检索结果-内蒙古大学图书馆

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Iwata, Takahiro Yoshioka, Seankein Miki, Daisuke Graduate School of Computer Science Chiba Institute of Technology Chiba Japan Chiba Institute of Technology Department of Computer Science Chiba Japan

ISBN: (纸本)9798350373332

In recent years, neural networks in deep reinforce-ment learning (D RL) have achieved success in various tasks, owing to their high expressiveness and flexibility. Neural networks are expected to be increasingly used for robot control. However, large neural networks consume a significant amount of power during training and operation. Given that the power supply that can be installed in robots is limited, challenges remain in the practical application of robot control using DRL, which includes large-scale neural networks. Conversely, spiking neural networks (SNNs) have high power efficiency, which is achieved through dedicated computational elements. Previous studies reported that SNNs can be applied to DRL to learn a robot's walking motion in a virtual environment and reduce energy consumption. Although previous studies have applied SNNs to DRL, they have the drawback of recursive computation, causing output delays. In this study, we propose a method that combines SNNs with a structure that addresses the issues of previous studies using a twin-delayed deep deterministic policy gradient (TD3). In addition, a burn-in strategy was introduced to estimate the action values using the internal states of the SNNs. Experiments in a virtual environment showed that the proposed method achieved higher rewards than the previous methods. © 2024 IEEE.

关键词： Deep reinforcement 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

Rough-to-Fine Model-based Non-contact Heart Rate Estimation using MIMO FMCW Radar

Rough-to-Fine Model-based Non-contact Heart Rate Estimation ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Shi, Xintong Bouazizi, Mondher Ohtsuki, Tomoaki Keio University Graduate School of Science and Technology Japan Keio University Department of Information and Computer Science Japan

ISBN: (纸本)9798350351255

MIMO FMCW Radar, a non-contact heart rate (HR) monitoring technology, has emerged as one of the superior alternatives to contact-based sensors, providing precise HR estimation without the drawbacks of discomfort or privacy concerns, and excelling in diverse environmental conditions. Recent HR estimation studies using conventional methods have achieved high accuracy but face challenges with lengthy processing times and sensitivity to experimental conditions, affecting real-time application and robustness. A previous Deep learning (DL)-based approach improves on these aspects but is limited by the range resolution of SISO FMCW Radar and the requirement for close positioning of subjects. Additionally, this method has inability to utilize contextual information from adjacent time windows restricts its effectiveness for time series analysis. Thus, our proposed method combines a Curve-Length (CL) approach with a DL rough-to-fine model, addressing the limitations of previous studies and improving HR estimation accuracy and robustness. This integrated process begins with human location detection through a CL-based approach and is followed by a two-phase rough-to-fine HR estimation. The experimental results show significant improvement over the conventional methods. © 2024 IEEE.

关键词： deep learning heart rate estimation MIMO FMCW radar rough-to-fine model

来源：评论

学校读者我要写书评

暂无评论

RobustFace: a novel image restoration technique for face adversarial robustness improvement

引用

Multimedia Tools and Applications 2025年第11期84卷 8965-8993页

作者： Sadu, Chiranjeevi Das, Pradip K. Yannam, V Ramanjaneyulu Nayyar, Anand Department of Computer Science and Engineering RGUKT Nuzvid Andhra Pradesh Nuzvid India Department of Computer Science and Engineering IIT Guwahati Assam Guwahati India School of Technology Woxsen University Telangana Hyderabad India Graduate School Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam

Machine Learning (ML) models, particularly Deep Learning (DL), have made rapid progress and achieved significant milestones across various applications, including numerous safety-critical contexts. However, these models have recently been discovered to be susceptible to adversarial attacks, which are well-crafted input images. The primary objective of this paper is to propose a novel methodology titled "RobustFace", which is based on deep image restoration networks, that significantly improves the facial adversarial robustness of various image-classification models. Adversarial images are created using the Private Fast Gradient Sign Method (P-FGSM), StyleGAN and Fast Landmark Manipulation (FLM) methods. The adversarial images are then enhanced using deep image restoration networks to bring back them into the original space. The encoded weighted local magnitude patterns (WLMP) are extracted and provided to different types of classifiers to detect facial adversarial images from the clean images. The effectiveness of RobustFace has been demonstrated on two real-world datasets and experimental outcomes show that it significantly improves facial adversarial robustness on all evaluating classifiers. It improves the highest classification accuracy from 98.75% to 99.00% on P-FGSM attacks, from 77.94% to 85.25% on adversarial attacks generated by StyleGAN and from 65.52% to 69.50% for FLM attacks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Independent Set Reconfiguration Under Bounded-Hop Token Jumping 19th

Independent Set Reconfiguration Under Bounded-Hop Token Jump...

