检索结果-内蒙古大学图书馆

An Optimized Chinese Filtering Model Using Value Scale Extended Text Vector

computer Systems Science & engineering 2023年第11期47卷 1881-1899页

作者： Siyu Lu Ligao Cai Zhixin Liu Shan Liu Bo Yang Lirong Yin Mingzhe Liu Wenfeng Zheng School of Automation University of Electronic Science and Technology of ChinaChengdu610054China School of Life Science Shaoxing UniversityShaoxing312000China Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA College of Computer Science and Cyber Security Chengdu University of TechnologyChengdu610059China

With the development of Internet technology,the explosive growth of Internet information presentation has led to difficulty in filtering effective *** a model with high accuracy for text classification has become a critical problem to be solved by text filtering,especially for Chinese *** paper selected the manually calibrated Douban movie website comment data for ***,a text filtering model based on the BP neural network has been built;Second,based on the Term Frequency-Inverse Document Frequency(TF-IDF)vector space model and the doc2vec method,the text word frequency vector and the text semantic vector were obtained respectively,and the text word frequency vector was linearly reduced by the Principal Component Analysis(PCA)***,the text word frequency vector after dimensionality reduction and the text semantic vector were combined,add the text value degree,and the text synthesis vector was *** show that the model combined with text word frequency vector degree after dimensionality reduction,text semantic vector,and text value has reached the highest accuracy of 84.67%.

关键词： Chinese text filtering text vector word frequency vectors text semantic vectors value degree BP neural network TF-IDF doc2vec PCA

来源：评论

学校读者我要写书评

暂无评论

A Domain-Adversarial Neural Network for Transferable Lithium-Ion Battery State-of-Health Estimation

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 7732-7742页

作者： Meng, Jinhao Hu, Dingcai Lin, Mingqiang Peng, Jichang Wu, Ji Stroe, Daniel-Ioan Xi’an Jiaotong University School of Electrical Engineering Shaanxi Xi’an710049 China Quanzhou Institute of Equipment Manufacturing Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Jinjiang362200 China Fujian Normal University Fuzhou350007 China University of Chinese Academy of Sciences College of Computer and Cyber Security Fujian College Fuzhou350002 China Smart Grid Research Institute Nanjing Institute of Technology Nanjing211167 China Hefei University of Technology School of Automotive and Transportation Engineering Anhui Hefei230009 China Aalborg University AAU Energy Aalborg9220 Denmark

As a key indicator of the lithium-ion (Li-ion) battery performance, state-of-health (SOH) estimation still faces challenges in model generalization between datasets. Electrochemical impedance spectroscopy (EIS) provides a nondestructive solution to capture the electrochemical dynamic processes inside the Li-ion battery, while it is highly sensitive to measurement conditions and battery status. To alleviate these issues, this work proposes a transferable data-driven framework for Li-ion battery SOH estimation with the domain-adversarial neural network (DANN) and EIS. The health feature is obtained from battery EIS through the latent representation of an autoencoder (AE) where valuable information can be automatically extracted from the original EIS measurement. The DANN can connect the feature distributions for the samples in both the source and target domains. Two datasets from both cycling and calendar aging tests are used to verify the superior performance of the proposed method in SOH estimation for different cases where the average root mean square error is only 1.28%. This method demonstrates significant potential in practical applications such as electric vehicles (EVs) and battery energy storage systems (BESSs), where accurate and reliable SOH estimation is critical for enhancing safety and prolonging battery lifespan. © 2015 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Image analysis and fine-tuned ResNet50 model for effective malware detection

引用

Procedia computer Science 2025年 260卷 1098-1106页

作者： Sanjeev Kumar Yudhishthira Sapru Jitendra Kumar Sugandha Sapru Cyber Security Technology Division Centre for Development of Advanced Computing Mohali India Indian Computer Emergency Response Team CERT-In Delhi India Department of Mathematics Bioinformatics and Computer Applications MANIT Bhopal India Department of Mathematics PGGC Panjab University Chandigarh India

