International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
A Review: Internet of Things with Machine Learning to Develop Intelligent Systems
Get PDFA fresh era of internet-connected sensing gadgets that bridge the gap between the real and virtual worlds has begun, thanks to the rapid advancements in hardware, software, and communication technologies. About twenty-five and fifty billion internet-enabled gadgets are predicted to be in use worldwide. The term "Internet of Things" is a term used to signify a system of electrical devices that communicate with one another. There is a wide variety of infrastructure, retail, transit, and individual healthcare services and applications made possible by the Internet of Things. IoT is a driving force behind the evolution of the Internet and other forms of modern communication technology. Smart computation and evaluation of massive data are crucial to the growth of Internet of Things applications. IoT applications may benefit from data science tools by discovering new patterns and insights in data. Industry applications of data science with the Internet of Things focus on volume, velocity, and pattern identification. With the help of machine learning's predictive analysis, programs can now anticipate both welcome and unwanted occurrences. Thus, machine learning systems not only identify out-of-the-ordinary conduct but also aid in deducing and predicting broader societal tendencies. Continuing modification and monitoring is necessary for efficacy and effectiveness in data analysis. There are two sections to this article: the first discusses the many uses of the Internet of Things where machine learning plays a role in creating an intelligent system, while the second looks ahead to the potential of IoT and machine learning in the advancement of communication devices. Questions such as "What is the classification of artificial intelligence that can be implemented in IoT?" and "How could machine intelligence be implemented in IoT applications?" will be answered in this article
Benchmark Evaluation of Image Fusion algorithms for Smartphone Camera Capture
Get PDFThis paper investigates the trade-off between computational resource utilization and image quality in the context of image fusion techniques for smartphone camera capture. The study explores various combinations of fusion methods, fusion weights, number of frames, and stacking (a.k.a. merging) techniques using a proprietary dataset of images captured with Motorola smartphones. The objective was to identify optimal configurations that balance computational efficiency with image quality. Our results indicate that multi-scale methods and their single-scale fusion counterparts return similar image quality measures and runtime, but single-scale ones have lower memory usage. Furthermore, we identified that fusion methods operating in the YUV color space yield better performance in terms of image quality, resource utilization, and runtime. The study also shows that fusion weights have an overall small impact on image quality, runtime, and memory. Moreover, our results reveal that increasing the number of highly exposed input frames does not necessarily improve image quality and comes with a corresponding increase in computational resources usage and runtime; and that stacking methods, although reducing memory usage, may compromise image quality. Finally, our work underscores the importance of thoughtful configuration selection for image fusion techniques in constrained environments and offers insights for future image fusion method development, particularly in the realm of smartphone applications
An Improved YOLOv8-Based Method for Small Object Detection in UAV perspective
Get PDFThe target objects in UAV aerial images are usually smaller targets, and the detection of such small targets is an important research area. Although the progress of target detection is constantly improving thanks to the advancement of deep learning technology, the accuracy of small target recognition in images still poses a great challenge. This study proposes an improved YOLOv8 algorithm to improve the performance of the small target object detection algorithm. This method proposes a C2F-DCNv2 module that integrates deformable convolutional network v2 (DCNv2) to replace the C2F module of the original backbone part; in addition, a Dynamic Head (DyHead) with a self-attention mechanism is used on the head) replaced the original detection head. Through training and testing in the VisDrones2019 data set, it is shown that the method proposed in this article reached 37.9% in the mAp50 indicator in the verification data set, and the average detection speed was 33.7 FPS. Compared with the results of the baseline model, the results increased by 3.6%. Experimental results show that the target detection algorithm proposed in this article significantly improves the recognition effect of small targets in UAV aerial images
An Influence of Data Visualization on the Decision-Making Process in the Business World
