检索结果-内蒙古大学图书馆

2nd IEEE Global Conference on Communications and Information technologies, GCCIT 2024

作者： Dhabliya, Dharmesh Yuvaraj, K. Chauhan, Rahul Sharma, Dikshit Kala Priyadarshini, G. Shankar Prasad, S. Vishwakarma Institute of Technology Department of Information Technology Pune India Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Graphic Era Hill University Uttarakhand Dehradun248002 India Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India School of Management - UG Management Karnataka Bangalore India

ISBN: (纸本)9798350388916

Ultra-Low-Power (ULP) Internet of Things (IoT) devices are becoming more important in the fast developing 5G and possible 6G networks, and this study tackles the problem of incorporating dynamic AI capabilities into these devices. We present the Dynamic AI-IoT design, a new framework that aims to do away with the tedium of firmware upgrades. This design makes use of Narrowband IoT (NB-IoT) to make cloud interactions run smoothly and includes specialized firmware modifications to make dynamic interactions with TinyML models possible. Many sectors rely on deep learning that is based on massive amounts of high-quality data. The information accumulation of the framework relies on real-time acquisitions, which makes it difficult to directly implement deep learning in a real-time system. But such systems' analytical activities can't be done by collecting data for a lengthy period since they need to be executed in real time. This research presents a novel progressive deep-learning architecture and performs experiments on picture identification to address the challenges of high-quality data collection, high-timeliness data processing, and the difficulties of directly integrating deep-learning algorithms in real-time systems. The experimental findings demonstrate the efficacy, performance, and ability to get a conclusion comparable to the deep-learning architecture using large-scale data. An advanced method for managing memory is presented for the effective handling of AI tasks;it is based on memory alignment and the dynamic resolution of AI activities. Through the use of ULP IoT gadgets on a 5G testbed, empirical investigations show that the implementation of a Dynamic AI-IoT network is feasible. With an average inference duration of around 46 ms and model updates averaging less than one second, the findings are impressive. © 2024 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Enhancing Internet of Things Safety with AI-Powered Intrusion Avoidance Systems

Enhancing Internet of Things Safety with AI-Powered Intrusio...

引用

Intelligent technologies (ACOIT), Asian Conference on

作者： Sachin Ramchandra Misal M. Monica Bhavani Chandra Rao Merla Ganieva Shodiya Azizovna Jumisree Sarmah Pathak Praveen Kumar International Institute of Management Science Chinchwad Pune India Data Science & Business Systems SRM University Kattankulathur Department of Computer Science & Engineering Malla Reddy Engineering College for Women Hyderabad Department of Methodology of Primary education Fergana State University Department of Physics Indian Institute of Teacher Education Gandhinagar Gujarat Astana IT University Astana Kazakhstan

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

The rapid proliferation of Internet of Things (IoT) devices has ushered in unprecedented levels of connectivity, offering enhanced automation and data sharing across diverse domains. However, this surge in interconnectivity has brought about a significant challenge regarding cyber security threats and intrusions. To overcome this problem, we propose a Hybrid Bayesian Tree Fusion (HBTF) for predicting the detection system. These systems leverage the capabilities of Artificial Intelligence to predict and proactively mitigate potential security breaches. We gather the NSL-KDD data set for evaluating the proposed method for forecasting intrusion detection. The collected data are preprocessed using Z score normalization to eliminate the noise. Extract the feature from the preprocessed data using kernel-based independent component analysis (KICA). The experimental findings of the proposed method are evaluated by recall, precision, f1-score, and accuracy from the result. The HBTF is greater than the existing method. The integration of AI augments the capability of IoT networks to counter emerging threats, ultimately fostering a safer and more secure interconnected world.

关键词： Automation Intrusion detection Independent component analysis Feature extraction Bayes methods Internet of Things Security Data mining Artificial intelligence computer crime

来源：评论

学校读者我要写书评

暂无评论

Establishing Baseline Biodiversity Through Hyper Spectral Imaging

Establishing Baseline Biodiversity Through Hyper Spectral Im...