With the rapid growth of connected assets to the Internet, malware attacks have increased exponentially, often causing substantial damage to these connected assets. Early detection of evolving malware attacks can avoid such damage to the Internet ecosystem. However, it requires an efficient and robust approach with little reliance on existing signature-based approaches, as these are no longer effective in detecting obfuscated and complex malware attacks. This study presents a new malware detection and classification approach using image analysis and a fine-tuned ResNet50 convolution neural network (CNN) model through transfer learning. The raw binary executable programs are transformed into grayscale images and resized to 224 × 224 × 1 image size to be fed to the deep CNN model for feature extraction. The pre-trained ResNet50 model is customized to extract the textural features by retaining the learned weight and bias from the source ImageNet data and making the last fully connected layer non-trainable. After that, a fully connected dense layer is added for dimension reduction of the feature map into N × 128, with N as the number of malware files. Two public datasets are used in experiments - MalImg and Microsoft BIG. This study uses comprehensive performance metrics to evaluate the model and obtained an accuracy of 98.50% for the MalImg dataset and 94.85% for the Microsoft BIG data set. The experiment results show that the proposed methodology can handle malware obfuscated by standard polymorphic techniques and is better than similar methods in the literature.

关键词： cybersecurity Convolution neural network ResNet Malware classification Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Slotted Aloha for Optical Wireless Communications in Internet of Underwater Things 32

Slotted Aloha for Optical Wireless Communications in Interne...

引用

32nd Wireless and Optical Communications Conference, WOCC 2023

作者： Petkovic, Milica Tegos, Sotiris A. Diamantoulakis, Panagiotis D. Vukobratovic, Dejan Panayirci, Erdal Stefanovic, Cedomir Karagiannidis, George K. Faculty of Technical Sciences Novi Sad Serbia Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Greece Kadir Has University Istanbul Turkey Aalborg University Aalborg Denmark Cyber Security Systems and Applied Ai Research Center Lebanon

ISBN: (纸本)9798350337150

In this work, we design and analyse a Slotted ALOHA (SA) solution for Optical Wireless Communication (OWC)-based Internet of Underwater Things (IoUT). In the proposed system, user devices exchange data with an access point (AP) which exploits the capture effect. The space spanned by the IoUT nodes is three-dimensional, i.e., users are located in half-sphere centered at the AP placed at the bottom of a floating object at the water surface level. The analytical expressions for the system throughput and reliability expressed in terms of the outage probability are derived. Based on the simulated signal-to-noise-and-interference-ratio statistics and derived analytical expressions, we present numerical results that investigate the trade-off between the system performance and the IoUT system parameters, such as the number of users, activation probability and type of water medium. The presented conclusions provide valuable insights into the design of an SA-based solution for IoUT communications. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning to Detect and Predict Diabetes in Polycystic Ovary Syndrome Patients: A Review

Leveraging Machine Learning to Detect and Predict Diabetes i...

引用

International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD)

作者： Julia Ndjene Attlee M. Gamundani Maria N. Kanyama Department of Informatics Namibia University of Science and Technology Windhoek Namibia Department of Cyber Security Namibia University of Science and Technology Windhoek Namibia Department of Computer Science Namibia University of Science and Technology Windhoek Namibia

ISBN: (数字)9798350387902

ISBN: (纸本)9798350387919

Polycystic ovary syndrome (PCOS) is a prevailing hormonal disorder affecting women in their childbearing years, often associated with hormonal imbalances and metabolic disturbances. PCOS is closely linked to various health complications, including Type 2 Diabetes Mellitus (T2DM). Early detection and prediction of T2DM among PCDS patients are essential steps in providing comprehensive care to mitigate the potential adverse effects that PCOS has on its sufferers, such as infertility. Extensive research has been conducted to leverage advanced tools, particularly Machine Learning (ML) algorithms, for detecting and predicting PCOS and diabetes. This review explores the efforts to address the intersection of PCOS and diabetes, specifically focusing on ML-based approaches. Through a thorough examination of recent literature, this paper reveals all ML algorithms, methodologies and datasets that apply to detecting and predicting T2DM among PCOS patients. This paper further aims to discover and discuss possible challenges and limitations in leveraging ML in addressing the intersection of PCOS and T2DM and the future directions of ML as far as personalised healthcare interventions targeting PCOS patients at risk of T2DM are concerned.