Get PDFData visualization has advanced from static representations to dynamic, interactive tools that have a big influence on how businesses communicate and make decisions. The impact of dynamic data visualization on corporate communication and decision-making is examined in this research. Customers are able to make better choices by gaining a more thorough knowledge of their financial data via interactive features, large databases, and access to a variety of information sources. Additionally, press releases with well-designed data visualizations expose brands to a wider audience and make a greater impact on readers. However, issues like data oversimplification, algorithmic human limits, and an excessive dependence on graphics present possible issues. Data visualization is still necessary and essential for turning unprocessed data into insights that can be put into action, despite these obstacles. Compelling communication and decision-making are worked with by various data visualization draws near, for example, line outlines, bar graphs, candle diagrams, region graphs, skyline graphs, cascade diagrams, timetable outlines, and multiline graphs. These graphs are customized to specific data and bits of knowledge. In the present data-driven professional workplace, data visualization gives associations an upper hand by further developing communication, decision quality, and hierarchical execution
Cyberbullying Framework and Trends on Social Media Platforms: An Analysis through Indian Perspectives from Real-World Data
Get PDFCyberbullying has become a prevalent problem that has deep effects on people's mental health and social interactions, especially on social media. This study presents an examination of cyberbullying examples and patterns inside the Indian setting, using genuine information removed from different virtual entertainment stages. The research aims to shed light on the distinct cultural, social, and technological factors that influence cyberbullying dynamics in the region by focusing on Indian perspectives. The study examines the prevalence, characteristics, and dynamics of cyberbullying incidents on social media platforms used by Indian users through a combination of descriptive, content, and network analysis. The findings shed light on the nature and extent of cyberbullying in India, as well as the types of cyberbullying behaviors, the demographics that are targeted, and popular platforms. Besides, the review investigates fleeting patterns, geological varieties, and social subtleties in cyberbullying designs, offering significant bits of knowledge for policymakers, teachers, and virtual entertainment organizations looking to address cyberbullying successfully. This research contributes to the development of targeted interventions and strategies aimed at creating a safer and more inclusive online environment for Indian users by comprehending the specific difficulties and dynamics of cyberbullying within the Indian framework
Novel Software Hybrid Testing Model by Using Trusted Computing Group Technology
Get PDFSoftware testing is a procedure that includes executing a program or application while checking for any errors or bugs in order to produce software that is free of defects. Only testing (software testing) can determine the quality of any software. Worldwide technological advancements have resulted to a development in the number of verification techniques and methodologies available for testing software before it goes to production and possibly makes its way into the market. Thus, automation testing has impacted the testing procedure. Automation tools are used for software testing, which not only minimizes the number of people using the application but also reduces the possibility of errors even with testers testing. Therefore, to increase the efficiency of testing this hybrid model is described. So, by using this testing errors can be detected accurately. This novel software hybrid testing model by using Trusted Computing Group (TCG) technology shows accurate result while testing the software. Hence, this model shows better results in terms of accuracy, time and precision
Design and Analysis of Students Academic Performance Prediction System Using Improved Machine Learning Methodologies
Get PDFAcademic achievement, social justice, and economic progress all depend on having access to higher education. But dropout rates are a big problem for schools all throughout the world. A number of factors, including socioeconomic status, contribute to the large variation in dropout rates among nations. To improve retention rates and implement effective interventions, at-risk students must be identified early. This study uses a range of machine learning techniques to predict whether students will succeed academically or drop out. We assessed the demographic, socioeconomic, academic, social, and macroeconomic characteristics of students enrolled in distinct majors The dataset includes 35 attributes, including special educational needs, gender, scholarship status, age at enrolment, debt status, tuition fee status, marital status, application mode, course, attendance type, prior qualifications, nationality, parental qualifications and occupations, and curricular unit performance. The data was pre-processed by identifying relevant classes and attributes, eliminating outliers using the Interquartile Range (IQR) method, and removing negative correlations from features. After normalizing the dataset using Standard Scaler, we divided it into two sets: a training set, which accounted for 67% of the total, and a testing set, which