Journal of Recent Innovations in Computer Science and Technology
Journal of Recent Innovations in Computer Science and TechnologyNot a member yet
25 research outputs found
Sort by
IoT Based Weather Monitoring System for Tourists
Get PDFThe rapid expansion of tourism has necessitated the provision of weather information to guarantee the safety, convenience, and improved travel experiences of travelers. An innovative solution is provided by an IoT-based weather monitoring system, which provides precise, current meteorological data that is specifically designed for visitors. The IoT has greatly impacted and improved many aspects of our daily lives and the same is likely to transform our travels. There is nothing worse than going for a trip and forgetting that the weather in the new location is different. When it comes to tourists, the role of weather is that it may greatly affect their schedule and activities while increasing or decreasing their level of comfort. As a result, there is the need to develop the Internet of Things (IoT) for a tourist-driven weather checking system. Wireless capability allows passengers to send their data to an online server and other related data like accurate local weather updates are processed and relayed back. This system is unique in that it is capable of observing and mapping weather at a given location and can be accessed remotely from any other location. IoT refer to a system of systems in which all the devices are interconnected through the internet to form a complex network. The many sensors that are placed strategically collect data that is then sent to a cloud-based platform where weather forecasts can be quickly and accurately delivered
Attack and Anomaly Detection in IoT Sensors Using Machine Learning Approaches
Get PDFThe extensive usage of IoT sensors significantly improved the collection and monitoring of data within various application domains, such as smart agriculture and industrial automation. On the other hand, the great dependence on IoT sensors makes systems vulnerable to hacks and anomalies. In this paper, we explore machine learning approaches that can be used to protect Internet of Things sensor networks against attacks and anomalies. Due to the limited resources available to IoT devices, traditional security measures fall short. There is, therefore, a need to develop more intelligent smart detection systems. This paper examines the capabilities of machine learning in identifying patterns of anomalies in IoT sensor data. Carried out on a dataset of simulated IoT environments, the research presents the stages of data pre-processing, exploratory data analysis, and feature engineering. In addition, three models; Logistic Regression, Decision Tree, and Random Forest were constructed and tested. The results show that it is possible to use machine learning algorithms for anomaly detection in IoT domains, thereby presenting the possibilities for improving IoT security and reliability. The findings of this study are important in that they highlight how advanced analytics can help organizations deal with IoT environments
Enhancing Voice Assistant Systems through Advanced AI and NLP Techniques
Get PDFIn the rapidly evolving digital age, voice assistants have become an indispensable tool for enhancing user interaction with technology. This paper explores the design, development, and functionality of a Python-based voice assistant system, leveraging cutting-edge advancements in Artificial Intelligence (AI), Natural Language Processing (NLP), and Machine Learning. The voice assistant is designed to bridge the gap between human commands and machine execution by employing robust speech recognition techniques and advanced contextual understanding. Unlike existing models, the proposed system integrates tone and mood recognition to offer personalized responses and recommendations, thereby elevating user experience. The research delves into significant challenges in the field, such as multi-language adaptability, mood inference, and offline processing capabilities, offering innovative solutions that enhance system reliability and efficiency. By incorporating Python libraries and APIs, the assistant performs diverse tasks, from executing basic commands like opening applications and retrieving weather updates to advanced functionalities like personalized news delivery and automated emotional support. Testing revealed an impressive accuracy rate of 91.87%, demonstrating its practical viability and effectiveness. The findings underscore the growing importance of voice assistants as a transformative technology in the fields of home automation, accessibility, and intelligent systems. This paper aims to contribute to the body of knowledge in AI and NLP, addressing current limitations and setting a foundation for future developments in voice assistant technology
Sustainable It Services: Advancing the Impact of Green Computing Practices
Get PDFThe needs of the growing information technology industry have made data centers, digital platforms and cloud computing achieve a never-before-seen growth, generating an enormous energy demand and environmental footprint. This paper follows the fundamental ideas of green computing best practices and goes further to detail how they can be converted to sustainability in IT services. With the second wave of green IT, the priority remains on cost savings and energy efficiency but second place to be addressed is the need to combine the ecological responsibility, business value, customer value as well as the societal value. It is through the critiquing of current approaches like virtualization, workload management, green power utilization, policy, and industry-driven, that this paper discusses the need to make sustainability part of the IT services. It also assesses trade-offs, offers best practice and reflects on what practices are most effective in terms of aligning IT operations with long-term corporate social responsibility and the triple bottom line framework
REAL-TIME OBJECT DETECTION IN AUTONOMOUS VEHICLES USING DEEP LEARNING
Get PDFObject detection is a crucial component of autonomous driving technology. Accurate and real-time detection of every object on the road is required to ensure the safe operation of vehicles at high speeds. In recent years, there has been a lot of research into how to balance detection speed with accuracy. Real-time object detection is one of the important technologies applied to autonomous vehicles that allow vehicles to move safely through traffic. This paper focuses on the use of deep learning, the YOLOv8 algorithm in object detection of self-driving cars. The real-world data set of real driving scenarios involved includes streets, roads, and intersections/squares. The powerful interaction of the model with the deep learning algorithms defines the objects and allows for a fast decision-making process applied in autonomous systems. The metrics used to assess the models include detection rates, accuracy of the bounding die placement, and accuracy of the objects’ detection. The outcome is beneficial in refining the object detection methods and advancing the perception capability for self-driven vehicles as well as making driving automation safer
Variational Autoencoder Model for Image Processing Methods in Game Design
