检索结果-内蒙古大学图书馆

Joint 12th international conference on soft computing and Intelligent Systems / 23rd international Symposium on Advanced Intelligent Systems (SCIS and ISIS)

作者： Ota, Ryunosuke Kinoshita, Yuichiro Go, Kentaro Univ Yamanashi Dept Comp Sci & Engn Kofu Yamanashi Japan

ISBN: (纸本)9781665499248

This research proposed a method for automatically creating patterns that match the impression desired by users in product design support. An impression rating experiment clarified the relationship between pattern physical aspects and impressions. Impression evaluation models that estimate the impression of patterns are implemented by training convolutional neural networks using experimental scores. patterns are generated by evolutionary computation with impression evaluation models serving as evaluation functions. The validity of the automatically generated patterns is examined by the generation of evolutionary computation and the final generation patterns.

关键词： automated design pattern impression design support

来源：评论

学校读者我要写书评

暂无评论

Real-time Hierarchical soft Attention-based 3D Object Detection in Point Clouds 26

Real-time Hierarchical Soft Attention-based 3D Object Detect...

引用

26th international conference on pattern recognition / 8th international Workshop on Image Mining - Theory and Applications (IMTA)

作者： Chen, Qiuxiao Qi, Xiaojun Song, Ziqi Utah State Univ Logan UT 84322 USA

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Deep neural network-based 3D object detection in LiDAR point clouds has achieved excellent performance in various applications including autonomous driving and robot vision. However, achieving high accuracy in real-time is paramount in time-critical applications. We propose a real-time Hierarchical soft Attention Network (HSAN) to employ soft attention in the backbone of the original network to increase the detection accuracy without slowing down its inference speed. The proposed HSAN applies a hierarchical structure on the baseline network to combine features at different scales to obtain rich and fine-grained information and utilizes the characteristic of a layered attention structure to give more attention to the correct regions of target objects. Our proposed system improves the baseline network and achieves comparable detection results in terms of detection accuracy and inference speed when compared with peer state-of-the-art systems on the KITTI validation 3D detection benchmark.

关键词： Point cloud compression Three-dimensional displays Laser radar Robot vision systems Object detection Information filters Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Fused Local Color pattern (FLCP): A Novel Color Descriptor for Face recognition 1

引用

14th international conference on soft computing and pattern recognition, SoCPaR 2022, and the 14th World Congress on Nature and Biologically Inspired computing, NaBIC 2022

作者： Karanwal, Shekhar Department of CSE Graphic Era University UK Dehradun India

ISBN: (数字)9783031275241

ISBN: (纸本)9783031275234

Literature suggests that when color information is used then there is immense improvement in accuracy. This work presented such novel descriptor so-called Fused Local Color pattern (FLCP) by using the RGB color format. Precisely from R component MRELBP-NI is imposed for feature extraction, from G component 6 × 6 MB-LBP is imposed for feature extraction and from B component RD-LBP is imposed for feature extraction. The features extracted from all three components are joined which is called as FLCP. Compaction and matching is done by PCA and SVMs. Results on GT confirms the effectiveness of the FLCP descriptor as compared to the individually implemented gray scale based descriptors. FLCP also outperforms various literature methods. The novelty of proposed work is the development of discriminant descriptor by fusing the features extracted from RGB color format. This concept is lacking in the previous work. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improvement of soft-YOLOv5 Algorithm for Stray Cats and Dogs Detection 6

Improvement of Soft-YOLOv5 Algorithm for Stray Cats and Dogs...

引用

6th IEEE international conference on pattern recognition and Artificial Intelligence, PRAI 2023

作者： Zhang, Zhen Li, Shutong Zhang, Dan Chen, Jingyi Chi, Xiling Zhang, Zhengrui Huizhou University School of Computer Science and Engineering Huizhou China

ISBN: (纸本)9798350325485

Real-Time monitoring and instantaneous tracking of stray cats and dogs within a specific area using image recognition and object detection in computer vision technology is currently the predominant trend. Cat and dog recognition, as a classic object detection project, serves the purpose of identifying the quantity and categories of cats and dogs in a single image or video frame. This study builds upon the YOLOv5 framework and addresses the practical challenges of cat and dog detection, such as overlapping and occlusion. To enhance detection accuracy and stability, the soft-NMS and Merge-NMS algorithms are contrasted with YOLOv5's NMS algorithm. The improved soft-NMS and Merge-NMS algorithms are evaluated through performance testing and compared with the original NMS algorithm. As a result of these two algorithm enhancements for YOLOv5's NMS algorithm, the soft-NMS algorithm demonstrates a 2.2% performance improvement over YOLOv5 using the NMS algorithm. Therefore, soft-YOLOv5 is better suited for the task of detecting stray cats and dogs in urban communities and streets. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Time Series pattern Matching Technique for Low-Energy Arrhythmia Classification in Implantable Cardiac Devices 3

Time Series Pattern Matching Technique for Low-Energy Arrhyt...

