检索结果-内蒙古大学图书馆

Unveiling factuality and injecting knowledge for LLMs via reinforcement learning and data proportion

science China(Information sciences) 2024年第10期67卷 389-390页

作者： Wenjun KE Ziyu SHANG Zhizhao LUO Peng WANG Yikai GUO Qi LIU Yuxuan CHEN School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(Southeast University) Beijing Institute of Technology Zhuhai Beijing Institute of Computer Technology and Application

Large language models(LLMs) have demonstrated remarkable effectiveness across various natural language processing(NLP) tasks, as evidenced by recent studies [1, 2]. However, these models often produce responses that conflict with reality due to the unreliable distribution of facts within their training data, which is particularly critical for applications requiring high credibility and accuracy [3].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetic Foot Ulcer Classification Using Deep Learning Approach 8th

Diabetic Foot Ulcer Classification Using Deep Learning Appro...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Sivakamasundari, P. Niranjana, G. Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

ISBN: (纸本)9783031736162

Podiatrist diagnosis and lesion localization are used as current testing approaches for Diabetic Foot ulcers (DFU). Current systems for automation concentrate on either categorization or division. One of the most common metabolic conditions, Diabetes (also called diabetes mellitus), is brought on by the pancreas incapacity to generate sufficient anti hyper-glycemic hormone to control glycemia levels. It may cause "Diabetic Peripheral Neuropathy," a collection of nerve diseases that can develop if the blood glucose level is left uncontrolled and unmanaged. Blood glucose levels may be efficiently maintained by recognising diabetes initially through constant surveillance and screenings. Using image processing methods such as data stretching with Deep Learning, image reduction and improvement, image division, and feature extraction, this paper offers a thorough approach for analysing thermal scans of the diabetic foot. By using these techniques, doctors may assess and track a patient's condition with fewer examinations. In this work, EfficientNetB3 architecture is compared with other Deep Learning models for accuracy in DFU identification. To create a powerful deep learning model, we gathered an extensive collection of 1,775 DFU photos. The basis of belief for this data gathering was created by two medical experts using annotator software to define the DFU region of interest. It took 48 ms to figure out a single image and 57.2 MB to validate the model. EfficientnetB3 got an average mean accuracy of 93%. This work demonstrates the effectiveness of Deep Learning for DFU localization in real-time, which could have improved with the use of a larger data set. © IFIP International Federation for Information Processing 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Comparative Methods of Implementation for Different Question Answering Systems 5

Comparative Methods of Implementation for Different Question...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Naveen, C. Amutha, B. Srm Institute of Science and Technology Department of Computer Science and Engineering Kattankulathur Chennai India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India

ISBN: (纸本)9798350385649

This research introduces an innovative Question Answering (QA) system tailored explicitly for government department inquiries regarding individuals. Harnessing the prowess of cutting-edge language models such as BERT and T5 (Text-to-Text Transfer Transformer), the system excels in understanding complex queries within diverse governmental domains. Moreover, it incorporates a specialized Knowledge Graph meticulously curated with interconnected information about people across various departments. By integrating BERT and T5 for versatile query comprehension and answer generation alongside a comprehensive People-centric Knowledge Graph, this system aims to revolutionize information retrieval within government entities. The seamless fusion of these technologies promises accurate, contextually rich responses, optimizing operational efficiency across government departments and fostering streamlined access to crucial information. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Optimal weight support vector regression ensemble with cluster-based subsampling for electricity price forecasting

引用

Journal of Intelligent and Fuzzy Systems 2024年第1期1卷 1-16页

作者： Li, Yuerong Zhang, Yuhua Che, Jinxing School of Science Nanchang Institute of Technology Jiangxi Nanchang China Key Laboratory of Engineering Mathematics and Advanced Computing Nanchang Institute of Technology Jiangxi Nanchang China

Accurate prediction of short-term electricity price is the key to obtain economic benefit and also an important index of power system planning and management. Support vector regression (SVR) based ensemble works have gained remarkable achievements in terms of high accuracy and steady performance, but they are highly dependent on data representativeness and have a high computational complexity O (k ∗ N 3) of data samples and parameter selection. To further improve the data representativeness and reduce its computational complexity, this paper develops a new approach to forecast electricity price via optimal weighted ensemble. In the model, the cluster-based subsampling algorithm is proposed to categorize the inputs being seasonally decomposed into several groups, and representative data are drawn from each group in a certain proportion to ensure that each subset trained with SVR has the same representativeness and features. Moreover, the optimal weighted combination method is presented to assign weights to the sub-SVRs to obtain the optimal support vector regression ensemble model (OWSSVRE). The experimental results show that the improved support vector regression ensemble model with the same features and representativeness of the subset has better performance in electricity price forecasting. As a result, it is suitable to support decision making in the energy and other sectors. © 2024 - IOS Press. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Network Security and Cryptography: Threats, Obstacles and Solutions-A Bibliometric Analysis

