Journal of Computer Based Parallel Programming

An Empirical Analysis of Blockchain Using a Decentralized Technique for Electricity Load Dispatch

R. Naveenkumar, Rubi Sarkar — Fri, 19 Jan 2024 00:00:00 +0000

In the dynamic landscape of technological evolution, the imperative for progress remains constant. Much like the inherent law of nature, technological advancements play a pivotal role in the development of countries, regions, and areas. A critical facet contributing to this development is the "Power Sector," universally acknowledged as the backbone of a nation's progress. Therefore, it is paramount that the power generation sector consistently employs cutting-edge technology to ensure optimal outcomes, including minimized costs, reduced time, and high-quality output.

Over time, modern technology has undergone significant transformations. This paper explores the transition from traditional "Load Dispatch Centres" in interconnected power systems to more contemporary solutions. These centres traditionally formulate plans for all power plants to generate the required power with minimal costs, leveraging historical data to predict current load dispatch schedules. While effective, the centralized nature of these systems poses limitations. This paper proposes the integration of blockchain technology to address these challenges, specifically in the context of a private blockchain. By leveraging the features of a distributed network, a private blockchain can revolutionize load dispatch operations, eliminating centralization-related restrictions and reducing dependence on historical data.

Tree Protection System

Paras Sutar, Sarvesh Salunkhe, Jahid Desai, Arjunsingh Rajput, S. A. Salunkhe — Thu, 04 Apr 2024 00:00:00 +0000

Illegal logging is an ongoing environmental problem that threatens ecosystems and sustainability. To combat this problem, we propose an innovative tree protection system using IoT and automation-based combined concepts. Two different prototypes with the same boards have been developed: one integrating sensors such as an accelerometer and communication modules to monitor vibrations caused by attempts to cut down trees, and the other with GSM capabilities for real-time alerts. This system aims to detect and quickly report unauthorized felling of trees, thereby contributing to sustainable forest management and environmental protection. The primary objective of the proposed system is to detect and alert authorities to any suspicious or unauthorized activities related to tree felling. Using this tree protection system based on the Internet of Things and automation, we aim to contribute to the protection of our natural environment by discouraging illegal tree-cutting and promoting sustainable forest management practices.

Artificial Intelligence Algorithms: Conspectus and Vision

Arpita Tewari — Mon, 08 Apr 2024 00:00:00 +0000

Artificial Intelligence (AI) is crucial for our survival and has evolved over six decades. It employs various algorithms and is essential for digital transformation solutions. AI technologies, such as neural networks for structured data and natural language processing (NLP) for unstructured data, are used in various domains like IoT, cybersecurity, mobile, business, health, and social media. This article presents a comprehensive view of AI algorithms and their applications, elucidating their fundamental principles and suitability in various practical domains. The paper aims to serve as a valuable resource for academia, industrial professionals, and decision-makers in real-world scenarios and application domains, focusing on the technical perspective.

The challenges and potential research directions based on this study are also emphasized by the author. This paper has a comprehensive objective of acting as a valuable resource for academia, industrial professionals, and decision-makers in diverse real-world scenarios and application domains, with a specific emphasis on the technical perspective.

The subsequent document elucidates the paramount methodologies and techniques, while also comparing the advantages and effectiveness of modern algorithms, and showcasing their noteworthy applications.

Blockchain-Powered Direct Farm-to-Consumer Supply Chains

Dattatray G. Takale, Parikshit N. Mahalle, Bipin Sule — Thu, 11 Apr 2024 00:00:00 +0000

This research paper explores the implementation and impact of blockchain technology in enhancing direct farm-to-consumer supply chains. With the increasing demand for transparency, traceability, and sustainability in food systems, blockchain offers a promising solution to revolutionize agricultural supply chains. By enabling secure, decentralized, and immutable record-keeping, blockchain facilitates the direct delivery of agricultural products from farmers to consumers while ensuring authenticity and trust. This paper examines the key components, benefits, challenges, and potential applications of blockchain-powered supply chains in reshaping the future of food distribution. Case studies and empirical evidence are analysed to illustrate the practical implications of blockchain adoption in fostering transparency, reducing intermediaries, enhancing efficiency, and empowering stakeholders across the agricultural ecosystem. Furthermore, the paper discusses future research directions, regulatory considerations, and scalability issues to fully harness the transformative potential of blockchain technology in creating more resilient, equitable, and sustainable food systems.

Deep Learning and Machine Learning for Timely Detection of Parkinson's Disease

Rahul A Patil, Deepak R Derle — Thu, 18 Apr 2024 00:00:00 +0000

Parkinson’s disease (PD) is a degenerative neurological disorder with a significant societal impact, which demonstrates the need for early-stage diagnosis and treatment. This research investigates the potential of Deep Learning and Machine Learning methods to support timely PD diagnosis. The proposed model leverages multiple data types such as medical imaging, sensor data, and clinical assessments to detect subtle patterns that indicate PD’s early stages. The dataset was collected to investigate the diagnostic value of speech and voice disturbances caused by PD. Class imbalance is the chief fault of the model overfitting and generalization errors. It is the disparity between one class, which includes all the most samples, and the other class, which includes all the least samples. This research addresses this flaw by employing three sample strategies. By aligning the number of samples in each class via dataset balancing, the classifier’s performance is improved and the problem of overfitting is minimized. The proposed hybrid model demonstrated effectiveness through a myriad of metrics used in evaluating its precision, accuracy, recall, and f1 score. Testing with a balanced dataset utilizing random oversampling revealed the simulation performed with optimal accuracy, recall, and f1 score. When employing the SMOTE technique, it generated 100% precision, a remarkable 97% recall, an outstanding AUC score of 99%, and a strong 91% f1 score. In brief, early returns signify a promising outlook, validating the competency of deep and machine learning methods in bettering the diagnosis of Parkinson's disease–thus empowering earlier treatment choices. Further validation involving more substantial datasets and clinical studies will be required to ascertain the feasibility and viability of the proposed approach. Larger-scale assessment may also provide deeper insight into maximizing performance metrics and optimizing for real-world diagnostic assistance.