International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
Daet AirWatch: A Framework for Measuring and Visualizing Air Pollution Levels in Daet, Camarines Norte
Get PDFAir pollution presents serious threats to public health and the environment, thus, effective techniques for mitigation and monitoring are required. In this study a comprehensive framework that integrates low-cost sensors, GPS technology, and data processing using an Arduino Uno and an ESP8266 Wi-Fi module is presented to address air pollution. The proposed framework allow real-time collection of pollutant data, including (PM), (VOCs), (CO), and ozone, alongside location information, temperature, and humidity. The gathered data is subjected to thorough processing, which includes converting sensor output values and calibrating and normalizing raw sensor readings. Moreover, the framework includes algorithms for translating pollutant concentrations into Air Quality Index (AQI) values, giving standardized metrics for evaluating air quality levels. The data is processed and then sent to an MQTT Broker for quick sharing of information and alerting about dangerous conditions. Additionally, the platform includes a user-friendly interface that displays pollution data on a web map, improving transparency and community awareness. By utilizing its effective data collection, processing, and visualization features, the suggested framework seeks to enhance public health results by giving people and communities the ability to make informed choices and take proactive steps to reduce air pollution dangers
Myriad Wavelet Transformed Certificateless Signcryptive Extreme Learning Steganography for Secure Medical Image Transmission
Get PDFMedical imaging is a vital part of the healthcare sector which facilitates the communication of medical images like X-rays, MRIs, and CT scans from one place to another. Medical images are now being sent over public networks due to improvements in the healthcare industry, which creates potential security challenges like authentication, integrity, and confidentiality. The medical images size being transmitted has also become a major concern after the rapid growth of computer networks and information technology. Therefore, ensuring secure medical image transmission and efficient compression are crucial aspects of modern healthcare systems. To enhance the security of image transmission while reducing image size, an efficient technique known as Myriad Wavelet Transformed Certificateless Signcryption Extreme Learning Steganography (MWTCSELS) has been introduced. The MWTCSELS involves four distinct processes namely image preprocessing, image compression, signcryption, and embedding. The first step is to denoise the medical image, the Wilcox indexive myriad filtering technique is used. Then after the preprocessing is done by compressing the image and minimizing the storage space in the communication, the Burrows-Wheeler Hilbert linear curve transform is used. In the third step, the Schmidt-Samoa cryptographic Certificateless Signcryption method is employed to encrypt the input image securely. Lastly, the Mar Wavelet transformed Extreme Learning Machine is used to embed confidential data into the image using a Stego key. The resulting Stego images can be transferred to the receiver end. The original images are restored from the Stego images by the authorized receiver after performing the extraction process. Subsequently, the unsigncryption and decompression processes are carried out to restore the original medical image with enhanced security. An experimental evaluation is conducted using medical chest X-ray images, to measure its performance based on aspects like peak signal-to-noise ratio (PSNR), compression ratio, space complexity, confidentiality rate, and integrity rate. The obtained results demonstrate that MWTCSELS is more efficient in achieving higher peak signal-to-noise ratios and compression ratios while maintaining strong confidentiality and utilizing less storage space compared to existing approaches
Real- Time Traffic Violation Detection Using Deep Learning Approach
Get PDFThis project tackles the growing issue of traffic violations in India. With a large population, rising commutes, and limitations in traditional traffic management, a real-time solution is crucial. This project proposes a deep learning approach for real-time traffic violation detection specifically designed for Indian traffic scenarios.
The system utilizes YOLOv8, a state-of-the-art object detection algorithm from Ultralytics, to identify and classify traffic violations in real-time video feeds. This approach aims to improve traffic safety and enforcement by automating violation detection
Edge Computing for AI and ML: Enhancing Performance and Privacy in Data Analysis
Get PDFCentralised cloud computing paradigms are encountering difficulties with latency, bandwidth, privacy, and security due to the exponential growth of data volumes produced by sensors and Internet of Things (IoT) devices. One potential approach to these constraints is edge computing, which moves computers and storage closer to the data sources. With this paradigm change, data privacy is improved, network congestion is decreased, and real-time processing is made possible. Aiming to improve the efficiency and confidentiality of data analysis applications powered by artificial intelligence (AI) and machine learning (ML), this article investigated the possibility of edge computing. We provide a thorough analysis of the latest developments in edge computing frameworks, algorithms, and architectures that allow for safe and fast training and inference of AI/ML models at the edge. We also go over the main obstacles and where the field may go from here in terms of research. Our research lays the groundwork for future intelligent edge systems by demonstrating the substantial advantages of edge computing in facilitating low-latency, energy-efficient, and privacy-preserving AI/ML applications.
