检索结果-内蒙古大学图书馆

Proceedings of the 5th International Conference on Information Management & Machine Intelligence

作者： Pushpa Negi AnishKumar Dhablia Hrishikesh bhanudas Vanjari Jayashree Tamkhade sharayu Ikhar shrinivas T. shirkande Symbiosis Law School Nagpur Campus Symbiosis International (Deemed University) India Engineering Manager Altimetrik India Pvt Ltd India E&TC Engineering Dept BVCOE Lavale SPPU Pune India E&TC VIIT India Department of Information technology Vishwakarma Institute of Information technology India Computer Science & Engineering S.B.Patil College of Engineering Indapur India

ISBN: (纸本)9798400709418

Abstract - The issue of diabetes is a significant and urgent matter in global health, necessitating the development of precise predictive models to facilitate early intervention and effective management. The ob.e.tive of this study is to assess the effectiveness of different feature selection techniques in improving the accuracy of diabetes prediction when employing the Random Forest algorithm. The present study evaluates the impact of three feature selection methods, namely Recursive Feature elimination (RFe), Mutual Information, and L1 Regularization (Lasso), on the performance of the model. This study employs a comprehensive dataset obtained from Kaggle, which includes various attributes such as age, blood pressure, and laboratory measurements. The primary ob.e.tive of this research is to systematically evaluate and compare the predictive performance of Random Forest models when integrated with different feature selection techniques. The evaluated metrics encompass accuracy, precision, recall, and F1-score. The findings demonstrate significant enhancements in the accuracy of predictions when employing feature selection techniques. specifically, the utilization of L1 Regularization (Lasso) resulted in the highest level of accuracy, reaching 98.45%. Furthermore, the features chosen by each method provide insight into the variab.e. that have the greatest impact on predicting diabetes. This study offers significant findings regarding the significance of feature selection in healthcare applications, thereby enabling more accurate and effective diagnosis and treatment of diabetes. The results of this study not only make a valuab.e.contribution to improving the accuracy of diabetes prediction, but also highlight the importance of carefully selecting relevant features when developing predictive models for healthcare datasets. This study promotes the need for additional investigation into feature selection methodologies and their implementation in the field of healthcare

关键词： Diabetes Prediction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Precision Grade-Quality Classification of Pomegranates

Deep Learning for Precision Grade-Quality Classification of ...

引用

Innovation and Novelty in engineering and technology (INNOVA), International Conference on

作者： RajinderKumar M. Math Nagaraj V. Dharwadkar Vijaykumar sajjanar M. N. Deshmukh Department of Electronics and Communication Engineering B.L.D.E.A's V.P Dr. P.G Halakatti College of Engineering and Technology Vijayapur Karnataka India Department of Computer Science Central University of Karnataka Kadaganchi Kalaburgi India

ISBN: (数字)9798331505134

ISBN: (纸本)9798331505141

The conventional methods of manual grading of fruits after agricultural harvest have always b.e. laborious, time-consuming, and prone to human errors. In order to speed up the grading process without human intervention, an automatic system is the need of the hour. This research has led to the development a Convolutional Neural Network (CNN) based deep learning technique to provide real-time grading of pomegranate based on its visual features. This automatic grading technique would help farmers in minimizing their efforts and time spent on manual sorting, at the same time ensuring error-free and uniform sorting and packaging of quality fruits that would, in turn, enhance the storage time post packaging. The methodology uses nine pre-trained models to train on a custom pomegranate dataset with twelve grade-quality classes of pomegranates. The grade-quality grading is obtained using the fine-tuning approach in transfer learning, reducing the computational resource requirements and drastically improving inference speed, which is necessary for real-time model deployment scenarios. The results reveal that the fine-tuning of DenseNet-169 model outperformed the other models by achieving highest values of 99.20% and 1 for (Accuracy, Precision, Recall, and Fl-score) and AUC, respectively.

关键词： Deep learning Visualization Technological innovation Computational modeling Transfer learning Manuals Packaging Real-time systems Convolutional neural networks sorting

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization in MANeT for Decreasing energy Consumption with ML Approaches

Ant Colony Optimization in MANET for Decreasing Energy Consu...

