检索结果-内蒙古大学图书馆

Intelligent computing and Networking - Proceedings of IC-ICN 2023

作者： Surbakti, Herison Kumar, Athmakuri Naveen Tara, Saikumar Keshta, Ismail khare, Amit Prasad, G.N.R. Faculty of Computing and Digital Technology HELP University Kuala Lumpur Malaysia Senior Software Engineer Glosoft Technologies Pvt Ltd Chennai India Department of ECE BVRIT Hyderabad College of Engineering for Women Hyderabad India Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Department of Technology JIET Institute of Design and Technology Rajasthan Jodhpur India Telangana Hyderabad500091 India

ISBN: (纸本)9789819931767

In recent years, support vector machine has become one of the most important classification techniques in pattern recognition, machine learning, and data mining due to its superior classification effect and solid theoretical base. However, its training time will increase dramatically as the number of samples increases, and training will become more sophisticated when dealing with problems involving multiple classifications. A quick training data reduction approach MOIS appropriate for multi-classification tasks is presented as a solution for the aforementioned issues. While eliminating redundant training samples, the boundary samples that play a vital role are chosen in order to considerably reduce training data and the problem of unequal distribution between categories. The experimental results demonstrate that MOIS may maintain or even improve the classification performance of support vector machines while substantially enhancing training efficiency. On the Opt digit dataset, the suggested method improves classification accuracy from 98.94% to 99.05%, while training time is reduced to 15% of the original;in HCL2000, the proposed method improves classification accuracy from 98.94% to 99.05%. When the accuracy rate is marginally increased (from 99.29% to 99.30%) on the first 100 categories dataset, the training time is dramatically reduced to less than 6% of the original. Additionally, MOIS has a high operational efficiency. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based multi-head self-attention model for human epilepsy identification from EEG signal for biomedical traits

引用

Multimedia Tools and Applications 2024年第33期83卷 80201-80223页

作者： Dutta, Ashit Kumar Raparthi, Mohan Alsaadi, Mahmood Bhatt, Mohammed Wasim Dodda, Sarath Babu Prashant, G.C. Sandhu, Mukta Patni, Jagdish Chandra Department of Computer Science and Information Systems College of Applied Sciences AlMaarefa University Ad Diriyah Riyadh13713 Saudi Arabia Alphabet Life Science DallasTX7506 United States Department of Computer Science Al-Maarif University College Al Anbar31001 Iraq Model Institute of Engineering and Technology J&K Jammu India Software Engineer Central Michigan University DallasTX75009 United States Department of Computer Science Texas Tech University Lubbock79409 United States Skill Faculty of Engineering & amp Technology Shri Vishwakarma Skill University Haryana Palwal India CSE School of advance Computing Alliance University Bengaluru India

The neurological condition epilepsy is demanding and even fatal. Electroencephalogram (EEG)-based epilepsy detection still faces various difficulties. EEG readings fluctuate, and different patients have various seizure activity patterns. EEG signal detection is time-consuming and labour-intensive, which puts a strain on medical staff and raises the possibility of erroneous detections. Usually, electrodes are inserted into the scalp or inside the brain for a brief period of time in order to obtain EEG data. It is essential to research efficient cross-patient automatic epilepsy detection techniques. The multi-head self-attention mechanism recognises long-distance dependencies with the same proficiency as it does temporal dynamic correlations between short-term temporal pattern characteristics and sequential relationships. The contextual representations are inputted into a bidirectional long short-term memory network (BiLSTM) so that information can be extracted in both directions. Classification and training are carried out utilising the log SoftMax algorithm. The experiments utilised scalp EEG data from the CHB-MIT database. Sensitivity, specificity, F1-score, and accuracy were computed to be 96.5 percent, 97.04 percent, 96.6 percent, and 96.2 percent, respectively. The results of the experiment show how well the technique works for detecting seizures in several patients utilising multi-channel EEG recordings. The results also demonstrate the method's improved generalisation capabilities and resilience and consistency in collecting seizure patterns. This is particularly critical for the tertiary diagnosis of epilepsy, and the findings indicate that the proposed method significantly improves the accuracy of detection. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Approach to Segment the Liver Cancer using Machine Learning Method 4

An Intelligent Approach to Segment the Liver Cancer using Ma...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Anand, L. Maurya, Mahesh Seetha, J. Nagaraju, D. Ravuri, Ananda Vidhya, R.G. School of Computing Srm Institute of Science and Technology Department of Networking and Communications India University of Mumbai K. C. College of Engineering Management and Research Mith Bunder Road Near Hume Pipe Maharashtra Thane400603 India Panimalar Engineering College Department of Computer Science and Business Systems Chennai India Sri Venkatesa Perumal College of Engineering and Technology Department of CSE Andhra Pradesh Puttur India Senior Software Engineer Intel Corporation HillsboroOR97124 United States Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798350300093

