检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Chen, Man-Sheng Li, Zhi-Yuan Lin, Jia-Qi Wang, Chang-Dong Huang, Dong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Sun Yat-sen University Guangzhou China College of Mathematics and Informatics South China Agricultural University Guangzhou China

Multi-view spectral clustering has achieved impressive performance by learning multiple robust and meaningful similarity graphs for clustering. Generally, the existing literatures often construct multiple similarity graphs by certain similarity measure (e.g. the Euclidean distance), which lack the desired ability to learn sparse and reliable connections that carry critical information in graph learning while preserving the low-rank structure. Regarding the challenges, a novel Sparse Graph Tensor Learning for Multi-view Spectral Clustering (SGTL) method is designed in this paper, where multiple similarity graphs are seamlessly coupled with the cluster indicators and constrained with a low-rank graph tensor. Specifically, a novel graph learning paradigm is designed by establishing an explicit theoretical connection between the similarity matrices and the cluster indicator matrices, in order that the constructed similarity graphs enjoy the desired block diagonal and sparse property for learning a small portion of reliable links. Then, we stack multiple similarity matrices into a low-rank graph tensor to better preserve the low-rank structure of the reliable links in graph learning, where the key knowledge conveyed by singular values from different views is explicitly considered. Extensive experiments on several benchmark datasets demonstrate the superiority of SGTL. The source code of SGTL would be publicly available soon. © 2023, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Context Transformer for Multi-level Semantic Scene Understanding

arXiv

引用

arXiv 2025年

作者： Hao, Luoying Hu, Yan Yue, Yang Wu, Li Fu, Huazhu Duan, Jinming Liu, Jiang Research Institute of Trustworthy Autonomous Systems Dept. of Computer Science and Engineering Southern University of Science and Technology China School of Computer Science University of Birmingham United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences University of Manchester United Kingdom MGI Tech Co. Ltd. China Singapore

A comprehensive and explicit understanding of surgical scenes plays a vital role in developing context-aware computer-assisted systems in the operating theatre. However, few works provide systematical analysis to enable hierarchical surgical scene understanding. In this work, we propose to represent the tasks set [phase recognition → step recognition → action and instrument detection] as multi-level semantic scene understanding (MSSU). For this target, we propose a novel hierarchical context transformer (HCT) network and thoroughly explore the relations across the different level tasks. Specifically, a hierarchical relation aggregation module (HRAM) is designed to concurrently relate entries inside multi-level interaction information and then augment task-specific features. To further boost the representation learning of the different tasks, inter-task contrastive learning (ICL) is presented to guide the model to learn task-wise features via absorbing complementary information from other tasks. Furthermore, considering the computational costs of the transformer, we propose HCT+ to integrate the spatial and temporal adapter to access competitive performance on substantially fewer tunable parameters. Extensive experiments on our cataract dataset and a publicly available endoscopic PSI-AVA dataset demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin. The code is available at https://***/Aurorahao/HCT. Copyright © 2025, The Authors. All rights reserved.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

Classifying Emotions in Roman Urdu Posts using Machine Learning 1

Classifying Emotions in Roman Urdu Posts using Machine Learn...

引用

1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021

作者： Nabeel, Zahra Mehmood, Maseeha Baqir, Anees Amjad, Anam Dept. of Software Engineering Sialkot Pakistan Ca'Foscari University of Venice Dept. of Environmental Sciences Informatics and Statistics Venice Italy National University of Sciences and Technology Dept. of Computer and Software Engineering Islamabad Pakistan

ISBN: (纸本)9781665424134

Emotion, a state of human mind has a significant impact on human behavior, social interactions and decision making. Few emotions from Carroll E. Izard model such as long-term fear, anger and sadness cause mental disorders which can lead to deterioration of mental and physical health. For the well-being of mental health, different psychological parameters such as voice, facial expressions and body movements were used to extract these emotions in earlier times. This paper focuses on verbal language for emotion classification. With the huge popularity of Web 3.0, people feel more comfortable in sharing their emotions over social media due to the anonymity of the web. Recently, researchers around the globe are interested to classify the emotions from social media posts (i.e., tweets, comments or micro-blogs etc.) using resource-rich languages e.g., English. However, less attention is paid towards the resource-poor language such as Urdu in Roman script. According to the Gallup survey in Pakistan, Urdu in Roman script is widely used to transmit text. To detect emotions in Roman Urdu text is a big challenge due to its scripting and morphology. In this paper, the following contributions are made;1) A corpus of Roman Urdu is developed for emotion classification. 2) We aim to identify user's mental states using textual posts on social media plat-forms;Instagram, Facebook, Twitter and YouTube. Particularly, Natural Language Processing methods incorporated with feature extraction methods (TF-IDF) and four supervised classifiers such as Support Vector Machine (SVM),Naïve Bayes, Random Forest and K-nearest Neighbor are used. By utilizing 80% training and 20% testing data, Naive Bayes secures 70.57% accuracy. 3) Moreover, suitability analysis is performed to identify the most suitable classifier in terms of accuracy, training and testing time. Results show that Naive Bayes is the most suitable classifier for emotion classification. © 2021 IEEE.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Psychological Stress Classification Using Extreme Gradient Boosting Algorithm

Psychological Stress Classification Using Extreme Gradient B...

