检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Hengkai Tan Songming Liu Kai Ma Chengyang Ying Xingxing Zhang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Beijing China

Transformer has shown promise in reinforcement learning to model time-varying features for obtaining generalized low-level robot policies on diverse robotics datasets in embodied learning. However, it still suffers from the issues of low data efficiency and high inference latency. In this paper, we propose to investigate the task from a new perspective of the frequency domain. We first observe that the energy density in the frequency domain of a robot's trajectory is mainly concentrated in the low-frequency part. Then, we present the Fourier Controller Network (FCNet), a new network that uses Short-Time Fourier Transform (STFT) to extract and encode time-varying features through frequency domain interpolation. In order to do real-time decision-making, we further adopt FFT and Sliding DFT methods in the model architecture to achieve parallel training and efficient recurrent inference. Extensive results in both simulated (e.g., D4RL) and real-world environments (e.g., robot locomotion) demonstrate FCNet's substantial efficiency and effectiveness over existing methods such as Transformer, e.g., FCNet outperforms Transformer on multienvironmental robotics datasets of all types of sizes (from 1.9M to 120M). The project page and code can be found https://***/fcnet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ARBS-YOLOv8 for Annotation Box Detection in Colonoscopy CADe Systems

ARBS-YOLOv8 for Annotation Box Detection in Colonoscopy CADe...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Zhang, Ruiyao Yoshida, Naohisa Dohi, Osamu Peng, Boyuan Liu, Xinkai Huang, Jie Zhu, Xin Graduate School of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Japan Department of Molecular Gastroenterology and Hepatology Graduate School of Medical Science Kyoto Prefectural University of Medicine Kyoto Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Tokyo Japan

ISBN: (纸本)9798350350548

Colonoscopy is the gold standard for colorectal lesion detection, with its accuracy directly influencing patient prognosis. The accurate detection of Annotation Boxes in computer-aided Detection (CADe) systems is important for improving their performance in colonoscopy procedures. This research introduces a novel algorithm that combines active learning with a modified YOLOv8 algorithm, named ARBS-YOLOv8 (Active learning with RepVGG Block and SIoU loss function base on YOLOv8), for the detection of Annotation Boxes generated by colonoscopy CADe systems. We compared standard YOLOv8, YOLOv6, YOLOX algorithms and their active learning variants using colonoscopy video data from 31 patients. The active learning method involves analyzing false positives generated by the initially trained model on an active learning dataset. These false detection samples are then reintroduced into the training set as negative examples. This active learning method led to substantial performance improvements across all algorithms, with particularly notable increase in precision. Notably, the application of active learning to YOLOv6 resulted in a significant increase in Precision by 23.28%, reaching 95.79%. Furthermore, when active learning was integrated with YOLOv8, it achieved an impressive F1 Score of 99.70% on the test set. Compared to the standard YOLOv8, ARBS-YOLOv8 demonstrated 0.88% increase in F1 Score while maintaining high Sensitivity. This improvement suggests that ARBS-YOLOv8 is more effective at extracting features from the data and increase the F1 score in detecting Annotation Boxes. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition 48

Front-End Adapter: Adapting Front-End Input of Speech Based ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chen, Xie Ma, Ziyang Tang, Changli Wang, Yujin Zheng, Zhisheng Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-Lance Lab Department of Computer Science and Engineering Shanghai China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9781728163277

Recent years have witnessed a boom in self-supervised learning (SSL) in various areas including speech processing. Speech based SSL models present promising performance in a range of speech related tasks. However, the training of SSL models is computationally expensive and a common practice is to fine-tune a released SSL model on the specific task. It is essential to use consistent front-end input during pre-training and fine-tuning. This consistency may introduce potential issues when the optimal front-end is not the same as that used in pre-training. In this paper, we propose a simple but effective front-end adapter to address this front-end discrepancy. By minimizing the distance between the outputs of different front-ends, the filterbank feature (Fbank) can be compatible with SSL models which are pre-trained with waveform. The experiment results demonstrate the effectiveness of our proposed front-end adapter on several popular SSL models for the speech recognition task. © 2023 IEEE.