引用

19th International Conference and Workshops on Algorithms and Computation, WALCOM 2025

作者： Hatano, Hiroki Kitamura, Naoki Izumi, Taisuke Ito, Takehiro Masuzawa, Toshimitsu Graduate School of Information Science and Technology Department of Computer Science Osaka University Osaka Suita Japan Graduate School of Information Sciences Tohoku University Sendai Japan

ISBN: (纸本)9789819628445

The independent set reconfiguration problem (ISReconf) is the problem of determining, for two given independent sets of a graph, whether one can be transformed into the other by repeatedly applying a prescribed reconfiguration rule. There are two well-studied reconfiguration rules, called the Token Sliding (TS) rule and the Token Jumping (TJ) rule, and it is known that the complexity status of ISReconf differs between the TS and TJ rules for some graph classes. In this paper, we analyze how changes in reconfiguration rules affect the computational complexity of ISReconf. To this end, we generalize the TS and TJ rules to a unified reconfiguration rule, called the k-Jump rule, which removes one vertex from a current independent set and adds a vertex within distance k from the removed vertex to obtain another independent set having the same cardinality. We give the following three results: First, we show that the computational complexity of ISReconf under the k-Jump rule for general connected graphs is identical for all k≥3. Second, we present a polynomial-time algorithm to solve ISReconf under the 2-Jump rule for split graphs. Third, we consider the shortest variant of ISReconf, which determines whether there is a transformation of at most steps, for a given integer ≥0. We prove that this shortest variant under the k-Jump rule is NP-complete for chordal graphs of diameter at most 2k+1, for any k≥3. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Growth Optimizer and Its Application to Multispectral Image Fusion

引用

computers, Materials & Continua 2024年第11期81卷 3033-3062页

作者： Jeng-Shyang Pan Wenda Li Shu-Chuan Chu Xiao Sui Junzo Watada College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China Department of Information Management Chaoyang University of TechnologyTaichung413310Taiwan Graduate School of Information Production and SystemsWaseda UniversityKitakyushu808-0135Japan

The growth optimizer(GO)is an innovative and robust metaheuristic optimization algorithm designed to simulate the learning and reflective processes experienced by individuals as they mature within the social ***,the original GO algorithm is constrained by two significant limitations:slow convergence and high mem-ory *** restricts its application to large-scale and complex *** address these problems,this paper proposes an innovative enhanced growth optimizer(eGO).In contrast to conventional population-based optimization algorithms,the eGO algorithm utilizes a probabilistic model,designated as the virtual population,which is capable of accurately replicating the behavior of actual populations while simultaneously reducing memory ***,this paper introduces the Lévy flight mechanism,which enhances the diversity and flexibility of the search process,thus further improving the algorithm’s global search capability and convergence *** verify the effectiveness of the eGO algorithm,a series of experiments were conducted using the CEC2014 and CEC2017 test *** results demonstrate that the eGO algorithm outperforms the original GO algorithm and other compact algorithms regarding memory usage and convergence speed,thus exhibiting powerful optimization ***,the eGO algorithm was applied to image *** a comparative analysis with the existing PSO and GO algorithms and other compact algorithms,the eGO algorithm demonstrates superior performance in image fusion.

关键词： Growth optimizer probabilistic model Lévy flight image fusion

来源：评论

学校读者我要写书评

暂无评论

Remote Inter-beat Interval Estimation: A Signal Reconstruction Approach with Multi-channel Input and Channel-Wise Attention Mechanism

Remote Inter-beat Interval Estimation: A Signal Reconstructi...

引用

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

作者： Wang, Shengze Bouazizi, Mondher Ohtsuki, Tomoaki Graduate School of Science and Technology Keio University Yokohama Japan Department of Information and Computer Science Faculty of Science and Technology Keio University Yokohama Japan

ISBN: (纸本)9798350350548

This paper presents a radar-based heart rate monitoring and Inter-beat interval (IBI) estimation. Traditional IBI estimation relies on peak detection combined with signal processing techniques. Our approach uses signal reconstruction with a neural network, which significantly improves the accuracy and robustness of IBI estimation compared to conventional methods. By utilizing multi-channel input data, our approach effectively mitigates various sources of noise and interference, resulting in highly accurate and reliable IBI predictions. Instead of relying solely on peak detection, we use the U-net architecture and cross-channel attention mechanism to reconstruct the triangular waveform generated from the ground truth ECG signals. The incorporation of multi-channel input and channel-wise attention mechanism improves our model’s ability to discriminate and emphasize critical features from different input channels, further improving IBI estimation accuracy. To evaluate the accuracy and robustness of our proposed method, we trained our model on the open-source dataset [1], and then performed leave-one-subject-out validation, which ensures our approach to be evaluated only on unseen independent subjects. We have achieved a Root Mean Square Error (RMSE) of 26.7 ms for the IBI of each heart-beat. Our results demonstrate the transformative potential of adopting signal reconstruction methods supported by state-of-the-art deep learning techniques. This shift in perspective promises more accurate and robust heart rate and IBI estimation, opening new avenues for improving the accuracy and reliability of cardiac monitoring systems. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

