检索结果-内蒙古大学图书馆

6th International Conference on Communication, Devices and Networking, ICCDN 2022

作者： Awotunde, Joseph Bamidele Sur, Nath Samarendra Imoize, Agbotiname Lucky Misra, Sanjay Gaber, Tarek Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electronics and Communication Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University East Sikkim Rangpo Majitar737136 India Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria Department of Electrical Engineering and Information Technology Institute of Digital Communication Ruhr University Bochum44801 Germany Department of Applied Data Science Institute of Energy Technology Halden Norway Faculty of Computers and Informatics Suez Canal University Ismailia41522 Egypt School of Science Engineering and Environment University of Salford ManchesterM5 4WT United Kingdom

ISBN: (纸本)9789819919826

Alzheimer's disease (AD) is a long-lasting, degenerative brain illness for which there is now no successful treatment. However, there are medications that can delay its growth and stop its tracks. Therefore, stopping and regulating the progression of AD depends greatly on its early diagnosis. computer-aided diagnosis (CAD) in health care has become more and more dependent on deep learning technologies. This has help in early diagnosis and detection of various disease in health care. New techniques for the early diagnosis of neurocognitive abnormalities are now possible thanks to advancements in medical imaging and computational capacity in an effort to stop or slow down cognitive aging. Therefore, this study proposes a residual network (ResNet) type 50 for early diagnosis of AD. Convolutional neural networks (CNNs) are first used in the study for features extraction and then make the ultimate diagnosis using the ResNet-50. To create a better architecture, the problem of AD diagnosis will be addressed by utilizing and incorporating ResNet-50, which improves the current categorization problem's accuracy to its maximum. With a 98.8% accuracy rate, the proposed model using ResNet-50 produces encouraging findings for AD prediction. The study reveals that the model can effectively circumvent CNNs for the diagnostic issue with AD. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Discrete control algorithms for systems with big dead time for control101 MATLAB toolbox

Discrete control algorithms for systems with big dead time f...

引用

Cybernetics & informatics (K&I)

作者： Ruth Bars Gyula Max J. Anthony Rossiter László Keviczky Department of Automation and Applied Informatics Budapest University of Technology and Economics Budapest Hungary School of Electrical and Electronic Engineering University of Sheffield Sheffield UK Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

ISBN: (数字)9798331541811

ISBN: (纸本)9798331541828

The first course of control is under a critical review. Both the teaching material covered and the teaching methods require new considerations. Introducing interactivity in the education process makes the learning more successful and enjoyable. MATLAB provides an effective environment for learning and applying different disciplines. Control101 is a new MATLAB toolbox under development which provides tools for interactive learning of control disciplines. This paper presents the framework for teaching discrete control algorithms applied for processes containing large dead times.

关键词： Visualization Systematics PI control Reviews Education Laboratories Process control Prediction algorithms PD control MATLAB

来源：评论

学校读者我要写书评

暂无评论

Exploring Grounding Abilities in Vision-Language Models through Contextual Perception

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Xu, Wei Zhou, Tianfei Zhang, Taoyuan Li, Jie Chen, Peiyin Pan, Jia Liu, Xiaofeng Hohai University College of Artificial Intelligence and Automation Changzhou213022 China Beijing Institute of Technology Department of Computer Science China De Anza College CA United States Nanjing Medical University Engineering Research Center of Intelligent Theranostics Technology and Instruments Ministry of Education Nanjing211166 China Nanjing Medical University School of Biomedical Engineering and Informatics Nanjing211166 China University of Hong Kong Department of Computer Science Hong Kong