关键词： Adapter Automatic Speech Recognition Front-end Feature Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Cyber-attack Detection Using Gradient Clipping Long Short-Term Memory Networks in Internet of Things 1

Cyber-attack Detection Using Gradient Clipping Long Short-Te...

引用

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Ayyalasomayajula, Madan Mohan Tito Mandala, Vishwanadham Prasad, Hanumat Gangopadhyay, Amit Shrivastava, Neeraj Sundaram, Ajith Aspen University School of Business & Technology Department of Computer Science Arizona United States Cummins Inc. IN United States Department of CSE- AI&ML Guntur India Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Department of Electronics and Communication Engineering Andhra Pradesh Tirupati India Medicaps University Indore India Amrita Vishwa Vidyapeetham Amrita Nagar Edappally Amrita School of Business Kochi Kerala Ernakulam India

ISBN: (纸本)9798350367003

The Internet of Things (IoT) is a network that connects a vast number of objects, enabling them to communicate and interact with each other with human intervention. The IoT is seeing rapid growth in the field of computing. However, it is important to acknowledge that IoT is very susceptible to many forms of assaults due to the hostile nature of the internet. In order to address this problem, it is necessary to implement practical steps to ensure the security of IoT networks, such as the implementation of network anomaly detection. While it is impossible to completely prevent assaults indefinitely, timely discovery of an attack is essential for effective defense. Because IoT devices have limited storage and processing power, standard high-end security solutions cannot protect them. In addition, IoT devices are now autonomously linked for extended durations. Consequently, it is necessary to create advanced network-based security solutions such as deep neural network solutions. While several researches have focused on the use of neural network methods for attack detection, there has been less emphasis on detecting assaults, especially in IoT networks. The objective of this research is to develop a gradient clipping long shortterm memory network (GC-LSTM) that can efficiently and promptly identify IoT network assaults. The Bot-IoT dataset is employed for evaluating various detection methodologies. The incorporation of additional features resulted in improved results. The GC-LSTM model, as proposed, achieves a remarkable accuracy of 99.98%, 97.67% of detection rate, 87.34% of TNR and 34.67% of FAR. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Deep CNN based brain tumor detection in intelligent systems

引用

International Journal of Intelligent Networks 2024年第1期5卷 30-37页

作者： Gupta, Brij B. Gaurav, Akshat Arya, Varsha International Center for AI and Cyber Security Research and Innovations & Department of Computer Science and Information Engineering Asia University Taiwan Taichung413 Taiwan Ronin Institute MontclairNJ United States Department of Electrical and Computer Engineering Lebanese American University Beirut1102 Lebanon Symbiosis International University Pune India School of Computing Skyline University College P.O. Box 1797 Sharjah United Arab Emirates Department of Business Administration Asia University Taiwan Taiwan Dehradun India

The early detection of brain tumor is crucial for effective treatment and improved patient prognosis in Industrial Information Systems. This research introduces a novel computational model employing a three-layer Convolutional Neural Network (CNN) for the identification of brain tumors in Industrial Information Systems. Leveraging advanced computational techniques, this proposed model can autonomously detect intricate patterns and features from medical imaging data, resulting in more accurate and expedited diagnoses. With an impressive 90 % precision rate, our model demonstrates the potential to serve as a valuable tool for medical professionals working in the field of neuroimaging. By presenting a dependable and precise computational model, this study contributes to the advancement of brain tumor identification within the domain of medical imaging. We anticipate that our methodology will aid healthcare providers in making more accurate diagnoses, thereby leading to enhanced patient outcomes. Potential avenues for future research encompass refining the model's fundamental architecture and exploring real-time therapeutic applications. © 2024 The Authors

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Attendance System via Internet of Things, Blockchain and Artificial Intelligence Technology: Literature Review 37th

Attendance System via Internet of Things, Blockchain and Art...

