检索结果-内蒙古大学图书馆

47th IEEE International Conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Horiguchi, Shota Takashima, Yuki Garcia, Paola Watanabe, Shinji Kawaguchi, Yohei Hitachi Ltd Hitachi Ibaraki Japan Johns Hopkins Univ CLSP & HLTCOE Baltimore MD 21218 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781665405409

Recent progress on end-to-end neural diarization (EEND) has enabled overlap-aware speaker diarization with a single neural network. This paper proposes to enhance EEND by using multi-channel signals from distributed microphones. We replace Transformer encoders in EEND with two types of encoders that process a multichannel input: spatio-temporal and co-attention encoders. Both are independent of the number and geometry of microphones and suitable for distributed microphone settings. We also propose a model adaptation method using only single-channel recordings. With simulated and real-recorded datasets, we demonstrated that the proposed method outperformed conventional EEND when a multi-channel input was given while maintaining comparable performance with a single-channel input. We also showed that the proposed method performed well even when spatial information is inoperative given multi-channel inputs, such as in hybrid meetings in which the utterances of multiple remote participants are played back from the same loudspeaker.

关键词： Speaker diarization multi-channel distributed microphones EEND

来源：评论

学校读者我要写书评

暂无评论

Learning from distributed Users in Contextual Linear Bandits Without Sharing the Context 36

Learning from Distributed Users in Contextual Linear Bandits...

引用

36th Conference on neural Information processing Systems (NeurIPS)

作者： Hanna, Osama A. Yang, Lin F. Fragouli, Christina Univ Calif Los Angeles Los Angeles CA USA

ISBN: (纸本)9781713871088

Contextual linear bandits is a rich and theoretically important model that has many practical applications. Recently, this setup gained a lot of interest in applications over wireless where communication constraints can be a performance bottleneck, especially when the contexts come from a large d-dimensional space. In this paper, we consider a distributed memoryless contextual linear bandit learning problem, where the agents who observe the contexts and take actions are geographically separated from the learner who performs the learning while not seeing the contexts. We assume that contexts are generated from a distribution and propose a method that uses approximate to 5d bits per context for the case of unknown context distribution and 0 bits per context if the context distribution is known, while achieving nearly the same regret bound as if the contexts were directly observable. The former bound improves upon existing bounds by a log(T) factor, where T is the length of the horizon, while the latter achieves information theoretical tightness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Moving Target Defense Approach for the distributed Dynamic network 21

A Moving Target Defense Approach for the Distributed Dynamic...

引用

21st IEEE International Symposium on Parallel and distributed processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhang, Lin Guo, Yunchuan Leng, Siyuan Li, Zifu Li, Fenghua Fang, Liang Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China

ISBN: (纸本)9798350329223

The distributed dynamic network is vulnerable to scanning attacks due to the openness of wireless channels. Traditional defense systems tend to be passive and exhibit delayed responses. A moving target defense approach, namely distributed network Address Shuffling (DNAS), is proposed to thwart attackers' network scanning through the shuffling of network addresses. To resolve address conflicts resulting from this shuffling, DNAS employs a dynamic diffusion method of allocated addresses before the shuffling process to reduce the probability of conflict generation, and utilizes a passive detection based conflict elimination algorithm after the shuffling process to eliminate any generated conflicts. To select low-risk addresses, DNAS leverages an artificial feature selection based Fully Connected neural network (FCNN) to recognize the attacker's scanning policy, and identifies low-risk addresses based on the scanning range of the policy. Empirical experiments and theoretical analysis indicate that DNAS significantly reduces the probability of address conflict generation at a minimal cost. It effectively eliminates all generated address conflicts within an average conflict resolution time of less than 500ms. Furthermore, DNAS exhibits an accuracy of 99.45% in recognizing scanning policies, surpassing pseudorandom address hopping in diminishing the success rate of sequential, local random, and mixed scanning. © 2023 IEEE.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

Application of the time-distributed layer in the controller of memory-augmented neural networks to classify brain activities into motor imagery and motor execution

引用

APPLIED SOFT COMPUTING 2024年 162卷

作者： Karimian-Kelishadrokhi, Morteza Safi-Esfahani, Faramarz Islamic Azad Univ Fac Comp Engn Najafabad Branch Najafabad Iran Islamic Azad Univ Big Data Res Ctr Najafabad Branch Najafabad Iran

Brain-Computer Interface (BCI) systems create a bridge between the human brain and the outside world, potentially rendering traditional methods of information transmission obsolete in the not-so-distant future. One of the key research areas in BCI is the classification of brain activity in electroencephalographic (EEG) data. On the other hand, new memory-augmented neural networks, such as the neural Turing Machine (NTM) and the Differentiable neural Computer (DNC), have demonstrated their impressive abilities in solving complex tasks. Therefore, it is useful to evaluate the capability of memory-augmented neural networks to enhance the classification of brain activity within EEG signals. Previous methods have suffered from low accuracy and generalizability in classifying brain activities;primarily due to a lack of proper classification of Motor Imagery/ Execution brain activities, an inability to extract valuable information at different time steps in time series data, and a failure to learn from longer dependencies. This article introduces TDMANN (Time-distributed Memory Augmented neural network), a framework that leverages the principles of NTM and DNC for the binary classification of brain activities in EEG signals. The controller component of the memory-augmented neural network is enhanced with a time-distributed approach, which significantly improves the performance of the network in binary classification tasks involving motor imagery/execution brain activities by extracting valuable information at each time step. The benchmark datasets used in this study are EEGmmidb BCI2000 (Imagery/Execution), BCI IV 2B, and BCI IV 2A, all containing motor imagery/execution brain activity data in EEG format. The results demonstrate that the classification accuracy achieved by the proposed DNC@TDMANN method exhibits a maximum improvement of 23.03% compared to baseline research works. The NTM@TDMANN method also shows a maximum improvement accuracy of 22.5%.