引用

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Maria Mahardini Sakanti Viacheslav Siniaev Aurelia Amaris Win-Jet Luo Suhartono C. Bambang Dwi Kuncoro Graduate Institute of Precision Manufacturing National Chin-Yi University of Technology Taichung Taichung Taiwan Institute of Applied Computer Science ITMO University St. Petersburg Russian Federation Department of Informatics Engineering Faculty of Computer Science Universitas Brawijaya Malang Indonesia Ph.D. Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung Taichung Taiwan Department of Refrigeration Air Conditioning and Energy Engineering National Chin-Yi University of Technology Taichung Taiwan

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

Stress, as a reaction to threatening situations, can raise heart rate and result in serious conditions that might cause significant damage or even be life-threatening. Traditional methods for evaluating stress, which rely on subjective self-reporting and clinical assessments, often suffer from biases and inconsistencies. Artificial intelligence models have been explored to predict stress levels more accurately. This paper investigates the application of Extreme Gradient Boosting in classifying psychological stress using the WESAD dataset, which includes parameters such as acceleration, electrocardiogram, electromyography, electrodermal activity, temperature, and respiration. The dataset was balanced and sampled to create a manageable subset for experimental. Extreme Gradient Boosting was chosen for its efficiency and scalability in handling complex datasets. The model was trained and validated, achieving a 95% accuracy in predicting stress levels. This study highlights the potential of integrating Extreme Gradient Boosting models into wearable devices for real-time stress monitoring. Future work involves optimizing the model to utilize fewer sensors without decreasing accuracy, ensuring it can be integrated into portable/wearable systems using tiny microcontrollers.

关键词： Accuracy Microcontrollers Psychology Human factors Predictive models Boosting Prediction algorithms Real-time systems Sensors Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Implementation of AI-Based Support Vector Machine Algorithm for Fraud Detection in Digital Payment Systems

Implementation of AI-Based Support Vector Machine Algorithm ...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Edy Prayitno Rikie Kartadie Uning Lestari Munengsih Sari Bunga Accounting Information Systems Faculty of Information Technology Universitas Teknologi Digital Indonesia Yogyakarta Indonesia Computer Engineering Study Program Faculty of Information Technology Universitas Teknologi Digital Indonesia Yogyakarta Indonesia Informatics Study Program Faculty of Science and Information Technology Universitas Akprind Indonesia Yogyakarta Indonesia Department of Computer Engineering Smart City Information Systems Politeknik Negeri Indramayu Indramayu Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

The increasing use of digital payment systems has led to a rise in fraudulent activities, presenting a significant challenge in ensuring secure transactions. This research focuses on implementing the Support Vector Machine (SVM) algorithm with a Radial Basis Function (RBF) kernel to detect fraud in digital payment systems. One of the main challenges addressed in this study is the severe class imbalance in the dataset, where fraudulent transactions account for only 0.17% of total transactions. To overcome this, the SMOTE (Synthetic Minority Over-sampling Technique) method was applied to balance the dataset, allowing the model to better recognize fraudulent patterns. The results indicate that the SVM model achieved an accuracy of 99.93%, with a precision of 86.23% and a recall of 75.51%. These results demonstrate that SVM, combined with SMOTE and RBF kernel, is highly effective in detecting fraudulent transactions while minimizing false positives. This research provides a strong foundation for improving fraud detection models in the context of digital payment systems, offering enhanced security and trust for users. Further research could explore hybrid models and real-time data analysis to improve performance.

关键词： Support vector machines Seminars Adaptation models Accuracy Data models Real-time systems Fraud Security Kernel Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Millimeter Wave Full-Duplex Networks: MAC Design and Throughput Optimization

Millimeter Wave Full-Duplex Networks: MAC Design and Through...

引用

Biennial Symposium on Communications, QBSC

作者： Shengbo Liu Wen Wu Liqun Fu Kaige Qu Qiang Ye Weihua Zhuang Sherman Shen Frontier Research Center Peng Cheng Laboratory Shenzhen China School of Informatics Xiamen University Xiamen China Department of Electrical and Computer Engineering University of Waterloo Waterloo Canada Department of Computer Science Memorial University of Newfoundland St. John's Canada

