MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Computer Engineering & Technology

Air pollution is a pressing concern that the entire world is striving to combat. Among air pollutants, particulate matter poses a significant threat to human health. The Sustainable Development Goals (SGD3, SGD7 and SGD11) include initiatives to address air pollution. Two innovative methods are proposed in this research to predict the PM2.5 concentration in advance. While multivariate time series prediction models typically employ multiple features as inputs, this research reduces the number of inputs, which makes the proposed combination of approaches simple and effective. The approaches involve the development of two new indexing methods, namely, the Hourly Relative Mean Index and the Hourly Weighted Index. This research offers innovative hybrid deep learning models that incorporate the newly developed indices, Long Short Term Memory (LSTM) models, and robust preprocessing techniques. Multivariate Isolation Forest Relative Index Bidirectional LSTM and Multivariate Isolation Forest Weighted Index LSTM methods are used to forecast PM2.5 concentration for an hourly time frame. Further, Multivariate Isolation Forest Relative Index LSTM and Multivariate Isolation Forest Weighted Index LSTM methods are used to forecast PM2.5 concentration 48 h ahead. The study establishes that the proposed combination of approaches outperform traditional ways to achieve superior performance with reduced complexities requiring fewer inputs for predictions. © 2023 IOP Publishing Ltd.

World University root node

Engineering and Technology

Physica Scripta

Deep learning approach to forecast air pollution based on novel hourly index

The duty of detecting pavement cracks is crucial for ensuring traffic safety. The process of manually detecting cracks takes a long time. To accelerate this process, an autonomous road fracture identification technology is necessary. However, because of the intensity inhomogeneity of cracks and the intricacy of the background, such as poor contrast with neighbouring pavements and probable shadows of similar intensity, it remains a difficult work. Recent breakthroughs in deep learning in computer vision have inspired us, so we will be using the most accurate method that involves deep learning to identify the gap in the pavement. In this research paper, we have compared various object detection techniques such as aYOLO v5 and Single Shot Detector(SSD) and come to a conclusion that SSD is most suitable for our purpose. It will also help for road safety purposes. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes in Networks and Systems

Comparison Between YOLOv5 and SSD for Pavement Crack Detection

Diabetic retinopathy is an eye disorder that affects people who have diabetes. Diabetic retinopathy occurs when high blood sugar levels harm the blood vessels in the eye. These blood vessels tend to swell and leak. They also can close, preventing blood from flowing through. Irregular new blood vessels are formed on the retina and eyesight becomes weak and blurred. Diabetic retinopathy can affect people with any type of diabetes (type 1, type 2, or gestational diabetes). Therefore, it is vital to detect diabetes retinopathy at an early stage. In this paper, we outlined the idea of diabetic retinopathy and highlighted the relevance of its methodologies, along with an exhaustive comparative study that helped us to shortlist the best performing model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes in Electrical Engineering

An Intelligent Technique for Detecting Diabetic Retinopathy by Comparative Analysis Based on Deep Learning

It's a perpetual human quest and a constant effort of science to develop and design equipment and aids to help physically challenged people live their lives independently and confidently. Blindness and visual impairment are prevalent disabilities that inhibit the independence of the patient and increase the reliance on family members, friends, and guide dogs for navigation and other daily duties. The proposed work outlines a reliable, low-cost, and power-efficient solution that enables safe and secure navigation for visually impaired people. Many researchers have worked on and proposed solutions to the typical problems, but those works have some shortcomings that are addressed in this study. Existing technologies have not focused on optimizing power consumption and reliability, thereby reducing the life of the system. It is vital to reduce power consumption in order to extend the operating lifetime of devices that use batteries as a power source. A methodology has been put forward to address the crucial concern of a gadget that is left on for an extended period of time without being switched off to improve the overall performance of the system. The IoT is entrusted with taking into account heterogeneous equipment that might be severely constrained by its nature and pose problems in the hardware layer of the system. So methods to make the system reliable, accurate, and resistant to failures are inscribed in this study. Additionally, existing systems aren't economical compared to the offered features, lack automation, and lack audio feedback, particularly notifying obstacles. This study proposes audio feedback in multiple languages and automates the command execution, thereby making it effortless for impaired people to engage with the product. Also, the present state of technology faces challenges in locating the misplaced stick, which means the person has to be dependent on loved ones, friends, or caretakers to find the stick. The proposed automated and handy Smart Stick for the blind using IOT (Internet of Things) is a potent Electronic Travel Aid (ETA) that gives artificial perceptivity of vision and discerns environmental hurdles and obstacles. © 2023 IEEE.