关键词： Brain-Computer Interface (BCI) Differentiable neural Computer (DNC) EEG Signals Motor Imagery/Execution Brain Activities neural Turing Machine (NTM) Signal processing Time distributed

来源：评论

学校读者我要写书评

暂无评论

CD-Sched: An Automated Scheduling Framework for Accelerating neural network Training on Shared Memory CPU-DSP Platforms

CD-Sched: An Automated Scheduling Framework for Accelerating...

引用

2023 International Conference on Power, Communication, Computing and networking Technologies, PCCNT 2023

作者： Xiao, Yuanyuan Lai, Zhiquan Li, Dongsheng National Key Laboratory of Parallel and Distributed Processing Computer College National University of Defense Technology Changsha China

ISBN: (纸本)9781450399951

DSP holds significant potential for important applications in Deep neural networks. However, there is currently a lack of research focused on shared-memory CPU-DSP heterogeneous chips. This paper proposes CD-Sched, an automated scheduling framework that aims to address this gap. By predicting the latency of operators on both CPU and DSP, CD-Sched automatically schedules the computation of operators to the appropriate computing device. This scheduling optimization accelerates the computation of individual operators and ultimately improves the overall training time of neural networks. In end-to-end training tasks, CD-Sched can significantly reduce the overall training time, with an average reduction of approximately 10.77%. © 2023 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Image Captioning with InceptionV3, LSTM, and PySpark Integration 3

Intelligent Image Captioning with InceptionV3, LSTM, and PyS...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Kurian, Thanu Mathew, Jimsha K. Syam Dev, R.S. Anand, P.K. Vignesh, A. Rakshith, B.S. New Horizon College of Engineering Dept of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798331515911

Image captioning is a challenging task in artificial intelligence that involves generating descriptive captions for images automatically. In this project, we propose a novel approach leveraging advanced technologies such as PySpark, LSTM, and InceptionV3 to develop an effective image captioning system. We harness the power of PySpark, a distributed computing framework, to efficiently process large-scale image datasets and extract high-level features from images using the InceptionV3 convolutional neural network (CNN) model. These features capture the semantic information present in the images and serve as input to the caption generation model. The caption generation model utilizes LSTM neural network as the decoder component. LSTM is well-suited for sequential data processing and is capable of generating coherent and contextually relevant captions based on the extracted image features. The InceptionV3 model acts as the encoder, extracting meaningful visual features from input images, while the LSTM decoder generates captions by decoding these features into natural language descriptions. This multimodal approach enables the model to understand and describe the content of images accurately. Through experimentation and evaluation on diverse image datasets, our proposed system demonstrates promising results in generating accurate and human-like captions for a wide range of images. By integrating PySpark, LSTM, and InceptionV3, our image captioning system achieves state-of-the-art performance, highlighting the effectiveness of leveraging advanced technologies in solving complex AI tasks. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fused feature extract method for 40-OTDR event recognition based on VGGish transfer learning

引用

APPLIED OPTICS 2024年第20期63卷 5411-5420页

作者： Gan, Jiaqi Xiao, Yueyu Zhang, Andong Shanghai Univ Key Lab Specialty Fiber Opt Opt Access Networks Sh Shanghai 200444 Peoples R China Shanghai Univ Joint Int Res Lab Specialty Fiber Opt & Adv Commun Shanghai 200444 Peoples R China Shanghai Univ Inst Fiber Opt Shanghai 200444 Peoples R China

Thanks to the development of artificial intelligence algorithms, the event recognition of distributed optical fiber sensing systems has achieved high classification accuracy on many deep learning models. However, the large-scale samples required for the deep learning networks are difficult to collect for the optical fiber vibration sensing systems in actual scenarios. An overfitting problem due to insufficient data in the network training process will reduce the classification accuracy. In this paper, we propose a fused feature extract method suitable for the small dataset of 40-OTDR systems. The high-dimensional features of signals in the frequency domain are extracted by a transfer learning method based on the VGGish framework. Combined with the characteristics of 12 different acquisition points in the space, the spatial distribution characteristics of the signal can be reflected. Fused with the spatial and temporal features, the features undergo a sample feature correction algorithm and are used in a SVM classifier for event recognition. Experimental results show that the VGGish, a pre-trained convolutional network for audio classification, can extract the knowledge features of 40-OTDR vibration signals more efficiently. The recognition accuracy of six types of intrusion events can reach 95.0% through the corrected multi-domain features when only 960 samples are used as the training set. The accuracy is 17.7% higher than that of the single channel trained on VGGish without fine-tuning. Compared to other CNNs, such as ResNet, the feature extract method proposed can improve the accuracy by at least 4.9% on the same dataset. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Deep learning Machine learning neural networks Optical fibers Pattern recognition Signal processing

来源：评论

学校读者我要写书评

暂无评论

BHMVD: Binary Code-based Hybrid neural network for Multiclass Vulnerability Detection 20

BHMVD: Binary Code-based Hybrid Neural Network for Multiclas...