Get PDFThis paper investigates the use of Variational Autoencoders (VAEs) as a deep learning-based generative framework for AI-assisted image processing in game design, focusing on the procedural generation of stylized visual assets. Its application in AI-assisted image generation in game design for the generation of diverse stylized visual assets is explored in this paper. In order to learn stylistic consistent content and generate new art for the Ethereal Monsters game, we propose a deep learning-based generative approach using VAEs to learn latent representations of existing game art. Pre-processing of a curated dataset of 10,000 game sprites spans parsing colour palette and sprite patterns, creating an adapted palette for less sparse variants of sprites, and creating training and testing sets through pooling sprites into images and grouping images for a generation. A convolutional VAE architecture is trained, its (re)construction loss and visual fidelity are evaluated, a prospective error correction test is performed, and the results are analysed. We show that the VAE model can effectively capture the main features of 2D game sprites and if iterated numerous times not only does it produce an endless number of variations, but it also keeps the game-specific aesthetic properties. It is compared with existing generative methods and improved visual coherence is found, whilst diversity is saturated. It adds to the exploration of AI-driven creativity in game design, in particular an increasing number of ways to generate assets and prototypes in a scalable way
Cloud Gaming: Redefining the Future of Entertainment beyond Conventional PCs
Get PDFCloud gaming, as a paradigm in which games are rendered and streamed over remote servers, promises to transform the digital entertainment sector, as it eliminates the reliance on powerful local hardware. The paper discusses the trend of the traditional PC/ console game to modern cloud-based systems with essential performance indicators such as latency, bandwidth demands, and user experience. The mixed-method approach is used, which relies on case studies of the most successful platforms, including Google Stadia, NVIDIA GeForce Now, and Xbox Cloud Gaming, as well as on empirical reports of performance and user experience. The results indicate that cloud gaming can greatly enhance accessibility especially among users with low-end platforms or when in an emerging market, yet real-time responsiveness is limited due to the network infrastructure Consumer preference to traditional gaming remains despite its disruptive potential, given that it benefits offline play, lower-latency performance, and ownership models . The research paper concludes that the future of 5G, edge computing and AI-based optimizations will play an instrumental role in solving latency and bandwidth issues. Cloud gaming, on the whole, turns out to be a disruptive technology that can widen the access and define the future of the entertainment industry
Object Detection in Autonomous Driving with Sensor-Based Technology Using YOLOv10
Get PDFThe creation of intelligent transportation systems, such as autonomous driving and traffic monitoring, is dependent on precise vehicle recognition. Autonomous vehicles detect and recognize objects in real-time, such as pedestrians, other vehicles, traffic signs, and obstacles. This paper improves the object detection ability of autonomous vehicles (AVs\u27) by integrating technologies including YOLOv10 and multi-modal sensor fusion. This paper takes a deep learning algorithm with sensor technology, about important issues in the areas of response time, real-time processing, and detection accuracy. They have used YOLOv10\u27s architectural and optimization strategies along with a comprehensive methodology that integrates data from LiDAR, radar, and cameras to construct a trustworthy perception system for dynamic and flexible driving settings. According to the experimental results, YOLOv10 outperformed both previous versions and competing object detection models with a significantly high accuracy of 96.8%, while maintaining a processing speed of 80 frames per second. Additionally, YOLOv10 had a significantly higher recall of 94.1%, and an accuracy of 95.4%, indicating its increased effectiveness at pedestrian and obstacle identification in the autonomous driving domain. With explicit attention to accounting for occlusions and poor lighting, the authors created a strong and scalable framework for deep learning to bridge the gap between theory and application in autonomous driving. Furthermore, the extension to address these issues enhances reliability and safety in autonomous systems and will ultimately aid the development and adoption of broader autonomous technology systems
Machine Learning Based Method for Forecasting Crop Yield
Get PDFApplications of machine learning are revolutionizing data processing and decision-making, which is having a significant effect on the global economy. Given the worldwide food supply crisis, agriculture is one of the industries where the effects are most noticeable. This paper focuses on crop yield prediction based on pattern analysis with the help of the machine learning approach, which focuses on data acquisition, preprocessing, and assessment. Taking the Crop Yield Prediction Dataset as a solution, the most potential factors, including rainfall, temperature, and pesticide, have been identified to have the most influential factors in creating better prediction models. Among these, Decision Trees, Random Forest, Support Vector Machine (SVM), Artificial Neural Network (ANN), Naïve Bayes, and Long Short-Term Memory (LSTM)are the most common and are checked for their effectiveness. It brings out facts that are instrumental in analysis to improve the yields on farms and come up with possible recommendations on precision farming and sustainable agriculture. This paper aims to provide insights that can help improve farm yields
Enhancing Crop Yields with IoT Driven Smart Agriculture Systems
Get PDFAs global food demand increases amid climate change and dwindling natural resources, there is an urgent need to adopt more intelligent and sustainable farming practices. Without real-time awareness and optimization, traditional ways of farming methods do not make full use of resources and bring about below-average crop results. With Internet of Things (IoT), farmers can automate tasks, watch over operations all the time, and rely on data for making decisions. The goal of this paper is to propose and examine an IoT framework for smart agriculture meant to improve environmental conditions and crop production efficiency. There are sensors in the system that measure moisture, temperature, humidity, and light, plus LoRa and 5G connections for communication, edge units for processing, and a cloud system for detailed analysis and visualization. Through the mobile and web portal, farmers can receive immediate feedback and useful information to improve their farming. Using this system on real farms resulted in better scheduling of irrigation, better crop health, and higher overall yields. Results conclude that IoT can lower expenses for farmers at the same time as producing a larger crop, making it a realistic and flexible solution for current agriculture in remote and under-resourced regions