引用

Integrated Circuits and Communication systems (ICICACs), Ieee International Conference on

作者： suresha P Gayatri Math siddapuram Arvind M bhaskar Naveen I G Department of Mechanical Engineering S.E.A College of Engineering and Technology Bengaluru India Department of Electronics & Communication Engg HKE society's B.V. Bhoomaraddi college of Arts science and commerce Degree college Bidar India Department of Computer Science & Engineering Hyderabad Institute of Technology and Management Telangana India Department of Computer Science & Engineering K L University Vadeeshwaram Vijayawada India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India

To coordinate access from the active nodes, MAC protocols are used in ad hoc networks. Many media access control (MAC) protocols have b.e. suggested for use in ad hoc networks, each with its own unique set of goals. The goal of many ad hoc networks is to increase the amount of time that its individual nodes, and by extension, the network, can function. Ad-hoc nodes are considered dead when their batteries run out, hence it is crucial to reduce power drain. because to the nature of MANeTs, in which nodes must depend on limited, portab.e.power sources, energy efficiency is a significant barrier to their widespread implementation. In multi-hop systems, where nodes must additionally expend energy to route packets for other nodes and assure the connection of the network, energy saving is difficult. since energy-efficient routing is a relatively new area of study, there are still many open questions that need to be investigated and no widely accepted standards in place. several routing protocols used the shortest route as a criterion for path selection; however, this is inappropriate due to the topology's significant and unexpected variability and does not assume the most efficient use of energy. simulation is the primary tool for testing the efficacy of several routing protocols in MANeTs, including RIP, RIPng, Ps-RIP, PsLLC-RIP, Ps-RIPng, PsLLC-RIPng, FLbUDTCRIP, and ANFIsbUDTCRIP. exata 5.4 GUI network simulator and OPNeT tools are used to analyse the efficiency of the suggested protocols. All the simulation results show \that the suggested protocols perform better than the current RIP protocols.

关键词： Wireless networks Authentication Media Access Protocol Routing Ad hoc networks Routing protocols energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Document Image Retrieval: Issues and Future Directions

Document Image Retrieval: Issues and Future Directions

引用

2021 International Conference on Computational Intelligence and Computing Applications, ICCICA 2021

作者： Dixit, Umesh D. shirdhonkar, M.s. B.L.D.E.A's V. P. Dr. P. G. Halakatti College of Engineering and Technology Department of Electronics and Communication Engineering Vijayapura586103 India B.L.D.E.A's V. P. Dr. P. G. Halakatti College of Engineering and Technology Department of Computer Science and Engineering Vijayapura586103 India

ISBN: (纸本)9781665420402

Document image retrieval is an interesting and popular area of research that has b.e. evolved into many stages. The current trends show that it is still an emerging area due to the availability of document scanner app with mobiles and handheld devices. The ob.e.tive of this paper is to provide an insight into document retrieval, classification, a general architecture, related issues and new opportunities for research in the domain. © 2021 Ieee.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

enhanced Rendering-based Approach for Improved Quality of Instance segmentation in Detecting Green Gram (Vigna Rediata) Pods

SSRN

引用

ssRN 2023年

作者： Dharwadkar, Nagaraj V. Math, RajinderKumar M. Department of Computer Science and Engineering Rajarambapu Institute of Technology Maharashtra Islampur India Department of Electronics and Communication Engineering B.L.D.E. Association’s V.P Dr. P.G. Halakatti College of Engineering and Technology Ashram Road Vijayapur India

The emergence of Artificial Intelligence, deep learning, and current computer vision algorithms are the main contributors to innovations in the agricultural domain. The most recent detection algorithms capab.e.of giving real-time detections at the edge nodes tackle most agricultural prob.e.s, such as disease, pest or insect detections, and maturity level detection of crops (fruits and vegetab.e.). Modern harvesters and fruit-picking robots rely heavily on the detection capability of the algorithms used. Various detection algorithms have b.e. proposed and used in literature, having good performance in terms of mean average precision. still, the current agricultural systems require not only high mean average accuracy but also algorithms should have high inference speeds. The research proposes a Detectron2-based framework with PointRend (Point-based Rendering), capab.e.of providing enhanced, high-quality pixel-level instance segmentation in identifying and detecting green gram pods or Mung bean (Vigna Radiata) in natural field conditions rendering crisp and smooth boundaries for accurately locating the green gram pods. The results indicate that the proposed framework outperforms the famous Mask R-CNN model to obtain higher mean average precision and improved quality of detections. © 2023, The Authors. All rights reserved.

关键词： Ob.e.t detection

来源：评论

学校读者我要写书评

暂无评论

Performance optimization of microbial electrolysis cell (MeC) for palm oil mill effluent (POMe) wastewater treatment and sustainab.e.bio-H2 production using response surface methodology (RsM)

