检索结果-内蒙古大学图书馆

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Lv, Yiqi Meng, Xiang Luo, Yong Pei, Yan The Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai University China and Jt. International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai University Shanghai China Doctoral Program Grad. Sch. of Comp. Science and Engineering Graduate Department of Computer and Information Systems University of Aizu Aizuwakamatsu Japan Computer Science Division University of Aizu Aizuwakamatsu Japan

ISBN: (纸本)9798400700705

This paper proposes a Complex-Valued Neural Network (CVNN) for glucose sensing in milli-meter wave (mmWave). Based on the propagation characteristics of millimeter wave in glucose medium, we obtain the S21 parameter of glucose with the concentration range of 0-300mg/dL in the 60-80 GHz frequency band by High Frequency Structure Simulator (HFSS) simulations. Then we combine the sensing model with a neural network to detect and predict the glucose concentration relying on the learning ability of the neural network. In the prediction of the concentration of unknown samples, the absolute error between the predicted value and the true value is within 5mg/dL, which confirms the ability of the proposed CVNN model. © 2023 ACM.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Determination of Giving 'Tips' Using Fuzzy Logic to Determine Restaurant Customer Service Satisfaction 3

Determination of Giving 'Tips' Using Fuzzy Logic to Determin...

引用

3rd International Conference on Computational Science and information Management, ICoCSIM 2019

作者： Priyanto, Dadang Zarlis, Muhammad Anggrawan, Anthony Graduate Program of Computer Science Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Informatics Engineering Universitas Bumigora Mataram Indonesia

Fuzzy logic can be used to represent obscurity based on terms such as high, old, hot, cold, and so on. Fuzzy logic can extend the range of truth values to all real numbers in intervals between 0 and 1. Numbers in this interval represent the possibility that the statement given is "true"or "wrong". The use of fuzzy logic can be used in everyday life, such as in the fields of medicine, engineering, agriculture, transportation, environmental science and also in economic and business applications. As in this study, it was used to calculate the ideal amount of 'tips' for restaurant waiters based on the service provided by restaurant waiters. The method used in this study is to use Mamdani fuzzy logic with the process of defuzzyfication using the Centroid of area (COA). The results of this study are that it can be determined the value crisp of giving tips to restaurant waiters is 45 thousand rupiah provided that the service provided for service = 7 (Excellent) and food service = 8 (Delicious).. © Published under licence by IOP Publishing Ltd.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Real-time Vehicle Detection and Tracking on Fisheye Traffic Monitoring Video in Compressed Domain

引用

APSIPA Transactions on Signal and information Processing 2023年第4期12卷

作者： Ardianto, Sandy Hang, Hsueh-Ming Cheng, Wen-Huang Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

Our goal is to develop real-time vehicle detection and tracking schemes for fisheye traffic monitoring video using the temporal information in the compressed domain without decoding the entire video. Two algorithms are proposed. The first algorithm starts with a conventional single-frame detector, but we introduce a multi-frame information fusion stage to improve the final detection and tracking accuracy, which is implemented using multi-modal bi-directional LSTM (MM bi-LSTM) network. The second algorithm first constructs multi-frame motion trail image, and then a single-image multi-head detector is designed to produce bounding boxes of an individual frame. The first scheme can be viewed as a detect-to-track design, and the second scheme is track-to-detect. We tested our proposals on the ICIP2020 VIP Cup dataset in H.265 video format. The aforementioned algorithms are applied to the motion fields and residual images in the H.265 compressed data set. It turns out that their detection and tracking performances are on par with their pixel-domain counterparts, and they can achieve the state-of-the-art accuracy of conventional video object detectors and trackers. If the decoding process for video compression is not counted, their computational complexities are much lower than the conventional pixel-domain video object detectors and trackers. © 2023 S. Ardianto, H.-M. Hang and W.-H. Cheng.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Techniques for Enhancing Vision-Based Detection System for Tire Sidewall Extraction 7

Preprocessing Techniques for Enhancing Vision-Based Detectio...

