检索结果-内蒙古大学图书馆

International Conference on Contemporary Computing and Informatics (IC3I)

作者： V.S Anusuya Devi N. Sreevani Amandeep Nagpal Susmita Kalyani K.Pushpa Rani Ali Albawi Departmento of Applied Sciences New Horizon College of Engineering Bangalore India Department of CSE(Cyber Security) Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Lloyd Law College Plot No. 11 Knowledge Park II Greater Noida Uttar Pradesh Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

HPC technology’s rapid rise has simplified gene expression research. A study proposes AI-GEM, which stands for “AI-Driven Gene Expression on High-Performance Computing Platforms.” We devised an approach to circumvent the issues associated with gene expression studies. We provide a full gene expression research strategy to improve accuracy, scalability, and comprehension. AI-GEM examined six methods: GEA-HPC, Expression AI, Genomic Solver, HPC-GENE, Bio AI-Express, and Gene Xcel. All approaches were tested. The findings suggest that AI-GEM outperforms other approaches. Our new approach averages 10.8 seconds, whereas the previous one took 45.7 seconds. The previous way is faster. AI-GEM is 95.2% accurate. This approach is far more accurate than the standard $\mathbf{7 1. 2 \%}$. This differs greatly from proper procedures. AI-GEM has far more potential than prior approaches, which could only handle 20,850 genes. AI-GEM outperforms other gene expression approaches in interpretability ($\mathbf{9. 2} \mathbf{v s}$. 4.4). One other reason: AI-GEM works better than conventional approaches. The AI-GEM system achieves $\mathbf{9 3 \%}$ client privacy, whereas traditional approaches obtain 58%. AI-GEM uses computer resources well, scoring $\mathbf{8 5 \%}$ vs. $\mathbf{6 6 \%}$ for other approaches. The final preprocessing time for AI-GEM is under 3.2 seconds. The previous best was 13.4 seconds, a significant improvement. AI-GEM is a novel gene expression data analysis tool for powerful computers. AI-GEM is a novel gene expression data analysis tool that is faster, more accurate, more scalable, simpler to comprehend, better at preserving privacy, more efficient in using resources, and reduces difficulties in pre-processing chores. This technology might aid biology and genetics in many ways.

关键词： Privacy Accuracy Data analysis Scalability Genomics Transforms Gene expression Reliability Bioinformatics Standards

来源：评论

学校读者我要写书评

暂无评论

Opinion mining in e-commerce: Evaluating machine learning approaches for sentiment analysis

Results in Control and Optimization

引用

Results in Control and Optimization 2025年 19卷

作者： Lakshmi, L. Ali, Ali B.M. Devi, K Dhana Sree Rafiq, Muhammad Shernazarov, Iskandar Othman, Nashwan Adnan Khan, M. Ijaz Department of DS & AI Faculty of Science and Technology ICFAI Foundation for Higher Education (IFHE) Hyderabad -501203 India Air Conditioning Engineering Department College of Engineering University of Warith Al-Anbiyaa Karbala Iraq Department of CSE GSOT GITAM University Hyderabad India College of Business Administration Prince Mohammad Bin Fahd University Saudi Arabia Department of Chemistry and Its Teaching Methods Tashkent State Pedagogical University Tashkent Uzbekistan Department of Computer Engineering College of Engineering Knowledge University Erbil 44001 Iraq Department of Computer Engineering Al-Kitab University Altun Kupri Iraq Department of Mechanical Engineering College of Engineering Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Department of Mechanical Engineering Lebanese American University Beirut Lebanon

In recent years, opinion mining has played a major role in analyzing text data from various sources such as Amazon, Capterra, Facebook, Google, GetApp, and Twitter. It enables companies to actively refine their business strategies. Sentiment analysis involves interpreting and classifying customer emotions (positive, neutral, and negative) expressed in reviews using sentiment analysis techniques such as BING and AFINN. This paper presents four approaches for customer review analysis and classification: the grade-based approach, content-based approach, content-based NRC-Emotion Lexicon approach, and collaborative approach. We employ three machine learning algorithms—stacking, random forest, and LogitBoost—to evaluate the performance of these approaches. A real-time dataset from Amazon product reviews is used for training and testing the model. Empirical results reveal that the collaborative approach outperforms the grade-based, content-based, and content-based NRC-Emotion Lexicon approaches across all three machine learning algorithms. Additionally, all approaches demonstrate outstanding performance when using the boosting algorithm for customer review classification. © 2025 The Author(s)