引用

INTeRNATIONAL JOURNAL OF HYDROGeN eNeRGY 2022年第34期47卷 15464-15479页

作者： Chandrasekhar, Abudukeremu Kadier ab Junying Wang ab K. Wang, Junying Chandrasekhar, K. Ab.e.hahian, Peyman Islam, M. Amirul Ghanbari, Farshid bajpai, Mukul Katoch, surjit singh bhagawati, Prashant basavaraj Li, Hui Kalil, Mohd sahaid Hamid, Aidil Abdul Abu Hasan, Hassimi Ma, Peng-Cheng [a]Laboratory of Environmental Science and Technology The Xinjiang Technical Institute of Physics and Chemistry Key Laboratory of Functional Materials and Devices for Special Environments Chinese Academy of Sciences Urumqi 830011 China [b]Center of Material and Opto-electronic Research University of Chinese Academy of Sciences Beijing 100049 China [c]School of Civil and Environmental Engineering Yonsei University Seoul 03722 Republic of Korea [d]Department of Biotechnology Engineering School of Lorena University of São Paulo São Paulo 12602-810 Brazil [e]Laboratory for Quantum Semiconductors and Photon-based BioNanotechnology Department of Electrical and Computer Engineering Faculty of Engineering Université de Sherbrooke Sherbrooke Québec J1K 2R1 Canada [f]Research Center for Environmental Contaminants (RCEC) Abadan University of Medical Sciences Abadan Iran [g]Environmental Engineering Lab Civil Engineering Department National Institute of Technology Hamirpur Hamirpur Himachal Pradesh 177005 India [h]Faculty of Engineering Department of Civil Engineering Annasaheb Dange College of Engineering and Technology Ashta Maharashtra 416301 India [i]Department of Chemical and Process Engineering Faculty of Engineering and Built Environment National University of Malaysia (UKM) UKM Bangi 43600 Selangor Malaysia [j]School of Biosciences and Biotechnology Faculty of Science and Technology National University of Malaysia (UKM) UKM Bangi 43600 Selangor Malaysia [k]Research Centre for Sustainable Process Technology Faculty of Engineering and Built Environment National University of Malaysia (UKM) UKM Bangi 43600 Selangor Malaysia

Microbial electrolysis cells (MeCs) are a new bio-electrochemical method for converting organic matter to hydrogen gas (H-2). Palm oil mill effluent (POMe) is hazardous wastewater that is mostly formed during the crude oil extraction process in the palm oil industry. In the present study, POMe was used in the MeC system for hydrogen generation as a feasib.e.treatment technology. To enhance biohydrogen generation from POMe in the MeC, an empirical model was generated using response surface methodology (RsM). A central composite design (CCD) was utilized to perform twenty experimental runs of MeC given three important variab.e., namely incubation temperature, initial pH, and influent dilution rate. experimental results from CCD showed that an average value of 1.16 m(3) H-2/m(3) d for maximum hydrogen production rate (HPR) was produced. A second-order polynomial model was adjusted to the experimental results from CCD. The regression model showed that the quadratic term of all variab.e. tested had a highly significant effect (P < 0.01) on maximum HPR as a defined response. The analysis of the empirical model revealed that the optimal conditions for maximum HPR were incubation temperature, initial pH, and influent dilution rate of 30.23 ?, 6.63, and 50.71%, respectively. Generated regression model predicted a maximum HPR of 1.1659 m(3) H-2/m(3) d could be generated under optimum conditions. Confirmation experimentation was conducted in the optimal conditions determined. experimental results of the validation test showed that a maximum HPR of 1.1747 m(3) H-2/m(3) d was produced. (c) 2021 Hydrogen energy Publications LLC. Published by elsevier Ltd. All rights reserved.

关键词： Microbial electrolysis cell (MeC) Hydrogen production Palm oil mill effluent (POMe) Wastewater Optimization Response surface methodology (RsM)

来源：评论

学校读者我要写书评

暂无评论

Advanced energy Consumption strategy in Mobility support enhancement for RPL with Multiple sinks

Advanced Energy Consumption Strategy in Mobility Support Enh...

引用

2020 International Conference on electronics and sustainab.e.Communication systems, ICesC 2020

作者： Jain, soniya Patel, Trupesh M.E. Computer Engineering Silver Oak College of Engineering Technology Ahmedabad Gujarat India M.E. Computer Engineering S.P.B Patel Engineering College Mehsana Gujarat India

ISBN: (纸本)9781728141084

In the environment of the internet of things decentralized type of network is utilized, where nodes communication takes place and data is transferred to the internet via the base station. The communication routing is applied using RPL in IoT. For LLNs (Low Power and Lossy Network) it is a systematic routing protocol. As static topologies, RPL was initially designed, for a lot of uses mobility assistance continues to be a significant necessity of LLNs. Additionally, the component of the applications mobility support for many sink nodes rather compared to a sink node. This's because of the point that in an information assortment wireless sensor networking (WsN), just a sink very easily results to a much faster power depletion, a lot more package loss, maximum latency, and smaller sized community range. Deploying several sinks in the networking is ab.e.to assist you to resolve the issues. This particular paper concentrates on dealing with mobility assistance in RPL with several sinks. A resolving response to this particular issue is deploying several sinks in wireless sensor networking. In direction to enhance the wireless sensor network performance overall in phrases of Packet loss, Lifetimes, every sensor node communicates just with the closest sink. When the sinks are actually distributed more than places that are diverse, this could lead to an average decrease in the number of hops and hence the growth in reduction and functionality of the ingested energy. © 2020 Ieee.

