检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Sharma, Aishita Singh, Sunil K. Kumar, Sudhakar Pan, Shin Hung Gupta, Brij B. Chui, Kwok Tai Department of CSE Chandigarh College of Engineering and Technology Chandigarh India Department of Information Management Asia University Taiwan Department of Computer Science and Information Engineering Asia University Taiwan University of Economics and Human Sciences Warsaw Poland Hong Kong Metropolitan University Hong Kong

ISBN: (纸本)9798331521165

Software Defined Networking enhances network management and security through centralized control, vital for the growth of consumer electronics. With the rise of smart devices and IoT systems, the demand for scalable network management has intensified. While SDN streamlines network operations and supports essential technologies, it remains vulnerable to DDoS attacks that can disrupt these services. However, SDN environments are vulnerable to Distributed Denial of Service (DDoS) attacks, posing significant risks to operational integrity. This paper analyzes the performance of various machine learning models at the individual level, providing insights into their effectiveness in detecting DDoS attacks. Based on these findings, a hybrid model is introduced, utilizing stacking techniques with a Deep Neural Network (DNN) as the meta-learner. The hybrid approach achieves a remarkable accuracy of 99.09%. The results underscore the crucial role of machine learning, particularly deep learning methodologies, in safeguarding SDN networks against cyber threats. As reliance on complex networked systems in consumer electronics increases, enhancing the security of SDN environments becomes essential for maintaining seamless operations. © 2025 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Web Traffic Modelling and Forecasting with a Hybrid Predictive Approach

引用

Journal of Web Engineering 2025年第3期24卷 409-456页

作者： Ujjwal Thakur Sunil K. Singh Sudhakar Kumar Harmanjot Singh Varsha Arya Brij B. Gupta Razaz Waheeb Attar Ahmed Alhomoud Kwok Tai Chui Department of CSE Chandigarh College of Engineering & Technology Chandigarh India Hong Kong Metropolitan University (HKMU) Hong Kong SAR China Center for Interdisciplinary Research University of Petroleum and Energy Studies (UPES) Dehradun India Department of Computer Science and Information Engineering Asia University Taichung Taiwan China Department of Medical Research China Medical University Hospital China Medical University Taichung Taiwan Symbiosis Centre for Information Technology (SCIT) Symbiosis International University Pune India University of Economics and Human Science Warsaw Poland Management Department College of Business Administration Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science College of Science Northern Border University Arar Saudi Arabia

Web traffic analysis is crucial for optimising user experience and engagement. This research explores a hybrid approach combining traditional statistical methods, like the autoregressive integrated moving average (ARIMA) model, with advanced techniques such as long short-term memory (LSTM) neural networks and the Prophet model. ARIMA effectively captures linear trends, seasonal effects, and cyclic behaviours, while LSTM handles complex non-linear patterns, and Prophet addresses seasonal variations and missing data. The hybrid model demonstrated 93% accuracy in predicting web traffic, highlighting the benefits of integrating these methodologies. This approach enables businesses to better manage resources, boost user engagement, and improve revenue. Future research will focus on refining hybrid models by incorporating new data features and ensemble methods to further enhance prediction accuracy, ultimately advancing the understanding of web traffic trends and user behaviour.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scalable Machine Learning Frameworks for Large-Scale Multimodal Image and Speech Signal Processing 8

Scalable Machine Learning Frameworks for Large-Scale Multimo...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Dankan Gowda, V. Pathak, Disha Prasad, K.D.V. Srinivas, Ved Manu, Y.M. Reddy, N. Sudhakar Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Symbiosis Centre for Management Studies-Hyderabad Mulshi Pune Maharashtra Lavale412115 India Symbiosis Institute of Business Management Hyderabad Pune India Thiagarajar School of Management Department of Human Resources Tamil Nadu Madurai India Adichunchanagiri University Bgs Institute of Technology Department of Computer Science and Engineering Nagamangala Taluk B.G.Nagara Karnataka Mandya District India Mohan Babu University School of Engineering Department of Ece Tirupati India

