检索结果-内蒙古大学图书馆

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Liang, Yiyuan Jia, Hong Wang, Licai Huang, Yangchen Yang, Zhe Big Data Research and Development Center North China Institute of Computing Technology Beijing China Tsinghua University Department of Computer Science and Technology Beijing China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350385557

In document-level event extraction tasks, multiple event types often coexist within a document (the multi-event problem), and arguments may play different roles across different events (the argument intertwining problem). Existing methods often suffer from significantly reduced event extraction accuracy, mainly when focusing on scenarios with scarce annotated data and imbalanced event-type distributions. This paper emphasizes enhancing the correlation between event triggers and arguments to address these challenges. Therefore, we propose the Relation-Augmented UIE Model (RADIE), which introduces entity relationships into prompts using prompt-based learning and designs a relation-augmentation algorithm to improve the accuracy and completeness of event extraction. Experimental results demonstrate that this approach significantly outperforms baseline methods, mainly showcasing excellent performance on datasets with long-tail distributions. © 2024 IEEE.

关键词： document-level event extraction relation augment Universal Information Extraction

来源：评论

学校读者我要写书评

暂无评论

Survey on Collaborative and Content-based Recommendation Systems 5

Survey on Collaborative and Content-based Recommendation Sys...

引用

5th International Conference on Smart Systems and Inventive technology, ICSSIT 2023

作者： Thorat, Sandeep A. Ashwini, Gavade Seema, Mane Government College of Engineering and Research Computer Engineering Department Avasari Pune India Sinhgad Institute of Technology and Science Information Technology Department Narhe Pune India

ISBN: (纸本)9781665474672

In recent times information available on Internet is growing at the exponential rate. This makes searching correct information very difficult and it is challenging to perform the same within shortest amount of time. In such context there is need of recommender systems which can help in information filtering and promoting the information which is likely as per corresponding user's interest. Recommender systems have become popular in widespread applications and many researchers are exploring it to make them more efficient and effective. Though recommendations systems are being used for a quite long time, many research challenges and issues in the design of effective recommendation systems are yet to be addressed in an effective manner. This paper discusses research challenges, opportunities and possible applications of recommender systems. Recommendation systems are categorized into collaborative and content-based filtering. This paper briefs working of both types of recommender systems and also discusses research challenges within them. The collaborative filtering approach suffers from many drawbacks, including data sparsity, gray sheep, cold start problem, and scalability. The content-based filtering approach suffers from reciprocity, sparsity and limited content analysis issues. Also, future research directions in collaborative filtering and content-based recommendation systems discussed. Various application domains have listed out where recommendation systems can be improved, such as healthcare, agriculture, etc. The paper describes possible future extensions in all these applications. Overall this paper will act as a guide for those who are interested in doing research in the recommendation system. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Machine Learning Based Ensemble Model for Prediction of Possible Diseases and Recommending Medicines

A Comprehensive Machine Learning Based Ensemble Model for Pr...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Priyanka Jangde Kamal Kumar Sethi Narendra Pal Singh Praveen Bhanodia Durgesh Mishra Computer Science and Engineering Acropolis Institute of Technology and Research Indore India Symbiosis University of Applied Sciences Indore India

Many instances remain untreated globally due to the lack and unavailability of medical services. In this regard, efficient monitoring and analysis of medical records will be helpful in timely identification and prediction of diseases. To enable a quicker and more precise diagnosis, a platform that keeps track of a patient's medical history and makes illness predictions based on the patient's present symptoms is needed. Early disease prediction allows users to determine the severity of a condition and take appropriate action timely. Thus, anticipation of illness in its early stage becomes essential but it's difficult for doctors to anticipate outcomes precisely and accurately based only on symptoms. Availability of medical data and its analysis with the help of machine learning techniques can help the healthcare system for appropriate predictions and recommendations of diseases. In this paper, based on the patient's symptoms and medical records, a general illness prediction system is proposed. Using the input image for disease prediction, we applied an ensemble model exploiting the KNN, SVM, Naïve bayes and deep learning techniques to accurately predict diseases. The proposed model superseded the existing techniques with 98% accuracy on experimental study performed using benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Medical Imaging: High-Performance Hardware for Image Processing, Machine Learning 24