Vision language models (VLMs) have demonstrated strong general capabilities and achieved great success in areas such as image understanding and reasoning. Visual prompts enhance the focus of VLMs on designated areas, but their fine-grained grounding has not been fully developed. Recent research has used Set-of-Mark (SoM) approach to unleash the grounding capabilities of Generative Pre-trained Transformer-4 with Vision (GPT-4V), achieving significant benchmark performance. However, SoM still has problems with label offset and hallucination of vision language models, and the grounding ability of VLMs remains limited, making it challenging to handle complex scenarios in human-robot interaction. To address these limitations and provide more accurate and less hallucinatory results, we propose Contextual Set-of-Mark (ConSoM), a new SoM-based prompting mechanism that leverages dual-image inputs and contextual semantic information of images. Experiments demonstrate that ConSoM has distinct advantages in visual grounding, improving by 11% compared to the baseline on the dataset Refcocog. Furthermore, we evaluated ConSoM’s grounding abilities in five indoor scenarios, where it exhibited strong robustness in complex environments and under occlusion conditions. We also introduced a scalable annotation method for pixel-level question-answering dataset. The accuracy, scalability, and depth of world knowledge make ConSoM a highly effective approach for future human-robot interactions. © 2016 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Word-Based Turkish Lip Reading System with Two Stream 3dcnn and Bilstm

SSRN

引用

SSRN 2023年

作者： Erbey, Ali Barışçı, Necaattin Department of Computer Programming Distance Education Vocational School Usak University Usak64200 Turkey Department of Information Systems Informatics Institute Gazi University Ankara Turkey Department of Computer Engineering Faculty of Technology Gazi University Ankara06500 Turkey

Lip reading is a technique that aims to understand spoken words by analyzing people's lip movements. Deep learning algorithms are used as a powerful tool for detecting and recognizing lip movements more accurately. In this study, we present a lip-reading architecture for the Turkish language. The architecture is trained to recognize Turkish words using 3DCNN (3D Convolutional Neural Network) architecture and two-stream deep learning methods. The model was trained on video data representing lip movements and learned to classify words accurately. The Turkish lip reading system has been trained and tested on a large Turkish lip reading dataset. In the experiments, an accuracy of 87.12% was achieved with the proposed model, indicating successful results in the Turkish language. The proposed model demonstrates high accuracy rates in recognizing Turkish words, showcasing its effectiveness. This paper introduces a novel architecture, a lip-reading system that employs deep learning techniques, providing a robust tool for successful Turkish lipreading applications. © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Packet Scheduling and UAV Trajectory Design in Air-Ground Integrated Network

Joint Packet Scheduling and UAV Trajectory Design in Air-Gro...

引用

IEEE Globecom Workshops

作者： Shichao Li Zhiqiang Yu Hongbin Chen Ning Zhang Mianxiong Dong School of Information and Communication Guilin University of Electronic Technology Guilin China Department of Electrical and Computer Engineering University of Windsor Windsor ON Canada Department of Sciences and Informatics Muroran Institute of Technology Muroran Japan

Compared with the terrestrial network, the air-ground integrated network consisting of unmanned aerial ve-hicles (UAV s) and high altitude platforms (HAPs) offers the advantages of large coverage, high capacity, and seamless connection, which can provide effective communication services for the Internet of remote things (IoRT). In this paper, we investigate the joint packet scheduling and UAV trajectory design problem, with the objective of minimizing the average packet queue delay of IoRT in the air-ground integrated network. Since the problem is a non-convex in nature, we reformulate it into a Markov decision process (MDP) firstly. Then, based on the multi-agent deep deterministic policy gradient (MADDPG) method, we propose a joint packet scheduling and UAV trajectory design (JPSTD) algorithm. Simulation results show that the proposed JPSTD algorithm outperforms the benchmark algorithms in terms of reducing the average packet queue delay.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speculative Vulnerability: Uncovering the Temporalities of Vulnerability in People s Experiences of the Pandemic