Cancer Liver cancer is difficult to detect and diagnose early. Machine learning has improved liver cancer diagnosis in recent years. This abstract describes a novel liver cancer detection and classification method using Autoencoder-Extreme Learning Machine (AE-ELM) and Convolutional Neural Network (CNN) technology. AE-ELM models extract features in the suggested method. The autoencoder-extreme learning machine AE-ELM technique learns high-level abstract characteristics from incoming data. AE-ELM extracts liver cancer-specific features by reducing the dimensionality of input data. A CNN model classifies the extracted features. CNNs are good at detecting spatial patterns in medical pictures like CT and MRI scans. The CNN model learns hierarchical representations of input information and classifies them into liver cancer subtypes or stages using various convolutional and pooling processes. AE-ELM and CNN are advantageous. First, AE-ELM decreases input data dimensionality to extract critical features without manual feature engineering. This simplifies feature selection and improves the model's capacity to handle big data. Second, the CNN model uses hierarchical convolutional processes to capture subtle patterns and spatial correlations in input data, enhancing liver cancer classification accuracy. The proposed liver cancer diagnostic method works in experiments. AE-ELM and CNN models outperform classic machine learning approaches and standalone CNN models. Improved liver cancer detection accuracy, sensitivity, and specificity help healthcare practitioners make quick and precise diagnosis. Finally, AE-ELM and CNN technologies can identify and classify liver cancer. This unique strategy uses both models to extract relevant characteristics and capture complicated patterns, improving liver cancer diagnosis accuracy and efficiency. To evaluate this approach's therapeutic promise and application in real-world healthcare settings, additional datasets are needed. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

“This Wasn’t Pedagogy, It Was Panicgogy”: Perspectives of the Challenges Faced by Students and Instructors during the Emergency Transition to Remote Learning Due to COVID-19

引用

college Teaching 2023年第4期71卷 227-243页

作者： Spinks, M’Lyn Metzler, Mike Kluge, Stacy Langdon, Jody Gurvitch, Rachel Smitherman, Marina Esmat, Tiffany Bhattacharya, Sylvia Carruth, Laura Crowther, Katy Denton, Ren Edwards, Ordene V. Shrikhande, Milind Strong-Green, Ashley WellStar College of Health and Human Services Kennesaw State University United States Center for Teaching and Learning Georgia State University United States Instructional Innovation Augusta University United States Georgia Southern University United States Georgia State University United States Department of Life Science Dalton State College United States WellStar College of Health and Human Services Exercise Science Kennesaw State University United States College of Computing and Software Engineer Engineering Technology Kennesaw State University United States Center for Excellence in Teaching and Learning Georgia State University United States Department of English Georgia State University United States Academic Affairs East Georgia State College - Statesboro Campus United States Department of Psychological Science Kennesaw State University United States Department of Finance Georgia State University United States Department of English Augusta Technical College United States

This qualitative study explores the impact of the emergency transition to remote education (ETRE) during the COVID-19 pandemic on instructors and students through the lens of self-determination theory (SDT). A modified thematic analysis of narratives from a cross-sectional survey revealed eight themes: Sense of loss/grief, Role conflict, Helplessness, I had no choice, This felt impossible, Lost connections, Am I safe, and They don’t care about me. Sub-themes expound on their associated themes. Participant narratives shared feelings of trauma and crisis as they related experiences of higher education during the mandated global shutdown. The stories of these experiences are indicative of loss of autonomy, competence, and relatedness, tenets of self-determination. These experiences, for the majority of students, led to a loss of motivation to learn, participate, or produce meaningful work. For most instructors, the experiences led to a similar lassitude and frustration. The authors conclude that the experience of the ETRE negatively impacted both teaching and learning in the higher education setting. Recommendations include further development in higher education to support both instructors’ and students’ self-determination during catastrophic change. © 2021 Taylor & Francis Group, LLC.

关键词： COVID-19 emergency transition instructors qualitative self-determination students

来源：评论

学校读者我要写书评

暂无评论

Forecasting COVID-19 Infections in Gulf Cooperation Council (GCC) Countries using Machine Learning

arXiv

引用

arXiv 2023年

作者： Ismail, Leila Materwala, Huned Hennebelle, Alain Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates Independent Data Scientist and Engineer Al Ain Abu Dhabi United Arab Emirates