关键词： Machine learning NRC-lexicon Product reviews Sentiment analysis Text classification

来源：评论

学校读者我要写书评

暂无评论

Thermal Images Based Mobile Application for Identifying Faults in Photovoltaics Modules

Thermal Images Based Mobile Application for Identifying Faul...

引用

International Symposium on Fundamentals of Electrical engineering (ISFEE)

作者： Alexandru-Ionel Constantin Ramona-Nicoleta Banaseanu Paula Anghelita Gabriela Iosif Dorian Marin Department of Renewable Resources and Energy Efficiency National Institute for Research & Development in Electrical Engineering ICPE-CA Faculty of Automatic Control and Computer Science National University of Science and Technology POLITEHNICA Bucharest Faculty of Electronics Telecommunications and Information Technology National University of Science and Technology POLITEHNICA Bucharest Office of Management for Knowledge and Information National Institute for Research & Development in Electrical Engineering ICPE-CA

ISBN: (数字)9798350308563

ISBN: (纸本)9798350308570

The paper describes few faults that can be present in Photovoltaic modules and presents results related to training and the testing of a mobile application designed for identifying faults in photovoltaic modules based on thermal images. The mobile application was trained and then tested with different individual and multiple faults. The mobile application can identify with high accuracy both the individual and multiple faults if the thermal images are preprocessed before to be uploaded for analysis.

关键词： Fault diagnosis Training Temperature distribution Temperature dependence Accuracy Thermal engineering Mobile applications

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

arXiv

引用

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study

Evaluating the Performance to Detecting Topic Shift of Large...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Pingfang Tian Deting Liu Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Institute of Scientific and Technical Information of China Beijing China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor.

关键词： Technological innovation Large language models Oral communication Signal processing Chatbots Context modeling

来源：评论

学校读者我要写书评

暂无评论

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

arXiv

引用

arXiv 2023年

作者： Li, Yingji Du, Mengnan Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs’ encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs’ parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Architecture of Bluetooth Security for Pairing Key and Better Authentication

Architecture of Bluetooth Security for Pairing Key and Bette...

引用

International Conference on Information Systems and computer Networks (ISCON)

作者： Asif Ikbal Mondal Bijoy Kumar Mandal Dumkal Institute of Engineering & Technology Murshidabad India NSHM Knowledge Campus Department of Computer Science and EngineeringDurgapurIndia713212

ISBN: (纸本)9781665447874

In this paper, we have deal with the authentication and identification of the device for higher security using key pairing and low computation. Bluetooth when start communication with other device it needs pairing, and then a number of other processes, Profile selection which defines the types of communication. The connection can be compromised and without pairing codes connection can be established. Once the connection is established passing command to the victim's device makes the device to work in favor of the attacker without being noticed by the owner of the device. One such tool is bluesnarfer which is used to pair two devices without being acknowledged by the owner or the victim. This paper is proposed for finding a solution to the same using asymmetric key cryptography and encrypted protocol values to gain access of the different function of the Bluetooth device. The solution is deployed in a number of phases. Public and private key based pairing is used which make the authentication more effective. This is the first phase. In the next second phase there will be we verification protocol in which referential connection is required for making a new connection. In the third phase information regarding profile choice is passed through a tunnel profile, which passed on to the actual profile required. This system contains a threshold function which defines that if at any stage a breach of the system is identified then the system will promote the attacker with improper information to miss lead the attacker so that either the attacker is kept stuck in a miss leading loop or the connection is closed.

