检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6723-6738页

作者： Qin, Lutong Zhang, Lei Li, Chengrun Song, Chaoda Cheng, Dongzhou Wang, Shuoyuan Wu, Hao Song, Aiguo Nanjing Normal University School of Electrical and Automation Engineering Nanjing210023 China Shanghai200240 China Case Western Reserve University Department of Computer and Data Sciences ClevelandOH44106 United States University of Macau Department of Computer and Information Science Taipa999078 China Yunnan University School of Information Science and Engineering Kunming650500 China Southeast University Department of Instrument Science and Engineering Nanjing210096 China

Recently, deep neural networks have triumphed over a large variety of human activity recognition (HAR) applications on resource-constrained mobile devices. However, most existing works are static and ignore the fact that the computational budget usually changes drastically across various devices, which prevent real-world HAR deployment. It still remains a major challenge: how to adaptively and instantly tradeoff accuracy and latency at runtime for on-device activity inference using time series sensor data? To address this issue, this article introduces a new collaborative learning scheme by training a set of subnetworks executed at varying network widths when fueled with different sensor input resolutions as data augmentation, which can instantly switch on-the-fly at different width-resolution configurations for flexible and dynamic activity inference under varying resource budgets. Particularly, it offers a promising performance-boosting solution by utilizing self-distillation to transfer the unique knowledge among multiple width-resolution configuration, which can capture stronger feature representations for activity recognition. Extensive experiments and ablation studies on three public HAR benchmark datasets validate the effectiveness and efficiency of our approach. A real implementation is evaluated on a mobile device. This discovery opens up the possibility to directly access accuracy-latency spectrum of deep learning models in versatile real-world HAR deployments. © 2020 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Towards Responsible Decisions with Limited Training data Using Human-in-the-Loop 20th

Towards Responsible Decisions with Limited Training Data Us...

引用

20th Principle and Practice of data and Knowledge Acquisition Workshop, PKAW 2024, held in conjunction with the 21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Mahidadia, Ashesh Bain, Michael Suryanto, Hendra Kang, Byeong Guan, Charles Compton, Paul Rich Data Corporation Sydney Australia School of Computer Science and Engineering University of New South Wales Sydney Australia School of Information and Communication Technology University of Tasmania Hobart Australia

ISBN: (纸本)9789819600250

A fundamental issue with machine learning is that the training data must contain sufficient examples of every data pattern of interest for the essentially statistical techniques of machine learning to derive a model that accurately covers all data patterns. For example, in real-world situations, samples from minority populations may not be adequately represented in available training datasets, resulting in models that are biased in favour of majority populations. We present an approach to partially address this problem by using domain knowledge to construct rules to correctly classify, specifically, those cases representing rare patterns in training data that the machine learning model has incorrectly classified. We use Ripple-Down Rules (RDR) to add rules, as it is a proven approach to knowledge acquisition and incremental maintenance that enables rules to be very easily and quickly added to a knowledge base on a case-by-case basis. This paper extends previous work using a human expert by using both artificial and real-world data and a simulated expert to add rules in multiple controlled experiments. Results show that domain knowledge can be successfully used in our approach to mitigate performance issues arising from a limited representation of a subgroup in the available training dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Approximation of Hodgkin-Huxley Model Using Neural Networks 12

Approximation of Hodgkin-Huxley Model Using Neural Networks

引用

12th International Conference on Awareness Science and Technology, iCAST 2023

作者： Li, Qin Zhu, Xin Shen, Wenfeng Graduate School of Computer Science and Engineering The University of Aizu Fukushima Aizu-Wakamatsu Japan School of Computer Engineering and Science Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China

ISBN: (纸本)9798350324693

Simulation of electrophysiological cardiac models plays a critical role in enabling researchers to investigate the heart’s activity under various conditions. In this domain, the cell model assumes a significant position, as its accuracy and complexity have a direct impact on the reliability of simulation outcomes. Presently, most cell models are grounded in the Hodgkin-Huxley theory. However, some of these models prove sensitive to the initial values or time steps utilized in solving ordinary differential equations (ODEs). With the rapid advancements in deep learning, the application of this technology has expanded beyond image processing. In this paper, we propose a novel method to construct a cell model based on a neural network. Through experiments, we demonstrate that our new model exhibits high accuracy and robustness when compared to traditional cell models. The results validate the potential of employing deep learning techniques to enhance the reliability and performance of cardiac simulations, opening new avenues for future research in this domain. © 2023 IEEE.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Intelligent Guitar Chord Recognition Using Spectrogram-Based Feature Extraction and AlexNet Architecture for Categorization

