International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
Recent Trends in Video Surveillance System in Dense Environment: - A Review Paper
Get PDFSnow, fog, lightning, torrential rain, and darkness degrade outdoor surveillance footage. The detection, categorization, and event/object recognition capabilities of video surveillance systems in congested environments have attracted considerable interest. Real-time video analysis algorithms in various weather conditions have been enhanced by technology. Other examples include background extraction, the see-through algorithm, deep learning models, CNN for nocturnal incursions, the system for high-quality underwater monitoring utilising optical-wireless video surveillance, LVENet, and edge computing. In the current study, these methodologies improved monitoring efficiency and decreased human error. This study details these video surveillance techniques, platforms, and supplementary materials. After discussing prevalent building and architectural styles briefly, significant system evaluations are presented. This study contrasts current surveillance systems with various methods for real-time video processing under challenging weather conditions in order to provide readers with a thorough understanding of the system. The following research is also highlighted
"Sustainable Strategies in the Food Supply Chain: Evaluating Environmental Impact with Life Cycle Assessment"
Get PDFThis study aims to evaluate the environmental impact of various sustainable strategies implemented within the food supply chain, utilizing Life Cycle Assessment (LCA) as a core methodology. The paper begins by identifying critical points in the food supply chain where sustainability practices can be integrated, ranging from agricultural production to processing, distribution, consumption, and waste management. Through a comprehensive review and application of LCA, the research quantifies the environmental benefits and trade-offs of adopting practices such as reduced use of chemical inputs, implementation of circular economy principles, and enhancement of logistics and packaging solutions. The findings demonstrate that strategic interventions in the supply chain can significantly reduce carbon footprints, water usage, and waste generation, contributing to the overall sustainability of the food system. The study further discusses the implications of these strategies for stakeholders, including policymakers, producers, retailers, and consumers, highlighting the importance of collaborative efforts in achieving sustainable outcomes. Additionally, the paper explores the challenges and opportunities in scaling these practices, considering technological, economic, and social factors. The research contributes to the growing body of knowledge on sustainable food systems and offers practical insights for implementing LCA in evaluating and improving environmental performance in the food supply chain
Modeling and Validating Structural Relationship among Customer Data Privacy in E Commerce and Data Breaches.
Get PDFThis abstract provides an overview of a comprehensive study aimed at modeling and validating the structural relationships between customer data privacy practices in e-commerce platforms and the occurrence of data breaches. This research bridges the gap in understanding how the level of investment and adherence to data privacy measures in e-commerce businesses influences the likelihood and severity of data breaches.The study employs a mixed-methods approach, combining quantitative analysis of large-scale data sets related to e-commerce platforms and data breach incidents with qualitative analysis of privacy policies, regulatory frameworks, and industry best practices
Covid 19 Treatment through Advanced Artificial Neural Network Algorithm
Get PDFThe development of computer science has been phenomenal. This computer development is exerting its dominance in all fields. In today's world, the need for computer usage is increasing. All departments are computerized in some way for their use. Every day in human life new diseases is attacking man. Covid19 disease confined all the people inside the house. This impacted the economy of all the people and affected the development of all sectors. Due to this, with the development of the computer industry, this research paper aims to cure the effect of this disease and detect its functions easily. In this we find solutions using Advanced Artificial neural network Algorithm applications
A Comprehensive Analysis of Password Authentication for Enhancing Security in Internet of Things (Iot)
Get PDFRecently, there has been a significant increase in customer demands and the variety of services provided due to the increasing use of mobile devices and the development of new networking technologies such as the Internet of Things (IoTs) and Big data networking. The proliferation of future smart cities, smart transport systems, and other Internet of Things (IoT) application areas presents a significant vulnerability to a multitude of security risks that can have detrimental impacts on the economy, the environment, and society. This vast range of functions raises several security concerns, such as data protection, virtualization vulnerabilities, segregation risks, network connectivity issues, and monitoring challenges. The objective of identity and access management is to ensure that the right individuals have access to the right resources. Implementing user identification and identity verification establishes a robust security measure that effectively separates potential attackers from accessing sensitive data. This study use a Systematic Literature Review (SLR) methodology to conduct a comprehensive review of security concerns and various computing approaches to mitigate them. Despite the existence of various approaches to address the specific challenges related to application design, security, and privacy, there is still a need for a comprehensive research study. This study should focus on the challenges and requirements of targeted applications, which currently have limited security enhancement solutions
Generic Iot Application Development and Testing Ecosystem
Get PDFThese days, there are more and more types of IoT, or connected gadgets. Very few businesses or organizations are currently developing SaS (Software as a Service) platforms that enable linked devices to send sensor data to cloud servers for statistics monitoring and report generation. However, connected devices have a set physical identity and are not as dynamically adjustable, which makes the system more vulnerable. The real-time or on-demand connectivity model used by connected devices means that enhancing security could shorten the reaction time of linked devices in real time. The goal of the proposed system is to create a web platform for on-demand notifications and safe generic SaS monitoring for Internet of Things or linked devices. With the help of this platform, any device with the necessary credentials and a unique API access key can connect to a web service and send its data to a server for additional analysis. The proposed system will use business intelligence (BI) to produce graphical data displays. The system will enable the user to receive notifications on predefined triggers on designated incoming records with the aid of triggering mechanisms. This model can be used with any compatible client and supports a wide variety of embedded or computing devices for data uploading thanks to web technologies. The basic idea behind the concept is to give embedded devices lightweight security and to create a secure generic platform for all linked devices
