检索结果-内蒙古大学图书馆

A Deep Residual-based Model on Multi-Branch Aggregation for Stress and Emotion Recognition through Biosignals 19

A Deep Residual-based Model on Multi-Branch Aggregation for ...

19th International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Mekruksavanich, Sakorn Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665485845

Stress and emotion recognition (SER) is a rapidly growing field of study that has applications in various areas, including psychological wellbeing, rehabilitative services, athletic training, and human-computer interaction. Biological information such as the electrocardiogram (ECG), electromyography (EMG), and electrodermal activity (EDA) has been frequently utilized for the SER for learning-based approaches. This study introduces a convolutional neural network motivated by ResNeXt to facilitate multimodal awareness. The proposed model, named StressNeXt, can extract high-level insights from raw bio-signal signals and classify emotional expressions effectively. We undertake a series of investigations using a publicly released standard dataset (WESAD) to determine the optimal implementation of the proposed solution for recognizing stress and emotion. After incorporating preliminary fusion events, we examined deep learning models using 5-fold cross-validation. Our study demonstrates that the suggested technique can comprehend robust multimodal representations with an accuracy of 87.73% utilizing EDA. Additionally, the identification was designed to provide better to 99.92% by fusing with accelerometer sensor data. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Sparse is enough in fine-tuning pre-trained large language models 24

Sparse is enough in fine-tuning pre-trained large language m...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Weixi Song Zuchao Li Lefei Zhang Hai Zhao Bo Du National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan P. R. China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan P. R. China and Hubei Luojia Laboratory Wuhan P. R. China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai P. R. China

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pretrained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscillations in the loss landscape and the quasi-sparsity in gradient distribution. Based on this, we propose a gradient-based sparse finetuning algorithm, named Sparse Increment Fine-Tuning (SIFT), and validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning. The code is accessible at https://***/song-wx/SIFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Effect of Sensor Placement for Accurate Fall Detection based on Deep Learning Model

The Effect of Sensor Placement for Accurate Fall Detection b...

引用

2022 research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

The development of inertial sensor technology and the growing utilization of wearable electronics (such as smartwatches, smart bands, and other intelligent gadgets) have facilitated the advancement of studies into automated Fall Detection Systems (FDSs). In the last decade, there has been significant scientific interest in maintaining FDSs. Focused on assessing the data acquired by wearable inertial sensors, machine learning (ML) techniques have demonstrated high efficacy in distinguishing falls from typical motions or activities of daily living (ADLs). In most research, unfortunately, the effectiveness of machine learning classifiers was constrained by feature extraction and selection processes that relied on human-made decisions. Recently, deep learning (DL) model findings s how their effectiveness for FDS. One of these effective DL models is the ResNeXt model, a deep neural network that operates based on convolutional layers with aggregated residual transformation. This study investigates the influence of sensor placement on various body locations for the fall detection issue. The ResNeXt model was assessed and compared to other baseline deep learning algorithms using the public UMAFall dataset for fall detection. Employing sensor data on waist location, the suggested model attained the most significant classification ac curacy of 97.275% when classifying falls. © 2022 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Tackling the Qubit Mapping Problem with Permutation-Aware Synthesis

arXiv

引用

arXiv 2023年

作者： Liu, Ji Younis, Ed Weiden, Mathias Hovland, Paul Kubiatowicz, John Iancu, Costin Mathematics and Computer Science Division Argonne National Laboratory United States Computational Research Division Lawrence Berkeley National Laboratory United States Department of Electrical Engineering and Computer Science University of California Berkeley United States

We propose a novel hierarchical qubit mapping and routing algorithm. First, a circuit is decomposed into blocks that span an identical number of qubits. In the second stage permutation-aware synthesis (PAS), each block is optimized and synthesized in isolation. In the third stage a permutation-aware mapping (PAM) algorithm maps the blocks to the target device based on the information from the second stage. Our approach is based on the following insights: (1) partitioning the circuit into blocks is beneficial for qubit mapping and routing;(2) with PAS, any block can implement an arbitrary input → output qubit mapping (e.g., q0 → q1) that reduces the gate count;and (3) with PAM, for two adjacent blocks we can select input-output permutations that optimize each block together with the amount of communication required at the block boundary. Whereas existing mapping algorithms preserve the original circuit structure and only introduce "minimal" communication via inserting SWAP or bridge gates, the PAS+PAM approach can additionally change the circuit structure and take full advantage of hardware-connectivity. Our experiments show that we can produce better-quality circuits than existing mapping algorithms or commercial compilers (Qiskit, TKET, BQSKit) with maximum optimization settings. For a combination of benchmarks we produce circuits shorter by up to 68% (18% on average) fewer gates than Qiskit, up to 36% (9% on average) fewer gates than TKET, and up to 67% (21% on average) fewer gates than BQSKit. Furthermore, the approach scales, and it can be seamlessly integrated into any quantum circuit compiler or optimization infrastructure. Copyright © 2023, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes

arXiv

引用

arXiv 2023年

作者： Li, Yunhao Xiao, Zhen Yang, Lin Meng, Dan Zhou, Xin Fan, Heng Zhang, Libo The Department of State Key Laboratory of Computer Science Institute of Software Chinese Academy of Science China Turing Quantum Company United States OPPO Research Institute The Department of Computer Science and Engineering University of North Texas Denton United States

Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender, hairstyle, body shape, and clothing features, which contain rich and high-level information, have been less explored. To address this gap, we propose a simple, effective, and generic method to predict pedestrian attributes to support general Re-ID embedding. We first introduce AttMOT, a large, highly enriched synthetic dataset for pedestrian tracking, containing over 80k frames and 6 million pedestrian IDs with different time, weather conditions, and scenarios. To the best of our knowledge, AttMOT is the first MOT dataset with semantic attributes. Subsequently, we explore different approaches to fuse Re-ID embedding and pedestrian attributes, including attention mechanisms, which we hope will stimulate the development of attribute-assisted MOT. The proposed method AAM demonstrates its effectiveness and generality on several representative pedestrian multi-object tracking benchmarks, including MOT17 and MOT20, through experiments on the AttMOT dataset. When applied to state-of-the-art trackers, AAM achieves consistent improvements in MOTA, HOTA, AssA, IDs, and IDF1 scores. For instance, on MOT17, the proposed method yields a +1.1 MOTA, +1.7 HOTA, and +1.8 IDF1 improvement when used with FairMOT. To encourage further research on attribute-assisted MOT, we will release the AttMOT dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Multi-resolution CNN for Lower Limb Movement Recognition Based on Wearable Sensors 1

引用

15th Multi-disciplinary International Conference on Artificial Intelligence, MIWAI 2022

作者： Hnoohom, Narit Chotivatunyu, Pitchaya Mekruksavanich, Sakorn Jitpattanakul, Anuchit Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Mahidol University Nakorn Pathom Thailand Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9783031209925

ISBN: (纸本)9783031209918

Human activity recognition (HAR) remains a difficult challenge in human-computer interaction (HCI). The Internet of Healthcare Things (IoHT) and other technologies are expected to be used primarily in conjunction with HAR to support healthcare and elder care. In HAR research, lower limb movement recognition is a challenging research topic that can be applied to the daily care of the elderly, fragile, and disabled. Due to recent advances in deep learning, high-level autonomous feature extraction has become feasible, which is used to increase HAR efficiency. Deep learning approaches have also been used for sensor-based HAR in various domains. This study presents a novel method that uses convolutional neural networks (CNNs) with different kernel dimensions, referred to as multi-resolution CNNs, to detect high-level features at various resolutions. A publicly available benchmark dataset called HARTH was used to evaluate the recognition performance to collect acceleration data of the lower limb movements of 22 participants. The experimental results show that the proposed approach improves the F1 score and achieves a higher score of 94.76%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

New Decision-Making Technique Based on Hurwicz Criteria for Fuzzy Ranking

引用

computers, Materials & Continua 2022年第12期73卷 4595-4609页

作者： Deepak Sukheja Javaid Ahmad Shah G.Madhu K.Sandeep Kautish Fahad A.Alghamdi Ibrahim.S.Yahia El-Sayed M.El-Kenawy Ali Wagdy Mohamed Department of Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadIndia Department of Mathematics Dr.APJ Abdul Kalam University Indore(M.P)India Department of Information Technology VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadIndia LBEF Campus Kathmandu44600Nepal Department of Management Information Systems College of Applied Studies and Community ServiceImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia Laboratory of Nano-Smart Materials for Science and Technology(LNSMST) Department of PhysicsFaculty of ScienceKing Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Research Center for Advanced Materials Science(RCAMS) King Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Nanoscience Laboratory for Environmental and Biomedical Applications(NLEBA) Semiconductor Lab.Department of PhysicsFaculty of EducationAin Shams UniversityRoxyCairo 11757Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Department of Mathematics and Actuarial Science School of Sciences Engineering The American University in CairoEgypt

Efficient decision-making remains an open challenge in the research community,and many researchers are working to improve accuracy through the use of various computational *** this case,the fuzzification and defuzzification processes can be very *** is an effective process to get a single number from the output of a fuzzy *** defuzzification as a center point of this research paper,to analyze and understand the effect of different types of vehicles according to their *** this paper,the multi-criteria decision-making(MCDM)process under uncertainty and defuzzification is discussed by using the center of the area(COA)or ***,to find the best solution,Hurwicz criteria are used on the defuzzified ***-making technique is proposed using Hurwicz criteria for triangular and trapezoidal fuzzy *** proposed technique considers all types of decision makers’perspectives such as optimistic,neutral,and pessimistic which is crucial in solving decisionmaking problems.A simple case study is used to demonstrate and discuss the Centroid Method and Hurwicz Criteria for measuring risk attitudes among *** significance of the proposed defuzzification method is demonstrated by comparing it to previous defuzzification procedures with its application.