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 758-767页

作者： Korade, Nilesh B. Salunke, Mahendra B. Bhosle, Amol A. Sangve, Sunil M. Joshi, Dhanashri M. Asalkar, Gayatri G. Kadu, Sujata R. Sarwade, Jayesh M. Department of Computer Engineering JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India Department of Computer Engineering PCET’s Pimpri Chinchwad College of Engineering and Research Ravet Maharashtra Pune412101 India Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Bibwewadi Pune411037 India Department of Computer Engineering Terna Engineering College Maharashtra Mumbai India Department of Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Chord prediction plays a key role in the advancement of musical technological innovations, such as automatic music transcription, real-time music tutoring, and intelligent composition tools. Accurate chord prediction can assist musicians, educators, and developers in constructing tools that help in learning, playing, and composing music. Background noise and audio distortions may have an impact on chord prediction accuracy, particularly in real-world situations. Chords can have distinct voicings or finger positions on the guitar, resulting in slight variations in audio representation. This study focuses on the classification of guitar chords using techniques of deep learning. There are eight major and minor guitar chords in the dataset. They have been turned into spectrograms, chromagrams, and Mel Frequency Cepstral Coefficients (MFCC) so that features can be extracted. Various deep learning architectures, including CNN, ResNet50, AlexNet, and VGG, were employed to classify the chords. Experimental results demonstrated that the spectrogram-based AlexNet model outperforms others, achieving good accuracy and robustness in chord classification. The proposed study demonstrates the efficiency of spectrograms and advanced deep learning models for audio signal processing in music applications. By automating chord detection, this study provides beneficial resources for music learners as well as educators, enabling more efficient learning and real-time feedback during practice sessions. © (2025), (Science and Information Organization). All Rights Reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Question-Answering Pair Matching Based on Question Classification and Ensemble Sentence Embedding

引用

computer Systems Science & engineering 2023年第9期46卷 3471-3489页

作者： Jae-Seok Jang Hyuk-Yoon Kwon Department of Computer Science and Engineering Seoul National University of Science and TechnologySeoul01811Korea Department of Industrial Engineering/Graduate School of Data Science Seoul National University of Science and TechnologySeoul01811Korea

Question-answering(QA)models find answers to a given *** necessity of automatically finding answers is increasing because it is very important and challenging from the large-scale QA data *** this paper,we deal with the QA pair matching approach in QA models,which finds the most relevant question and its recommended answer for a given *** studies for the approach performed on the entire dataset or datasets within a category that the question writer manually *** contrast,we aim to automatically find the category to which the question belongs by employing the text classification model and to find the answer corresponding to the question within the *** to the text classification model,we can effectively reduce the search space for finding the answers to a given ***,the proposed model improves the accuracy of the QA matching model and significantly reduces the model inference ***,to improve the performance of finding similar sentences in each category,we present an ensemble embedding model for sentences,improving the performance compared to the individual embedding *** real-world QA data sets,we evaluate the performance of the proposed QA matching *** a result,the accuracy of our final ensemble embedding model based on the text classification model is 81.18%,which outperforms the existing models by 9.81%∼14.16%***,in terms of the model inference speed,our model is faster than the existing models by 2.61∼5.07 times due to the effective reduction of search spaces by the text classification model.

关键词： Question-answering text classification model data augmentation text embedding

来源：评论

学校读者我要写书评

暂无评论

Face micro-expression recognition algorithm based on ResNet depth model 8

Face micro-expression recognition algorithm based on ResNet ...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Wang, Liquan Zhan, Shu Hefei University of Technology Key Laboratory of Big Data Knowledge Engineering Ministry of Education School of Computer and Information Engineering Hefei China

ISBN: (纸本)9798350302455

Micro Expression (ME) is the subtle facial expressions that people show when they express their inner feelings. To address the problem that micro-expression recognition is difficult and less accurate due to the small number of samples and uneven distribution of different categories, we propose a model framework to improve the accuracy of micro-expression recognition. The peak frames containing more key expression information in the micro-expression video sequences are extracted;SE-ResNeXt-50, an improved residual network with SE module, is used to extract features from the peak frames of micro-expressions, where the SE module can better learn the key information in the features, and ResNeXt simplifies the structure by replacing the dense structure with the sparse structure through group convolution, which improves the recognition efficiency. The recognition efficiency is improved by replacing the dense structure with the sparse structure by group convolution. At the same time, the Focal Loss loss function can better solve the model performance problem caused by the imbalance of micro-expression data. Simulation experiments are conducted on the micro-expression dataset CASME, and it is found that the improved residual network and peak frame improve the accuracy and F1 value of micro-expression recognition. The improved residual network and peak frame can reduce the effect of small data set, make the model have good fitting effect, and improve the performance of different categories, improve the recognition accuracy of micro-expressions, and have better recognition performance for micro-expression recognition. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PALCT: vehicle-to-vehicle communication based on pseudonym assignment and encryption scheme using delay minimisation cover tree algorithm

引用

International Journal of Vehicle Information and Communication Systems 2025年第2期10卷 132-147页

作者： Tandon, Righa Gupta, P.K. Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering Jaypee University of Information Technology HP Solan173 234 India Department of Data Science School of Computing Mohan Babu University AP Tirupati517 102 India