Optimizing Medical Imaging: High-Performance Hardware for Im...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Kalyan Chakravarthy, N.S. Balapanur, Mouli Chandra Pandian, Arun Nambi Pulikanti, Jyothi Prasad, D. Syed Masood, Jafar Ali Ibrahim High-Performance Computing Research Laboratory QIS College of Engineering and Technology Andhra Pradesh Ongole India Department of Internet of Things School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798400709586

The demand for high-performance hardware solutions for machine learning tasks is growing as medical imaging evolves. In this paper, we will focus on the latest hardware advanced technologies: GPUs, TPUs and FPGAs that can be used for image processing optimization in medical imaging such as brain tumor segmentation or chest X-ray classification. We test these devices on the BraTS and ChestX-ray14 datasets to show how running models quicker increases diagnostic performance. The study offers a comprehensive performance and energy efficiency evaluation of all the considered hardware solutions when training deep learning models for medical imaging, providing clinical guidelines to choose appropriate new-generation accelerators before engaging in expensive leasing contracts. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： GPUS

来源：评论

学校读者我要写书评

暂无评论

Network Abnormal Traffic Detection Approach Based on Multi-Scaled Deep-CapsNet 5

Network Abnormal Traffic Detection Approach Based on Multi-S...

引用

5th International Conference on Inventive research in Computing Applications, ICIRCA 2023

作者： Tanwar, Shashi Thokala, Rishi Reddy Thapak, Sonika Maranan, Ramya Kumar, Sudheer Sravanthi, S. Aravali College of Engineering and Management Department of Computer Science and Engineering Haryana Faridabad India Srm Institute of Science and Technology Computer Science Engineering India Ies Collage of Technology Computer Science and Engineering India Saveetha School of Engineering Simats Department of Research and Innovation Tamil Nadu Chennai602105 India Piet Parul University Computer Science & Engineering Gujrat Vadodara India St. Martin's Engineering College Department of Computer Science Engineering secunderabad India

ISBN: (纸本)9798350321425

It is crucial for network security to be able to detect a variety of threats and unusual network traffic. In order to accomplish aberrant traffic detection, existing detection methods required enormous volumes of data. However, there are rare circumstances in which even a fewshot attack sample can be stopped. The shift in feature attitude will also have an impact on traffic attribute discrimination. However, the standard neural network model is unable to recognize this shift in perspective. As a result, few-shot sample anomalous traffic detection has poor accuracy and efficiency. This research has proposed a strategy for detecting unusual network traffic with a small number of samples. Multi-scale Deep-CapsNet and adversarial-reconstruction (MDAR) made up the system. To begin, the Deep-CapsNet's EM vector clustering is revamped. The prediction is finalized by transforming low-level to high-level features using the attitude transformation matrix. Second, the Deep-CapsNet was improved with the help of a multi-scale convolutional capsule. Finally, a reconstruction classification network (ARCN) that is vulnerable to adversarial input is proposed. Classification of the supervised source data and reconstruction of the unsupervised target data are both completed. In addition, an adversarial training technique that reduced the impact of noise on the reconstruction process is suggested. Using a mixture of MDAR, classification is obtained from a small number of samples (point 4). The results are tested on the ICSX2012 and CICIDS2017 datasets. The experimental outcomes validate the superior training performance of the approach. Additionally, its accuracy is unparalleled in both two- and multi-classification tasks. It is especially useful for real-time few-shot aberrant network traffic detection because to its good anti-noise performance and quick operating time. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Driven Possibilistic Clustering with Automatic Cluster Elimination

