Authors - Manita Rajput, Pranali Choudhari Abstract - Internet of Things (IoT) technology is witnessing widespread integration across diverse sectors including manufacturing, automotive and healthcare. It has a vast application area and exponential growth rate. Lately, IoT has seen remarkable utility in the health care sector. The technology of IoT used in the medical field is called Internet of medical Things (IoMT). The sensitive biomedical data of patients need a secure transit and cloud storage. Securing the data at the sensor level or transit level is a challenging task. The huge amount of data exchanged between IoT nodes to cloud brings new risks and more challenges. People illicitly obtain the personal Identifiable information (PII) and misuse it for various unlawful purposes. Few encryption algorithms are specifically designed for low power IoT nodes but are vulnerable to attacks. There is a need of extensive analysis of the existing algorithms specifically for IoMT applications. This paper focusses on the 5 encryption algorithms that consume less power and memory and can be used at the end nodes of an IoMT network. These algorithms are implemented in C and analyzed with respect to important performance metrics such as memory size and execution time. The performance of algorithms have been tested with values of biomedical parameters.
Authors - Sneh Soni, Mahek Siroya, Rutva Shingala, Purvi Prajapati, Madhav Ajwalia, Hemant Yadav Abstract - A growing challenge in agriculture is identifying new cases of new cases of fungal-caused plant diseases, which is made even worse by the consistently changing climate and its unpredictable impacts These diseases are among the biggest threats to agriculture as they lower the quality of crops, undermine the sustainability of farming, cause financial losses, and lead to nutritional deficiency. In fact, the agricultural sector suffers substantial annual losses, with pests affecting up to 20–40% of global productivity. In this research, we aim to tackle this very problem using state-of-the-art technologies. We are particularly using Convolutional Neural Networks (CNNs) and Deep Learning, a subset of artificial intelligence, to automate the detection and classification of mango leaf diseases. Through these innovative technologies, we seek to not only enhance the techniques of disease management but also drastically cut crop losses, which will lead to the sustainability and resilience of agricultural systems across the globe.
Authors - Dhruvi Patel, Mansi Deshpande, Anil Jadhav Abstract - Online consumer reviews consist of product ratings and product reviews, which are becoming increasingly powerful in supporting potential customers in making well-informed purchasing decisions. Online reviews are very important to for potential customers because they help them make better informed and rational purchase decisions. Objective of this study is to examine the consistency between customer reviews and ratings. Our research methodically examined the consistency between product ratings and consumer reviews for headset purchases by employing a TextClassifier model. Confusion matrix, chi-square tests and Cohen’s Kappa test were used in conducting the statistical analysis that was aimed at determining the association between these two aspects. The results conclusively indicate a notable consistency between reviews and ratings.
Authors - Shradha Sahu, Sreerag Rajesh, Sahil Wake, Abhishek Tiwari, Namrata Patel Abstract - In today's fast-paced world, the demand for an efficient and reliable healthcare decision support system has never been greater. With the increasing prevalence of diseases such as cancer, stroke, and heart disease, there is a critical need for a system that can accurately predict these conditions and provide users with comprehensive healthcare information. Enter the Clinical Decision Support System, a state-of-the-art web application designed to meet this need head-on. Utilizing advanced algorithms, this system offers personalized disease predictions, enhancing the accuracy of healthcare outcomes. An integral component of this system is its AI chatbot, which provides users with immediate access to essential information, including symptoms, causes, treatments, and the nearest healthcare facilities. This innovative tool streamlines the process of acquiring healthcare knowledge, thereby improving the decision-making process for both patients and healthcare providers. The Clinical Decision Support System is more than just a prediction tool; it is a gateway to a wealth of healthcare information and a step towards revolutionizing the healthcare industry. With the potential for future integration with blockchain technology, the system promises enhanced data security and management, further solidifying its position as a critical tool in modern healthcare. This project represents a significant advancement in healthcare technology, offering promising solutions to improve patient care and outcomes.
Authors - Arshpreet Kaur, Kumar Shashvat Abstract - Identifying inter-ictal activity in EEG amidst of artefacts is a primary challenge for diagnosis of epilepsy. Artifacts corrupt the EEG; such that identifying inter-ictal activity becomes difficult. There are different artefacts that present the EEG some of the prominent ones are movement artifact, eye movement, electrode and emg artifact. The evaluation of EEG is a subjective procedure and detecting inter-ictal activity among the artifacts is a challenge. We have designed convolution neural network to identify between different artifacts and inter-ictal activity. For this work five sets have been considered, the first four sets compare each artefact with inter-ictal activity and set E, compares all artefacts with inter-ictal activity. The proposed method has achieved 100% accuracy in identifying electrode and emg artifacts from each other while for other artefacts the method also performed efficiently.
Authors - Purnima Gandhi Abstract - Modern users demand fast, scalable, simple, user-friendly, and cost-effective solutions to perform complex analytics on complex and disparate data including spatial data. The complex characteristics of spatial data have made analytics and management more challenging. The paper highlights the overall research and development done in the area of big data management including geometry attributes. The state-of-the-art databases, frameworks, and architectures are reviewed and compared with significant parameters. It also presents issues and challenges to meet the current demand of modern users to perform spatial analytics and management.