引用

7th International Seminar on Research of information Technology and Intelligent Systems, ISRITI 2024

作者： Loo, Jia Hao Jauw, Veronica Lestari Lim, Chin Seong Sarmin, Khairul-Rijal Qomariyah, Nunung Nurul Fajar, Ahmad Nurul University of Nottingham Malaysia Department of Mechanical Materials and Manufacturing Engineering Malaysia Continental Tyre Technology Centre Malaysia Petaling Jaya Malaysia Bina Nusantara University School of Computing and Creative Arts Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Information System Management Department Jakarta Indonesia

ISBN: (纸本)9798331519643

This study aims to develop a system for extracting crucial information from tire sidewalls using Optical Character Recognition (OCR). Initially, images of tire were captured manually by smartphone cameras, including Redmi 9T, iPhone 11, and Galaxy S23 Ultra. The captured images are then transferred to a computer for storage. Subsequently, these images were cropped according to the boundaries identified by Hough Circle Transform (HCT). The cropped images were then further pre-processed. During the pre-processing phase, geometrical transformation and image sharpening techniques are applied to enhance the clarity and readability of the text images. The text is then extracted using Google Vision, with the extracted text categorized by size, DOT, brand and pattern. The results indicated that the effectiveness of image pre-processing was constrained by the accuracy of circle detection, which reached a maximum rate of 87.1%. This causes parts of the text to be cut out inaccurately, leading to a suboptimal extraction accuracy of 55.65%. It is also observed that the Redmi 9T camera produced inconsistent results compared to other devices. Specifically, the iPhone 11 and Samsung Galaxy S23 Ultra demonstrated superior extraction accuracies of 69.71% and 66.37%, respectively, whereas the Redmi 9T achieved a lower extraction accuracy of 37.76%. © 2024 IEEE.

关键词： OCR text extraction text identification tire handling tire sidewalls information

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and Data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

2024 7th International Conference on Healthcare Service Management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Tourist Feedback on Riau Attractions Through Indonesian Language YouTube Opinion Using Naïve Bayes Algorithm

Exploring Tourist Feedback on Riau Attractions Through Indon...

引用

2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2023

作者： Kurniawan, Rahmad Iskandar, Iwan Lestari, Fitra Harpizon, Habibi Al Rasyid Husti, Ilyas Faculty of Mathematics and Natural Sciences Universitas Riau Department of Computer Science Pekanbaru Indonesia Universitas Islam Negeri Sultan Syarif Kasim Riau Department of Informatics Engineering Pekanbaru Indonesia Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor Bangi Malaysia Graduate Program Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (纸本)9798350313635

YouTube is a widely-used platform in Indonesia, with 93.8% of its users. As such, it presents a valuable opportunity for marketing tourist destinations, particularly in Riau province, which aims to become Indonesia's top Halal travel destination. Tourism is a vital contributor to the economic growth of regions, and each province in Indonesia competes to promote its tourist attractions to attract more visitors every year. However, the large volume of data can challenge the manual analysis of feedback from YouTube's features, such as likes, dislikes, and comments. A literature review suggests that the Naive Bayes algorithm, which uses machine learning, is helpful for sentiment analysis. Therefore, this study aims to analyze public sentiment toward tourist destinations in Riau province by analyzing YouTube comments using the Naïve Bayes algorithm. The study used 1680 opinions collected from 10 YouTube videos showcasing tourist destinations in Riau. The Naive Bayes algorithm classified 60% of the comments as positive, 32% as neutral, and 8% as negative. The experimental results indicated an accuracy and precision of 73%, a recall of 94%, and an F-1 Score of 82%. The study used the word frequency technique to reveal that Riau could become a popular halal tourist destination based on several frequently occurring words in the comments. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Clustering Analysis of a Spatiotemporal Dataset with a Novel Kernel Density Estimator

Clustering Analysis of a Spatiotemporal Dataset with a Novel...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jen-Chien Yu Chun-Chieh Yang John Reuben Gilbert Rou-Jun Liu Yen-Jen Oyang Meng-Han Yang Department of Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung City Taiwan ROC Master Program in Statistics National Taiwan University Taipei Taiwan ROC Department of Computer Science & Information Engineering National Taiwan University Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University

