attention on Masked Entities and Sections). Leveraging the attention mechanism of the BERT transformer, our method effectively processes both global and local entity context information. By incorporating section titles into a sequence of text chunks and training the model on masked entities, our approach achieves remarkable performance. Specifically, our model achieves an F1-measure of 74.10% and 72.30% in partial matching evaluation, outperforming state-of-the-art models on two distinct full-text research paper datasets: SciREX for machine learning and CRAFT for biomedical entities. [ABSTRACT FROM AUTHOR]

The document classification (DC) task assigns predefined classes to unlabeled documents using trained models. In the medical field, DC is crucial for tasks like categorizing risk factors and classifying electronic health records. This paper addresses challenges in medical document analysis, such as the prevalence of abbreviations and acronyms. Existing classification performance in medical documents is suboptimal. The paper introduces novel feature engineering methods leveraging domain-specific knowledge to enhance classification performance. Results indicate that the Three-Stage approach surpasses related works, showcasing improved medical document classification performance. [ABSTRACT FROM AUTHOR]

This paper introduces Abstract Map Creator (AMC), a tool designed to visualize abstract spaces using heuristically defined dimensions to improve regional management. AMC aims to provide a dynamic and detailed representation of various projects, facilitating better resource allocation, monitoring, and strategic planning. The study outlines the development procedure for creating abstract maps and emphasizes the importance of integrating this tool with existing GIS technologies and ICT systems. Insights from discussions with public administration representatives highlight the need for a comprehensive, integrated tool that supports various levels of data access and ensures data security. The paper addresses potential challenges, such as the ongoing update process of interfacing systems. By visualizing both current and historical data, as well as projections, the proposed tool offers significant potential to enhance decision-making processes, transparency, and accountability in regional management. Future research directions include practical implementation, development of user-friendly software, and leveraging AI and machine learning to enhance tool functionality further. This study contributes to the broader discussion on the utility of visualizing abstract spaces for specific management purposes, emphasizing its potential to improve regional management practices significantly. [ABSTRACT FROM AUTHOR]

The International Code of Signals (INTERCO) consists of codes and signals used to communicate messages regarding the safety of navigation. These codes are used by vessels, and the signals can be sent in various ways, including flaghoist, signal lamp, flag semaphore, or as a radio message. This paper focuses only on flag signals, proposing their detection and classification using deep learning algorithms. The paper also addresses a specific scenario, where the detection and classification of flag signals are necessary for verifying the current status, operations, and behaviours of vessels, in line with the intention conveyed by the flag signal. The system discussed is regarded as a component of a larger system for ensuring navigation safety and monitoring ship behaviours near critical infrastructure such as ports, offshore wind farms, or other offshore constructions. To tackle this challenge, a convolutional neural network (CNN) has been employed. The paper delves into the process of preparing the image dataset, including annotation and augmentation, and discusses the CNN learning process based on the YOLO algorithm implementation, finally discussing the results of the computational experiment. [ABSTRACT FROM AUTHOR]

The development of the internet and social media means that people can easily convey various personal opinions or expressions. In line with this, many researchers are interested in examining the sentiments they make, considering that nowadays their opinions can be useful for various sectors such as product analysis, latest news analysis, or even political opinion analysis. Several approaches used to analyze public opinion on social media are Machine Learning and Deep Learning. This paper is devoted to finding the best AI-based models for sentiment analysis on social media especially those that are known for higher precision in complexity solving by using Systematic Literature Review (SLR). Of the many papers with the same topic interest, there are a total of 13 papers that meet our criteria which include title, methods, and results. Then, the papers are evaluated one by one in-depth and compared to find the best results. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) attacks pose a significant threat to online services by flooding targets with unusually high volumes of traffic or data, disrupting services and causing financial and reputational damage. This paper explores the workings and impact of DDoS attacks, with a variety of methods used by attackers to exploit vulnerabilities in the target infrastructure. To address these risks, this paper advocates the application of Machine Learning (ML) techniques. ML allows computers to learn patterns from data and make decisions autonomously and offers a proactive defense against DDoS attacks. Using UNSW-NB15 Dataset, this study evaluates the performance of eight ML algorithms Logistic Regression, KNN, SVM, Random Forest, Decision Tree, LSTM, MLP, and GRU, the evaluation of this study is based on Accuracy, Precision, Recall, and F1 Score metrics. The results show that Random Forest is the most effective algorithm, showing superior performance across all metrics with 97.68% accuracy. This explains the potential of Machine Learning, specifically the Random Forest algorithm. can be considered to improve security and reduce the risk posed by DDoS attacks. [ABSTRACT FROM AUTHOR]