 
Hypervisor-Level Ransomware Detection in Cloud Using Machine Learning
Get PDFRansomware attack incidences have been on the rise for a few years. The attacks have evolved over the years. The severity of these attacks has only increased in the cloud era. This article discusses the evolution of ransomware attacks targeting cloud storage and explores existing ransomware detection solutions. It also presents a methodology for generating a dataset for detecting ransomware in the cloud and discusses the results, including feature selection and normalization. The article proposes a system for detecting attacks in virtualized environments using machine learning models and evaluates the performance of different classification models. The proposed system is shown to have high accuracy of 96.6% in detecting ransomware attacks in virtualized environments at the hypervisor level
Unmasking the Threat: Exploring Effective Techniques for Investigating ATM Malware Through Digital Forensic Analyses
Get PDFHackers have developed new techniques to directly breach a system or device, responding to the surge in numerous cybercrimes. Criminals frequently attack automated teller machines (ATMs) because of the vulnerabilities they present. ATM security must monitor and investigate these attacks because ATMs may contain and manage enormous sums of cash, making them good targets for hackers. Because of this, ATM security needs to monitor and investigate these assaults. Because automated teller machines may hold and handle significant quantities of money, the security at ATMs needs to monitor and analyze assaults of this kind. In the present study, using Studio to analyze ATM malware is essential to identifying malware signatures and behaviours that can improve ATM security. Banks and ATM manufacturers must implement specific measures to prevent ATM malware attacks. Based on present research on ATM malware analysis, researchers have uncovered critical insights that are highly beneficial for those seeking to investigate Malware aimed at breaching automated teller machines (ATMs). It is an invaluable tool for conducting such investigations. This paper will serve as a means of sharing insightful findings and aiding others in deepening their understanding of this crucial topic
Transform Domain-Based Perceptual Detection and Reduction of Blocking Artifacts
Get PDFIn this paper, provide a simple and effective method for measuring blocking artefacts with an ideal 2-D step function in this study. First, a basic edge detection technique for measuring blocking artefacts is proposed. The ideal 2-D step function is chosen based on the presence of blocking artefacts in the edge image. The blocking artefact reduction algorithm in frequency domain is designed to extract all of the parameters required to detect the presence of blocking artefacts and replace the optimal step function with a ramp function by replacing the coefficient of the first row of horizontal blocks with the coefficient of the shifted block. The proposed strategy was tested on various standard benchmark photos and found to increase the perceptual quality of JPEG compressed images after blocking artefact removal with the proposed method
System for Entry and Advancement in E-commerce, Case: Retailers of Clothing and Accessories in the City of Torreón, Coahuila Mex.
Get PDFThe present study addresses the issue of a lack of knowledge to engage in electronic commerce, which has resulted in a series of imbalances in the commercial dynamics of micro and small enterprises. This is because online sales channels are causing a greater displacement of products that offer advantages compared to the traditional sales scheme. Therefore, the design and implementation of a system for entering and advancing in electronic commerce is proposed. All of this is done through surveys applied to managers, directors, and owners of micro and small retail businesses in clothing and accessories in the city of Torreón, Coahuila. Strategies, factors, and conditions for venturing and advancing in e-commerce sales were identified. The corresponding dimensions that directly influence the success or failure of a micro or small retail business in clothing and accessories in online sales were defined. The resulting instrument was validated using the Delphi method with the input of 10 experts, followed by a pilot test applied initially to 33 directors, managers, or owners of micro or small businesses. The Cronbach's Alpha was then calculated for its reliability
Analysis of Fault Detection in Analog Circuits Using WSF-SKC Optimized SVM Technique
Get PDFMany industrial applications and control systems depend heavily on analogue electrical circuitry. The conventional method of diagnosing such circuit faults can be time-consuming and erroneous, which might have a severe impact on the industrial output. The fault detection and analysing of analogue circuits with intelligent effective model is proposed in this work. The suggested technique primarily consists of two main stages one is extraction of features and the other is classification of faults. The analysis is performed on the response of frequency in analogue circuits. For extracting features particle swarm optimization (PSO) is utilized. The PSO is used to evaluate the fitness function of Wilks A-Statistic Filters sallen-key circuit (WSF-SKC). With fault characteristics retrieved using the particle swarm approach that are carefully selected, the fault classes may be separated more quickly. To categorise different failures in a benchmark circuit, a Support Vector Machine (SVM) classifier is built. Utilising firefly optimisation, the classifier is improved. Different fault codes were tested in experiments for defect detection and identification. The findings of the experiment indicate that this proposed technique can significantly increase the accuracy of fault diagnosis. The accuracy obtained for WS-LPF is 99.95%, WS-HPF is 99.97 and WS-BPF is 99.90% respectively
New Cloud-Based Service for Broadcasting and Identification for Solving Data Traffic Re-Using for Mobile Communications
Get PDFIn recent decades, the majority of mobile communications data traffic has relied on RF technology. Even if optimization efficiency for use or reuse is implemented, there are limits to the growing traffic demand for RF communications. Visible light communications (VLC) is a new technology that can work with RF to overcome these limitations. The standard for VLC was published in 2011 as IEEE 802.15.7, which specifies specifications for the MAC layer and PHY layer. This standard is one of the first for this technology. The light emission decoding operation at the receiver in IEEE 802.15.7 is mainly based on photo detectors. However, with the development of image sensors (photodiode arrays) in smart devices, changes to the IEEE 802.15.7 specification are being considered. This expansion will primarily focus on communications with image sensors, called optical camera communications (OCC). In this paper, we analyze the performance of camera communication systems based on different types of image sensor architectures. We then propose OCC-ID, a novel streaming service application that uses camera communication and a cloud model. The proposed architecture is a general implementation scenario for camera communications. Optical camera communication has great potential in future wireless communications due to the advantages of VLC and business trends. A revision of the IEEE 802.17.5 standard is currently under study. However, OCC's issues regarding timing, data rate, and interference still need to be resolved. Synchronization is an important issue because the signal received from the camera is a discrete image from the transmitter without any feedback information and because camera communication applications are based on a transmission topology. Roller blinds have more advantages in terms of timing than overall blinds. In this study, we present and evaluate the performance of two image detection techniques, namely rolling shutter and global shutter. The performance of the two image sensors and their considerations will play an important role in the standard's contribution. Finally, we propose a new service application for OCC based on cloud architecture, called OCC-ID. Invisible identification can be accomplished using visible light communications, camera communications, and cloud computing technology. The ID is integrated into the optical channel using OOK or OOK frequency shift modulation. The receiver uses the camera to decode the information embedded in the LED and then transmits it to the cloud server transmission link based on the detected ID. The OCC-ID system shows the advantages of dynamic content management compared to traditional identification systems