引用

37th International Conference on Advanced Information Networking and Applications, aiNA 2023

作者： Abidemi, Sarumi Usman Mubarak, Auwalu Saleh Akanni, Olukayode Ameen, Zubaida Said Cacciagrano, Diletta Al-turjman, Fadi Artifiical Intelligence Engineering Department AI and Robotics Institue Near East University Mersin 10 Nicosia Turkey Computer Science Division School of Science and Technology Camerino University Camerino62032 Italy Research Center for AI and IoT Faculty of Engineering University of Kyrenia Mersin 10 Kyrenia Turkey

ISBN: (纸本)9783031286933

Many researchers have make efforts on creating several attendance systems to keep track of student attendance in school which is also part of academic curriculum that will have great impact in student academic performance. There have been different technologies such as RFID, face recognition, biometric, web-based attendance system etc. To capture attendance in a way that’s better than the traditional method of pen and paper or roll call system. Making this attendance record available on blockchain network and applying artificial intelligence algorithm for prediction or classification in correlation with the data captured from student attendance purpose. Several articles, papers and journals has been reviewed from different research plethora of research publishers’ database through internet such as Google scholar, IEEExplore, Springerslink etc. This will make it easy for comparing several attendance systems with respect to internet of things, blockchain and artificial intelligence to address the research gap in this aspect. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Dynamic Transfer Learning Switching Approach Using Resource Benchmark in Edge Intelligence

引用

IEEE Internet of Things Journal 2025年第13期12卷 25148-25170页

作者： Nkenyereye, Lionel Rajkumar, Chellakannu Lee, Boon Giin Chung, Wan-Young Pukyong National University Artificial Intelligence Convergence Education and Research Group Busan48513 Korea Republic of Pukyong National University Department of Electronic Engineering Busan48513 Korea Republic of University of Nottingham Ningbo China School of Computer Science Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute Ningbo315104 China Pukyong National University Department of AI Convergence Department of Electronic Engineering Busan48513 Korea Republic of

Machine learning (ml) techniques are applied for profiling computing and processing resources data collected while running deep neural network models on edge devices. Adaptive deep neural network (DNN) model switching requires proper benchmarking for categorizing ai models based on their applications and computational resources enabled by their processing accelerators. Based on benchmark metrics, DNN models can be classified into tiny, low, small, medium, and large resources, then identify DNN models that perform well within resource constraints. Ensure efficient resource allocation, latency management, and trade-off between accuracy and resource. In this work, we propose a benchmark for edge transfer artificial intelligence learning service (TALS) that uses ml techniques. They aim at classifying DNN models by their target edge applications while running edge inferences. We used both unsupervised learning (UL) and supervised learning (SL) techniques to identify the most effective features for the TALS models and to benchmark the performance of edge devices. To achieve this, two approaches were investigated: first, determining features based on edge inference’s computing resources profiling using principal component analysis;and second, classifying the DNN models at the target application level using a regression approach based on historical resource utilization data. In addition, we propose a dynamic model transfer learning that switches between a set of pre-trained and optimized and quantized DNN models based on the cost function. ml techniques learn resource-aware prediction from new resource allocation data and ensure that the multicriteria switch cost selects the inference task models that meet the edge resource constraint requirements. The experimental results highlight a strong relationship between the supervised learning model and the clustering execution method. The dynamic switching approach on real edge devices demonstrates dynamic switching between models

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Face-Off: Performance Analysis for Breast Cancer Detection

Machine Learning Face-Off: Performance Analysis for Breast C...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Mohammed Hamza Md Mokhlesur Rahman Md Lutful Kabir Sohag Kabir School of Computer Science AI and Electronics University of Bradford UK Department of Computer Science and Engineering Military Institute of Science and Technology Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Breast cancer (BC) is the most common cancer among women, underscoring the need for accurate and reliable early detection systems. Machine learning (ml) algorithms have shown great promise in healthcare by improving diagnostic methods for various diseases. This study evaluates the performance of several ml classifiers for breast cancer detection by analyzing ultrasound images. The classifiers tested include Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Neural Networks Multi-Layer Perceptron(NNmlP). The dataset was split into various training and testing ratios. Experimental results showed that the NNmlP classifier consistently achieved the highest accuracy, particularly in the 90/10%, 70/30%, and 60/40% splits. The SVM classifier also performed well, especially in the 70/30% split. The study concluded that the 70/30% split is the most effective, yielding the highest accuracy and balanced performance across multiple classifiers. Future studies should concentrate on optimizing hyperparameters, exploring ensemble methods, and enhancing the dataset with additional data augmentation to further boost model performance and reliability in breast cancer diagnosis.

