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 Electronics & Communication Engineering

Purpose: The deep learning-aided automatic bone age assessment systems have obtained the best results but still depending on the advanced methods to attain highly accurate region of interest (ROI) segmentation and error-free bone age assessment based on different regions of bone. By avoiding these drawbacks, this paper presents a comparative analysis on a deep learning-aided bone age assessment using 5 regions over 13 regions under Tanner-Whitehouse 3 (TW3) method. Methods: The segmentation of both 5 regions and 13 regions is employed by both adaptive Otsu thresholding and improved U-Net segmentation. Further, the adoption of enhanced “deep convolutional neural network (CNN) is used for the bone age assessment (BAA)” using the 13 region and 5 regions. The development of Opposition Searched Harris Hawks Optimization (OS-HHO) is preferable for both segmentation and prediction. Results: From the analysis, the root mean square error (RMSE) of 5th region is 8.45% better than that of the 13th region. Similarly, the mean absolute squared error (MASE) of 5th region was 2.30% higher than the 13th region. Conclusion: The assessment of bone age by 5 regions was better when compared with the 13 regions for the suggested bone age assessment (BAA) model, respectively. © 2022, Sociedade Brasileira de Engenharia Biomedica.

World University root node

Engineering and Technology

Research on Biomedical Engineering

Comparative analysis of 5 regions over 13 regions bone age assessment via TW3 method with deep learning

Bone Age Assessment (BAA) is a general medical practice for investigating genetic, endocrinology and growth defects in kids and adults. Nowadays, automatic techniques for assessment of wrist and hand radiographs were introduced that reduce interrater-variability over manual techniques. Deep learning (DL) is a proliferating and useful method of machine learning (ML). Varied appliances, like medical image processing, speech detection, and so on have deployed DL, as it is offering accurate resultants. This survey makes a significant analysis on about 30 papers regarding BAA using ML and DL schemes. More particularly, varied performance measures that are contributed in diverse articles are analyzed. In addition, a comprehensive study is made regarding the chronological analysis and finally, the future challenges to be resolved are discussed. © Grenze Scientific Society, 2022.

13th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2022

A Systematic Literature Review on Bone Age Assessment using Machine Learning and Deep Learning Models

Voice quality enhancement is a significant method for any speech communication model. Speech Enhancement (SE) and noise reduction approaches can significantly improve the perceptual voice quality of a hands-free communication system and increase the recognition rates of automatic speech recognition systems. Speech communications in real-world cases require high-performance enhancement techniques for addressing the distortions, which can corrupt the intelligibility and quality of the speech signal. Recent portable devices generally incorporate several microphones that can be easily used for improving signal quality. This paper plans to present a novel dual-channel SE model using the coherence function and heuristic concepts. The adaptive coherence function relates to the dual-microphone SE approach suitable for smartphones with primary and reference microphones. With this improved signal, the enhancement is performed by optimising denoising using Discrete Wavelet Transform (DWT) by Adaptive wind speed-based Deer Hunting Optimization Algorithm (AWS-DHOA). The considered objective function depends on the quality measure called Perceptual Evaluation of Speech Quality (PESQ) score. From the results, the RMSE of the proposed model using AWS-DHOA is 39.8%, 45.5%, 53.8% and 45.5% minimised than GWO-CFD, WOA-CFD, CSA-CFD, and RDA-CFD, respectively, on considering the babble noise. Finally, the comparative analysis confirmed that the proposed method improves speech quality and intelligibility by comparing diverse algorithms when different noise types corrupt the speech. © 2022 World Scientific Publishing Co.

Journal of Information and Knowledge Management

Automated Dual-Channel Speech Enhancement Using Adaptive Coherence Function with Optimised Discrete Wavelet Transform

Massive Multiple Input Multiple Output (MIMO) has the potential to satisfy the requirements of the fifth generation (5G) and beyond networks with regard to factors like high data rate, high efficiency, reliability, better performance, and degree of freedom. However, increasing the number of antennas can lead to design challenges such as hardware complexity, higher cost, and large circuit power consumption. In addition to the parameters mentioned above, Energy Efficiency (EE) also needs to be considered a key parameter to analyze the performance of a cellular network. In this paper, Transmit Antenna Selection (TAS) technique based on the normalized power received by the user is proposed for a single-cell multiuser massive MIMO system. The energy efficiency equation is derived by considering both uplink and downlink communication for Zero Forcing (ZF) technique. The power consumption in the Radio Frequency (RF) chain, channel estimation process, and linear processing of the base station are considered for the analysis. The proposed TAS technique improves EE by 5 Mbit/Joule compared to the conventional massive MIMO system for ZF. This study compares Maximal Ratio Transmission (MRT), Minimum Mean Square Error (MMSE), and Zero Forcing based on energy efficiency performance using transmit antenna selection. © 2022 Seventh Sense Research Group®