Air is very beneficial and crucial for every living creature on earth, hence it is very important to protect the air quality in order to avoid diseases. However, due to the increase in population, some human activities have been causing detrimental damage to the air quality. Some people have realized the potential impact of this problem and have done studies on predicting future air pollution. Some implemented machine learning models such as random forest regression, support vector machine, etc, while others have utilized deep learning models in their research.. This study will implement five different models, specifically linear regression, ridge regression, random forest regression, and multilayer perceptron regression. There will be two datasets used in this paper which will be merged and processed. There will be three key evaluation metrics being used in this paper namely root mean squared error, mean absolute error, and r-squared. The results from all of the models have concluded that more optimization and factors are needed in order to boost the final result of this study. [ABSTRACT FROM AUTHOR]

Skin diseases are growing all over the world. Many times, these diseases are malignant too. Detection of the type of skin disease is highly critical for designing the best treatment procedure. In this paper, we proposed a computer aided diagnosis (CAD) approach to identify the type of skin disease. Our research paper introduces an important improvement in dermatological diagnostics by introducing artificial intelligence technology known as Convolutional Neural Network (CNN). In our approach, we have utilized a convolutional neural network-based model. We have used a swin transformer to detect the type of skin disease in ISIC 2019 data set. We have analyzed how this technology pushes the traditional methods to accurately analyze skin lesions and identifying complex patterns that may have been overlooked. With the proposed approach, the accuracy of detecting skin lesion type can be achieved up to 73%. We also address ethical concerns and envision a future where AI integrates into dermatological practice. Overall, our work not only enhances diagnostic accuracy but also contributes to a future where technology and healthcare come together to improve patients' health. [ABSTRACT FROM AUTHOR]

By combining machine learning AI model with traditional credit risk measurement model, this paper aims to more accurately measure the credit default risk of real estate enterprises. Through professional credit management knowledge, the integration of these two models can fill the gaps of traditional models outside of financial data, and use the research experience of traditional models in the financial field to provide guidance for machine learning. This paper focuses on the key issues of capital intensity, exploration of Supply Chain Finance Growth and Credit Risk Control within the Real Estate Sector. By combining qualitative and quantitative methods. Through literature research and empirical analysis, this paper develops a supply chain finance credit risk assessment index system tailored for small and medium-sized enterprises operating in China's real estate sector. The index system comprises 23 risk assessment indicators, and comprehensively considers many factors such as corporate financial status and market environment. Then, a credit risk assessment model for small and medium-sized real estate enterprises is developed from a supply chain finance perspective, utilizing genetic algorithm optimization for Support Vector Machine (GA-SVM)., and the advantages of this model compared with the traditional model in accuracy and generalization ability are verified through comparative analysis of experiments. The research results can help reduce the information asymmetry in the real estate industry, enhance the credit rating evaluation process for small and medium-sized enterprises, and furnish references to aid commercial banks in credit and credit risk management within the real estate supply chain finance sector.which has important theoretical and practical value. [ABSTRACT FROM AUTHOR]

This paper explores the application of artificial intelligence technology in ensuring the security of digital currencies. With the increasing popularity of digital currencies, ensuring their security has become a crucial concern. AI techniques, such as machine learning and deep learning, can be employed to identify and prevent security threats in digital currency systems. Additionally, it investigates how AI enhances security measures and risk control on digital currency trading platforms, offering insights into real-time risk alert systems. Therefore, through empirical research in four distinct sections, this paper continuously refines and revises the theoretical model proposed in this project. The ultimate goal is to provide new theoretical tools for the management of financial stability in the process of Digital Currency replacing M0. this project gives the research content of the four parts, which include public perception, delivery path, underlying technology and virtual currency bubble, we hope that this research can offer valuable insights to relevant field managers. [ABSTRACT FROM AUTHOR]

The traditional electrical control system has the problem of insufficient function control. This paper designs the engineering electrical control system through the learning algorithm based on fuzzy neural network. The control strategy design module combines fuzzy reasoning with neural network to design intelligent control strategy. Develop a variety of control principles and strategies that can meet the needs and characteristics of the system. The user interface module assists users to monitor and adjust the system, and has the functions of real-time data display and setting control parameters. Fuzzy neural network modeling module combines fuzzy logic with neural network to model the system. In this paper, the sliding window technology is used to collect and process data in real time. When the running time is 1 hour, the system output value is 100.2 and the output fluctuation value is 0.6; When the running time is 2 hours, the system output value is 99.8 and the output fluctuation value is 0.7. The learning algorithm based on fuzzy neural network has little fluctuation and stable performance. [ABSTRACT FROM AUTHOR]

Breast Cancer (BC) is a significant cause in women and is the leading cause of death worldwide. The analysis and diagnosis of breast cancer using medical imaging analysis is a promising research area that facilitates the decision-making of different diseases. This paper provides advanced research papers that mainly define breast cancer detection (BCD) using machine learning (ML) in medical imaging. The research articles are tabulated with their advantages, disadvantages, machine learning methods, the dataset used in their experiments, and the performance metrics obtained from their experimental results. Some research challenges and future research suggestions in breast cancer detection using ML in medical imaging are discussed. This paper has more potential and is helpful for beginners in this research field. [ABSTRACT FROM AUTHOR]

