检索结果-内蒙古大学图书馆

2nd International Conference for Innovation in technology, INOCON 2023

作者： Utamajaya, Joy Nashar Supangat, Suhono Harso Gaol, Ford Lumban Ranti, Benny BINUS University BINUS Graduate Program School of Information System Jakarta Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatic Bandung Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program Computer Science Jakarta Indonesia University of Indonesia Computer Science Department Faculty of Computer Science Depok Indonesia

ISBN: (纸本)9798350320923

In general, public or private organizations or companies have used information-based technology as a support to improve business performance to be more effective and efficient in order to achieve a company's business goals. Given the large contribution of information technology in the application of hotel applications as a supporting information system, it is a vital system that must avoid risks that can hinder and cause harm to the hotel management business processes. Therefore, it is necessary to carry out risk management using the COBIT 5 framework to manage possible risks that may occur based on the APO12 (Manage Risk) domain. From the evaluation results of the data obtained through observation and interviews as well as the calculation of the results of the questionnaire based on 6 APO12 subdomains, the results of the risk management level capability assessment in hotel applications are still at level 3 or have reached the level of established process with the target to be achieved at level 4 resulting in a gap of 1 level. Based on the results obtained, it is necessary to propose recommendations that can be used by hotels in improving the application of information technology risk management so that in the future it can achieve the expected target level so that the APO12 level of capability can increase and become more optimal. © 2023 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

CONDITION ASSESSMENT OF 150 KV OUTDOOR COMPOSITE INSULATORS FOLLOWING A VEGETATION FIRE EVENT 23

CONDITION ASSESSMENT OF 150 KV OUTDOOR COMPOSITE INSULATORS ...

引用

23rd International Symposium on High Voltage engineering, ISH 2023

作者： Mavrikakis, Nikolaos C. Siderakis, Kiriakos Mouratis, Kiriakos Koudoumas, Emmanouel Section of Crete-Rhodes Transmission System Islands Network Operation Department Hellenic Electricity Distribution Network Operator S.A. Heraklion Greece High Voltage Laboratory Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece Center of Materials Technology and Photonics Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece

ISBN: (纸本)9781839539954

In electric power transmission and distribution systems, the use of overhead lines instead of underground cables is preferred by power utilities mainly due to the lower construction cost and the easier maintenance access. On the other hand the equipment used in overhead lines is stressed by several factors, such as weather conditions, lightning, vegetation fires, etc. In particular, vegetation fires under the overhead transmission lines could have catastrophic results for the installed equipment and can cause long-lasting electricity interruptions. In this study, condition assessment results are presented for eighteen 150 kV composite insulators exposed to a forest fire event, occurred in the August 2021, in the island of Rhodes, Greece. The evaluation of the fire effects on composite insulators was performed by employing several macroscopic and microscopic diagnostic techniques including visual inspection, hydrophobicity classification, Fourier Transform Infrared spectroscopy (FTIR) and optical microscopy analysis. © The Institution of engineering & technology 2023.

关键词： Construction equipment

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Hate Speech Detection and Recognition Utilising Advanced Machine Learning Algorithms and Techniques 3

A Comprehensive Analysis of Hate Speech Detection and Recogn...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Mannepalli, Praveen Kumar Sharma, Saurabh Rajput, Neha Kalamdhad, Sanjay Chandigarh University Department of Computer Science & Engineering Mohali India Chandigarh University Department of Computer Science and Engineering Mohali India Chandigarh University Department of Computer Science and Engineering Punjab India St. Vincent Pallotti College of Engineering and Technology Department of Computer Science & Business System Nagpur India