Proceedings of the 8th International Conference on Communication and Electronics Systems, ICCES 2023

Handy Smart Stick: A Guide for Visually Impaired People

Conventional homes have grown to be smart homes (SM) with the assistance of the Internet of Things (IoT). A unified gateway connects all Internet-enabled devices. Those gateways need to be secured by the usage of a sturdy safety method due to the fact safety is very vital. In order to conquer those problems, this observation shows employing Blockchain Technology (BC) for secured houses to make certain information private and safe. To cope with the safety problem with SH gateways, this paper proposes a solution. A reliable Q-learning algorithm with Blockchain assistance is proposed for the SH gateway to save data. three sections make up the protocol Q Learning Algorithm with Blockchain Support (QLABS). First, a Lattice cryptosystem based on Cipolla’s extended Euclidean distance algorithm is used to record and store user data (CEED-LC). Second, while preserving data secrecy and integrity, the proposed cryptosystem offers a small Key Generation (KG) with excellent security. Third, with the assistance of QLABS protocol agreement, the blocks are created with a specific gateway enrolment-ID. The testing results demonstrate how highly safe the suggested framework is against the vulnerabilities by obtaining a higher throughput along with a higher Packet Delivery Ratio (PDR) value. The results show that the recommended approach tops other existing algorithms in terms of PDR and throughput. © 2023, Taru Publications. All rights reserved.

Journal of Discrete Mathematical Sciences and Cryptography

Blockchain enabled security mechanism for preventing data forgery in IoT-based smart homes

Machine Learning Prediction if the Patient is at Risk of Undergoing Surgery Based on Preoperative Medical Reports

The resting-state functional magnetic resonance imaging (rs-fMRI) is an advanced imaging method with several benefits compared to functional magnetic resonance imaging (fMRI) techniques. Major benefits of rs-fMRI are easy receiving of the signal, needs minimum effort from the patient, and good at differentiating the functional areas in patients. Resting-state fMRI (rs-fMRI) identifies the amount of Blood Oxygen Level-called as BOLD. These are variations at frequencies smaller than 0.1 Hz to identify the functional variations of the brain. Usage of this BOLD level allows viewing resting-state networks (RSN). RSN are distinct areas of the brain which are spatially distributed and which confirm synchronous BOLD fluctuations at rest. In the pipeline for fMRI data, various preprocessing steps are carried out as a normal procedure for achieving a better quality of data. In this paper, these steps for preprocessing are altered/changed in the pipeline of CONN neuroimaging software, and its effects on graph theory outcomes are explored and discussed. © 2023 Seventh Sense Research Group®

International Journal of Engineering Trends and Technology

Optimization of Pipeline through Preprocessing Steps Sequence Alteration using Graph Theory for Resting State fMRI

In the Wireless Sensor Network (WSN), the data prediction approach is needed to attain data effectively by diminishing node energy consumption. Hence, in this research, Water cycle Fire Fly Optimization and Deep Long Short-Term Memory (WCFO+ Deep LSTM) approach is employed for aggregation and reduction of data. The processes involved in the developed method are node simulation, cluster-based topology construction, routing tree construction, and data aggregation. Initially, IoT nodes are simulated in the network environment. The cluster-based topology construction is made using the WCFO algorithm. The WCFO is developed by the integration of the Firefly Optimization Algorithm (FOA) and Water cycle algorithm (WCA). The cluster-based topology is constructed by considering the objective function that includes the parameters, including distance, delay, link quality, and energy. After that, the routing process is performed using developed WCFO approach for constructing a routing tree and estimating the optimal path. Finally, the Deep LSTM is trained by the proposed WCFO algorithm, which is utilized for executing data reduction and data aggregation process with minimum energy consumption. The devised WCFO+ Deep LSTM approach achieved better performance in terms of prediction error, delay, energy, and Packet delivery ratio (PDR) with values 0.029, 0.001s, 0.161J and 99.054%, respectively. © 2023 World Scientific Publishing Company.