ISBN: (纸本)9798350376425

The machine learning algorithm proposed in this paper is suitable for Big Data multimodal datasets and in particular for integrating image and speech data. Preliminary feature extraction is based on convolutional neural network (CNN) for image analysis and recurrent neural network (RNN) for speech processing, while the fusion was done in a fusion layer. For assessment, the system's performance is compared on the aspect of accuracy and latency, computational overhead, and resource consumption. The above experiment results prove that the proposed framework reduces the latency to 120ms and the required computational power, but the training and validation set accuracies as high as 90% and 87% are higher than the corresponding values of basic models such as CNN and hybrids of CNN+LSTM. It also illustrates the system's scalability: inference time of less than 2s in the range of moderate batch size, and lower memory consumption (110 MB) in comparison with the baseline models. The characteristics of the model mean that it takes less resources to process data, making the model ideal for use in applications where there is a need for processing of data in real time. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading 31

Self-supervised learning of a tailored Convolutional Auto En...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Tabatabaei, Zahra Colomer, Adrián Engan, Kjersti Oliver, Javier Naranjo, Valery Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano Spain HUMAN-tech Universitat Politècnica de València Spain ValgrAI - Valencian Graduate School Research Network for Artificial Intelligence Spain Department of Electrical Engineering and Computer Science University of Stavanger Norway Department of Artificial Intelligence Tyris Tech S.L. Valencia Spain

ISBN: (纸本)9789464593600

According to GLOBOCAN 2020, prostate cancer is the second most common cancer in men worldwide and the fourth most prevalent cancer overall. For pathologists, grading prostate cancer is challenging, especially when discriminating between Grade 3 (G3) and Grade 4 (G4). This paper proposes a Self-Supervised Learning (SSL) framework to classify prostate histopathological images when labeled images are scarce. In particular, a tailored Convolutional Auto Encoder (CAE) is trained to reconstruct 128×128×3 patches of prostate cancer Whole Slide Images (WSIs) as a pretext task. The downstream task of the proposed SSL paradigm is the automatic grading of histopathological patches of prostate cancer. The presented framework reports promising results on the validation set, obtaining an overall accuracy of 83% and on the test set, achieving an overall accuracy value of 76% with F1-score of 77% in G4. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Query Rewriting for Retrieval-Augmented Large Language Models

arXiv

引用

arXiv 2023年

作者： Ma, Xinbei Gong, Yeyun He, Pengcheng Zhao, Hai Duan, Nan Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Microsoft Research Asia China Microsoft Azure AI

Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an LLM to generate the query, then use a web search engine to retrieve contexts. Furthermore, to better align the query to the frozen modules, we propose a trainable scheme for our pipeline. A small language model is adopted as a trainable rewriter to cater to the black-box LLM reader. The rewriter is trained using the feedback of the LLM reader by reinforcement learning. Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice QA. Experiments results show consistent performance improvement, indicating that our framework is proven effective and scalable, and brings a new framework for retrieval-augmented LLM. Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy

arXiv

引用

arXiv 2023年

作者： Marinov, Zdravko Jäger, Paul F. Egger, Jan Kleesiek, Jens Stiefelhagen, Rainer The Computer Vision for Human-Computer Interaction Lab Department of Informatics Karlsruhe Institute of Technology Adenauerring 10 Karlsruhe76131 Germany Girardetstraße 2 Essen45131 Germany Heidelberg Interactive Machine Learning Group Im Neuenheimer Feld 223 Heidelberg69120 Germany The Helmholtz Imaging DKFZ Im Neuenheimer Feld 223 Heidelberg69120 Germany

Interactive segmentation is a crucial research area in medical image analysis aiming to boost the efficiency of costly annotations by incorporating human feedback. This feedback takes the form of clicks, scribbles, or masks and allows for iterative refinement of the model output so as to efficiently guide the system towards the desired behavior. In recent years, deep learning-based approaches have propelled results to a new level causing a rapid growth in the field with 121 methods proposed in the medical imaging domain alone. In this review, we provide a structured overview of this emerging field featuring a comprehensive taxonomy, a systematic review of existing methods, and an in-depth analysis of current practices. Based on these contributions, we discuss the challenges and opportunities in the field. For instance, we find that there is a severe lack of comparison across methods which needs to be tackled by standardized baselines and benchmarks. Appendixes are here. © 2023, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Incremental Feature Selection for Dynamic Incomplete Data Using Sub-Tolerance Relations

SSRN

引用

SSRN 2023年

作者： Zhao, Jie Ling, Yun See-To, Wing-Kuen Eric Huang, Faliang Wang, Jiahai School of Management Guangdong University of Technology Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