引用

computers, Materials & Continua 2024年第9期80卷 4917-4945页

作者： Xianghui Hu Yiming Tang Witold Pedrycz Jiuchuan Jiang Yichuan Jiang The School of Computer Science and Engineering Southeast UniversityNanjing211189China The School of Computer and Information Hefei University of TechnologyHefei230601China The Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6R 2V4Canada The Systems Research Institute Polish Academy of SciencesWarsaw00-901Poland The School of Information Engineering Nanjing University of Finance and EconomicsNanjing210023China

Traditional Fuzzy C-Means(FCM)and Possibilistic C-Means(PCM)clustering algorithms are data-driven,and their objective function minimization process is based on the available numeric ***,knowledge hints have been introduced to formknowledge-driven clustering algorithms,which reveal a data structure that considers not only the relationships between data but also the compatibility with knowledge ***,these algorithms cannot produce the optimal number of clusters by the clustering algorithm itself;they require the assistance of evaluation ***,knowledge hints are usually used as part of the data structure(directly replacing some clustering centers),which severely limits the flexibility of the algorithm and can lead to *** solve this problem,this study designs a newknowledge-driven clustering algorithmcalled the PCM clusteringwith High-density Points(HP-PCM),in which domain knowledge is represented in the form of so-called high-density ***,a newdatadensitycalculation function is *** Density Knowledge Points Extraction(DKPE)method is established to filter out high-density points from the dataset to form knowledge ***,these hints are incorporated into the PCM objective function so that the clustering algorithm is guided by high-density points to discover the natural data ***,the initial number of clusters is set to be greater than the true one based on the number of knowledge ***,the HP-PCM algorithm automatically determines the final number of clusters during the clustering process by considering the cluster elimination *** experimental studies,including some comparative analyses,the results highlight the effectiveness of the proposed algorithm,such as the increased success rate in clustering,the ability to determine the optimal cluster number,and the faster convergence speed.

关键词： Fuzzy C-Means(FCM) possibilistic clustering optimal number of clusters knowledge-driven machine learning fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Accelerating Medical Visual Question Answering by Image Rearrangement 21

Accelerating Medical Visual Question Answering by Image Rear...

引用

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Han, Wang Lei, Zhao Center for Future Media The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610000 China Sichuan Artificial Intelligence Research Institute Yibin China

ISBN: (纸本)9798331519254

Medical Visual Question Answering is designed for supporting clinical diagnosis by leveraging advanced language and visual comprehension ability. While Large Vision-Language Models offer medical visual question answering powerful generative and interpretative capabilities, they encounter significant computational challenges due to quadratic complexity that scales with sequence length, especially as image embeddings dominate the input sequence. To address this, we propose an Image Rearrangement algorithm, which reduces the number of image embeddings with minimal impact on model performance. The Image Rearrangement algorithm aggregates similar image embeddings based on their relative alignment to text embeddings. We evaluate the Image Rearrangement algorithm method across three distinct datasets using two medical visual question answering models, observing that the Image Rearrangement algorithm achieves substantial computational savings while maintaining diagnostic accuracy. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Virtual Twin Modelling for Strengthening IoT Software Security Protocols 1

AI-Enhanced Virtual Twin Modelling for Strengthening IoT Sof...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Kumara, Bharath Barmola, Pareshwar Prasad Arora, Renuka Parikh, Swapnil M Maranan, Ramya Ramaiah University of Applied Science Department of Electronics and Communication Engineering Bengaluru India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Jagannath University Department of Computer Science and Engineering Haryana India Parul Institute of Engineering and Technology Parul University Faculty of Computer Science and Engineering Vadodara India Simats Saveetha School of Engineering Department of Research and Innovation Chennai India

