<p>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;</p>

<p>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;</p>

<p>&nbsp;</p>

MIT World Peace University

School of Electronics & Communication Engineering

<h2>Estimating the Employment Opportunity of Engineering Students with the Aid of Fuzzy Logic ControllerAbstract — The point of this exploration work exhibits a classification technique for analyzing engineering student's employment opportunities. From the given 60 attributes, take 46 attributes as inputs. In view of this input data, we design the fuzzy logic system. This design is utilized for finding the employment opportunity potential score of particular individuals. Based on these 46 attributes, generate the rule as low and high. At that point, we need to take the count of low and high; after analyzing the count, find the output level (low, medium, high). In the outcome, three diverse membership functions such as trapezoidal, Gaussian and triangle have been designed. In this threemembership function, we explore diverse designing and validation points (50-50, 60-40, 70-30 and 80-20). The sensitivity value for the triangle is 76%, the specificity value for the triangle is 93%, and the accuracy value for a triangle is 89%. From this, the triangle membership function is enhanced contrasted with other membership functions.</h2>

Engineering and Technology

International Journal of Engineering Trends and Technology

<p>Estimating the Employment Opportunity of Engineering Students with the Aid of Fuzzy Logic Controller</p>

World University root node

Lecture Notes in Networks and Systems

Web Crawling-Based Search Engine for Programming Languages

5G architecture allows the use of new radio alongside long-term evolution-A (LTE-Advanced) and enables cellular mobile networks to handle extraordinarily high traffic volume data. The major challenge in current uplink data transmission systems is making resource blocks (RBs) available in a continuous form and assigning them to active users in an optimum manner to improve the system's spectral efficiency. The best N-subset (BNS) minimization technique is suggested to identify the best of the best continuous chunks of RBs from the existing system bandwidth, followed by a modified recursive maximum expansion (RME) algorithm to assign RBs to users in the most optimal manner. The algorithm together is referred to as a multiuser uplink scheduler BNSRME algorithm. A constraint utility maximization problem is formulated to allocate RBs to UEs in the most optimized manner. Utility matrix is then converted into a weighted sum-rate maximization problem allowing weights to be updated adaptively based on marginal utility values. In addition, a threshold limit is considered based on the signal-to-noise ratio in the BNSRME-TH algorithm, which satisfies multiusers in terms of assigned resources and improves system performance, spectral efficiency, and throughput. This MU scheduling strategy is used in the 5G uplink non-stand-alone cellular network. The findings exhibit that the proposed multiuser algorithm increases system spectral efficiency by 31.65% in comparison with the existing opportunistic algorithms. It has been observed that the performance of the system is further increased by using the MU-MIMO framework. © 2022 John Wiley & Sons Ltd.

Transactions on Emerging Telecommunications Technologies

Uplink transmission with multiuser scheduling in non-stand-alone cellular network using virtual MIMO system

Hand gestures are observed as an effective tool for making the interaction in the community with individuals having intellectual disabilities. It is highly essential for communicating the computers and people. Therefore, it is aimed to design an automatic hand gesture recognition approach that is utilized for repeatedly performing human-computer interaction. Sign languages are considered the natural languages utilized by hearing-impaired people that involve some expressional way of communication in routine life. It reveals the sentences, words, and letters present in the spoken language for performing the gesticulations that enable communication between them. The deaf community makes communicates with normal people using an automation system that relates the signs with the words of speech. The hand gesture recognition system is implemented independently of requiring any unique hardware rather than using the webcam. Thus, it is highly significant to make a short review of hand gesture recognition based on deep learning techniques considering the Indian sign language. Hence, this paper discusses and clarifies existing research work based on hand gesture recognition in Indian sign language with algorithmic classification. This survey also compares different performance measures, datasets utilized, and also different tools used for the implementation. Then, upcoming research and also current research gaps in hand gesture recognition in Indian sign language are analyzed. This review on state-of-the-art hand gesture recognition for Indian sign language tools has shown their potential for providing the right solution in different real-life situations. It is hoped that the contents and illustrations in this paper assist researchers in laying a good foundation to inform their studies. © 2023 IEEE.