COVID-19 has infected more than 68 million people worldwide since it was first detected about a year ago. Machine learning time series models have been implemented to forecast COVID-19 infections. In this paper, we develop time series models for the Gulf Cooperation Council (GCC) countries using the public COVID-19 dataset from Johns Hopkins. The dataset set includes the one-year cumulative COVID-19 cases between 22/01/2020 to 22/01/2021. We developed different models for the countries under study based on the spatial distribution of the infection data. Our experimental results show that the developed models can forecast COVID-19 infections with high *** Codes 68-04, 68T05, 68T07, 68T20 © 2023, CC BY-NC-ND.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Integrating GPS and GSM Technologies for Enhanced Women’s Safety: A Fingerprint-Activated Device Approach

Integrating GPS and GSM Technologies for Enhanced Women’s S...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Kamred Udham Singh Varun Chaudhary Pradeep Kumar Sharma Pushpendra Kumar Neeraj Varshney Teekam Singh School of Computing Graphic Era Hill University Dehradun India IMS ENGINEERING COLLEGE Ghaziabad India Technical Architect HCL Technologies Noida UP Sr Software Engineer Scanno System Greater Noida Department of Computer Engineering & Applications GLA University Mathura UP India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun

The creation of a safety system that is based on GPS and is developed exclusively for the health and safety of women via the incorporation of novel elements in order to meet the rising concerns about crimes committed against women. The gadget is capable of contacting authorities, conveying the user’s position via SMS, and generating a loud noise to attract attention. It may be triggered in anticipation of potential danger and can be activated in the event that danger is imminent. In order to guarantee that only authorized users are able to activate the device, the system makes use of fingerprint recognition in a very unique way. Using technologies such as global positioning system (GPS), global system for mobile communications (GSM), and microcontrollers, this study makes a contribution to the continuing efforts to improve the safety of women via technological innovation. It provides a proactive approach to prevent violence against women and save lives. The research emphasizes the significance of combining hardware and software in order to provide a complete safety tool. It also illustrates the vital role that quick support plays and the potential of such gadgets to promote confidence among women in public places.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Explicit Group Sparse Projection in Optimizing 5G Network Resource Allocation and Topology Design

Application of Explicit Group Sparse Projection in Optimizin...

引用

Innovation in Technology (ASIANCON), Asian Conference on

作者： Kodanda Rami Reddy Manukonda Hemanth Swamy R. Sankar Chidambaranathan C. M. Haribabu.k Saranya. Department of Consulting IBM Senior Software Engineer Motorola Solutions Department of EEE Chennai Institute of Technology Chennai Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of ECE MLR Institute of Technology Hyderabad Department of AI & DS Dhanalakshmi College of Engineering Chennai

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

The growing adoption of 5G networks in diverse domains like IoT, smart cities, healthcare, and industrial automation necessitates advanced optimization techniques. While existing approaches have shown promise, they are often limited by computational intensity, lack of adaptability, and specific focus on geometric constraints. This paper presents EGSP-5G, a novel methodology employing Explicit Group Sparse Projection (EGSP) for 5G network resource allocation and topology design. Its capability to achieve targeted sparsity levels allows for efficient utilization of network resources, thereby making it a versatile and powerful tool for various optimization tasks. Remarkably, EGSP-5G achieved a resource utilization rate of 90.02% and a throughput of 110.32 in networks comprising 1000 nodes. It stands as a robust and versatile solution for optimizing 5G networks across diverse application domains.

关键词： Technological innovation Automation 5G mobile communication Network topology Smart cities Medical services Throughput Topology Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Approach to Segment the Liver Cancer using Machine Learning Method

An Intelligent Approach to Segment the Liver Cancer using Ma...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： L Anand Mahesh Maurya J. Seetha D Nagaraju Ananda Ravuri R G Vidhya Department of networking and communications School of computing SRM Institute of science and Technology K. C. College of Engineering Management and Research University of Mumbai Mith Bunder Road Near Hume Pipe Thane Maharashtra India Department of Computer Science and Business Systems Panimalar Engineering College Chennai Department of CSE Sri Venkatesa Perumal College of Engineering and Technology Puttur Andhra Pradesh India Senior Software Engineer Intel corporation Hillsboro Oregon USA Department of ECE HKBK College of Engineering Bangalore