Vehicle-to-vehicle communication is one of the new paradigms of networking, which should be secure, fast, and efficient. In this paper, we propose a framework that implements the pseudonym-based authentication scheme in which communication among vehicles is encrypted by using a matrix array symmetric key (MASK), digital signature algorithm (DSA), and intelligent water drop (IWD). The proposed security scheme also ensures the handling of many security attacks like key-guessing, non-repudiation, replay, and modification. In the proposed scheme, to preserve the identity of the vehicle, we have provided the different pseudonyms for each vehicle in the network that ensure secure communication among vehicles. Furthermore, the proposed delay minimisation cover tree algorithm ensures the issue of timed delay during vehicle-to-vehicle communication. In this algorithm, we have used Dijkstra’s algorithm for finding the optimal shortest path during vehicular communication. The results obtained show that the proposed scheme is effective and efficient, as it reduces the time delay by 4% for 140 vehicle nodes and 28.4% for 1000 vehicle nodes. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

A DL Intrusion Detection Method for Low-Rate Denial of Service Attacks

A DL Intrusion Detection Method for Low-Rate Denial of Servi...

引用

2023 Asia-Pacific Conference on Image Processing, Electronics and computers, IPEC 2023

作者： Wu, Yuhong Lv, Yunshan Hu, Xiangdong School of Big Data & Computer Science Engineering Chongqing College of Mobile Communication China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Key Laboratory of Public Big Data Security Technology Chongqing Chongqing China School of Big Data & Computer Science Engineering Chongqing College of Mobile Communication Key Laboratory of Public Big Data Security Technology Chongqing China School of Automation Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9781665457033

Denial of service (DoS) attacks is among the most harmful network threats. Low-rate DoS (LDoS) attacks feature good concealment and are likely to evade detection by conventional signal analysis-based methods. A LDoS attack detection method that combines the convolutional neural network and the gated recurrent unit is proposed in the present work. To evaluate the proposed method, we collect real user traffic from a university's website, label the traffic with LDoS attacks as normal traffic. In order to get the real attack traffic, this paper has collected some new LDoS attack programs, such as slowloris, slowhttptest, pwnlloris, torhammer and httplog, which can be obtained from public channels, and constructed a LAN environment that conformed to the working scenario of the program. By running the attack program, the attack traffic could be obtained. In a large sample scenario, the average detection rate of our proposed method can reach 98.68%. This article focuses on the research: the average detection rate of the detection method proposed in this article in the case that the security agency can only intercept a small number of attack samples. That is, in the small sample scenario, the detection of the collected traffic shows that the average detection rate of the proposed detection method can reach 89.54% in a small sample scenario. Its effective detection rate is obviously superior to the existing similar detection methods. © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Automode: The Automatic LoRA Based on Stable Diffusion

Automode: The Automatic LoRA Based on Stable Diffusion

引用

International Conference on Vision, Image and Signal Processing (ICVISP)

作者： Yao Wu Yifan Lu School of Computer and Data Engineering NingboTech University Hangzhou China School of Computer and Data Engineering NingboTech University Ningbo China

ISBN: (数字)9798331541460

ISBN: (纸本)9798331541477

Stable Diffusion is a powerful tool for image generation but encounters difficulties in generating images of untrained subjects, such as newly introduced customized content. Traditional fine-tuning methods often require the manual creation of datasets, followed by computationally expensive full-parameter training or low-rank adaptation, as seen in LoRA. While LoRA mitigates the cost associated with full-parameter training, traditional methods still face challenges regarding scalability and efficiency. To address these limitations, we introduce a novel automated annotation pipeline that integrates an advanced attention-based image captioning system with LoRA-based fine-tuning. Our approach not only automates the annotation process but also optimizes training by reducing the parameter space, leading to more efficient and scalable fine-tuning. We validated our approach using a custom dataset of newly introduced customized content, demonstrating significant improvements in both annotation efficiency and image generation quality. This work extends the capabilities of automated fine-tuning in generative models, providing a reliable solution for artificial content creation.

关键词： Training Costs Annotations Image synthesis Scalability Pipelines Manuals Signal processing Reliability Faces

来源：评论

学校读者我要写书评

暂无评论

Real-Time Pothole Detection at night to prevent road accidents using YOLOV5 6

Real-Time Pothole Detection at night to prevent road acciden...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Mandal, Gouranga De, Anurag Dey, Arindam Gangarapu, Sudeepthi Chekuru, Sharmila Rani Nandini, Chekuri Vellore Institute of Technology School of Computer Science and Engineering Andhra Pradesh 522237 India Vellore Institute of Technology School of Computer Science and Engineering with Specialization in Data Analytics Andhra Pradesh 522237 India

ISBN: (纸本)9798350394702

This article proposes a technique to create a pothole detection system that can operate both during the day and at night. This model was developed using the real-time object identification YOLO (You Only Look Once) technique. The potholes are located using a pre-trained model with YOLO v5. In its creation, the PyTorch framework is utilized. The first YOLO model created using the PyTorch framework is YOLOv5, which is a lot more user-friendly and lightweight. In a manner similar to real-time object detection systems, the proposed method displays potholes in real time and emphasizes them with boundary boxes for accurate identification. The accuracy achieved with this method is 97% during the day and 92% at night which is found to be satisfactory. © 2023 IEEE.

关键词： Image acquisition

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：