Recent Advances in Computer Science and Communications

引用

Recent Advances in computer science and Communications 2025年第2期18卷 83-101页

作者： Singh, Purushottam Dutta, Sandip Pranav, Prashant Department of Computer Science and Engineering Birla Institute of Technology Mesra Ranchi835215 India

Background: In the wake of escalating cyber threats and the indispensability of ro-bust network security mechanisms, it becomes crucial to understand the evolving landscape of cryptographic research. Recognizing the significant contributions and discerning emerging trends can guide future strategies and technological advancements. Our study endeavors to shed light on this through a bibliometric analysis of publications in the realms of Network Security and Cryptography. Method: To chronicle and synthesize the progression of research methodologies from their in-ception to the present day, we undertook a comprehensive Bibliometric Analysis of Network Security and Cryptography. Our data set was culled from the Clarivate Analytics Web of science Database, encompassing 3,897 papers, 603 sources, and 7,886 authors from across the globe. Results: Our analysis revealed a marked upsurge in cryptographic research since 1992, with China standing out as a dominant contributor in terms of publications. Notably, while 'security' and 'cryptography' emerged as recurrent research themes, there's an observable downtrend in international collaborations. Our study also highlights pivotal topics shaping the network security domain, offering insights into the trajectories of research source growth, structural variabil-ities in research relevance, and prospective intellectual and collaborative avenues as guided by authorship patterns. Conclusion: Cryptographic research is on an upward trajectory, both in volume and signifi-cance. However, the tapering of international collaborations and an evident need to concentrate on emergent challenges, such as data privacy and innovative network attacks, emerge as nota-ble insights. This bibliometric review serves as a compass, directing researchers and academi-cians towards areas warranting heightened attention, thereby informing the roadmap for future investigative pursuits. © 2025 Bentham science Publishers.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Design of a ML-based trust prediction model using intelligent TrustBoxes in challenged networks

引用

International Journal of Systems, Control and Communications 2024年第3期15卷 209-234页

作者： Barai, Smritikona Kundu, Anindita Bhaumik, Parama Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu India Department of Information Technology Jadavpur University Kolkata India

Challenged networks (CNs) contain resource-constrained nodes deployed in regions where human intervention is difficult. Opportunistic networks (OppNets) are CNs with no predefined source-to-destination paths. Due to their inherent properties, CNs and OppNets are highly susceptible to black-hole (BH) attacks, resulting in degraded packet-delivery ratio. In this work, an ML-based trust prediction model (MLTPM) is proposed to identify potential BH nodes in OppNets. MLTPM uses a novel function to calculate the total-trust-value (TTV) of each node. Intelligent TrustBoxes are introduced in the network to identify possible BH nodes, using TTV, along with five more node-behaviour features. TrustBoxes reduce the computational overhead of the resource-constrained nodes. Three simulated scenarios are compared - no detection, non-ML-based detection, and MLTPM, each using epidemic, prophet, and spray-and-wait routing protocols. MLTPM performs best with spray-and-wait, exhibiting about 25.21% and 80% mean improvement in delivery-ratio and dropped-message numbers respectively, compared to non-ML-based detection. An overall 12.62% improvement in delivery-ratio and 26.7% improvement in dropped messages is observed using MLTPM, compared to the above-mentioned scenarios. © 2024 Inderscience Enterprises Ltd.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Convergence of various computer-aided systems for breast tumor diagnosis: a comparative insight

引用

Multimedia Tools and Applications 2025年第16期84卷 16709-16756页

作者： Singh, Saket Kumar Patnaik, K. Sridhar Department of Computer Science and Engineering Birla Institute of Technology Mesra Ranchi835215 India