International Journal of Engineering Trends and Technology

Transmit Antenna Selection in Massive MIMO: An Energy-Efficient Approach

Grape is considered as a cash-crop throughout the world. As compared to other fruits, shape of every grape cluster is different from each other. The change in region of grape cluster with respect to image size is sparse in nature and hence involves lot of errors. So it's a bit challenging to find shape and estimate weight of grape cluster using modern algorithms as well. In this paper, we proposed a deep learning regression model with combination of basic structures of U-net, VGG-16 and attention modules. The sequence combinations of layers such as convolution layers, max-pooling layers and average pooling layers along with concatenation operations are the main characteristics of these models. This model is capable of predicting weight of grape clusters present in images with a reduced error. © 2022 IEEE.

2022 International Conference for Advancement in Technology, ICONAT 2022

Grape Yield Prediction using Deep Learning Regression Model

Accidents and road crashes occurring due to dissociation of driver from his consciousness is one of the hot topics researchers have been contemplating to curtail, from the past few years. This dissociation wanes the driver's ability to concentrate on the road while driving and promotes occurrence of mishaps. There has been a challenge to non-intrusively detect drowsiness and fatigue-level of drivers in real-time environments and concomitantly make it computationally faster and less complex. The paper proposes a faster real-time driver inactiveness detection system capable of alerting drivers of their drowsiness by inspecting and scrutinizing the state of eyes and mouth and follows a non-obtrusive approach. The system utilizes eyes to monitor the drooping nature of eyes and examines the mouth's current state to detect any yawning activity performed. Initially, it uses Haar transform to extract facial features and strong classifiers for detecting faces by incorporating Adaboost algorithm. Next, shape predictors are used to locate the key points for obtaining position of mouth and eyes within the face area. States of the mouth and eyes are continuously monitored with the help of the metrics viz. Eye Aspect Ratio (EAR) and Mouth Yawn Width respectively and are used to alert the driver through voice-enabled commands followed by a warning alarm sound to trigger them thereby aiding in regaining their consciousness back and focusing on their driving. The algorithm used in this system is tested under different lighting conditions and against different possible situations and accurate results in terms of successful detection rates are obtained. © 2022 IEEE.

2022 6th International Conference on Computing, Communication, Control and Automation, ICCUBEA 2022

Real-Time Voice Enabled Drivers' Safety Monitoring System Using Image Processing

For deaf persons it is very difficult to establish a communication, by using Hearing Aid System it becomes possible. But the Hearing Aid which are available in the market are having many issues like heavy weight, more power consumption, voice with less clarity, delay in receiving the signal, cost, stigma associated with wearing the hearing aid system etc. To overcome mentioned problems and to help the deaf people we have designed the filter bank with variable bandwidth (VBF) which can be used in hearing aid system to improve the performance by reducing the hardware, by removing the noise, also by improving the speech quality and reducing the delay. The developed filter bank is implemented using MATLAB, audiograms of different patients and achieved better performance by reducing unwanted noise and increasing the speech intelligibility finally the attained performance of developed filter is contrast with the subsist filter banks in the parameters like consumption of power, matching error, and delay in processing, to check the performance of developed filter © 2022 IEEE.

Audiogram Study in Filter Bank Used for Hearing Aid System to Enhance the Performance

Market basket analysis is a data processing methodology for discovering relationships between different items. The primary goal of market basket analysis in retail is to provide information to the distributor about a customer’s purchasing habits, which can aid the distributor in making the best choices. Market basket analysis can be performed using a variety of algorithms. This paper compares two popular market basket analysis techniques, to determine which approach is optimal for rule generation and visualization on a common dataset. The results can be used as a guide for cross-selling, creating promotions, and determining the best location for products in the store to boost sales. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.