Feature selection is an important problem in Rough Set and is widely used in data analysis. The extended theory of tolerance relations can effectively deal with the realistic problem of incomplete data. However, the space and time complexity of computing the positive region using TRS increases dramatically. Simultaneously, redundant features are allowed to enter the feature subset, resulting in poor classification accuracy, because the positive region-based significance measure neglects uncertain information. To overcome these drawbacks, this paper introduces a subrelation-based tolerance class (STC) approach. STC transforms the TRS positive region calculation into a two-stage certainty measurement of objects, and thus divides the entire universe into two regions of certainty and uncertainty at each stage, by decomposing the tolerance relation into two subrelations. The computational space is reduced by progressively filtering out of the regions of certainty. Using STC, a new incremental mechanism is proposed. Furthermore, we propose a new significance measure using both certain and uncertain information, which effectively reduces the number of redundant features and subsequently improves computational efficiency and classification accuracy. Experiments on real data sets and comparisons with existing algorithms have been conducted to verify the superiority of the method. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification

Domain-Specific Pre-training Improves Confidence in Whole Sl...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Soham Rohit Chitnis Sidong Liu Tirtharaj Dash Tanmay Tulsidas Verlekar Antonio Di Ieva Shlomo Berkovsky Lovekesh Vig Ashwin Srinivasan Department of Computer Science & Information Systems Birla Institute of Technology and Science Pilani Faculty of Medicine Health and Human Sciences Macquarie University Boolean Lab University of California San Diego TCS Research India

Whole Slide Images (WSIs) or histopathology images are used in digital pathology. WSIs pose great challenges to deep learning models for clinical diagnosis, owing to their size and lack of pixel-level annotations. With the recent advancements in computational pathology, newer multiple-instance learning-based models have been proposed. Multiple-instance learning for WSIs necessitates creating patches and uses the encoding of these patches for diagnosis. These models use generic pre-trained models (ResNet-50 pre-trained on ImageNet) for patch encoding. The recently proposed KimiaNet, a DenseNet121 model pre-trained on TCGA slides, is a domain-specific pre-trained model. This paper shows the effect of domain-specific pre-training on WSI classification. To investigate the effect of domain-specific pre-training, we considered the current state-of-the-art multiple-instance learning models, 1) CLAM, an attention-based model, and 2) TransMIL, a self-attention-based model, and evaluated the models’ confidence and predictive performance in detecting primary brain tumors - gliomas. Domain-specific pre-training improves the confidence of the models and also achieves a new state-of-the-art performance of WSI-based glioma subtype classification, showing a high clinical applicability in assisting glioma diagnosis. We will publicly share our code and experimental results at https://***/soham-chitnis10/WSI-domain-specific.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

Isoform Function Prediction Based on Heterogeneous Graph Att...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kuo Guo Yifan Li Hao Chen Hong-Bin Shen Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Computational Biology Department School of Computer Science Carnegie Mellon University Pittsburgh PA USA

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DSLA: Defending against selective forwarding attack in wireless sensor networks using learning automaton

引用

IEIE Transactions on Smart Processing and Computing 2020年第1期9卷 58-74页

作者： Jamshidi, Mojtaba Esnaashari, Mehdi Ghasemi, Shahin Qader, Nooruldeen Nasih Meybodi, Mohammad Reza Department of Information Technology University of Human Development Sulaymaniyah Iran Faculty of Computer Engineering K. N. Toosi University of Technology Tehran Iran Kermanshah University of Medical Sciences Kermanshah Iran Computer Science Department University of Human Development Sulaymaniyah Iraq Computer Engineering and Information Technology Department Amirkabir University of Technology Tehran Iran

Abstract: Selective forwarding attacks (SFAs) can harm the mission of critical applications such as military surveillance and forest fire monitoring. In these attacks, malicious nodes behave like normal nodes most of the time, but selectively drop sensitive packets, such as a packet that reports on the movement of opposing forces, and therefore, detection of this kind of attack is hard. In this paper, a fully distributed, dynamic, intelligent, lightweight algorithm based on learning automata is proposed in order to defend against the selective forwarding attack. In this algorithm, an overhearing mechanism, along with the learning automata model, is used to select secure routes for forwarding packets in a multi-hop routing algorithm. Each node is equipped with a learning automaton, which helps the node select the next hop for forwarding its data towards the base station. The proposed algorithm is simulated using J-SIM. Simulation results show the superiority of the proposed algorithm over existing algorithms, such as the single path forwarding algorithm, the multi-hop acknowledge based algorithm, the multi-data flow algorithm, the multi-path algorithm, and the neighbor watch system based algorithm, in packet delivery rate, packet drop rate by malicious nodes, communications overhead, and energy consumption. © 2020 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Sensor nodes

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：