Blockchain is an emerging technology with Big data, Artificial Intelligence, and Machine Learning. It disrupted industries such as health, education, manufacturing, and banking. However, the increasing popularity of Blockchain ex- poses the scalability issues of major public blockchain platforms (e.g., Bitcoin and Ethereum) and dramatically affects its development. The scalability problem manifests in terms of Low throughput, high transaction latency, and massive energy consumption. Several reviews and studies cover these factors and their potential solutions, yet these studies need to highlight more information through actual application to natural systems or projects. This study investigates all relevant papers on current research solutions for public blockchain scalability issues. The scope of this paper is to explore the implementation of different state-of-the-art scalability solutions to natural systems and projects while simultaneously highlighting the results. This study discusses the methods and techniques used and the challenges encountered that have yet to future researchers must explore. [ABSTRACT FROM AUTHOR]

JSON Web Token (JWT) is a simple, compact way to share claims in a space-constrained environment. JWT is part of the interoperable JSON-based identity suite. Many libraries that provide JWT-based authentication and authorization exist. While the JWT standard is secure, some implementations still need to be made. This research paper delves into a comprehensive analysis of the prominent Python libraries utilized for JWT authentication. By meticulously examining these libraries, we aim to provide an in-depth understanding of their features and capabilities. Our investigation encompasses an enumeration of the distinct signing algorithms that are supported by each of these JWT Python libraries. To ensure the robustness and security of these libraries, we employ a multifaceted approach that utilizes various statistical application Security Testing (SAST) tools. These tools play a pivotal role in our assessment by not only evaluating the adherence of the codebase to the PEP8 standard but also by meticulously scanning for common security vulnerabilities and bugs that could potentially compromise the integrity of the authentication process. Our research goes beyond mere identification; we meticulously analyze each warning generated by the SAST tools, emphasizing those warnings that hold the most tremendous significance regarding potential security risks. Furthermore, our investigation extends to gauging the popularity and adoption of each library. To achieve this, we leverage GitHub statistics and harness the power of the Sourcegraph code search utility. By delving into these metrics, we gain a comprehensive view of the community's engagement, usage trends, and overall traction of each library. In summary, this paper thoroughly explores the landscape of JWT authentication in Python, encompassing library evaluation, security assessment, warning analysis, and popularity metrics. [ABSTRACT FROM AUTHOR]

Emotion AI deals with the sentiments of human beings at various domains. It is named emotion AI as using the capabilities of AI the emotions of humans would be interpreted and analysed. The objective of this paper is to learn from the experience of patients towards the healthcare facilities by studying and analysing the sentiments of the patients using machine learning. This paper focus on training the machine for reading the reviews given by patients who have used various healthcare facilities. The machine will be trained to understand the polarity for each healthcare facility in terms of cleanliness, availability of doctors, interaction of doctors with patients etc. The code is implemented in python with various libraries required for machine Learning. The code is able to extract the polarity and is able to handle the emotions of the patients for questions answered in the dataset by patients. The paper would contribute and help the patients decides which healthcare facility they shall choose based on the experiences of various other patients. For this the goodness score for every healthcare facility is calculated and implemented using Machine learning. It's the contribution of artificial Intelligence and machine learning for healthcare Domain. [ABSTRACT FROM AUTHOR]

This paper explores the synergies between collective intelligence and edge computing, presenting a novel paradigm that harnesses decentralized processing power for collaborative problem-solving. Edge devices, such as sensors and IoT devices, collect spatial data in real time from their local environments. They can incorporate machine learning algorithms to analyze spatial data, enabling quicker and more context-aware decision-making. Spatial clustering, a pivotal strategy in IoT edge computing, is examined to optimize localized data processing, enhance resource efficiency, and enable real-time analytics in decentralized environments. By leveraging the physical proximity of devices, spatial clustering contributes to the effectiveness and sustainability of IoT deployments at the edge. The paper introduces an innovative approach to adaptive spatial clustering by adopting swarm intelligence, drawing inspiration from the collective behavior of a flock of birds. Building upon the classical flock model of Reynolds, our extended model incorporates movement in a multi-dimensional space and introduces different types of birds. In this context, the birds serve as agents for discovering points with specific characteristics in a multidimensional space. The integration of swarm intelligence into spatial clustering presents a promising avenue for addressing the challenges of decentralized processing in edge computing environments, paving the way for more efficient and responsive IoT deployments. [ABSTRACT FROM AUTHOR]