ISBN: (纸本)9798331542375

Social networking sites have come into demand as a way of sharing ideas and opinions with other people. But unfortunately, people tend to misuse social media to write nasty comments. Victims' lives might be negatively impacted by behaviours that are abusive and humiliating. Social networks give people a great tool to share information on ideas on multiple topics and opinions. However, these platforms are often abused to announce toxic and offensive comments, which eventually negatively affect victims and demographics. This study offers a thorough method for identifying hate speech (HS) on social media by utilising cutting-edge ML algorithms. A publicly available Twitter dataset containing 159,571 tweets classified into six categories, including toxic and identity hatred, was utilised. The methodology comprises data collection, conditioning, and categorisation that employs BiLSTM, which is particularly appropriate for the tasks demanding contextual sensitivity. These operations include symbol removing, stemming and stop-word eliminating, feature extraction using TF-IDF, and using the Bag-of-Words model. For classification of the data between hate and non-hate, the dataset is then split into training and testing datasets and the BiLSTM model used to provide classifications for the text. The evaluation of the BiLSTM model demonstrates superior performance, achieving an accuracy86%, a precision90%, a recall86%, and an F1-score88% • A comparison between the model and other models such as SVM and CNN reveals the strength of the BiLSTM in contextual classification tasks. The results demonstrate that BiLSTM can tackle problems with hate speech detection, providing a strong answer to the problem of harmful content on social media and helping to make the internet a better place for everyone. © 2025 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Identification of a Distant Speaker and Its Robustness*

引用

Chinese Journal of Electronics 2023年第2期20卷 278-282页

作者： Ye Jiang Zhenmin Tang Longbiao Wang School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Department of System Engineering Shizuoka University Japan

Robust speaker identification is presented for speech recorded by distant microphones. Three compensation approaches are investigated to improve the robustness of speaker identification in such environments. The first approach applies spectral subtraction before feature extraction to reduce the late-reverberation effect. The second approach makes use of feature warping as feature compensation in distant speaker identification under mismatched training-testing conditions. The third approach employs a novel method of initializing Gaussian mixture model parameters: combined division and k-means clustering. The experiment results show that, relative to the baseline system based on CMN, the channel-average recognition rates for the compensated system were 11.4%, 15.4%, 17.0%, and 17.8% higher for the TIMIT database and 6.8%, 6.4%, 9.3%, and 14.0% higher for the JNAS database for four different environments. In addition, the results show that the combination of the three approaches has better performance than the use of a single compensation method.

关键词： Databases Feature extraction Robustness Gaussian mixture model Microphones

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Information Retrieval with a Language Model

Enhancing Medical Information Retrieval with a Language Mode...

引用

Cognitive Robotics and Intelligent systems (ICC - ROBINS), International Conference on

作者： Yuvaraj Natarajan Sri Preethaa K.R Sasikumar Pandian Shruti Umapathi Geetha Sujadharshini Senthilkumar Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore Department of Robot and Smart System Engineering Kyungpook National University Daegu Republic of Korea

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

In this ever-evolving healthcare landscape, with the integration of cutting-edge technology, this study has exemplified a medical chatbot by harnessing the advanced Llama2 model. This chatbot places significant emphasis on instance training by changing and adding the meta, which enables it to continuously adapt and stay updated with the latest medical developments. Its adaptability also encompasses capabilities such as question-answering and mining knowledge from an extensive meta dataset. By leveraging its extensive ability to learn medical terminology, the chatbot provides precise and real-time responses to medical inquiries by establishing itself as a reliable information source. Access to a specially collected meta dataset further enhances its ability to deliver comprehensive medical insights while self-supervised learning techniques enhance the model efficacy. Consequently, this chatbot reshapes the way individuals access precise medical information by enabling a new era of advanced digital healthcare assistants in the digital age.

