检索结果-内蒙古大学图书馆

Biomedical Materials and Devices 2025年 1-21页

作者： Potadar, Mahesh P. Holambe, Raghunath S. Chile, Rajan H. Department of Electronics and Telecommunication Engineering Pune Vidyarthi Griha’s College of Engineering and Technology & GKPIM 44 Vidyanagari Shivdarshan Parvati Pune 411009 India Department of Instrumentation Engineering SGGS Institute of Engineering & Technology Swami Ramanand Teerth University Vishnupuri Maharashtra Nanded 431606 India

Early brain tumor detection can avert millions of fatalities and the improvement of survival of patients can be attained by the use of Magnetic Resonance Imaging (MRI), which aids in further treatment. Most of the existing techniques in brain tumor detection are less accurate, time-consuming, and less efficient. Hence, automatic classification is performed for the effective classification of tumors. In this research, the Egocentric Critter Fish Optimization-based Deep Convolutional Neural Network (ECFO-DCNN) is proposed for the effective classification of brain tumors. The effective classification is attained using the ECFO-based segmentation and Binary, Directional, Orientational, and Entropy (BDOE) features that boost the convergence and reduce the classifier’s required computational time. The effectiveness of the method is established through the comparison with existing approaches, where the ECFO-DCNN method achieved 90.43% accuracy, 80.65% sensitivity, and 95.32% specificity using the Figshare brain tumor dataset. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Brain tumor Convolutional neural network Deep learning Magnetic resonance imaging Optimization

来源：评论

学校读者我要写书评

暂无评论

Acute mental stress level detection: ECG-scalogram based attentive convolutional network

Franklin Open

引用

Franklin Open 2025年 10卷

作者： Ramteke, Ramyashri B. Gajbhiye, Gaurav O. Thool, Vijaya R. Biomedical Lab SGGS Institute of Engineering and Technology Nanded India CVPR Lab SGGS Institute of Engineering and Technology Nanded India

In today's competitive environment, everyone is under psychological stress. Long-term exposure to stress can lead to serious issues such as high blood pressure, depression, violence, cardiac and brain damage, and even suicide. To live a healthy lifestyle, it is critical to monitor stress and its levels regularly. Existing methods detect stress specifically, whereas detection of multiple levels of stress has yet to be explored. To address this issue, the paper presents the lightweight ECG-stress-ScaloNet model, which employs an attentive convolutional neural network (CNN) to analyze short-term ECG scalogram images. In this work, a unique inception-attention block is created. The inception module captures multi-scale information;additionally, attention focuses on extracting meaningful features from multi-scale feature maps by utilizing cross-channel and spatial information. Two databases are used to evaluate the proposed ECG-stress-ScaloNet model. The first is Physionet driver stress and normal ECG data that is publicly available, and the second is self-created academic practical-viva stress and normal ECG data. The ECG-stress-ScaloNet outperforms the existing methods, with a test accuracy of 98.28% for the Physionet dataset and 95.71% for the self-created dataset. For the intended application, the ECG-stress-ScaloNet model is reliable and accurate since it has fewer learnable parameters and decreases computational complexity. © 2025

关键词： Attentive convolutional neural network ECG-stress-ScaloNet Electrocardiogram (ECG) Mental stress analysis Scalogram

来源：评论

学校读者我要写书评

暂无评论

TQM with quality perception: A system dynamics approach

引用

TQM Magazine 2006年第4期18卷 341-357页

作者： Wankhade, Lalit Dabade, B.M. SGGS Institute of Engineering and Technology Nanded India

Purpose - Prevailing information asymmetry in business processes alters the market dynamics. Quality uncertainty ensues from this phenomenon. Philosophy of information economics is implemented to correlate total quality management (TQM) practices in industry with quality perceived by customers. Quality perception, a newly coined term, is discussed at length, along with causal factors. This paper aims to provide a system dynamics framework for quality perception and to investigate the role of the changing level of market-side enablers on quality perception. Design/methodology/approach - System dynamics is used for modeling and analysis. To realize the impact of information asymmetry on quality perception, simulation runs are carried out for an Indian case. Findings - Enablers, such as advertising, word-of-mouth, rebate, warranty and guarantee, mitigate the effect of information asymmetry on quality perception, and commensurately translate TQM to market value. Research limitations/implications - The study of some aspects of information asymmetry and quality perception is attempted. Further study is required to understand repercussions of information asymmetry on the complete supply chain processes. Practical implications - The model has a practical relevance to implement quality perception enhancement by deciding upon the policy mix. Originality/value - With quality perception defined and modeled, the paper attempts market orientation to quality paradigm. © Emerald Group Publishing Limited.