This paper presents a novel framework for enhancing privacy in Vehicular Ad Hoc Networks (VANETs) by integrating homomorphic encryption with machine learning applications. VANETs, essential for Intelligent Transport Systems (ITS), face significant challenges in privacy and security due to their highly dynamic and heterogeneous nature. Our framework addresses these challenges by employing a simplified but effective machine learning algorithm, the K-nearest neighbors (KNN), to ensure the security and privacy of the network. The flexibility of the framework allows for the incorporation of other machine learning algorithms, enhancing its adaptability and efficiency in various VANET scenarios. Key to this framework is the use of homomorphic encryption (HE), a cryptographic technique that enables computations on encrypted data without the need for decryption. This feature preserves data confidentiality and allows for secure third-party computations. Our paper discusses the evolution and types of homomorphic encryption, emphasizing the importance of Fully Homomorphic Encryption (FHE) for its ability to evaluate complex polynomial functions. The paper also highlights the different domains of cybersecurity concerns in VANETs, including in-vehicle systems, ad-hoc and infrastructure networks, and data analysis. The proposed framework aims to mitigate these vulnerabilities, particularly focusing on preventing common attacks like DoS and location tracking. A significant advantage of our approach is its general nature, making it applicable to various privacy issues in VANETs. We propose the potential integration of homomorphic encryption with other privacy-preserving techniques, such as differential privacy or secure multi-party computation, to enhance computation times while ensuring robust privacy protection. [ABSTRACT FROM AUTHOR]

Diabetes mellitus remains a global health challenge, requiring innovative solutions for effective disease management. This paper offers a thorough analysis of diabetes technologies, highlighting their various roles in diabetes care. Through a thorough review of the literature and analysis of emerging trends, we explore the multifaceted impact of technology on diabetes care. We investigate the key role of continuous glucose monitoring systems, insulin pumps and smart insulin pens in achieving optimal glycaemic control. The paper also evaluates the integration of artificial intelligence and machine learning algorithms in predictive modelling for early detection of glucose fluctuations, ultimately preventing diabetes-related complications. Additionally, studies the potential of telemedicine and mobile applications in enhancing patient engagement and self-management. Moreover, the review covers advancements in closed-loop insulin delivery systems, offering insights into their clinical effectiveness and potential to revolutionize diabetes care. Ethical and privacy considerations related to the use of patient data in these technologies are discussed, emphasizing the importance of striking a balance between technological innovation and patient security. This paper's evidence synthesis underscores the increasing influence of diabetes technologies on patient outcomes, quality of life, and healthcare systems. It underscores the need for multidisciplinary collaboration between healthcare professionals, researchers and technology developers to ensure the seamless integration and accessibility of these tools to patients living with diabetes. This study serves as a valuable resource for clinicians, researchers, and policymakers, providing a comprehensive view of evolving diabetes technologies and their potential in the field. [ABSTRACT FROM AUTHOR]

The rapid growth of e-commerce platforms has emphasized the significance of personalized recommendation systems in enhancing user engagement and satisfaction. This research paper presents the development and evaluation of an innovative Product Recommendation System that leverages advanced Artificial Intelligence (AI) techniques to provide tailored product suggestions. The primary objective is to create a user-centric experience by integrating an AI assistant, enabling natural and interactive interactions. Through a comprehensive survey conducted to understand customer behaviour while purchasing product using AI, the study aims to assess the system's effectiveness in delivering accurate recommendations and providing a seamless purchasing experience. The paper contributes to the field by showcasing the practical implementation of AI-driven recommendation systems, highlighting their potential to transform e-commerce interactions. [ABSTRACT FROM AUTHOR]

The increasing exploitation of Artificial Intelligence (AI) technologies has enabled the design of user interfaces in a way that integrating artificial intelligence capabilities has become crucial in the modern digital landscape. Exploring the main features and best practices for designing user interfaces for Web applications, which effectively support and leverage AI functionalities, is currently one of the relevant topics in this context. This research work discusses the fundamental principles of user interface (UI) design, and the challenges posed by the integration of AI into web applications. It emphasizes the need to strike a balance between the AI advanced capabilities and the users' ability to understand and control the system. Furthermore, the paper highlights the importance of creating intuitive and engaging UI designs that empower users to interact with AI-driven features effortlessly. The study presents a comprehensive analysis of various UI design techniques specifically tailored for AI-enabled web applications user interfaces. Additionally, the paper explores the incorporation of AI-driven recommendation systems, personalized interfaces, and adaptive designs, which dynamically adapt to users' preferences and behavior. To validate the proposed user interface design principles, the study presents a proposal for a guidelines structure that promotes empirical evaluations through user studies and usability testing. Results collected via a survey based on measuring the effectiveness and user satisfaction of AI-enabled Web interfaces. User interfaces in real-life scenarios are presented and provides information on the impact of UI design decisions on user interaction and overall experience. The outcomes of this research work contribute to a deeper understanding of UI design for AI-supported Web applications user interfaces and offer practical guidelines for designers and developers. By embracing the suggested principles, organizations and designers can create Web interfaces that effectively harness the power of AI while prioritizing user-centricity, accessibility, and ethical considerations. [ABSTRACT FROM AUTHOR]