关键词： Training Adaptation models Terminology Self-supervised learning Chatbots Information age Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Design of 12-Lead Electrocardiogram Smart Clothing Based on Capacitive Sensing Technique

引用

IEEE Sensors Journal 2024年第10期24卷 16826-16835页

作者： Chang, Wei-Ting Lin, Bor-Shing Tsai, Wei-Lun Chen, Heng-Yin Liu, Chengyu Lin, Bor-Shyh Chi Mei Medical Center The Department of Cardiology Tainan71004 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan Institute of Imaging and Biomedical Photonics National Yang Ming Chiao Tung University Tainan71150 Taiwan Industrial Technology Research Institute System Design and Integration Department Hsinchu31057 Taiwan Southeast University School of Instrument Science and Engineering Nanjing210096 China

A 12-lead electrocardiogram (ECG) is one of the most commonly used tools for evaluating cardiovascular diseases (CVDs). In clinical, the conventional Ag/AgCl electrodes with conductive gel are usually used to monitor ECG, but they may encounter gel drying and skin allergic reaction problems for long-term ECG monitoring. In order to improve the above issue, several dry electrodes, made by conductive materials, was proposed in the design of wearable devices, but they still encounter the problems of electrode shifting and stretching, and the risk of skin irritation. Capacitive electrode can access biopotential without contacting skin directly and can completely avoid skin irritation. However, for capacitive electrode, how to maintain a good electrode-skin contacting condition is still a challenge due to electrode fixation problem, in particular in multichannel ECG measurement. In this study, a 12-lead ECG smart clothing based on capacitive sensing technology was proposed to monitor ECG in daily life. To improve the electrode-skin contacting condition, elastic conductive foams were used as the electrode plate to effectively fit the rough body contours. Moreover, a specific wearable belt mechanism was also designed to improve the convenience of use, and it could also provide good friction and proper pressure to reduce the electrode slippage and maintain a good electrode-skin contact condition. The experimental results showed that the proposed smart clothing could stably access the good ECG signal quality under different motion levels, and the specific ECG features corresponding to different CVDs could also be reflected on the measured ECG signal in clinical experiment. © 2001-2012 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Analysis of cloud services using OWASP security design

Analysis of cloud services using OWASP security design

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Poongavanam, Elumalaivasan Munirathinam, T. Murugesan, Sankar Kayalvizhi, V. Department of Data Science and Business System SRM Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350305708

Cloud computing is extremely popular model among enterprises. It provides more availability of cloud resources when needed with high scalability and extremely cost-effective model. Security is one of the least understood concepts to provide and access for OWASP applications in cloud computing. Many enterprises especially banking clients are risk-averse and have less cloud adoption rate. In this study, security research in the area of cloud security is reviewed and AWS (Amazon Web Service) is the top provider of cloud computing. Since, we have also demonstrated how it works in the security exploration. This paper's major goal is to make cloud computing security is a key activity and prevent unauthorized access to the apps used in the real world. © 2023 IEEE.

关键词： cloud computing AWS On demand services security

来源：评论

学校读者我要写书评

暂无评论

Monkeypox Lesion Classification: A Transfer Learning Approach for Early Diagnosis and Intervention 7

Monkeypox Lesion Classification: A Transfer Learning Approac...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Al Noman, Abdullah Fardin, Hasib Chhabra, Gunjan Sultana, Shayma Haque, Rezaul Ahmed, Md. Redwan Hasibunnahar, Swarna Kaushik, Keshav Westcliff University Department of Information Technology United States Westcliff University Department of Engineering Management United States Graphic Era Hill University Department of Cse Uttarakhand Dehradun India Graphic Era Deemed to be University Uttarakhand Dehradun India International American University Department of Management Information System United States East West University Department of Computer Science and Engineering Bangladesh Huzhou University Department of Life Sciences China Amity University Amity School of Engineering and Technology Punjab Mohali India