Cancer Liver cancer is difficult to detect and diagnose early. Machine learning has improved liver cancer diagnosis in recent years. This abstract describes a novel liver cancer detection and classification method using Autoencoder-Extreme Learning Machine (AE-ELM) and Convolutional Neural Network (CNN) technology. AE-ELM models extract features in the suggested method. The autoencoder-extreme learning machine AE-ELM technique learns high-level abstract characteristics from incoming data. AE-ELM extracts liver cancer-specific features by reducing the dimensionality of input data. A CNN model classifies the extracted features. CNNs are good at detecting spatial patterns in medical pictures like CT and MRI scans. The CNN model learns hierarchical representations of input information and classifies them into liver cancer subtypes or stages using various convolutional and pooling processes. AE-ELM and CNN are advantageous. First, AE-ELM decreases input data dimensionality to extract critical features without manual feature engineering. This simplifies feature selection and improves the model’s capacity to handle big data. Second, the CNN model uses hierarchical convolutional processes to capture subtle patterns and spatial correlations in input data, enhancing liver cancer classification accuracy. The proposed liver cancer diagnostic method works in experiments. AE-ELM and CNN models outperform classic machine learning approaches and standalone CNN models. Improved liver cancer detection accuracy, sensitivity, and specificity help healthcare practitioners make quick and precise diagnosis. Finally, AE-ELM and CNN technologies can identify and classify liver cancer. This unique strategy uses both models to extract relevant characteristics and capture complicated patterns, improving liver cancer diagnosis accuracy and efficiency. To evaluate this approach’s therapeutic promise and application in real-world healthcare settings, additional datasets are needed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An innovation analysis of LZ77 and LZ78 Compression Algorithms for Data Compression & Source Coding

An innovation analysis of LZ77 and LZ78 Compression Algorith...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Rakesh Kumar Giri Abhinav Mishra Aruna Sri Rongali Laxmi A. Bewoor R Raghavendra M. S. Kavitha Department of Computer Science & Engineering Sunrise University Alwar India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Information Technology Emphasis/Technology Software Engineer Ph.D University of The Cumberlands US Department of Computer Engineering Vishwakarma Institute of Technology Pune INDIA College of Computing Sciences And Information Technology Jain (deemed to be) University Bangalore Karnataka India Department of ECER. M. K. Engineering College RSM Nagar Kavaraipettai

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This paper evaluates innovation on two of the most widely used compression algorithms — the LZ77 and the LZ78 algorithms — for information compression and supply coding programs. A detailed assessment of these algorithms presents insights approximately their design philosophy, technical traits, and performance metrics. Additionally, the studies offer a complete overview of their packages and implementations. The paper investigates the prominent considerations for implementing compression algorithms and analyzes their relative blessings and downsides. An exploration of the constraints of every algorithm is likewise undertaken. Furthermore, the research explores distinctive design elements of the algorithms, such as data structure, compression engine, and set of rules optimization. Eventually, the paper assesses the algorithms by reading the exchange-offs between their performance and complexity. This study facilitates practitioners and developers to apprehend the results of using those algorithms for diverse compression and supply coding applications. It can assist practitioners in identifying the first-class compression set of rules for their unique application needs. This paper gives an innovative evaluation of the LZ77 and LZ78 Compression Algorithms. These algorithms are algorithms designed for statistics compression and source coding. They’re used to take a given series of characters (or bits) and encode them right into an area-green representation. The innovation evaluation presents a valuable perception of how the algorithms improve compression ratios and shop area. It also discusses the effect of positive parameters such as window length, repeat cycle, and buffer size on compression efficiency. ultimately, the paper will speak to future studies’ challenges in this region and the capability packages of those algorithms.

关键词： Measurement Technological innovation Image coding Codes Philosophical considerations Source coding Green products Approximation algorithms Compression algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

SCMC: Smart city measurement and control process for data security with data mining algorithms

引用

Measurement: Sensors 2024年 31卷

作者： Selvarajan, Shitharth Manoharan, Hariprasath Goel, Sonali Akili, Chiranjeevi Prakash Murugesan, S. Joshi, Vaishali School of Built Environment Engineering and Computing Leeds Beckett University Leeds LS1 3HE United Kingdom Department of Electronics and Communication Engineering Panimalar Engineering College Poonamallee Tamil Nadu Chennai 600123 India Department of Electrical Engineering ITERSOA Deemed to be University Odisha Bhubaneswar India Software Engineer US Technology International Pvt Ltd India Department of Computer Science and Engineering R.M.D Engineering College Kavaraipettai 601206 India School of CSIT Symbiosis University of Applied Sciences Indore India

In this paper the importance of monitoring smart city with integration of sensors and Internet of Things (IoT) is discussed with establishment of node control process. To describe the feature of smart cities time measurements are considered with one hop distance between various nodes. Hence the system model is established for various parameters that are integrated with K-means algorithm for clustering and C4.5 for classification. As a result of combining the dual algorithms with system model it is possible to establish a secured state for each data with proper response factor. The major significance of proposed method is to introduce node point where all increasing queues in smart cities are controlled due to the information that is achieved from every data points. Moreover the improvement in projected model can be observed with four scenarios where security at every data point plays an important role at an increased level of 84%. In addition to security the amount of stable points is increased with reduction in disparities for about 2% thereby every applications in smart cities are monitored in a precise way. © 2023 The Authors

关键词： Measurement and control Security Sensors Smart city

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：