This paper acknowledges the need for a user-centric solution that helps with emotional regulation and stress management in children with ADHD. The paper presents a unique and comprehensive solution that integrates Reinforcement Learning (RL) algorithms to enhance user experience and aid children with ADHD to regulate their emotions and behaviours through a reward-based system. Through careful analysis of existing literature, and user requirements assessment, a comprehensive framework that integrates machine learning algorithms, physical and digital solution components through a user-centric design approach has been proposed. The core objective is to design and develop a sensory regulation system specifically tailored to the requirements of children with ADHD. Through the development of an engaging and impactful sensory regulation system, children can experience social and academic aspects of school positively while also having the opportunity to expand their social circle through inclusive play environments and ultimately improving their daily experiences. This paper aims to address the imminent need for emotional regulation and stress management tools catering to children with ADHD. By incorporating Reinforcement Learning (RL) algorithms with a reward-based interaction, this paper aims to solve critical challenges faced by children with ADHD, like emotional regulation difficulties, stress management, poor social skills, and academic performance issues so that they can lead more holistic lives. [ABSTRACT FROM AUTHOR]

Fault prediction is the process of using data analysis and machine learning models to anticipate potential defects or faults in the software system. Using only the base machine learning models for software fault prediction leads to limited performance, difficulty in handling non-linear relationships and imbalanced data, inadequate feature representation, and limited complexity handling. Hence, in order to overcome these challenges, this paper proposes a new technique for the selection of classifiers that forms a heterogeneous ensemble. The main goal is to remove or trim out the classifiers that show poor performance compared to the other base classifiers, which can result into a more effective ensemble and can produce better results. The algorithm proposed in this paper finds a set of classifiers that can perform better than using all the classifiers. The challenge that was faced was how to identify the poor-performing classifiers. This challenge is dealt with by performing an experiment using different threshold values to choose the trimmed set of classifiers. For evaluation of the proposed model, 8 different benchmark software fault datasets were used, which are taken from PROMISE and the Apache repository, and AUC is used as the performance measure. The results obtained after the experimental analysis demonstrate the effectiveness of our algorithm compared to the traditional approaches, which used all the base classifiers. There is a significant increase in the AUC values for 6 datasets out of 8, while using the average of probabilities and majority voting, it was seen that there is improvement in 7 out of 8 datasets used. The best-performing dataset by using the average of probabilities is ARC, where the AUC values increase from 0.6505 to 0.694, and while using majority voting, the best-performing dataset is XALAN, where the AUC values increase from 0.5455 to 0.679. From this, it can be seen that the proposed ensemble approach achieved higher AUC values for the tested datasets when compared to the base machine learning classifiers. [ABSTRACT FROM AUTHOR]

Missing data imputation is a critical task in the data pre-processing stage to ensure the quality, stability, and reliability of machine learning models. If missing values are imputed incorrectly, it can result in erroneous predictions and inconsistent model performance. Traditional imputation methods often struggle with complex data patterns having non-linearity and uncertainties. By integrating soft clustering principles, the proposed work provides a flexible framework for imputing missing data by taking into account the underlying inherent data pattern. To address the missing data challenges, this paper presents a novel imputation technique called Radial Basis Kernel Intuitionistic Fuzzy Ⅽ-Means Imputation (KIFCMI), which builds upon the standard Intuitionistic Fuzzy Ⅽ-Means (IFCM) technique. KIFCMI explores the application of centroid-based imputation using IFCM by incorporating the RBF kernel-induced metric in the data space as a replacement for the original Euclidean norm metric. By employing a kernel function, KIFCMI enables the clustering of data that lacks linear separability within the original space, enabling the formation of homogeneous clusters in a space of higher dimensionality. The effectiveness of the proposed imputation technique is validated on ten diverse real-world datasets obtained from the Public Library UCI with 10% and 20% missing data. The comparative analyses of the proposed technique KIFCMI, is carried out with three conventional techniques, namely fuzzy c-means imputation (FCMI), kernelized fuzzy c-means imputation (KFCMI), and intuitionistic fuzzy c-means imputation (IFCMI). The experimental results using two performance measures, namely RMSE and MAE, showcase the robustness and versatility of the proposed technique across other imputation outcomes. This research paper contributes to the evolving landscape of missing data imputation, offering insights into the practical applications of fuzzy clustering techniques. [ABSTRACT FROM AUTHOR]