ISBN: (纸本)9798350350067

Monkeypox is a viral disease found in Central and West Africa, and it presents notable public health challenges due to its clinical similarity to smallpox. Recent outbreaks in over 40 countries have underscored the urgent need for quick and accurate diagnosis, especially in settings with limited resources where traditional diagnostic methods may be inadequate. This study explores the application of deep learning techniques to classify four specific types of monkeypox skin lesions. Transfer learning was employed to evaluate the performance of different models using a dataset of 770 skin lesion images. Various methods, including data augmentation and image preprocessing, were utilized to improve the effectiveness of the models. The results indicate that the custom SqueezeNet model was the most successful, achieving an accuracy of 98.85% and an F1 score of 98.89%. These results surpass previous research benchmarks across four key evaluation measures. Additionally, the model was integrated into a web-based diagnostic tool capable of reliably detecting different forms of monkeypox. This study represents a significant advancement in utilizing artificial intelligence for disease detection, offering a practical approach for early and accurate monkeypox diagnosis. The proposed system has thex potential for seamless integration into clinical practice, aiding healthcare professionals in timely interventions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Deep Learning Framework for Breast Cancer Prediction

A Novel Ensemble Deep Learning Framework for Breast Cancer P...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2023

作者： Shaker Reddy, Pundru Chandra Nithyapriya, S. Sharma, Nipun Maheswari, S. Jayaram, B. Katale, Tejaswini SR University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Anna University Artificial Intelligence and Data Science Bannari Amman Institute of Technology Tamil Nadu Chennai India Presidency University Bangalore Electronics and Communication Engineering Karnataka India Sathyabama Institute of Science and Technology Department of Mathematics Tamil Nadu Chennai India Computer Science and Business System RMK Engineering College Tamil Nadu Kavaraipettai India Vishwakarma Institute of Technology Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798350319200

Because of its high incidence and high mortality rate, breast cancer requires reliable means of early detection and diagnosis to improve survival rates for its patients. With advantages including increased accuracy and efficiency, deep learning (DL) and machine learning (ML) methods are quickly becoming indispensable in the fight against breast cancer. However, there is a need for additional study because existing approaches have scalability and performance constraints. Utilizing a pre-trained ResNet50V2 and ensemble-based ML approaches, we offer a hybrid approach to reliable breast cancer diagnosis in this study. Learning and extracting latent trends from complex breast-cancer(BC) images is made possible by DL's incorporation, with ML strategies contributing interpretability and generalizability. We performed wide experiments utilizing a openly accessible Invasive-Ductal-Carcinoma(IDC) dataset based on breast histopathology images of varying sample sizes. The resilience and great performance of our hybrid model are supported by the results of our extensive experiments. When compared to state-of-the-art models, our 95% accuracy rate, 94.5 precision, 94.2 recall, and 94.6 F1 score are all improvements. We also found that the best ML model to use with the ResNet50V2 architecture is the Light Boosting Classifier (LGB). This study's findings provide substantial contributions to the field of breast cancer diagnosis thanks to its novel approach, in-depth performance analysis, and trustworthy evaluation. In addition, it may help doctors make better decisions, provide better care, and boost results for people with breast cancer. © 2023 IEEE.

关键词： breast histopathology-image Breast-cancer DL ML transfer-learning

来源：评论

学校读者我要写书评

暂无评论

Low Parameters UNet for Energy-Efficient Cloud Detection

Low Parameters UNet for Energy-Efficient Cloud Detection

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Chen, Chun-Fu Lee, Pei-Jun Bui, Trong-An The Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan The Institute of Aerospace and System Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9798331521165

Applying cloud detection algorithms to edge devices using semantic segmentation poses significant challenges due to the high computational complexity and power consumption. This paper proposes a parameter reduction method that combines linear channel pruning and adaptive pruning techniques to effectively compress the large UNet model. Linear channel pruning efficiently reduces model redundancy, while adaptive pruning further enhances the model's sparsity. This approach not only maintains performance comparable to the original UNet in terms of Intersection over Union (IoU) and other key metrics, but also significantly reduces the model's parameter count, thereby lowering DRAM access power consumption. Experimental results show that the first and second stages of parameter reduction decreased the model's parameter count by 98.5% and 70.3%, respectively, while reducing memory access by 67.5% and 65%, respectively. © 2025 IEEE.

关键词： Semantic Segmentation

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：