Proceedings of the 2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

Review and Trends on Hand Gesture Recognition of Sign Language based on Deep Learning Approaches

A plant disease of any kind has a significant impact on the yield and quality of a harvest. The tomato is an important crop with a high commercial value on the global market. Early disease detection is critical for a successful crop yield. Plant disease has recently been the subject of a slew of studies. This research proposes the use of leaf pictures to classify tomato illnesses. Deep learning outperforms machine learning in a number of ways, and this is an important step forward in terms of categorization accuracy and the global reach of applications. ResNet50 and Xception architecture were used in this paper for comparison. Three different optimizers Adam, Nadam, and RMSProp have been used with learning rates of 0.0001, 0.002, and 0.04. All tests were done with data that was available to the public. Rotation, zooming, height shifting, breadth shifting, and other data augmentation techniques are used. Xception Architecture with Adam optimizer and Learning rate of 0.0001 gives greater accuracy, recall, precision, and F-score values of 99% on average when compared to Nadam and RMSProp optimizers and learning rates. These values are higher than those obtained with any other combination of learning rates and optimizers. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes in Electrical Engineering

Classification of Tomato Leaf Diseases: A Comparison of Different Optimizers

International Journal of Advanced Computer Science and Applications

VHDL based Design of an Efficient Hearing Aid Filter using an Intelligent Variable-Bandwidth-Filter

Application of Cohort Intelligence Algorithm for Numerical Integration

Vehicle Cluster Development

Day by day pollution in cities is increasing due to urbanization. One of the biggest challenges posed by the rapid migration of inhabitants into cities is increased air pollution. Sustainable Development Goal 11 indicates that 99 percent of the world’s urban population breathes polluted air. In such a trend of urbanization, predicting the concentrations of pollutants in advance is very important. Predictions of pollutants would help city administrations to take timely measures for ensuring Sustainable Development Goal 11. In data engineering, imputation and the removal of outliers are very important steps prior to forecasting the concentration of air pollutants. For pollution and meteorological data, missing values and outliers are critical problems that need to be addressed. This paper proposes a novel method called multiple iterative imputation using autoencoder-based long short-term memory (MIA-LSTM) which uses iterative imputation using an extra tree regressor as an estimator for the missing values in multivariate data followed by an LSTM autoencoder for the detection and removal of outliers present in the dataset. The preprocessed data were given to a multivariate LSTM for forecasting PM2.5 concentration. This paper also presents the effect of removing outliers and missing values from the dataset as well as the effect of imputing missing values in the process of forecasting the concentrations of air pollutants. The proposed method provides better results for forecasting with a root mean square error (RMSE) value of 9.8883. The obtained results were compared with the traditional gated recurrent unit (GRU), 1D convolutional neural network (CNN), and long short-term memory (LSTM) approaches for a dataset of the Aotizhonhxin area of Beijing in China. Similar results were observed for another two locations in China and one location in India. The results obtained show that imputation and outlier/anomaly removal improve the accuracy of air pollution forecasting. © 2023 by the authors.

School of Computer Engineering & Technology

School of Electrical Engineering

Algorithms

Novel MIA-LSTM Deep Learning Hybrid Model with Data Preprocessing for Forecasting of PM2.5

Automating human activity recognition is one of computer vision's most appealing and pragmatic research areas. In this article, we have addressed the problem of video-based student activity detection. The student’s activity detection using YOLO (SADY) aims to recognize the normal and abnormal student activities to ensure immediate intervention in case of any risk or necessity. We created our classroom data set of around 220 recordings depicting seven student classroom activities. The YOLOv4 Tiny model was retrained using 5000 labeled keyframes extracted from the train videos. The model was then tested for single or multiple activity detections. We presented the evaluated results for various values of hyperparameters like confidence threshold and Intersection Over Union (IoU) thresholds for the proposed model. The model assigns a unique confidence score and action label to each frame for the test videos by positioning recurrent activity labels. The proposed approach achieved a mean average precision (mAP) of 95% and a frame per second rate (FPS) of 45 for the student activity Class Room (CR) dataset and mAP of 95.18 % for the LIRIS dataset. The experimental findings using the Class Room recorded and LIRIS publicly accessible dataset show that our proposed approach outperforms existing approaches regarding recognition accuracy and speed. The comparable results obtained in this research work imply that the proposed framework could effectively monitor student’s activities in schools, colleges, and universities. © IJASEIT is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.