引用

20th IEEE Int Symposium on Parallel and distributed processing with Applicat / 15th IEEE Int Conf on Social Comp and networking / 12th IEEE Int Conf on Big Data and Cloud Comp / 12th IEEE Int Conf on Sustainable Comp and Commun

作者： Cui, Ningning Chen, Liwei Du, Gewangzi Wu, Tongshuai Zhu, Chenguang Shi, Gang Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9781665464970

Precise binary code vulnerability detection is a significant research topic in software security. Currently, the majority of software is released in binary form, and the corresponding vulnerability detection approaches for binary code are desired. Existing deep learning-based detection techniques can only detect binary code vulnerabilities but cannot precisely identify the types of vulnerabilities. This paper proposes a Binary code-based Hybrid neural network for Multiclass Vulnerability Detection, dubbed BHMVD. BHMVD generates binary slices according to the control dependence and data dependence of library/API function calls, and then extracts syntax features from binary slices to generate type slices, which can help identify vulnerability types. This paper uses a hybrid neural network of CNN-BLSTM to extract vulnerability features from binary and type slices. The former extracts local features, while the latter extracts global features. Experiment results on 19 types of vulnerabilities show that BHMVD is effective for binary code-based multiclass vulnerability detection, and using a hybrid neural network can improve detection ability.

关键词： Binary Code Multiclass Vulnerability Detection Hybrid neural network Type Slices Binary Slices

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Scheduling of Hybrid DNN Tasks in Embedded Real-Time Systems 29

Hierarchical Scheduling of Hybrid DNN Tasks in Embedded Real...

引用

29th IEEE International Conference on Parallel and distributed Systems, ICPADS 2023

作者： Feng, Jiaxin Zhu, Kun Zhang, Tong Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9798350330717

With the widespread application of deep learning (DL) technology in the modern Internet of Things (IoT) areas such as autonomous driving, smart cities and homes, embedded real-time systems are increasingly used at the edge of the network to complete various hybrid DNN tasks. Although embedded real-time systems are equipped with heterogeneous CPU and GPU cores to reduce the response time of inference jobs, the computing resources of heterogeneous devices are not fully utilized, and there is still plenty of room for schedulability to be improved. In this paper, we propose a layer-based hybrid deep neural network (DNN) tasks scheduling algorithm in embedded real-time systems (LHTS) that maps DNN layers to CPU and GPU devices and regulates their start time to avoid confliction. We evaluate LHTS through extensive simulations. The experimental results show that LHTS can achieve more sufficient use of heterogeneous CPU and GPU resources in embedded real-time systems, reduce the worst-case execution time and enhance the schedulability performance of hybrid DNN tasks. © 2023 IEEE.

关键词： deep neural network optimization real-time system resource allocation task scheduling

来源：评论

学校读者我要写书评

暂无评论

Scalable Perception-Action-Communication Loops With Convolutional and Graph neural networks

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION processing OVER networkS 2022年 8卷 12-24页

作者： Hu, Ting-Kuei Gama, Fernando Chen, Tianlong Zheng, Wenqing Wang, Zhangyang Ribeiro, Alejandro Sadler, Brian M. Texas A&M Univ Dept Comp Sci & Engn College Stn TX 77843 USA Rice Univ Dept Comp & Elect Engn Houston TX 77005 USA Univ Texas Austin Dept Elect & Comp Engn Austin TX 78712 USA Univ Penn Dept Elect & Syst Engn Philadelphia PA 19104 USA US Army Res Lab Adelphi MD 20783 USA

In this paper, we present a perception-action-communication loop design using Vision-based Graph Aggregation and Inference (VGAI). This multi-agent decentralized learning-to-control framework maps raw visual observations to agent actions, aided by local communication among neighboring agents. Our framework is implemented by a cascade of a convolutional and a graph neural network (CNN/GNN), addressing agent-level visual perception and feature learning, as well as swarm-level communication, local information aggregation and agent action inference, respectively. By jointly training the CNN and GNN, image features and communication messages are learned in conjunction to better address the specific task. We use imitation learning to train the VGAI controller in an offline phase, relying on a centralized expert controller. This results in a learned VGAI controller that can be deployed in a distributed manner for online execution. Additionally, the controller exhibits good scaling properties, with training in smaller teams and application in larger teams. Through a multi-agent flocking application, we demonstrate that VGAI yields performance comparable to or better than other decentralized controllers, using only the visual input modality and without accessing precise location or motion state information.

关键词： Vision based control graph neural networks convolutional neural networks flocking decentralized control

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：