关键词： Support vector machines Accuracy Ultrasonic imaging Artificial neural networks Data augmentation Breast cancer Data models Reliability Ensemble learning Tuning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Protein Structure Prediction in Bioinformatics

Machine Learning Techniques for Protein Structure Prediction...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Abdiqayumovich, Aliyev Nurillo Jaisudha, J. Al-Farouni, Mohammed Khare, Neha Kaur, Gurmandeep Koduru, Siva Sai Fergana Medical Institute Of Public Health Assistants Of The Department Of Biophysics And Information Technologies Fergana Uzbekistan Prince Shri Venkateshwara Padmavathy Engineering College Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Ies University Ies Institute of Technology and Management Department of Computer Science & Engineering M.P. Bhopal India Chandigarh Group of Colleges Chandigarh Engineering College Department of Computer Application Punjab Jhanjeri Mohali140307 India Saveetha Institute of Medical and Technical Sciences Dapartment of Ai & Ml Tamilnadu Chennai India

ISBN: (纸本)9798350390759

This work analyses and discusses the use of machine learning methods in the field of bioinformatics concerning protein structure prediction. The steps of the proposed methodology include: acquiring and cleaning the relevant proteins sequences datasets;and creation and training of deep learning models, including Convolutional Neural Networks (CNNs), and Recurrent Neural Networks, (RNNs). Overall, adding data augmentation and transfer learning boosts the performance of the models to a mean accuracy of 87%. Predictors Evaluation: In evaluating the predictors, the model used an accuracy of 6% and a Matthews correlation coefficient (MCC) of 0. 74. The generality and efficiency of the proposed model are tested and compared with results from other similar standard datasets. Study shows that the results of the model have higher reliability than the traditional method of the machine-learning algorithm especially in the classification of the second and third levels of varied types of proteins. The research will demonstrate the applicability and possibility of the large-scale and cost-efficient approaches to the protein structure prediction using machine learning, while emphasizing the drawbacks of experimental tools. Recommendations for future work are to enhance the interpretability of the resulting models, better combine methods based on the use of information from hybrid schemes with physical models, and use more extensive databases for enhancing accuracy. This research highlights the profound impact that machine learning can have in the field of bioinformatics as a tool to enhance knowledge of such protein structures and to further practice improvements in the understanding of life processes and a and drug design. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Detectability Analysis of ai-generated Research Articles

Detectability Analysis of AI-generated Research Articles

引用

International Conference on computer and Information Technology (ICCIT)

作者： Neeraj Md Mokhlesur Rahman Md Lutful Kabir Sohag Kabir School of Computer Science AI and Electronics University of Bradford UK Department of Computer Science and Engineering Military Institute of Science and Technology Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

The rapid surge of ai-generated content, driven by advanced large language models (LLMs) such as ChatGPT, threatens to undermine academic integrity and redefine the boundaries of plagiarism in scholarly work. This article evaluated the efficacy of five publicly available ai content detection tools in differentiating human-generated content from ai-generated ones. During the assessment, an ai-authored article was analysed using Sapling ai, Turnitin, GPTZero, Copyleaks, and Quillbot tools to assess their effectiveness in detecting ai-generated content. Following the detection reports, the paper was manually revised and resubmitted to the same tools to assess their ability to detect altered ai-authored content. This approach highlighted the susceptibility of these tools to modified texts and emphasised the difficulties in reliably detecting ai-created content. The analysis was conducted using the tools in their default state as black-box systems, without a thorough analysis of their underlying mechanisms or algorithms. Furthermore, the evaluation is confined to a single article on a specific topic, and as such, the performance of the tools assessed cannot be regarded as representative. To gain a comprehensive understanding of the effectiveness of these tools, further research and assessment involving articles from diverse disciplines and a variety of writing styles is essential.

关键词： Generative ai Large language models Plagiarism Writing Chatbots Reliability Artificial intelligence Surges Information technology Monitoring

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：