关键词： Total quality management

来源：评论

学校读者我要写书评

暂无评论

Unbounded Fuzzy Hypersphere Neural Network Classifier

引用

Journal of The Institution of Engineers (India): Series B 2022年第4期103卷 1335-1343页

作者： Mahindrakar, M.S. Kulkarni, U.V. SGGS Institute of Engineering and Technology Vishnupuri Maharashtra Nanded India

This paper presents the supervised classifier called unbounded fuzzy hypersphere neural network (UFHSNN) model. The basic fuzzy min-max neural network (FMMN), fuzzy hypersphere neural network (FHSNN) and many more its variants use expansion parameter to tune the model. Such tuned model gives good classification accuracy with minimum number of hyperboxes, but always needs to take multiple iterations to find optimal value of expansion parameter and train the model. However, in the proposed model, use of expansion parameter is removed, due to which the model can be trained in a single iteration. The different datasets are applied for verification of the model;also, outcomes are compared with some current FMMN variations. The analysis of outcomes shows that the presented model gives magnificent accuracy with reduced computational complexity. © 2022, The Institution of Engineers (India).

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Drying Model and Quality Analysis of Turmeric Using Solar Thermal System

引用

Applied Solar Energy (English translation of Geliotekhnika) 2020年第4期56卷 233-241页

作者： Nukulwar, M.R. Tungikar, V.B. SGGS Institute of Engineering and Technology Nanded Maharashtra431606 India

Abstract—: This study is aimed to find the quality and appropriate thin layer mathematical model suitable for drying kinetics of turmeric which has the least impact of weather conditions. A user-friendly indirect natural convection solar dryer (INCSD) working on compound parabolic concentrator (CPC) was developed and fabricated for this purpose. It is observed that there is a dominant impact of the environmental conditions on the efficiency of solar drying. Adverse weather conditions hinder the collection of solar radiation. It was observed that the moisture content reduces from 77 to 18% in the solar dryer in 24 h as compared to open sun-drying, which requires 40 h. Six thin layer mathematical models reported in the literature have been tried for INCSD and open sun-drying. Thin layer mathematical modeling at different temperatures is presented with quality analysis. Maximum curcumin percentage 3.73% in the turmeric is found at 55C drying air temperature. Minimum ash content is found to be 6.5% at 60C. Experimental results reveal that the page model fits best for INCSD as well as for open sun-drying (OSD). © 2020, Allerton Press, Inc.

关键词： Concentration (process)

来源：评论

学校读者我要写书评

暂无评论

Influence of hard turning parameters on cutting forces of EN 353 steel

引用

Materials Today: Proceedings 2022年 63卷 149-156页

作者： Balwan, Vishal R. Dabade, Balaji Wankhade, Lalit Department of Production Engineering SGGS Institute of Engineering and Technology Vishnupuri Nanded431606 India

Hard turning is used for materials having a hardness greater than 45 HRC. Cutting forces, tool wear, and surface finish are all affected by variations in hardness, cutting rate, feed, and cutting depth during machining. The goal of this investigation is to learn more about cutting forces when turning hardened EN353 steel with CBN insert. The effects of speed, depth of cut, tool nose radius, hardness, and feed on cutting forces are explored in this study. The cutting forces were determined with the help of a Kistler dynamometer. The cutting force values were observed and displayed using Dyno-ware programming software. To determine the optimal input and output parameter combinations, ANOVA is utilized. The GRA algorithm is then used to determine the relationship as well as the influence on each parameter. The L27 orthogonal array is created using all of the input parameters. Among the components analyzed, cutting depth has the highest impact on cutting forces, while the tool nose radius of the insert has the least impact. The new research benefits in the prediction of a key parameter that affects tool cutting forces. © 2022

关键词： Hardness

来源：评论

学校读者我要写书评

暂无评论

Optimization of surface finish and material removal rate while turning hardened EN 353 steel using GRA

引用

Materials Today: Proceedings 2022年 59卷 331-338页

作者： Balwan, Vishal R. Dabade, B.M. Kabnure, Bahubali B. Research Scholar SGGS Institute of Engineering and Technology Nanded431606 India Department of Production Engineering SGGS Institute of Engineering and Technology Nanded Vishnupuri431606 India Department of Mechanical Engineering DKTES TEI Ichalkaranji416115 India