Air writing is a unique method that allows individuals to freely write or draw in the air without the need for sensor devices. One of the significant applications is aimed at addressing the challenges faced by dyslexic children, who often struggle with reading, writing, and spelling. Currently, there is a lack of tailored applications to guide dyslexic children through their learning process. This paper presents a groundbreaking solution designed to assist dyslexic individuals in mastering the art of writing alphabets, digits, and words. Using various hand gestures, children can effortlessly write any character, digit, or word on a virtual canvas and memorize them easily through the hand movements. This approach not only makes learning enjoyable but also boosts a child's confidence. Additionally, the application allows children to unleash their imagination by creating doodles. While existing air writing methods have limitations, such as reliance on devices and restricting content to digits and characters within predefined boundaries. These limitations have been overcome in our proposed approach. Leveraging afordable technologies, our system caters to the needs of dyslexic learners and serves as an interactive tool to enhance their writing skills. It also provides a means of communication for the deaf and mute community. Utilizing cutting-edge technologies such as machine learning, deep learning, computer vision, and web development, we have developed a practical application that seamlessly tracks finger movements and gestures, capturing trajectories and images for classification. Our model exhibits remarkable performance, achieving a training accuracy rate of 98.57% for digit recognition, 98.80% for character recognition, and 97.09% for doodle recognition. This paper contributes valuable insights into the development of an effective and engaging tool to improve learning skills for students, particularly dyslexic children, while also addressing communication barriers for the deaf and mute community. Our approach opens up new possibilities for inclusive and accessible learning experiences. [ABSTRACT FROM AUTHOR]

Fake news generation and propagation is a major challenge of the digital age, resulting in various social impacts namely bandwagon, validity, echo chamber effects, deceiving the public with spams, misinformation, malicious content and many more. The widespread proliferation of fake news not only fosters misinformation but also undermines the credibility of news sources. The veracity of the information is a major concern at all the stages of generation, publication, and propagation. To comprehend the critical need for addressing this pervasive problem, this research paper presents a framework for automatic detection of fake news using a knowledge-based approach. An automatic fact checking mechanism is applied using concepts of Information Retrieval (IR), Natural Language Processing (NLP) and Graph theory. The knowledge base is generated using Twitter dataset, which basically contains four attributes: Subject-Predicate-Object (SPO) triplet, SPO sentiment polarity, SPO occurrence, and topic modeling. These attributes serve as pivotal indicators for the development of a knowledge base, subsequently employed to detect prevalent patterns and traits linked to deceptive or false information. We have employed Named Entity Recognition (NER) model to extract SPO triples and Latent Dirichlet Allocation (LDA) for topic modeling, thereby contributing to knowledge base generation. To evaluate the efficacy and efficiency of our proposed model, we utilize deep learning algorithms like RNN, GRU, LSTM, GPT-3 and BERT Transformer providing an acceptable level of accuracy. This research paper delivers valuable insights into addressing the proliferation of fake news on Twitter, employing data-driven approaches and advanced deep learning algorithms. [ABSTRACT FROM AUTHOR]

A critical aspect of software engineering is Software fault prediction which aims to identify and prevent errors in software systems before their release which can cause failures or issues for its users. Various techniques and tools have been developed to detect software faults, including static code analysis, dynamic testing, and machine learning-based approaches. In past few years, the world has seen a growing interest in the use of ML models for predicting software faults, as they can effectively analyse high dimensional datasets and detect complex patterns which are difficult for human experts to detect. However, developing accurate and reliable software fault detection models requires careful selection of data, feature engineering, and model evaluation. This purpose of this paper is to present a comprehensive analysis of potential applications and future research directions in the field of software fault detection. The study emphasizes the importance of identifying and addressing software faults to ensure the reliability and efficiency of software systems. Additionally, the paper outlines various approaches and techniques that can be employed for effective software fault detection. [ABSTRACT FROM AUTHOR]

In an era where the demand for efficient and practical machine learning (ML) solutions on resource-constrained devices is evergrowing, the realm of tiny machine learning (TinyML) emerges as a promising frontier. Motivated by the need for lightweight, low-power models that can be deployed on edge devices, this research paper presents an innovative TinyML model tailored to recognize Arabic hand gestures executed in mid-air. With a primary emphasis on the precise classification of Arabic numbers through these expressive hand movements, the paper unveils a comprehensive dataflow architecture. This intricate architecture processes accelerometer and gyroscope data to derive exact 2D gesture coordinates, a fundamental component of the recognition process. The cornerstone of the proposed model is the integration of Convolutional Neural Networks (CNNs), elucidating their exceptional role in achieving an impressive 93.8% accuracy rate in the classification of diverse Arabic Numbers gestures. This remarkable level of precision underscores the model's efficacy and resilience, rendering it an ideal candidate for real-time deployment in various gesture recognition scenarios. [ABSTRACT FROM AUTHOR]

Energy consumption forecasting plays a pivotal role in modern resource management and sustainable development. This paper presents a concise overview of state-of-the-art techniques and methodologies employed in the field of energy consumption forecasting, with a particular emphasis on the application of Machine Learning (ML) models. The paper surveys recent advancements, addresses key challenges, and identifies promising directions for future research in this critical domain. By examining the current landscape of energy consumption forecasting through the lens of machine learning, this review aims to offer researchers and practitioners valuable insights and guidance for enhancing the accuracy and efficiency of energy consumption pattern prediction. [ABSTRACT FROM AUTHOR]