关键词： Defuzzification decision-making fuzzy numbers Hurwicz multicriteria decision-making ranking order

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoder

arXiv

引用

arXiv 2024年

作者： Han, Tingxu Huang, Shenghan Ding, Ziqi Sun, Weisong Feng, Yebo Fang, Chunrong Li, Jun Qian, Hanwei Wu, Cong Zhang, Quanjun Liu, Yang Chen, Zhenyu The State Key Laboratory for Novel Software Technology Nanjing University Jiangsu210093 China The School of Computer Science University of New South Wales NSW2052 Australia The School of Computer Science and Engineering Nanyang Technological University Nanyang639798 Singapore The Department of Computer Science The Director of the Network & Security Research Laboratory The University of Oregon United States

With the development of deep learning, self-supervised learning (SSL) has become particularly popular. SSL pre-trains an encoder (e.g., an image encoder) to learn generic features from a large amount of unlabeled data, releases it on a third-party platform, and allows any downstream task (e.g., an image classification task) to further fine-tune the encoder with task-specific data to derive the model for the task. However, despite the tremendous performance improvements it brings, SSL faces serious security risks. An adversary can poison pre-training datasets used to pre-train an encoder or publish a poisoned encoder directly to third-party platforms, which will also poison the model for any downstream task that uses these encoders. In this paper, we study a defense against poisoned encoders in SSL called distillation, which is a defense used in supervised learning originally. Distillation aims to distill knowledge from a given model (a.k.a the teacher net) and transfer it to another (a.k.a the student net). Now, we use it to distill benign knowledge from poisoned pre-trained encoders and transfer it to a new encoder, resulting in a clean pre-trained encoder. In particular, we conduct an empirical study on the effectiveness and performance of distillation against poisoned encoders. Using two state-of-the-art backdoor attacks against pre-trained image encoders and four commonly used image classification datasets, our experimental results show that distillation can reduce attack success rate from 80.87% to 27.51% while suffering a 6.35% loss in accuracy. Moreover, we investigate the impact of three core components of distillation on performance: Teacher net, student net, and distillation loss. By comparing 4 different teacher nets, 3 student nets, and 6 distillation losses, we find that fine-tuned teacher nets, warm-up-training-based student nets, and attention-based distillation loss perform best, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Cyber Deception System based on Monte Carlo Simulation in the Mobile Edge Computing (MEC)

Cyber Deception System based on Monte Carlo Simulation in th...

引用

International Conference on computer, Information and Telecommunication Systems (CITS)

作者： Joelle Kabdjou Elie Fute Tagne Danda B. Rawat Jaime Acosta Charles Kamhoua Department of Mathematics and Computer Science University of Dschang Dschang Cameroon Department of Computer Engineering University of Buea Buea Dschang Cameroon Department of Electrical Engineering and Computer Science Howard University Washington USA DEVCOM Army Research Laboratory Network Security Branch Adelphi US

The frequency of malicious activities by cyber attackers is on the rise, posing a significant challenge to counter cyber attacks in the Mobile Edge Computing (MEC) environment. The vulnerability of wireless networks, which serve as the primary communication media for MEC servers and IoT applications, is due to their open nature of communication. This work proposes a MEC architecture that utilizes Network Function Virtualization (NFV) and Service Function Chain (SFC) to combat cyber adversaries. Additionally, we evaluate the performance of a cyber deception system, which leverages a software-defined networking (SDN) controller and decision- maker to continuously monitor incoming MEC traffic and direct cyber adversaries to a deception MEC server. The deception MEC server collects information about cyber adversaries' intent, capabilities, and potential damage to the system, thus securing legitimate users from cyber attacks. The proposed approach was evaluated using Monte Carlo simulations, and numerous results were obtained which demonstrate the effectiveness of cyber deception in MEC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction

arXiv

引用

arXiv 2023年

作者： Peng, Tianshuo Li, Zuchao Zhang, Lefei Du, Bo Zhao, Hai National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Luojia Laboratory Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Universal Information Extraction (UIE) has been introduced as a unified framework for various Information Extraction (IE) tasks and has achieved widespread success. Despite this, UIE models have limitations. For example, they rely heavily on span boundaries in the data during training, which does not reflect the reality of span annotation challenges. Slight adjustments to positions can also meet requirements. Additionally, UIE models lack attention to the limited span length feature in IE. To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework. Specifically, our contribution consists of two concepts: fuzzy span loss and fuzzy span attention. Our experimental results on a series of main IE tasks show significant improvement compared to the baseline, especially in terms of fast convergence and strong performance with small amounts of data and training epochs. These results demonstrate the effectiveness and generalization of FSUIE in different tasks, settings, and scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval

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：