关键词： energy utilization

来源：评论

学校读者我要写书评

暂无评论

Umpire gesture detection and recognition using HOG and non-linear support vector machine (NL-sVM) classification of deep features in cricket videos 2

Umpire gesture detection and recognition using HOG and non-l...

引用

2nd International Conference on Advances in Physical sciences and Materials 2021, ICAPsM 2021

作者： Nandyal, suvarna Kattimani, suvarna Laxmikant Department of Computer Science and Engineering P. D. A. College of Engineering Affiliated to Visvesvaraya Technological University 590018 Kalaburgi Karnataka Belagavi585102 India Department of Computer Science and Engineering B.L.D.E.A's V.P. Dr. P. G. Halakatti College of Engineering and Technology Affiliated to Visvesvaraya Technological University Belagavi-590018 Karnataka Vijayapur586103 India

Gesture Recognition pertains to recognizing meaningful expressions of motion by a human, involving the hands, arms, face, head, and/or body. It is of utmost importance in designing an intelligent and efficient human-computer interface. The applications of gesture recognition are manifold, ranging from sign language through medical rehabilitation, monitoring patients or elder people, surveillance systems, sports gesture analysis, human behaviour analysis etc., to virtual reality. In recent years, there has b.e. increased interest in video summarization and automatic sports highlights generation in the game of Cricket. In Cricket, the Umpire has the authority to make important decisions about events on the field. The Umpire signals important events using unique hand on signals and gestures. The primary intention of our work is to design and develop a new robust method for Umpire Action and Non-Action Gesture Identification and Recognition based on the Umpire segmentation and the proposed Histogram Oriented Gradient (HOG) feature extraction oriented Non-Linear support Vector Machine (NL-sVM) classification of Deep Features. Primarily the 80% of Umpire action and non-action images in a cricket match, about 1, 93, 000 frames, the Histogram of Oriented Gradient Deep Features are calculated and trained the system having six gestures of Umpire pose. The proposed HOG Feature extraction oriented Non-Linear support Vector Machine classification method achieves the maximal accuracy of 97.95%, the maximal sensitivity of 98.87%, the maximal specificity of 98.89% and maximal Precision of 97.02% which indicates its superiority. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence based Model Detection of Disease using Chest Radiographs

Computational Intelligence Based Model Detection of Disease ...

引用

emerging Trends in Information technology and engineering (ic-eTITe), Conference on

作者： Hrishikesh Mane Parag Ghorpade Vedant bahel Student (B.E.) Department of Computer Engineering Modern Education Society’s College of Engineering Pune India Student (B.E.) Department of Information Technology G H Raisoni College of Engineering Nagpur India

ISBN: (数字)9781728141428

ISBN: (纸本)9781728141435

There are many diseases associated with lungs or thoracic cavity and the diagnosis of these diseases at once becomes difficult for any medical profusion. The most common way of screening done when the thoracic cavity comes into the picture is Chest Radiography. However, diagnosing multiple diseases from a single scan becomes difficult. This paper proposes an intelligent machine learning-based model which tries to detect 14 chest diseases out from a single radiograph with greater accuracy. This paper makes use of advanced deep learning techniques like neural networks, masking algorithms, etc. to assure higher performances.

关键词： Radiographs Deep Neural Network Imagining Healthcare X-Ray Film Health Care Artificial Intelligence Computational intelligence Thoracic Cavity Disease diagnosis maladjustment Thoracic Radiography single scan Thorax boxes

来源：评论

学校读者我要写书评

暂无评论

A study on Cloud enab.e. Applications and their security Issues

A study on Cloud enabled Applications and their Security Iss...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Vidhi Mody Vrushti Mody soham Parekh B.Tech. Computer Engineering Mukesh Patel School of Technology Management and Engineering NMIMS B.E. Computer Engineering Dwarkadas Jivanlal Sanghvi College of Engineering

ISBN: (数字)9781728168517

ISBN: (纸本)9781728168524

Cloud computing was first established to connect people and data at anytime from anywhere in the 1960s. Today cloud computing is one of the most widely used technologies. Its applications include Multi-cloud, healthcare, testing, finance, data storage and handling big data to increase efficiency and how it differs from traditional systems. We have stated how cloud computing can be used in various domains and have compared its efficiency to traditional systems in terms of data recovery, access control, management, security and cost. However, like any other technology, this one too might have flaws which can be exploited. This paper also lists the security challenges that will have to be kept in mind while implementing these systems.

关键词： Cloud computing security Medical services Real-time systems Maintenance engineering Data privacy Computational modeling

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：