In several places around the world, recent years have been marred by a series of indoor and outdoor fires; forest fire pose the greatest danger. This disaster affects our environment and our lives. It's often possible to avoid similar calamities, if the detection of the fire outbreak is fast enough, reliable and even early. Thanks to new technologies, there's an opportunity to take a measures and observe various phenomena continuously. In fact, it's becoming essential to develop new approaches based on significant progress in artificial intelligence related to images and videos processing. This paper describe some studies in related with deep learning algorithms of AI based on forest fires detection using satellite images.We begin by introducing various deep learning methods commonly used for forest fire detection. Following this, we review popular satellite image datasets utilized in this field. Finally, we present a comparative study of different deep learning methods based on existing research and studies on forest fire and smoke detection and prediction. [ABSTRACT FROM AUTHOR]

The widespread usage of the Internet in numerous everyday life applications has resulted in an increase in the number of phishing assaults. Phishing attacks exist in a variety of forms and have gotten increasingly sophisticated which, making traditional security measures no longer efficient. According to many researches. Methods based on artificial intelligence especially, Machine Learning (ML), and Deep Learning (DL) have proven to be an efficient solution of cyber Security. The aim of this study paper is to propose an efficient and accurate approach for enhancing phishing emails detection, based on Learning model and features selection technique to extract only the significant features. For that reason, different computational models were developed including Random Forest, SVM, and XGBoost and were tested rigorously using a specialized dataset. The experimental results revealed that the SVM model achieved the highest scores in all validation tests, with an accuracy of 0.976120, followed by the XGBoost with an accuracy of 0,966192. This demonstrates that our approach can enhance the accuracy rate with a minimum time of execution and that our model is robust and accurate in terms of email phishing detection. [ABSTRACT FROM AUTHOR]

The importance of text classification algorithms has increased due to the growing availability of large-scale data. This has led to a greater demand for efficient classification techniques and encoding algorithms. Word embedding techniques, like Glove, have shown significant success in encoding semantic relationships between words. This research paper aims to reassess the effectiveness of Glove embeddings coupled with deep learning algorithms. The impact of Glove embedding on two widely used deep learning models: Recurrent Neural Networks (RNN) and Recurrent Convolutional Neural Networks (RCNN) is analyzed. The results highlight the impact of Glove embeddings on deep learning models, showcasing significant performance enhancements in some cases while having minimal effects in others. By examining the impact of Glove embeddings on traditional ML algorithms in a previous study, valuable context for understanding the performance differences between the two approaches is obtained. [ABSTRACT FROM AUTHOR]

The advent of artificial intelligence (AI) technologies presents promising prospects for analyzing short texts, significantly impacting the psychosocial health sector. The classification and categorization of texts represent arduous and time-consuming tasks, necessitating systematic automation to optimize the processing of traditional manual workflows. This paper presents a comparative study of various machine learning (ML) techniques in natural language processing (NLP). These techniques, designed to replace manual data categorization effectively, primarily rely on traditional algorithms such as K-Nearest Neighbors (k-NN), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGBoost), as well as deep learning approaches, including fine-tuning, SetFit, and few-shot learning based on transformers. A detailed analysis of different evaluation metrics revealed that the SetFit approach, integrating the sentence-transformer model, outperformed the best traditional models, with an average accuracy of 70.74% compared to 68.69 % achieved by the SVM model. [ABSTRACT FROM AUTHOR]

This paper investigates the effectiveness of phishing awareness methods amidst the rising tide of cyberattacks. A quantitative analysis of 115 participants was conducted to assess individual vulnerability to phishing and evaluate the impact of various awareness strategies. Descriptive and inferential statistics were used to explore the influence of demographic variables on susceptibility to phishing. The findings indicate that traditional courses and interactive games are beneficial but require continuous re-evaluation. Machine learning models, including Logistic Regression and Random Forest, were developed based on these findings to predict phishing vulnerability. The analysis highlights the importance of age and field of activity in predicting vulnerability, while gender shows a less significant impact. This research underscores the shortcomings of current approaches and suggests improvements for more inclusive and adaptive strategies to counter evolving phishing threats. Future research should explore real user behaviors influenced by psychological factors and ensure balanced participant distribution to enhance the understanding of phishing vulnerability and defense mechanisms. [ABSTRACT FROM AUTHOR]

The paper introduces the assessment model of effectiveness of surrogate model for predicting indoor air temperature in buildings using a range of machine learning techniques and optimized data sampling algorithms, with the primary objectives of enhancing prediction accuracy. The main aim is to improve the forecasting accuracy. Among the evaluated models, the SVM demonstrates the highest error rates, as evidenced by its higher mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) values. A negative R² value also indicates that the SVM model is performing poorly, unable to capture the underlying patterns in the data effectively. In contrast, linear regression performs significantly better, with lower error rates and an R² value of 0.871, explaining 87.1% of the variance in the data and indicating a strong linear relationship. Gradient Boosting demonstrates excellent performance, with low error rates and a high R² value of 0.992, which almost completely covers the variance of the data and provides highly accurate predictions. AdaBoost surpasses all other models by achieving the lowest errors. With an R² value of 0.998, it accounts for 99.8% of the data's variance, making it the most precise model for this dataset. Overall, AdaBoost exhibits the highest accuracy with the smallest error rates and the highest R² value, with Gradient Boosting coming in second. [ABSTRACT FROM AUTHOR]