ISBN: (纸本)9798350352931

To fortify security mechanisms in software systems for the Internet of Things (IoT), this article presents a framework for AI-Enhanced Virtual Twin Modelling. In order to track and examine the actions of IoT devices in real-time, the suggested method makes use of virtual twin technology that is combined with machine learning techniques. Automated response generation, continuous threat assessment, and anomaly detection are made possible by creating a digital clone of the actual IoT network using the virtual twin paradigm. By combining deep learning models like CNNs and LSTMs, it becomes easier to forecast possible security risks in network traffic data by seeing intricate spatial and temporal patterns. When tested in a virtual Internet of Things (IoT) setting, the suggested framework outperforms conventional rule-based approaches by a wide margin, reducing reaction time by 35% while achieving an accuracy of 9 6. 2 %in threat identification. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Effective Traffic Model for Intelligent Traffic Monitoring Enabled Deep RNN Algorithm for Autonomous Vehicles Surveillance Systems 4

Effective Traffic Model for Intelligent Traffic Monitoring E...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Leelavathy, S. Nithya, M. Dhaya, R. Muthuselvan, S. Kanthavel, R. Rajakumari, K. Department of Computer Science and Engineering Chennai India Salem India Department of Computer Science and Engineering Salem India Kcg College of Technology Department of Information Technology Chennai India School of Cse Hindustan Institute of Technology of Science and Technology Chennai India Bharath Institute of Higher Education and Research Chennai India

ISBN: (纸本)9798350300888

Regardless of the terrain, weather, visibility, or road surface conditions, improving detection and forecast accuracy is a critical priority for autonomous cars. Little shifts in the images to be collected should be understood even in low-light settings because the vehicle needs more data to make a binding judgment. As a subfield of AI and DL, Recurrent Neural Networks (RNNs) are structured with temporally aware connections between their nodes. As a result, the network can engage in sequential action driven entirely by internal incentives for an extended period. Moreover, cars require enormous computational capacity and a substantial quantity of data sets in an autonomous environment, such as unexpected events, opposing movement, lane conditions, and indestructible barriers. This study presents an effective deep recurrent neural network (Deep RNN) technique for autonomous cars to meet the need for recurrent nodes and capture sequence patterns within the acquired data. In addition, this study shows how to use deep RNN for efficient data annotation. Simulated findings show a significant drop in error when the proposed Deep RNN is utilized in autonomous cars. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantified Analysis of Highly Efficient Halide Perovskite Solar Cell 8

Quantified Analysis of Highly Efficient Halide Perovskite So...

引用

8th IEEE International Conference for Convergence in technology, I2CT 2023

作者： Pharne, Indrajit D. Patil, Santosh V. Rana, Ashish D. Bhargava, Kshitij Institute of Infrastructure Technology Research and Management Department of Electrica & Computer Science Engineering Ahmedabad380026 India Sanjay Ghodawat University Kolhapur416118 India Institute of Infrastructure Technology Research and Management Department of Electrical & Computer Science Engineering Ahmedabad380026 India Annasaheb Dange College of Engineering and Technology Maharashtra Ashta416301 India

ISBN: (纸本)9798350334012

This study focuses on designing of lead halide-based perovskite solar cell (PSC). PSCs have achieved an efficiency above 20% within 10-12 years of active research. Methyl ammonium lead iodide (MAPbI3) based PSCs have emerged as a promising replacement for silicon solar cells [1], [2]. The electron and hole transport layers (ETLs and HTLs) have an important role in the performance of PSCs. Here, we investigate the effect of various combinations of ETLs and HTLs for achieving optimized high-efficiency MAPbI3-based PSCs using SCAPS-1D. The selected ETLs were SnO2, TiO2, PCBM, WS2, and ZnO and HTLs were Cu2O, CuI, CuSCN, PEDOT: PSS, Spiro-OMeTAD. A total of 25 cells were analyzed to achieve maximum power conversion efficiency. The best efficiency of 23.7% was yielded by a cell having PCBM as ETL and Cu2O as HTL. The simulated J-V characteristics and performance metrics are shown in Figure. © 2023 IEEE.

关键词： Lead compounds

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：