引用

Communication, computer sciences and Engineering (IC3SE), International Conference on

作者： Anuj Kumar Indu Sharma Samir Rana Ritu Sawanni Atul Pal Siddhant Thapliyal Department of Information Technology Management Education & Research Institute(MERI) Affiliated to GGSIP University New Delhi India Department of Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand India Department of Computer Science and Engineering Rajkiya Engineering College Kannauj Affiliated to Dr. A.P.J. AKTU Lucknow Uttar Pradesh India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

Hyper spectral imaging (HSI) is an era that is getting used to map and measure biodiversity in distinct regions. Biodiversity refers to the variety and variability of residing organisms located in a selected environment. It plays a critical position in preserving the stability and functioning of ecosystems, and is considered to be an important indicator of the fitness and resilience of the planet. Using HSI for estimating and monitoring biodiversity is gaining momentum due to its capability to capture detailed and unique statistics approximately the spectral reflectance of plant life, animals, and different organisms. HSI systems work by means of shooting photos of a place the use of hundreds of slim bands of the electromagnetic spectrum. The woodland and water body instructions were completed with the maximum precision, while the agricultural land elegance was found to have the lowest accuracy. The hyperspectral imaging data provided an accurate and comprehensive depiction of the observation area, enabling the differentiation of different land cover types. This enables researchers to analyze the spectral signatures of different species gift in the vicinity and discover them based totally on their unique reflectance *** of the key advantages of the use of HSI for estimating biodiversity is its potential to offer a complete and correct baseline assessment of the species present in a place. Traditional methods of biodiversity assessment, which include subject surveys, are time-eating and may regularly omit essential species due to their confined scope and attain. HSI, however, covers large vicinity and may come across a wide range of species, which includes the ones which might be tough to observe with the naked eye.

关键词： Reflectivity Surveys Accuracy Ecosystems Sociology Imaging Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Computational Analysis for computer Network Model with Fuzziness

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1909-1924页

作者： Wafa F.Alfwzan Dumitru Baleanu Fazal Dayan Sami Ullah Nauman Ahmed Muhammad Rafiq Ali Raza Department of Mathematical Sciences College of SciencePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Mathematics Cankaya UniversityBalgatAnkara06530Turkey Institute of Space Sciences Magurele-Bucharest077125Romania Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Department of Mathematics School of ScienceUniversity of Management and TechnologyLahore54000Pakistan Department of Mathematics and Statistics University of LahoreLahore54590Pakistan Department of Mathematics Faculty of Science and TechnologyUniversity of Central PunjabLahore54000Pakistan Near East University Mathematics Research CenterDepartment of MathematicsNear East BoulevardPC:99138Nicosia/Mersin 10Turkey Department of Mathematics Govt.Maulana Zafar Ali Khan Graduate College WazirabadPunjab Higher Education Department(PHED)Lahore54000Pakistan

A susceptible,exposed,infectious,quarantined and recovered(SEIQR)model with fuzzy parameters is studied in this *** in the model arises due to the different degrees of susceptibility,exposure,infectivity,quarantine and recovery among the computers under consideration due to the different sizes,models,spare parts,the surrounding environments of these PCs and many other factors like the resistance capacity of the individual PC against the virus,*** individual PC has a different degree of infectivity and resis-tance against *** this scenario,the fuzzy model has richer dynamics than its classical counterpart in *** reproduction number of the developed model is studied and the equilibrium analysis is *** different techniques are employed to solve the model *** simulations are performed and the obtained results are *** and convergence are maintained by the suggested technique which are the main features of the epidemic models.

关键词： NSFD method computer virus fuzzy parameters convergence stability

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning for Efficient Network Traffic management in Edge Computing

Adaptive Federated Learning for Efficient Network Traffic Ma...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Kuricheti Suresh Babu S Venkatasubramanian S. Kishore K Kavya Ramya Sree Ch.Lavanya Susanna Goda Srinivasa Rao Ajanthaa Lakkshmanan Department of Computer Science and Engineering PACE Institute of Technology and Sciences Valluru AndhraPradesh Department of Computer Science and Business Systems Saranathan college of engineering Trichy India Department of CSBS B V RAJU INSTITUTE OF TECHNOLOGY Narsapur Medak Telangana Department of AI&ML Aditya University Surampalem Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of CSE KL University Vaddeswaram Guntur Andhra Pradesh India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Campus Kattankulathur

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

With the increasing prevalence of edge computing environment, there is a need to establish effective network traffic management that are able to manage vast data while also protecting the privacy of users. The proposed method enhances efficiency of bandwidth, reduce the network latency and manages computational demands without managing data privacy. This is achieved by utilizing the design of edge devices. The adaptable nature of the method enables it to react in real time to different traffic situations. It optimizes the distribution of resources and improves the overall performance of the network. Additionally, it can reduce the possibility of centralized data exposure, providing robust privacy preservation through the allowance of local model training on edge devices. Finally, this method is superior. The employment of federated learning to network traffic management provide efficiency to optimize the traffic in edge computing which is both scalable and safe. This makes it suitable for a wide variety of applications that are utilized in next generation networks

关键词： Training Adaptive systems Federated learning Computational modeling Telecommunication traffic Bandwidth Real-time systems Optimization Next generation networking Edge computing

来源：评论

学校读者我要写书评

暂无评论

The Sentiment Analysis of Human Behavior on Products and Organizations using K-Means Clustering and SVM Classifier 3

The Sentiment Analysis of Human Behavior on Products and Org...