引用

3rd international conference on computing and Machine Intelligence (ICMI)

作者： Sengupta, Prianka John, Eugene B. Texas A&M Univ Dept Elect & Comp Engn Coll Satation TX 77843 USA Univ Texas San Antonio Dept Elect & Comp Engn San Antonio TX 78249 USA

ISBN: (纸本)9798350372977;9798350372984

Implantable cardiac devices (ICDs) are often used as an effective treatment for arrhythmia. Although these devices have access to a live Electrocardiogram (ECG) stream, currently they do not offer on-device classification of arrhythmia due to the limited computing capability and severe power constraints. In this paper we propose a low-energy computing method for extracting shape-based features from ECG in combination with machine learning techniques for classifying nine different cases of arrhythmia. This is achieved by using a Localized Longest Common Subsequence (LLCS) algorithm which has low computational requirements that allows on-device execution. The proposed method strongly focuses on maintaining minimal energy and computational footprint, in line with the operating constraints of implantable devices. To demonstrate the energy efficiency and low computation load of the proposed method we implement the classification pipeline on a low-power RISC microcontroller and compare its performance with existing classification techniques. The classification accuracy and energy of the proposed method is compared with state-of-the art research in arrhythmia classification.

关键词： Low-energy computing Machine Learning Localized Longest Common Subsequence Low-energy Arrhythmia Classification Time Series pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Analysis of Job Offers to Measure Gender Barriers through Natural Language Processing and soft computing Techniques

引用

international JOURNAL OF pattern recognition AND ARTIFICIAL INTELLIGENCE 2025年第5期39卷

作者： Puente, Cristina Sanchez-Perez, Ivan Kolomiyets-Ludwig, Evhenia Palacios-Castrillo, Clara Wang, Patrick S. P. Palacios, Rafael Comillas Pontifical Univ ICAI Sch Engn Dept Comp Sci Alberto Aguilera 23 Madrid 28015 Spain Univ Carlos III Madrid Dept Phys & Engn Av Univ 30 Madrid 28911 Spain Comillas Pontifical Univ ICADE Business Sch Alberto Aguilera 23 Madrid 28015 Spain Carnegie Mellon Univ Dept Elect & Comp Engn 5032 Forbes Ave Pittsburgh PA 15289 USA Comillas Pontifical Univ Inst Res Technol IIT ICAI Sch Engn Alberto Aguilera 23 Madrid 28015 Spain Northeastern Univ 360 Huntington Ave Boston MA 02115 USA MIT Cybersecur Sloan CAMS 77 Massachusetts Ave Cambridge MA 02139 USA

Gender-biased language is still traced in job advertisements. Legal requirements to avoid direct gender-biased adjectives, and the usage of special software to detect and substitute gender-based words, scale up the issue more than solve it. The veil of discrimination on gender in job advertisements becomes more sophisticated with each succeeding level of its official and technical (including AI) prevention. This paper is mainly focused on the application of natural language processing (NLP) to detect gender-biased and discrimination of candidates by analyzing job offers posted online. NLP is an Artificial Intelligence tool that was applied in combination with Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA) to analyze the type of language used in job advertisements, detect the most relevant words used in the ads, and ultimately detect gender-bias. The main objective of this work is to provide equal access to employment opportunities from the very initial stage of the recruitment process. In addition, clustering techniques were applied to create groups based on the target public and the type of language used, providing evidence of gender-biased practices. The system was tested using a database of 2000 job ads in four different sectors: nursery, secretarial, managerial, and engineering.

关键词： Gender-biased job advertisement natural language processing artificial intelligence equal opportunities text classification techniques machine learning

来源：评论

学校读者我要写书评

暂无评论

recognition of Greek Alphabet Characters with Memristive Neuromorphic Circuit 2

Recognition of Greek Alphabet Characters with Memristive Neu...

引用

2nd Edition IEEE international conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023

作者： Chatzinikolaou, Theodoros Panagiotis Chatzipaschalis, Ioannis K. Tsakalos, Karolos-Alexandros Karamani, Rafailia-Eleni Fyrigos, Iosif-Angelos Kitsios, Stavros Bousoulas, Panagiotis Tsoukalas, Dimitris Sirakoulis, Georgios Ch. Democritus University of Thrace Department of Electrical and Computer Engineering Xanthi Greece Universitat Politécnica de Catalunya Department of Electronic Engineering Barcelona Spain National Technical University of Athens Department of Applied Physics Athens Greece

ISBN: (纸本)9798350300802

pattern recognition is a critical aspect of modern computing and artificial intelligence, enabling robotic and computing systems to classify and categorize information based on its patterns and relationships. In this context, memristors are emerging as a promising new type of device for pattern recognition due to their memory capabilities as non-volatile two-terminal elements and in-memory computing potential. In this work, we present a novel approach to character recognition using CBRAM memristors by combining traditional machine learning techniques with a memristor-based oscillator exhibiting neuromorphic properties. The proposed approach demonstrates the feasibility of a pattern recognition specific hardware based on memristors that can be integrated in edge computing applications, aiming to bring computation and data storage closer to the source of data, rather than relying on centralized data centers, and consequently, leading to improved latency, increased reliability, and reduced costs. © 2023 IEEE.