EarLock: Personal Authentication System for Hearables Using Sound Leakage Signals

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6183-6196页

作者： Amesaka, Takashi Watanabe, Hiroki Sugiura, Yuta Sugimoto, Masanori Shizuki, Buntarou Keio University Department of Information and Computer Science Yokohama108-0073 Japan Future University Hakodate Department of Media Architecture Hokkaido 041-0803 Japan Hokkaido University Graduate School of Information Science and Technology Sapporo060-0808 Japan University of Tsukuba Department of Computer Science Tsukuba305-8577 Japan

Earphone-type wearable devices, also known as "hearables," will have many functions in the future. Some of those functions will require authentication of the wearer for access to the user's privacy information or settlement of payments. In this study, we propose a new personal authentication system for hearables called EarLock. EarLock authenticates the wearer by acquiring and analyzing ear canal and auricle shape information using sound leakage from the device. The system can be implemented using a speaker and external microphone that are highly compatible with hearables. We implemented three prototype devices and investigated EarLock’s authentication performance under various practical scenarios, including walking conditions, noisy environments, and situations with object interference. Experimental results showed that the in-ear, open-ear, and bone-conduction devices achieved balanced accuracy (BAC) scores of 87.2–93.7%, 83.4– 94.7%, and 85.9–90.0%. © 2002-2012 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Secure Consumer-Centric Demand Response Management in Resilient Smart Grid as Industry 5.0 Application with Blockchain-Based Authentication

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 1370-1379页

作者： Ayub, Muhammad Faizan Li, Xiong Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Omar, Marwan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu12599 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Illinois Institute of Technology Information Technology and Management ChicagoIL60616 United States

The development of the industrial Internet of Things and smart grid networks has emphasized the importance of secure smart grid communication for the future of electric power transmission. However, the current deployment of smart meters and wireless communication methods presents several security concerns that must be addressed to ensure sustainable and resilient smart grid networks for Industry 5.0, with a focus on consumer-centric technologies. In this context, we propose a privacy-focused authentication solution for secure consumer-centric demand response management in smart grid networks, incorporating consumer electronics. Our proposed protocol utilizes blockchain-based authentication to enhance resistance against potential attacks and ensure the integrity of demand response data. Additionally, we have incorporated a PUF to prevent physical attacks. We have conducted informal and formal security analyses to verify the effectiveness of our proposed protocol against various threats and to confirm the session key security. Our comparison study has demonstrated that our protocol provides superior security and added functionalities, with lower computation and communication costs compared to similar protocols. Furthermore, we have measured the computational time for implementing the blockchain component of our protocol while considering the impact of varying numbers of block additions and transactions per block. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

DFNet: Dense fusion convolution neural network for plant leaf disease classification

引用

Agronomy Journal 2024年第3期116卷 826-838页

作者： Faisal, Muhamad Leu, Jenq-Shiou Avian, Cries Prakosa, Setya Widyawan Köppen, Mario Department of Electronic and Computer Engineering (ECE) National Taiwan University of Science and Technology Taipei City Taiwan Department of Computer Science and Systems Engineering (CSSE) Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Iizuka-shi Japan

The early identification of plant diseases is crucial for preventing the loss of crop production. Recently, the advancement of deep learning has significantly improved the identification of plant leaf diseases. However, most approaches depend on a single convolutional neural network (CNN) to extract the leaf features, ignoring the opportunity to take full advantage of the feature richness available in the images. This paper explores a novel CNN model with multiple automated feature extractors, namely, dense fusion CNN (DFNet), for classifying plant leaf diseases. DFNet aims to increase the diversity of extracted features in order to improve discrimination. Instead of using a single-CNN model, DFNet relies on a double-pretrained CNN model, MobileNetV2 and NASNetMobile, as the feature extractor. The features extracted from each CNN are fused in the fusion layer using a fully connected network. The proposed method was evaluated using corn (Zea mays L.) and coffee (Coffea canephora) leaf disease datasets and compared to the existing models. The experiment showed that DFNet is superior and consistent to other CNN methods by achieving an accuracy of 97.53% for corn leaf diseases and 94.65% for coffee leaf diseases. © 2023 The Authors. Agronomy Journal © 2023 American Society of Agronomy.

关键词：

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：