Full-duplex (FD) technique can remarkably boost the network capacity in the millimeter wave (mmWave) bands by enabling simultaneous transmission and reception. However, due to directional transmission and large bandwidth, the throughput and fairness performance of a mm Wave FD network are affected by deafness and directional hidden-node (HN) problems and severe residual self-interference (RSI). To address these challenges, this paper proposes a directional FD medium access control protocol, named DFDMAC to support typical directional FD transmission modes by exploiting FD to transmit control frames to reduce signaling overhead. Furthermore, a novel busy-tone mechanism is designed to avoid deafness and directional HN problems and improve fairness of channel access. To reduce the impact of RSI on link throughput, we formulate a throughput maximization problem for different FD transmission modes and propose a power control algorithm to obtain the optimal transmit power. Simulation results show that the proposed DFDMAC can improve the network throughput and fairness by over 60% and 32%, respectively, compared with the existing MAC protocol in IEEE 802.11ay. Moreover, the proposed power control algorithm can effectively enhance the network throughput.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ProBLeSS: A Proactive Blockchain Based Spectrum Sharing Protocol Against SSDF Attacks in Cognitive Radio IoBT Networks

IEEE Networking Letters

引用

IEEE Networking Letters 2020年第2期2卷 67-70页

作者： Patnaik, Milan Prabhu, G. Rebeiro, Chester Matyas, Vashek Veezhinathan, Kamakoti Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai600036 India Faculty of Informatics Masaryk University Brno Czech Republic

Spectrum Sharing Data Falsification (SSDF) attacks can cause heavy performance degradation to Cognitive Radio (CR) based Internet of Battlefield Things (IoBT) networks. The challenge in such networks is to handle this security problem real time, in addition to spectrum sharing. This requires a robust CR architecture and protocol that can provide integrity of the spectrum sensing data being shared between Secondary Users (SUs) for collaborative spectrum decisions in protocols like PROLEMus. We propose one such protocol called Proactive Blockchain based Spectrum Sharing (ProBLeSS) protocol which leverages a blockchain to provide security against SSDF attacks in CR-IoBT networks. © 2019 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multimodal Feature Extraction for Memes Sentiment Classification 2

Multimodal Feature Extraction for Memes Sentiment Classifica...

引用

2nd IEEE Conference on Information Technology and Data Science, CITDS 2022

作者： Ouaari, Sofiane Tashu, Tsegaye Misikir Horvath, Tomas Elte - Eötvös Loránd University Faculty of Informatics Department of Data Science and Engineering Pázmány Péter sétány 1/C Budapest1117 Hungary Institute of Computer Science Faculty of Science Pavol Jozef Šafárik University Jesenná 5 Košice040 01 Slovakia College of Informatics Kombolcha Institute of Technology Wollo University Kombolcha208 Ethiopia

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

In this study, we propose feature extraction for multimodal meme classification using Deep Learning approaches. A meme is usually a photo or video with text shared by the young generation on social media platforms that expresses a culturally relevant idea. Since they are an efficient way to express emotions and feelings, a good classifier that can classify the sentiment behind the meme is important. To make the learning process more efficient, reduce the likelihood of overfitting, and improve the generalizability of the model, one needs a good approach for joint feature extraction from all modalities. In this work, we proposed to use different multimodal neural network approaches for multimodal feature extraction and use the extracted features to train a classifier to identify the sentiment in a meme. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Feature Fusion from Head to Tail for Long-Tailed Visual Recognition

arXiv

引用

arXiv 2023年

作者： Li, Mengke Hu, Zhikai Lu, Yang Lan, Weichao Cheung, Yiu-Ming Huang, Hui Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China

The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://***/Keke921/H2T. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Time-Stretched Imaging Flow Cytometry and Photonic Neuromorphic Processing for Particle Classification

Time-Stretched Imaging Flow Cytometry and Photonic Neuromorp...

引用

Conference on Lasers and Electro-Optics Europe (CLEO EUROPE)

作者： Ioannis Tsilikas Aris Tsirigotis Stavros Deligiannidis Georgios N. Tsigaridas Adonis Bogris Charis Mesaritakis Dept. Physics National Technical University of Athens Athens Zografou Greece Dept. Information and Communication Systems Engineering University of the Aegean Karlovasi Samos Greece Dept. Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (纸本)9798350345995

In this work, we investigate the compression capabilities of a photonic neuromorphic accelerator relying on an optical spectrum slicing technique [1], following a high-flow 1D imaging cytometry setup, able to image 62000 particles/sec. The utilized image scheme relies on a technique, where spatial information is transfered to the spectrum and subsequently through dispersion to the temporal domain. Therefore, it can replace high speed spectrometers with a single photodetector [2]. On the other hand, the elevated image acquisition rate, trigger the generation of a staggering amount of data, which can cause a processing backlog at the digital backend. In this context, we explore, for the first time, the use of a photonic neuromorphic pre-processing unit, following the cytometer that can reduce the number of trainable parameters at a lightweight digital backend by a factor of 2.5, while at the same time, it can project incoming data to a high dimensional space boosting accuracy.

关键词： Cytometry Diffraction gratings Mode-locked fiber lasers Neural networks Photodetectors Spectrometers

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：