The present study attempts to critically analyze investigations into surface finish and material removal rate when machining hardened steel. EN 353 case hardened steel is used as a material of tool considered for study. The work is carried on Maxturn CNC machine. The effect of depth of cut, tool nose radius, hardness, speed and feed on the surface finish of specimen and material removal rate of tool are examined in this study. The CNGN 12 04 04 BKU 203 tool inserts is taken for machining. The surface finish is measured using Mitutoyo SJ-410 instrument. The actual MRR is calculated by weight of specimen before and after turning and actual turning time for respective trial. After obtaining the results, effect of input variables considered for study on surface finish and MRR are tabulated. The ANOVA method is used to obtain the optimal arrangements of input and output parameters. Then GRA method is used to obtain the relationship as well as its impact on every parameter. L27 orthogonal array is prepared from all the input parameters. And output i.e., surface finish and MRR for all the 27 experimental combinations are obtained. The input parameter which has more impact on surface finish and MRR is calculated using GRA optimization method. The feed is found to be most impactful factor amongst all input variables. The speed is found to be least impactful factor for the current study. The present work helps to predict the MRR and surface roughness for selected material with mathematical equations. © 2022

关键词： Surface roughness

来源：评论

学校读者我要写书评

暂无评论

Sliding mode control for underactuated mechanical systems via nonlinear disturbance observer: stabilization of the rotational pendulum

引用

International Journal of Dynamics and Control 2018年第4期6卷 1663-1672页

作者： Majumder, Kakoli Patre, B.M. Department of Instrumentation Engineering SGGS Institute of Engineering and Technology NandedMaharashtra431606 India

This paper presents design of the sliding mode controller (SMC) via a nonlinear disturbance observer (NDO) for stabilization of the rotational pendulum. The mathematical model is depicted by four first-order nonlinear differential equations with two outputs and single input. The linear model is obtained by linearizing nonlinear equations. This linearized version is found to be highly unstable. The applied NDO is capable of estimating extremely nonlinear terms (disturbance) present in the model. Then, the NDO based SMC is designed using linear model and disturbance estimation, and hence is applied to the original nonlinear system. The developed controller is enough to drive a sliding surface (which holds both actuated and unactuated dynamics) attaining the sliding mode against severe nonlinearities existing in the model, in addition large parameter variations and/or external disturbance. The sliding coefficients are determined using the linear quadratic regulator (LQR) technique. The obtained controller parameters can establish the zero dynamics as of sliding mode dynamics asymptotically. Also, the proposed control algorithm has potential to alleviate the chattering phenomenon occurred in the control signal. Overall, the control scheme expands the stability region of an arm (in horizontal half-plane) and a pendulum (over vertical half-plane) both for large initial conditions. Lastly, numerical simulations and quantitative measurements are validated with an established controller in the literature. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Pendulums

来源：评论

学校读者我要写书评

暂无评论

A new state and perturbation observer based sliding mode controller for uncertain systems

引用

International Journal of Dynamics and Control 2016年第1期4卷 92-103页

作者： Ginoya, Divyesh Shendge, Pramod D. Patre, Balasaheb M. Phadke, Shrivijay B. College of Engineering Pune PuneMaharashtra India SGGS Institute of Engineering and Technology Nanded India

This paper proposes a new continuous sliding mode controller and observer for perturbed systems. The controller, which does not need any knowledge of bounds of any perturbation, is estimated using the uncertainty and disturbance estimation technique and implemented with observer states. The stability of the overall observer-controller combination is proved. The controller-observer combination is validated by implementing the scheme for an actual hardware set-up of serial flexible joint in laboratory. © 2014, Springer-Verlag Berlin Heidelberg.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Effect of a multi-lead PCA approach on modified moving average method for T-wave alternans detection

引用

Journal of Medical engineering and technology 2014年第8期38卷 396-401页

作者： Deogire, Aruna Hamde, Satish MET's Institute of Engineering Nashik Maharashtra India SGGS Institute of Engineering and Technology Vishnupuri Nanded India

T-wave alternans, a beat-to-beat re-polarization pattern variation phenomenon, plays an important role in sudden cardiac death prediction. The proposed method modifies the currently available Modified Moving Average Method (MMAM) by a multi-lead principal component analysis (PCA) approach. Application of PCA will concentrate the alternans effect, which is supposed to be distributed on multiple leads in a single derived lead. MMAM is applied to the derived lead and alternans magnitude is measured. Results are compared with MMAM, implemented by the authors and by an open source tool, TWAnalyser. The TWA Physionet/CinC 2008 Challenge Database is used for testing. Performances are measured in terms of root mean square error (rmse) and correlation coefficients. The rmse is highest for TWAnalyser results and lowest for the proposed method. While the correlation coefficient is highest for the proposed method, 0.88, that for normal MMAM is 0.73 and for TWAnalyser is 0.75. The proposed multi-lead PCA approach provides improved performance of current MMAM. © 2014 Informa UK Ltd. All rights reserved.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：