A vast number of spatiotemporal datasets collected from a wide range of sources has motivated scientists to develop effective approaches to identify interesting patterns hidden in these datasets. In this respect, kernel density estimators, which belong to a class of non-parametric estimators in statistics, have been widely exploited in recent years. With this background, we have developed a novel kernel density estimator aiming to provide accurate analysis results. According to the evaluation with a real spatiotemporal dataset, which collected emergency medical service records in a county in the United States, the proposed kernel density estimator can approximate the probability density function significantly more accurately than a conventional kernel density estimator. Furthermore, we have exploited the proposed kernel density estimator to identify interesting patterns hidden in the real spatiotemporal dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physarum Route Optimization: Bio-inspired Strategies for Mobile Robot Navigation

Physarum Route Optimization: Bio-inspired Strategies for Mob...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Dieisson Martinelli André Schneider de Oliveira Vivian Cremer Kalempa Graduate Program in Electrical and Computer Engineering Universidade Tecnológica Federal do Paraná (UTFPR) Curitiba Brazil Department of Information Systems Universidade do Estado de Santa Catarina (UDESC) São Bento do Sul Brazil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

The objective of this project is to explore the applicability of a bioinspired approach, derived from the behavior of the Physarum polycephalum fungus, in optimizing trajectory navigation for mobile robot structures. The precise organism Physarum, which has the capability to quick locate efficient paths among factors in complicated environments, serves as a herbal version for constructing inspired trajectory algorithms. In this project, the development of a trajectory set of rules is proposed, that’s as compared to conventional trajectory introduction techniques, aiming to introduce a novel approach to cellular robot navigation. This work is presented thru a aggregate of experimental observations and computational simulations that show the effectiveness of this bioinspired approach in trajectory choice. As a end result, an set of rules is developed that mimics the behavior of the Physarum and, similarly to conventional navigation algorithms, paves the manner for research and improvement.

关键词： Shortest path problem Navigation Heuristic algorithms Memory management MIMICs Dynamic scheduling Organisms Trajectory Mobile robots Resource management

来源：评论

学校读者我要写书评

暂无评论

Dynamic Digital Signage System: A Cost-Effective and Unified Web-Based Solution for Content and Analytics Management 2

Dynamic Digital Signage System: A Cost-Effective and Unified...

引用

2nd International Conference on Image Processing and Media Computing, ICIPMC 2023

作者： Cabading, Kriselyn Malaca, Orlando Juanatas, Ronaldo Tena, Policarpio Goh, Joselito Eduard Goh, Marie Luvett Juanatas, Irish Juanatas, Roben Technological University of the Philippines College of Engineering Manila Philippines Technological University of the Philippines College of Industrial Education Manila Philippines Technological University of the Philippines Graduate Program and External Studies Manila Philippines College of Information System de la Salle - College of Saint Benilde Manila Philippines Far Eastern University - Institute of Technology College of Computer Studies and Multimedia Arts IT Department Manila Philippines Far Eastern University Information Technology Department Quezon City Philippines National University Philippines College of Computing and Information Technology Manila Philippines

ISBN: (纸本)9798350326611

While several content management systems (CMS) and audience analytics tools are available for digital signage in the market, they are often sold separately and can be expensive. Therefore, this project aims to design a cost-effective and unified web-based solution for digital signage that combines content management and audience analytics functions, reducing the need for multiple purchases. This can be achieved by utilizing Raspberry Pi technology, known for its cost-effectiveness and versatility in integrations, along with a face recognition camera and machine learning methods. This proof of concept demonstrates the integration of these components to create a dynamic digital signage system. Overall, this project has the potential to offer an affordable solution for companies aiming to efficiently manage and optimize their digital marketing strategies, especially in the Digital Out-of-Home (DOOH) Advertising space. © 2023 IEEE.

关键词： Websites

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

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

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：