In the course of the research, a digital patient twin architecture based on deep reinforcement learning techniques was developed. The aim of the paper is to develop and validate a digital patient twin architecture that integrates deep learning and reinforcement learning techniques to improve the accuracy of medical predictions and individualize treatment. The existing information-analytical systems for health monitoring were analyzed, which allowed us to identify their limitations and define areas for improvement. The developed digital twin architecture integrates data from various sources including electronic health records, biometric sensors and genetic information. A deep reinforcement learning model is trained on patient data and tested to evaluate its ability to accurately predict health status. Results showed high accuracy, completeness, and F-measure scores, indicating the model's ability to effectively classify and predict health risks. The proposed system provides physicians with a tool for personalized diagnostics and development of individual treatment plans. The architecture of the digital twin of the patient is a promising solution for improving the accuracy of medical prognoses and optimizing treatment processes in clinical practice. [ABSTRACT FROM AUTHOR]

This paper presents an interactive web-based platform for clinical predictive modeling, designed for healthcare professionals. Developed using Flask, the platform integrates machine learning algorithms including K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Naive Bayes (NB), and Decision Trees (DT). It features user-friendly tools for data preparation, model training, and result visualization, simplifying complex processes through automation. The study aims to improve accessibility to Machine Learning (ML) resources in healthcare, facilitating the analysis of specifc clinical data sets. This platform demonstrates the potential to advance data-driven decision-making in clinical settings. [ABSTRACT FROM AUTHOR]

Recently, emotion recognition has become a promising area of research in the field of human-computer interaction. With the integration of Machine Learning (ML) techniques and Internet of Things (IoT) technologies, emotions can be identifed through facial expressions, voice, body language, and more. However, physiological signals are particularly valuable in this context due to their spontaneous and uncontrollable nature. In this paper, we describe the fundamental steps of an emotion recognition system based on physiological signals from preprocessing and feature extraction to feature selection through Principal Component Analysis (PCA) and classification using various ML models. We also propose a comparative analysis between different Artificial Intelligence (AI) models for classifying the four basic emotions: happiness, sadness, comfort, and anger. These emotions are represented by the commonly used dimensions of valence and arousal. Using the publicly available Database for Emotion Analysis using Physiological Signals (DEAP), our study yields interesting results. The Random Forest (RF) model achieved a top accuracy of 75.5% for arousal prediction using 25 PCA components, while K-Nearest Neighbors (KNN) reached 75% accuracy for valence prediction with 26 PCA components. [ABSTRACT FROM AUTHOR]

In the Industrial Internet of Things (IIoT), leveraging Internet of Things (IoT) technologies such as machines, sensors, and software in industrial applications has been instrumental in enhancing productivity. However, the inherent vulnerability of IIoT systems to cyber-attacks poses significant threats to critical infrastructure and security. This paper explores the improvement of IIoT intrusion detection with ML techniques, using supervised models such as Random Forest and Decision Tree on the NF-UNSW-NB15-v2 dataset. SMOTE is applied to balance the data and improve accuracy, recall, and F1-Score. Two approaches, a multiclass classification and a binary classification followed by a multiclass, are evaluated via performance metrics. This study highlights the potential of machine learning to enhance IIoT security and highlights the importance of data balance in intrusion detection systems. [ABSTRACT FROM AUTHOR]

The ability to predict energy consumption in buildings and homes is becoming an increasingly crucial aspect of energy management. This ability could help the environment and the economy by making buildings more energy efficient and reducing operational costs. This paper proposes a system for predicting energy consumption for non-residential buildings. It compares traditional machine learning (ML) models and clustering techniques such as K-means, DBSCAN and Hierarchical. The goal is to improve energy consumption predictions by analyzing energy consumption data. These features are used to group similar buildings together. We evaluate two representative time series for each cluster: an average and the time series of the building close to the centroid. ML models such as Linear Regression (LR), Step-wise LR, Tree, SVM, Efficient LR, Ensemble and Random Forest were evaluated for the two representative time series to identify the best one. Numerical results demonstrate that the Random Forest model delivered the lowest root mean square error (RMSE) of the predicted variable for each cluster, with the exception of cluster 3, where the ensemble ML model exhibited the lowest error. Finally, when evaluating the prediction based on the selected models for the rest of the time series belonging to a cluster, the average time series has the lowest RMSE compared to the time series of the building closest to the centroid of the cluster. [ABSTRACT FROM AUTHOR]