关键词： Pediatrics Machine learning algorithms Reviews Focusing Medical services Prediction algorithms Robustness

来源：评论

学校读者我要写书评

暂无评论

Mapping Quantum Circuits to 2-Dimensional Quantum Architectures

Mapping Quantum Circuits to 2-Dimensional Quantum Architectu...

引用

2022 Informatik in den Naturwissenschaften, INFORMATIK 2022 - 2022 computer Science in the Natural Sciences, INFORMATIK 2022

作者： Datta, Kamalika Kole, Abhoy Sengupta, Indranil Drechsler, Rolf Cyber Physical System Bremen Germany JIS University Department of Computer Science and Engineering Kolkata India Indian Institute of Technology Kharagpur Department of Computer Science and Engineering India University of Bremen Group of Computer Architecture Bremen Germany

ISBN: (纸本)9783885797203

We have been witnessing a rapid growth in quantum computing research over the years, with the emergence of demonstrable quantum computers of moderate size. The major issues that are faced to run a quantum algorithm reliably on these systems are: (i) lower qubit coherence period, (ii) noisy primitive gate operations, (iii) limited number of available physical qubits, and (iv) support of restricted set of 2-qubit operations. Overcoming these issues mandates physical resources that exceeds the capabilities of these noisy intermediate scale quantum (NISQ) systems. On the other hand, computation using bare qubits get further disturbed due to the inclusion of additional gates to mitigate the nearest neighbor constraints. In the present work, the 2-dimensional square, heavy-hex and fully hexagonal qubit coupling lattices are considered for mapping quantum circuits. The benefits are assessed in terms of minimal additional gates needed to satisfy the nearest neighbor (NN) constraint and the compilation complexity of mapping circuits on these architectures. From the experiments by mapping benchmark circuits on 16-qubit square and 65-qubit heavy-hex architectures from IBM as well as on a 64-qubit fully hexagonal architecture, it is observed that none of the square or heavy-hex lattice architecture provides uniform compilation advantage compared to the fully hexagonal architecture. It is expected that beyond the NISQ era, strongly connected lattices like hexagonal will become practically feasible. © 2022 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

A Novel Human Face Expression Recognition Based on Image Processing Assisted Convoluted Deep Learning Methodology

A Novel Human Face Expression Recognition Based on Image Pro...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Tamilselvi, M. Venkata Siva Prasad, Ch. Kumari, M. Varuna Lavanya, R. Sai Nandurkar, Y. Al-Mousa, Mohammad Rasmi Dept of Ece Chennai India Jeppiaar Engineering College Department of Ece Rajiv Gandhi salai Chennai119 India Qis College of Engineering and Technology Department of S&h Pondur Road Vengamukkapalem Ongole Prakasam Andhra Pradesh Prakasam District523272 India Qis College of Engineering and Technology Department of Mca Pondur Road Vengamukkapalem Ongole Prakasam Andhra Pradesh Prakasam District523272 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India College of Information Technology Zarqa University Department of Cyber Security zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Facial expression recognition has become a critical component in applications involving human-computer interaction, security systems, and behavioral analysis. This paper presents a novel approach to human face expression recognition using a convoluted deep learning methodology supported by image processing techniques. The system is designed to accurately classify seven fundamental emotions - Anger, Disgust, Fear, Happy, Sadness, Surprise, and Neutral - using the FER2013 dataset. The methodology includes preprocessing steps such as noise reduction, grayscale conversion, and face registration. Feature extraction is performed using Gabor filters and Local Binary Patterns (LBP), while Convolutional Neural Networks (CNNs) are employed to learn deep hierarchical features. The system was optimized through hyperparameter tuning, achieving an overall accuracy of 96.29% on the test set. Precision, recall, and F1-scores for each emotion also exceeded 95%, with 'Happy' and 'Surprise' emotions showing the best performance. The results indicate that the model is effective for real-time applications requiring reliable emotion detection. The paper concludes with discussions on model performance, challenges in classifying similar emotions, and recommendations for future improvements. © 2024 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Electrical Transmission Lines Robot Inspector: Design Challenges

Electrical Transmission Lines Robot Inspector: Design Challe...