引用

3rd International Conference on Intelligent Engineering and management, ICIEM 2022

作者： Chaudhury, Sushovan Achyutha Prasad, N Chakrabarti, Sudakshina Kumar, Chevella Anil Elashiri, Mohamed A. University of Engineering and Management West Bengal Kolkata India East West Institute of Technology Department of Computer Science and Engineering Karnataka Bangalore India Chettinad Academy of Research and Education Anatomy Chettinad Hospital and Research Institute Tamilnadu Chengalpattu India Jawaharlal Nehru Technological University Kukatpally Hyderabad India Beni-Suef University Faculty of Computers & Artificial Intelligence Computer Science Department Institute Beni-Suef Egypt

ISBN: (数字)9781665467568

ISBN: (纸本)9781665467568

Sentiment analysis Sentiment analysis is the process of extracting information from the text and it is considered as opinion mining. Machine learning experiments have been shown in the study that involves review, blog, for some texts that are written in different languages including Dutch, English and French. Set of example sentence have been set that are manually labeled, neutral, positive or negative. The study covers the curiosity of the consumer regarding the specific consumption products. Categorization models have been developing that has been used in the study. Number of issues that includes noisy nature of the text has been discussed in the study. With an accuracy of roughly 83 percent for English texts, we can determine positive, negative, and neutral sentiments toward the subject under investigation using unigram features augmented with linguistic information. The role of active learning approaches in minimizing the number of instances that need to be manually annotated is discussed in this article. Our studies also give data on the transferability of learned models between domains and languages. Here, Sentiment analysis of a particular person has studied using a K-Means Clustering and SVM classifier to classify the sentiment of a person from the text © 2022 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Designing Scalable and Energy-Efficient Computation: Magnetoelectric Spin-Orbit Circuitry

Designing Scalable and Energy-Efficient Computation: Magneto...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Amit Kumar Sharma Ritika Mehra Brijesh Kumar N. V. Balaji K. Sriram Kumar V.S. Gaikwad Department of Physics TMU School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand School of Commerece And Management IIMT University Meerut Department of Computer Science Karpagam Academy of Higher Education Coimbatore Department of Information Technology Karpagam Institute of Technology Coimbatore Computer Engineering Vishwakarma Institute of Information Technology Pune

Using a magnetoelectric spin-orbit circuit, this study suggests a revolutionary method for developing scale and cost-effective computer. Despite semiconductors miniaturization, the leading technology of today, CMOS, has basically not evolved in terms of operational ideas throughout the years. The research investigates alternate dimensions expanded logic strategies to boost the performance of numerical control schemes and allow for the growth of novel methods like machine learning. The proposed optical logic device links the spinning energy of the electron with its mobility through spin-orbit communication and magnetism property toggle. The gadget has collaboration and senses due to the incorporation of cutting-edge linked chemicals and quasi constituents. In the areas of shifting energy, voltage, and computation efficacy, the study shows that this novel technique beats the technology known as CMOS. Additionally, it allows for minimum idle power usage and the possibility of multigenerational computation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CSO — VGG-19: Prediction of Cervical Cancer Using Cuckoo Search-Based Deep VGG-19

CSO — VGG-19: Prediction of Cervical Cancer Using Cuckoo Se...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： M.Suresh Anand S. Manimozhi Abul Ala Walid A Naresh Kumar P. Dharmendra Kumar N.V.S. Suryanarayana Department of Computing Technologies School of Computing SRM Institute of Science & Technology Kattankulathur Department of Computer Science and Applications Periyar Maniammai Institute of Science and Technology Vallam Thanjavur Department of Computer Science and Engineering Khulna University of Engineering & Technology (KUET) Khulna Department of Computer Science and Business Systems Sri Sairam Engineering College West Tambaram Chennai Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram AP India HVPE Central Tribal University of Andhra Pradesh Vizianagaram