关键词： memristive neuromorphic circuit memristive oscillators neuromorphic computing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Vehicle Intrusion Classification using Deep Learning and Simulated Sensor Networks 18

Vehicle Intrusion Classification using Deep Learning and Sim...

引用

18th INDIAcom;11th international conference on computing for Sustainable Global Development, INDIACom 2024

作者： Rababaah, Aaron Rasheed Rababah, Haroun Musa American University of Kuwait College of Engineering and Applied Sciences Salmiya Kuwait Royal Jordanian Air Force - Jraf Markah Jordan

ISBN: (纸本)9789380544519

This paper presents a development of classification Deep Learning (DL)-based model for simulated vehicles intruding a sensor network. The study proposes a DL architecture that is capable of learning and classifying a set of six different vehicle classes including motorcycles, military SUV, trucks, tank, etc. The proposed DL architecture consists of number of layers including: input, convolution, activation, pooling, flatten, fully-connected, and soft-max layers. To train and validate the proposed model, a simulated sensor network was developed to detect intruding vehicles to a guarded area. Simulated sensors were deployed on large scale, detection patters are collected and fed to the DL model for training and validation. The experimental results showed that the proposed model was effective and reliable with an average accuracy of 95.41% and a highest accuracy of 98.31%. The primary outcome of this study is that simple large-scale deployment of simple sensors is effective in detecting and tracking objects within a sensor network. We believe the proposed model can be extended to different domains such as wildlife surveys and forest protection. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： convolution neural networks deep learning machine intelligence military applications pattern recognition sensor networks vehicle intrusion

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System based on pattern recognition using CNN

Intrusion Detection System based on Pattern Recognition usin...

引用

2023 international conference on Sustainable computing and Smart Systems, ICSCSS 2023

作者： Azarudeen, K. Harish Kumar, S. Aswin Vijay, T.V. Thirukumaran, P. Barath Balaji, V.S. Velammal College of Engineering and Technology Department of Cse Madurai India

ISBN: (纸本)9798350333602

The Intrusion Detection System (IDS) is a security tool that uses pattern recognition algorithms to detect unusual activity in a network. IDS-based pattern recognition techniques search through network traffic for patterns that might indicate a security issue. IDS-based pattern recognition may find attacks of various types, such as malware infections, brute-force attacks, and insider threats. IDS-based pattern recognition techniques may be trained using methods based on machine learning, which allows the system to learn from previous attacks and improve its accuracy. Even though signature-based IDS analyzes network data for known attack patterns, anomaly-based IDS looks for anomalous network behaviour. IDS uses pattern recognition-based machine learning methods to enhance detection precision while decreasing false positives. The ability to identify previously unidentified attacks and the flexibility to shifting attack patterns are just two advantages of pattern recognition-based IDS. The 2 categories of pattern recognition-based IDS are signature-based and anomaly-based systems. Security staff can get alerts and notifications, that allows them to respond quickly to reduce security hazards. IDS-based pattern recognition systems rely on training data to learn what constitutes a security threat. If the training data is biased or incomplete, this can lead to inaccurate or incomplete detection. For example, if the training data only includes examples of attacks from a specific geographic region or industry sector, the system may not be able to detect attacks that occur outside of these parameters © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Investigation on Deployment pattern of Wi-Fi Transceivers for CSI-based Indoor Localization and Activity recognition 14

Investigation on Deployment Pattern of Wi-Fi Transceivers fo...

引用

14th international conference on Mobile computing and Ubiquitous Network (ICMU)

作者： Kai, Kiichiro Choi, Hyuckjin Arakawa, Yutaka Kyushu Univ ISEE Fukuoka 8190395 Japan

ISBN: (纸本)9784907626525

In recent years, many studies explore CSI-based Wi-Fi sensing produce high accurate results in device-free localization, human activity recognition. Channel state information (CSI) represents how wireless signals propagate from transmitter to receiver and provides rich information to identify human presence. By collecting CSI from the specific devices, the machine learning model can be trained to recognize the human activity. However, in multi-room residential settings where walls and furniture obstruct signals, effective coverage with a limited number of transceivers becomes a crucial challenge, underlining the importance of their optimal placement. In this paper, we deployed multiple transceivers in a smart home environment in our university and studied transceiver arrangement patterns for CSI-based indoor localization and activity recognition. We compared the accuracy of localization and activity recognition for a total of 18 patterns consisting of up to five transceivers. In the activity recognition, we used Support Vector Machine (SVM) to classify whether or not a person is moving. The results show that the pattern using only one pair of transceivers achieved an accuracy 85% and covered the entire house. Meanwhile, in the localization we used Light Gradient Boosting Machine (LGBM) to classify which room the person is. The results show that accuracy decreases as the number of devices is reduced. Therefore, we investigated deployment pattern to achieve accuracy with smaller number of transceivers.

关键词： Wi-Fi sensing channel state information (CSI) human activity recognition smart home applications machine learning

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：