引用

2022 International Conference on Industrial engineering, Applications and Manufacturing, ICIEAM 2022

作者： Boufares, Fatma Doudech, Imen Bahrami, Mohammad Reza High Institute of Applied Sciences and Technology of Sousse Department of Mechanical Engineering Sousse Tunisia Institute of Information Security and Cyber-Physical Systems Innopolis University Innopolis Russia

ISBN: (纸本)9781665483698

High voltage electrical transmission lines (ETL) require maintenance and examination which are both time-consuming and dangerous, as it has been carried out by workers using traditional means. That is why the invention and evolution of the field of robotics in inspection transmission lines have emerged as a novel, more convenient, also safer process of executing difficult works. This article foreshadows the growth and development of the power line transmission robot over the years from the prototype design of a robot capable to bypass obstacles on ETL until a recent year, where the developed robot can multitask, such as cleaning, avoiding obstacles, crossing the junctions of the tower, move through the cable. Not only that the robot can climb itself to inspect the electrical transmission line. More precisely, the evolution whether it is at the level of the robot's heart that is to say of the programming, and the handling, or at the level of the design which has been brought from one year to the next so that it conforms better to our living conditions. In this article, we categorize the challenges that the ETL robot inspector may face during its operation. A survey was conducted to list the published papers related to electrical transmission robot inspectors and challenges for designing, challenging like climate, communication systems, safety, etc. © 2022 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

A Secure RPL Rank Computation and Distribution Mechanism for Preventing Sinkhole Attack in IoT-based Systems

A Secure RPL Rank Computation and Distribution Mechanism for...

引用

2023 IEEE INFOCOM Conference on computer Communications Workshops, INFOCOM WKSHPS 2023

作者： Mishra, Alekha Kumar Puthal, Deepak Tripathy, Asis Kumar National Institute of Technology Dept. of Computer Science and Engineering Jamshedpur India Khalifa University Center for Cyber-Physical Systems and Department of EECS Abu Dhabi United Arab Emirates School of IT and Engineering VIT Vellore India

ISBN: (纸本)9781665494274

The sinkhole attack detection mechanisms that have been reported till date are distributed in nature. Defending a sinkhole attack requires protecting the act of forging the rank computation task. This paper propose a secure centralized mechanism to ensure protection of rank computation process against sinkhole nodes in the IoT-Based Systems. The expectation maximization algorithm is used to optimally cluster the nodes into a group bearing the same rank. The distribution of ranks to the nodes is protected by the signature of the sink. The experimental results show that the optimal rank computation is secure against sinkhole nodes, however requires additional network communication between nodes and the sink node. © 2023 IEEE.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

A Deep CNN-GRU Framework for Personalized News Recommendation

A Deep CNN-GRU Framework for Personalized News Recommendatio...

引用

Data Science and Business Systems (ICDSBS), International Conference on

作者： C.R. Dhivyaa K. Nithya A. Devipriya A. Sivaranjani Department of Database Systems School of Computer Science and Engineering Vellore Institute of Technology Vellore Computer Science and Engineering SRM Institute of Science and Technology Tiruchirappalli Department of Information Security School of Computer Science and Engineering Vellore Institute of Technology Vellore Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Vellore

ISBN: (数字)9798331585600

ISBN: (纸本)9798331585617

News Recommendation Systems designed significantly for readers interest and there are number social networking sites like Twitter, Facebook, LinkedIn are popular nowadays. Users of these sites look popular news updates in that site itself instead of going to individual news websites. Our research work, gives the predominant solution for this problem. In this proposed work, a novel deep convolutional neural network based Word2Vec embedding technique is used along with GRU for recommending the news which is interested to the readers specially in twitter. In twitter, journalists of Republic, Times Now and BBC News India are used to post the news updates in the form of tweets and these tweets are collected then CNN along with Word2Vector embedding is preferred for feature extraction. All the aggregated features are given as input to the Gated Recurrent Unit which finds the highly preferred news and classifies the news for each user using softmax function. The proposed model is compared with various feature extraction techniques and computational approaches. Among these state-of-the-art techniques our proposed CNN with word2vec embedding technique provides the promising results with the F -Measure of 93.60%.

关键词： Social networking (online) Computational modeling Blogs Semantics Data science Feature extraction Data models Convolutional neural networks History Recommender systems

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：