Secure Data Transactions in Mobile Cloud Computing using FAAS
Get PDFIn recent times, security breaches have come to light in mobile cloud transactions, raising concerns about the vulnerability of data stored in mobile clouds. This data is at risk of tampering or unauthorized modification by external users, especially because it resides within a public cloud infrastructure managed by organizations. Such breaches can significantly impact the authenticity and integrity of the stored data. Mobile cloud computing (MCC) is a technology designed to facilitate the transfer of data and communication with end-users over the internet through a mobile cloud infrastructure. To address the urgent need to secure and protect data stored in mobile clouds, we propose the implementation of the Mobile Cloud-Security Model (MCSM). This innovative model is poised to provide an elevated level of data security and integrity for user data by harnessing the power of Federated Learning (FL) and Federation as a Service (FaaS). Federated Learning (FL) seamlessly integrates into the data training process, culminating in the generation of a model using the data hosted in the mobile cloud. This pioneering approach enables collaborative model training while steadfastly upholding data privacy and security. Federation as a Service (FaaS) represents a cloud-based solution that streamlines collaboration and data sharing among diverse organizations or entities. It simplifies the complex processes of configuring trust relationships, managing identities, and establishing data exchange agreements among federated entities, all made possible through the provision of Service Level Agreements (SLAs) for data stored in the mobile cloud. The user data stored in the mobile cloud will be retrieved using Machine Learning (ML) algorithms that learn from user data. Subsequently, this data is offloaded from the edge devices. The outcome of this research is to maintain user data within the FAAS cloud service with higher-level of confidentiality, security and integrity of user’s data
Perception of Groundnuts Leaf Disease by Neural Network with Progressive Re-Sizing
Get PDFIndia is the world's second-largest groundnut producer after Brazil. An major crop of oilseeds is groundnuts. Because of this, the crop's quality and yield have declined, which has had a detrimental effect on the agricultural economy. This is partly because the crop is more susceptible to various diseases. It is required to create more precise and reliable automated approaches to address this problem and improve the identification of groundnut leaf diseases. This article proposes a deep learning-driven approach based on a progressive scaling technique for the accurate classification and identification of groundnut leaf diseases. The five main groundnut leaf diseases that are the subject of this study are leaf spot, armyworm effect, wilts, yellow leaf, and healthy leaf. The proposed model is trained using both progressive resizing and conventional techniques, and its performance is assessed using cross-entropy loss. A fresh dataset is meticulously curated in Gujarat state, India's Saurashtra region, for training and validation. Due to the dataset's uneven sample distribution across disease categories, an extended focus loss function was used to correct this class imbalance. In order to evaluate the performance of the suggested model, a number of performance metrics are utilized, including accuracy, sensitivity, F1-score, precision, and sensitivity. Notably, the suggested model has a 96.12% success rate, which signifies a considerable increase in the disease identification accuracy. It's important to note that the model incorporating progressive resizing beats the basic neural network-based model based on cross-entropy loss, highlighting the potency of the recommended approach
A Deep Learning Technique to Clinch the Detection of Parkinson’s Disease using Speech and Voice Attributes
Get PDFAmong the neurodegenerative diseases Parkinson’s Disease ranks second only to Alzheimer’s disease. Though extensive research is carried out in this area there have been no biomarker suggested. At present the diagnosis and monitoring of the disease progression is possible only through clinical examination and function symptoms observation. Voice impairment has been identified as an early marker for Parkinson’s Disease and hence the research in this field is gaining popularity. Machine Learning algorithms have proved useful in analyzing the enormous data with high dimensionality. But this has not been successful in extricating features that will have a strong correlation in predicting the disease accurately. This calls for a more effective and powerful technique like Deep Learning that uses deep neural networks that can select the optimal features and can contribute in the identification of the disease. In this paper an initial step was made by designing an Artificial Neural Network model. This yielded a train and test accuracy more than ninety-nine percentage and seventy-five percentage respectively for classifying the disease but showed overfitting problem which resulted in a decrease in the performance. Hence, the Artificial Neural Network model was hyper-tuned to reduce this problem and there was a slight improvement in the performance. Two methods were employed for optimization – a regularization method early stop and another validation method called Stratified K -Fold Cross Validation. Among these the second approach showed better results by slightly reducing the overfitting issue and it yielded a train and test accuracy score of approximately ninety-nine percentage and ninety-seven percentage with K-fold as five and Stochastic Gradient Descent as the optimizer. Even though the results were promising it was unable to unravel the prime attributes that would eventually identify the disease
House Price Prediction using Machine Learning Algorithms
Get PDFHouse prices are a major financial decision for everyone involved in the housing market, including potential home buyers. A major part of the real estate industry is housing. An accurate housing price prediction is a valuable tool for buyer and seller as well as real estate agents. The study is done for the purpose of knowledge among the people to understand and estimate the pricing of their houses. The prediction will be made using four machine learning algorithms such as linear regression, polynomial regression, random forest, decision tree. Linear Regression has good interpretability. Decision tree is a graphical representation of all possible solutions. Polynomial regression can be easily fitted to a wide variety of curves. Regression and classification issues are resolved with random forests .Among the given algorithm, Random forest provides better accuracy of about 89% for given dataset