关键词： Wireless communication Industries Bluetooth Protocols Authentication computer architecture computer networks

来源：评论

学校读者我要写书评

暂无评论

Silicone Oil-Water Interaction and Emulsification Visual Simulation for Intraocular Silicone Oil Tamponade

Silicone Oil-Water Interaction and Emulsification Visual Sim...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Song, Chongming Xu, Yanrui Wang, Xiaokun Wang, Jiamin Huang, Houbin Zhu, Zhihong Ban, Xiaojuan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing China Chinese PLA General Hospital Department of Ophthalmology Beijing China Hainan Hospital of PLA General Hospital Department of Ophthalmology Hainan China Beijing Key Laboratory of Knowledge Engineering for Materials Science University of Science and Technology Beijing Beijing China

ISBN: (纸本)9781665401265

Vitrectomy combined with silicone oil tamponade is an effective treatment for rhegmatogenous retinal detachment (RRD). The high viscosity and surface tension of the silicone oil make it suitable for treating large retinal tears by pressing against the retina. However, silicone oil becomes emulsified over time as it remains in the eye, which can cause serious complications. Clear visual acquisitions of silicone oil-water interaction and silicone oil emulsification progress are difficult during and after the surgery. To help doctors and patients perceive the two-phase interaction and emulsification progress intuitively, we propose a physically based simulation method for intraocular silicone oil visualization. For the visualization of immiscible silicone oil-water interaction, we introduce a volume-incompressible Smoothed Particle Hydrodynamics (SPH) approach to improve simulation precision of multiphase flow coupling. A diffusion model based on volume fraction is proposed to visualize emulsification progress. Additionally, we combine our method with cohesion and surface-minimization driven surface tension model to describe the high surface tension of silicone oil. Experiments show that our scheme can obtain a precise pressure gradient near phase boundary and perform noticeable mixing effect that evolves over time. Our method has the advantage of higher accuracy than other visualization methods, and has the potential to help doctors make decisions and estimate surgical outcomes. © 2021 IEEE.

关键词： Hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Nondestructive Chicken Egg Fertility Detection Using CNN-Transfer Learning Algorithms

arXiv

引用

arXiv 2023年

作者： Saifullah, Shoffan Drezewski, Rafal Yudhana, Anton Pranolo, Andri Kaswijanti, Wilis Suryotomo, Andiko Putro Putra, Seno Aji Khaliduzzaman, Alin Prabuwono, Anton Satria Japkowicz, Nathalie Institute of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Center of Knowledge Engineering and Data Science Department of Electrical Engineering and Informatics Universitas Negeri Malang Malang65145 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia College of Computer and Information Hohai University Nanjing211100 China Department of Informatics Faculty of Industrial Technology Universitas Ahmad Dahlan Yogyakarta55166 Indonesia Faculty of Agricultural Engineering and Technology Sylhet Agricultural University Sylhet3100 Bangladesh Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science American University WashingtonDC20016 United States

This study explored the application of CNN-Transfer Learning for nondestructive chicken egg fertility detection for precise poultry hatchery practices. Four models, VGG16, ResNet50, InceptionNet, and MobileNet, were trained and evaluated on a dataset (200 single egg images) using augmented images (rotation, flip, scale, translation, and reflection). The training results demonstrated that all models achieved high accuracy, indicating their ability to learn and classify chicken eggs’ fertility. However, variations in accuracy and performance were observed when these models were evaluated on the testing datasets. The InceptionNet exhibited the best overall performance, accurately classifying fertile and non-fertile eggs. It demonstrated excellent performance in all parameters of the evaluation metrics for both training and testing datasets. When evaluated on the testing datasets, it achieved an accuracy of 0.98, a sensitivity of 1 for detecting fertile eggs, and a specificity of 0.96 for identifying non-fertile eggs. The higher performance is attributed to its unique architecture, efficiently capturing features at different scales, which leads to improved accuracy and robustness. Further optimization and fine-tuning of the models might be necessary to address the limitations in accurately detecting fertile and non-fertile eggs using other models. This study highlighted the potential of CNN-transfer learning for nondestructive fertility detection and emphasized the need for further research to enhance the models’ capabilities and to ensure accurate *** Codes CS-Class: 68T07, 68T45, 68U10, ICT-Class: 94A08 © 2023, CC BY-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution

Feature Aggregating Network with Inter-Frame Interaction for...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

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：