Nearly four percent of women worldwide have cervical cancer, which can be fatal if not detected and treated early. When contrasted to current numbers, the death rate a few decades ago was unacceptably high. In recent years, clinics have intended to employ advancements in digital image and machine learning to improve cervical cancer screening. Women that test negative have a low risk of developing cancer of the cervical cavity over the following ten years, even if the majority of cervical infections that result in positive testing do not cause precancer. For the prompt identification as well as prompt cure for cervical cancer, it is crucial to identify important genes in cancer, identify healthy people as cervical cancer predictors, and perform an initial evaluation of a high-through expression information. The major objective of the suggested effort is to identify cervical cancer in order to forecast cervical genes. To find the cervical genes, a cuckoo-based deep conversion is created. To some degree, the proposed model predicts the progression of cervical cancer using the VGG-19 model. The deep conversion-based cuckoo search technique can be used to identify cervical cancer patients. The proposed model obtains a 99.30% accuracy rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A mandatory contribution-based collaborative gaming approach to enhancing students’ collaborative learning outcomes in science museums

引用

Interactive Learning Environments 2023年第5期31卷 2692-2706页

作者： Hsin-Yi Liang Tien-Yu Hsu Gwo-Jen Hwang Shao-Chen Chang Hui-Chun Chu a Graduate Institute of Applied Science and Technology National Taiwan University of Science and Technology Taiwan b Department of Operation Visitor Service Collection and Information Management National Museum of Natural Science Taichung Taiwan c Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taipei Taiwan d Department of Computer Science and Information Management Soochow University Taiwan

ABSTRACTIn the past decades, collaborative game-based learning has been used to facilitate students’ learning in authentic learning contexts. Although several previous studies have reported the potential of this approach for students’ learning performance and motivation, unequal participation could negatively influence the learning effectiveness of collaborative learning. To this end, this study developed a mandatory contribution-based collaborative gaming approach (MCCG) to enhance the competencies for conducting practical solutions related to environmental issues during a cross-field learning activity between a school and a museum. MCCG and a conventional collaborative gaming approach (CCG) were implemented to investigate the effects of individual contributions on collaborative learning. Both individual learning achievements and collaborative learning outcomes were assessed. The results showed that game-based collaboration supports can support competency-based education to enhance students’ competencies, such as problem-solving and critical thinking competencies. Those students who learned with the mandatory contribution approach had better collaborative learning outcomes.

关键词： Collaborative learning competency-based learning game-based learning contextual learning mobile learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Pattern Recognition with HOG Features for Detection of Islanding

Machine Learning Based Pattern Recognition with HOG Features...

引用

International Conference on Electrical Power and Energy Systems (ICEPES)

作者： Kumaresh Pal Subhadip Goswami Anshuman Bhuyan Santanu Koley Bidisha Bera Sarmistha Basu Department of Electrical Engineering National Institute of Technology Jamshedpur India Department of Electrical Engineering National Institute of Technology Arunachal Pradesh India Department of Electrical Engineering Gandhi Institute for Education & Technology Bhubaneswar India Department of Computer Science Engineering Haldia Institute of Technology Haldia India Department of Computer Science and Technology Global Institute of Science and Technology Haldia India Department of Physics Calcutta Institute of Engineering and Management Kolkata India

ISBN: (数字)9798350390728

ISBN: (纸本)9798350390735

Islanding is a significant difficulty that arises from the high integration of distributed generation sources. Islanding could potentially damage the clients and their equipment. According to the IEEE 1547 DG interconnection requirements, islanding must be detected within two seconds, and the DG must be shut down. This research introduces a new method for identifying islanding using image pattern recognition utilising a Machine Learning classification algorithm. The suggested technique utilises the Random Forest (RF) classification algorithm. Images are utilised to extract the histogram of oriented gradient (HOG) features in order to detect both non-islanding and islanding occurrences. The spectrogram images are formed from the time-series signal collected from the point of common coupling. The images are utilised to extract features from histogram of oriented gradient, which are subsequently used as feature vector inputs for training and testing the RF classifiers. The spectrogram image is derived using the rate of change of the voltage parameter. The efficacy of the RF classifier is evaluated using 5, 10, 20, and 25-fold cross-validations. The classification findings indicates that islanding detection utilising a Random Forest classifier and Histogram of Oriented Gradients (HOG) feature for image pattern recognition obtained outstanding performance with 98.75% accuracy and a detection time of 192 milliseconds.

关键词： Histograms Accuracy Voltage Feature extraction Vectors Pattern recognition Classification algorithms

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：