Breast Cancer, with an expected 42,780 deaths in the US alone in 2024, is one of the most prevalent types of cancer. The death toll due to breast cancer would be very high if it were to be totaled up globally. Early detection of breast cancer is the only way to decrease the mortality caused by it. In order to diagnose breast cancer, even the most competent and qualified pathologists and radiologists have to examine hundreds of high-resolution images, which is a massive burden on them. Compared to the number of cases, very few experts are available to manage this burden. Additionally, as humans are more prone to mistakes, the likelihood of finding false positive cases is also high. Numerous AI techniques, including machine learning and deep learning, are ideally suited to address these issues, inspiring many researchers to introduce novel computer-aided detection systems. In this study, we have comprehensively reviewed pre-existing literature aimed at developing computer-aided systems based on using machine learning, deep learning, and vision transformers to identify and classify breast cancer. We have discussed numerous imaging modalities for detecting breast cancer, along with the widely used data pre-processing approaches, machine learning and deep learning models, as well as ensemble learning methods suitable for the task. Popular datasets and their sources are also listed for future referencing. Finally, we have identified a few gaps and addressed potential future research directions with an intent of aiding researchers select approaches tailored to case-specific needs. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Optimized Neural Network for Automated Cardiovascular Disease Classification: Meta-heuristic Enabled Model

引用

SN computer science 2025年第1期6卷 1-14页

作者： Kusuma, S. Jothi, K.R. Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology & Science Madanapalle India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

Cardiovascular disease remains a major issue for mortality and morbidity, making accurate classification crucial. This paper introduces a novel heart disease classification model utilizing Electrocardiogram (ECG) signals. The model consists of two main steps: feature extraction using a refined Lion Algorithm with New Mutated evaluation (LA-NM) and classification through an ensemble approach combined with a Neural Network (NN). The proposed model significantly outperforms traditional classifiers. At 80% training data, it achieves accuracy improvements of 8.4% to 3.11% over Neural Network (NN), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and ensemble models. At 90% training data, it shows precision improvements ranging from 1.03% to 0.31% better than the comparison models and specificity improvements ranging from 13.92% to 0.52%. These results underscore the effectiveness of the model and suggest its potential for further development in personalized treatment recommendations based on patient history. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Ensemble models Feature extraction Heart disease classification Neural network Optimization

来源：评论

学校读者我要写书评

暂无评论

Maximizing Profit of the Service Providers through Efficient Content Placement and Retrieval in an IoT-enabled Edge-Cloud Platform 18

Maximizing Profit of the Service Providers through Efficient...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Gandhi, Preet Mahanta, Abhishriya Ghose, Manojit Sahu, Aryabartta Indian Institute of Technology Department of Computer Science and Engineering Guwahati India Indian Institute of Technology School of Computing and Electrical Engineering Mandi India Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798350391725

In today's 5G era, the amount of data generated by the Internet of Things (IoT) devices is enormous. Data is processed and stored in the cloud under a traditional cloud computing architecture, and real-time processing and retrieval of these data is time-consuming. Therefore, an edge-cloud framework comes in handy where the content generated is placed on the edge nodes of the network, and it can reach the endusers in a time-bound manner. A majority of the previous research works on content placement under the edge-cloud architecture primarily aimed at improving the latency of the system. However, the approach proposed in this paper aims to maximize the profit of the service provider by effectively placing the content in a hierarchically organized edge-cloud network. We propose two strategies and compare them with random and greedy approaches for both synthetic and real data sets. The experimental results demonstrate the effectiveness of the proposed strategies, and the profit of the service providers increases by 38.81% (maximum) and 10.51% (on average) for the synthetic dataset and by 65.74% (maximum) and 22.83% (on average) for the real-world dataset when compared with the greedy approach. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

IWM-LSTM encoder for abstractive text summarization

引用

Multimedia Tools and Applications 2025年第9期84卷 5883-5904页

作者： Gangundi, Ravindra Sridhar, Rajeswari Department of Computer Science and Engineering National Institute of Technology Tamilnadu Tiruchirappalli620015 India

Sequence-to-sequence models are fundamental building blocks for generating abstractive text summaries, which can produce precise and coherent summaries. Recently proposed, different text summarization models aimed to enhance summarization performance through the use of copying mechanisms, reinforcement learning, and multiple-level encoders. However, there has been limited research on improving the summarization output by modifying the structure of the long short-term memory (LSTM) cell. We introduced an improved version of LSTM called improved working memory LSTM (IWM-LSTM). IWM-LSTM removes the output gate and enhances the input and forget gates by incorporating cell state information into these gates. In our sequence-to-sequence model for text summarization, we replaced the LSTM encoder with a bi-directional IWM-LSTM, resulting in better summaries with minimal training time and less computational intensiveness. Additionally, we utilized Bidirectional encoder representations from transformers (BERT) embeddings to enhance the rouge score. The CNN/DailyMail dataset is used to train and test the model performance. The proposed model achieves better Recall-oriented understudy for gisting evaluation (ROUGE) scores than state-of-the-art models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Embeddings

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

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

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：