included the remaining 33%. Grid search was used to optimize the hyperparameters. Six classification algorithms—SVM, Decision Tree, Random Forest, Naive Bayes, K-Nearest Neighbors (KNN), and Logistic Regression—were used to create prediction models. The SVM model was shown to have the best accuracy, precision, recall, and F1-score. Compared to Naive Bayes, KNN, and Decision Trees, Random Forest and Logistic Regression performed better. The results demonstrate the efficacy of Random Forest, SVM, and Logistic Regression models in forecasting students' school departure times. This study highlights the importance of machine learning in improving educational administration and raising student achievement by giving schools useful tools for early risk assessment and tailored intervention tactics
Enhancing Road Safety Through Ai: A Comprehensive Analysis of Accident Prevention Strategies
Get PDFThis paper focuses on integrating AI to improve road safety by designing an AI approach, Random Forest Classifier, for estimating the severity of accidents. By leveraging a comprehensive dataset containing variables such as weather conditions, speed, and traffic flow, the study involves several key methodologies: parsing the data, feature extraction, model testing, and tuning. The developed model got an accuracy equal to 85% and had satisfactory performance indicators with the required precision of 82%, the recall value of 78%, and the F1 score of 80%. Based on these findings, it can be concluded that the Random Forest model is able to pinpoint and categorise the level of accidents, which leads to a better tool for enhancing the safety of roads. In the final phase of this study which is the deployment phase, the trained model was serialized and saved as random_forest_model.pkl of traffic forecasting and analysis which can be applied directly to traffic signal control systems. The integration of this AI model into operational frameworks enables the prevention of accidents that have the potential of occurring as well as improving on the traffic flow by benefitting from real-time data to provide predictions. It becomes clear that the development of AI technologies to a certain extent can reveal the prospects for not only foreseeing the severity of the accident but also assessing the measures introduced in the field of safety. Possible directions for future research will be the improvement of the model utilization of more samples and study of other methods of machine learning to increase the accuracy and efficiency of the operating factors
Comparing NLP Tools and AI Generators in the Context of Achieving Optimal Textual Analysis in an Educational Setting
Get PDFIn recent years, automated tools have played a pivotal role in reshaping research within the humanities and social sciences. The term "Digital Humanities," coined in 2001, according to Ref. [1], introduces a groundbreaking approach that empowers researchers to delve into texts without physical contact. This approach highlights the potential benefits of micro and macro analysis when integrated with humanities studies. In this study, students explore the dual facets of digitalization accessible through the Internet: NLP Tools and AI generators. Implemented in a semester-course at the University of Athens under the umbrella of "Digital Humanities," the academic program spans various foreign language departments. Within this framework, students employ NLP online tools to conduct comprehensive textual analyses, including tasks such as extracting term frequencies within corpora and assessing texts based on linguistic attributes, density, readability, and other relevant parameters. Specifically, the integration of ChatGPT is recommended for literary texts in Italian, Greek, or English, offering students a rich exposure to online tools that seamlessly blend applied linguistics with literary analysis. The core of this proposal revolves around the conceptualization of an instructional activity where students employ sophisticated NLP online tools like Voyant Tools. Subsequently, they replicate the same analytical process using ChatGPT [2] for the identical text, leading to a comparative evaluation of the outcomes. In the realm of big data, a Natural Language Processing (NLP) tool proves advantageous due to its specialized design for processing extensive corpora. However, limitations arise in the free edition of ChatGPT, as it doesn't support lengthy texts. Consequently, the applicability of this investigation and the ensuing comparison of these two methodologies are confined to instances where the literary text under consideration is a poem or constitutes a small passage from a novel
Contributions as a Scrum Master: Facilitating Agile Project Management in Bioinformatics Research with AI
Get PDFIn this research, Agile approaches, AI algorithms, and project management tools are integrated with bioinformatics. Analysis of computational models and implementations of AI techniques like CNNs, RF, and K-Means Clustering is covered. Comparisons focus on algorithm selection, while Agile project management tools like JIRA and Trello are discussed. Collaboration and workflow efficiency are stressed in the conclusion. Future developments include AI integration, Agile methods, and bioinformatics project management systems