scispace - formally typeset
Search or ask a question
JournalISSN: 2581-9429

International Journal of Advanced Research in Science, Communication and Technology 

Shivkrupa Publication's
About: International Journal of Advanced Research in Science, Communication and Technology is an academic journal published by Shivkrupa Publication's. The journal publishes majorly in the area(s): Computer science & Artificial intelligence. It has an ISSN identifier of 2581-9429. It is also open access. Over the lifetime, 3137 publications have been published receiving 428 citations.

Papers published on a yearly basis

Papers
More filters
Journal ArticleDOI
TL;DR: A brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders are provided.
Abstract: Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.

89 citations

Journal ArticleDOI
TL;DR: The objective of the project is to promote green power and to improve smartness of electric vehicle by monitoring the battery parameters such as voltage, temperature, current and charge avaibility by using IoT techniques.
Abstract: This paper describes the application of IoT Technology for monitoring different parameters of battery of electric vehicle. Electric vehicle totally depends upon the source of energy from the battery. In this project, the idea of monitoring the performance of the vehicle using IoT techniques is proposed, so that monitoring can be done easily and directly. The objective of the project is to promote green power and to improve smartness of electric vehicle by monitoring the battery parameters such as voltage, temperature, current and charge avaibility. Also, these values displayed in cloud, which brings the concept of Internet of Things (IoT). The IoT based battery monitoring system consist of two major parts i) Monitoring device and ii) User interface. Based on experimental results, the system is capable to detect battery performance.

22 citations

Journal ArticleDOI
TL;DR: A comprehensive overview of blockchain technology is provided in this paper , where the authors compare some common consensus algorithms utilized by various blockchains and provide an overview of the architecture of blockchains.
Abstract: Blockchain, which is the backbone of Bitcoin, has recently received a lot of attention. Blockchain functions as an immutable ledger that enables decentralized transactions. Numerous fields, such as the Internet of Things (IoT), reputation systems, and financial services, are being covered by blockchain-based applications. However, blockchain technology still faces numerous difficulties, such as scalability and security issues, that need to be resolved. A comprehensive overview of blockchain technology is provided in this paper. First, we compare some common consensus algorithms utilized by various blockchains and provide an overview of the architecture of blockchains. In addition, a brief list of recent advancements and technical difficulties is provided. In addition, we outline potential blockchain trends for the future.

20 citations

Journal ArticleDOI
TL;DR: A smart helmet can detect the accident's locations also save lives and makes two-wheeler driving safer from previously and is propounded in this paper.
Abstract: A motorcycle frequently called motorbike or two-wheelers, which is the most used than another form of automobiles because of its low price. But another side, this is the most unsafe automobile. The accident can happen for driving fast or drunk driving. Safety and security in vehicle traveling are a pre-eminent concern for all. With the rapid urbanization and staggering growth of transport networks like two-wheeler vehicles, safety on the roads and security on the bike has emerged as an inescapable priority for us. It has expanded the rate of accidents, which leads to several damages with loss of lives. In many circumstances, we cannot able to detect the accident's location. A helmet is a form of protecting gear worn to keep safe the head from injuries. More specifically, the helmet aids the skull in protecting the brain. A smart helmet can detect the accident's locations also save lives and makes two-wheeler driving safer from previously. This paper propounds a smart helmet system to avoid the accident. The system divides into three parts helmet circuit, automobile circuit, and mobile application. At first, the helmet circuit has IR and alcohol detection sensor. The automobile circuit has a 3-axis accelerometer, Bluetooth module, relay, and load sensor. The helmet circuit sends a signal to the automobile circuit to start if the helmet is wearied and no alcohol detects. Then the automobile circuit checks the status of the load to start. 3-axis accelerometer senses crash or hit. After detecting an accident mobile application sends the accident location automatically to police and emergency contact number via the database.

11 citations

Journal ArticleDOI
TL;DR: Along with machine learning models, a deep neural network was used on the same dataset, and the deep Neural network was found to have the greatest accuracy of 99.6%.
Abstract: Chronic Kidney Disease is one of the most serious illnesses nowadays, and it is vital to have a good diagnosis as soon as possible. Machine learning has proven to be effective in medical therapy. The doctor can diagnose the ailment early with the use of machine learning classifier algorithms. This article has examined Chronic Kidney Disease prediction from this standpoint. The Chronic Kidney Disease dataset was obtained from the University of California at Irvine's repository. The artificial neural network, C5.0, Chi-square Automatic interaction detector, logistic regression, linear support vector machine with penalty L1 & with penalty L2, and random forest classifier techniques were used in this study. The dataset was also subjected to the significant feature selection technique. The results were computed for each classifier using I full features, (ii) correlation-based feature selection, (iii) Wrapper method feature selection, (iv) Least absolute shrinkage and selection operator regression, (v) synthetic minority over-sampling technique with least absolute shrinkage and selection operator regression selected features, and (vi) synthetic minority over-sampling technique with full features. The results show that in synthetic minority over-sampling technique with full features, LSVM with penalty L2 has the maximum accuracy of 98.86 percent. Along with precision, recall, F-measure, and area, accuracy, precision, recall, and area. The GINI coefficient and beneath the curve have been computed, and the results of various algorithms have been compared in the graph. After synthetic minority over-sampling technique with full features, the least absolute shrinkage and selection operator regression selected features with synthetic minority over-sampling approach produced the best results. Again, the linear support vector machine had the maximum accuracy of 98.46 percent in the synthetic minority over-sampling technique with the least absolute shrinkage and selection operator selected features. Along with machine learning models, a deep neural network was used on the same dataset, and the deep neural network was found to have the greatest accuracy of 99.6%.

9 citations

Performance
Metrics
No. of papers from the Journal in previous years
YearPapers
20231,329
20222,041