引用

Proceedings of the ACM on Human-computer Interaction 2022年第CSCW2期6卷 1-27页

作者： Seberger, John S. Obi, Ike Loukil, Mariem Liao, William Wild, David J. Patil, Sameer Department of Information Science College of Computing and Informatics Drexel University 3675 Market Street PhiladelphiaPA19104 United States Department of Computer Graphics Technology Purdue Polytechnic Institute Purdue University 401 N. Grant St. West LafayetteIN47907 United States Mediterranean Institute of Technology Les Jardins du Lac 2 Tunis1053 Tunisia Department of Informatics Luddy School of Informatics Computing and Engineering Indiana University Bloomington 901 E. Tenth Street BloomingtonIN48104 United States School of Computing University of Utah 50 Central Campus Dr. Salt Lake CityUT84112 United States

Pandemic-tracking apps may form a future infrastructure for public health surveillance. Yet, there has been relatively little exploration of the potential societal implications of such an infrastructure. In semi-structured interviews with 23 participants from India, the Middle East and North Africa (MENA), and the United States, we discussed attitudes and preferences regarding the deployment of apps that support contact tracing to contain the spread of COVID-19. Through interpretive analysis, we examined the relationship between persistent discomfort and vulnerability when using such apps. Such an examination yielded three temporal forms of vulnerability: real, anticipatory, and speculative. By identifying and defining the temporalities of vulnerability through an analysis of people's pandemic-related thoughts and experiences, we develop the overlapping discourses of humanistic infrastructure studies and infrastructural speculation. In doing so, we explore the concept of vulnerability itself and present implications for the study of vulnerability in Human-computer Interaction (HCI) and for the oversight of app-based public health surveillance. © 2022 Owner/Author.

关键词： Public health

来源：评论

学校读者我要写书评

暂无评论

Real Time Sound Source Localization Using von-Mises ResNet

Real Time Sound Source Localization Using von-Mises ResNet

引用

IEEE/SICE International Symposium on System Integration

作者： Mert Bozkurtlar Benjamin Yen Katsutoshi Itoyama Kazuhiro Nakadai Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Department of Industrial Engineering Faculty of Management Istanbul Technical University Harbiye Maçka/Beşiktaş/İstanbul Türkiye Department of Computer Engineering Faculty of Computer and Informatics Engineering Istanbul Technical University Ayazaga Sariyer/İstanbul Türkiye Japan Society for the Promotion of Science (JSPS) at the Nakadai Lab Tokyo Institute of Technology Honda Research Institute Japan Co. Ltd Saitama Japan

This paper addresses the task of learning periodic information using deep neural networks to achieve real-time, environment-independent sound source localization. Previous papers showed phase data is the most significant cue in sound source localization tasks and the proposed vM-B DNN was validated to be able to handle such periodic information using on synthesized data. However, they haven't shown its effectiveness and robustness in realistic use cases. This paper introduces a more complex model based on residual networks and adapts vM-B activation function for convolutional layers for use cases that require real-time predictions in dynamically changing environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Analyzing Texture and Morphometry Markers of Glioblastoma TERT Promoter Mutations in DAPI Fluorescence Images

A Machine Learning Approach for Analyzing Texture and Morpho...

引用

Medical Imaging 2025: Digital and Computational Pathology

作者： Afsari, Fatemeh Naglah, Ahmed Gupta, Akshita Lohaan, Harshit Onubogu, Ugoma Janiszewska, Michalina Sarder, Pinaki Division of Nephrology Hypertension and Renal Transplantation-Quantitative Health Section Department of Medicine College of Medicine University of Florida GainesvilleFL32603 United States Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida GainesvilleFL32611 United States Department of Computer and Information Science and Engineering University of Florida GainesvilleFL32611 United States Department of Molecular Medicine The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology JupiterFL33458 United States

ISBN: (纸本)9781510686045

Advanced molecular and imaging techniques, such as STAR-FISH, are frequently required to identify mutations in tissue specimens to properly diagnose Glioblastoma (GBM), an aggressive type of brain tumor. Mutations to the telomerase reverse transcriptase promoter (TERTp) are common in cancer and present in approximately 80% of all GBM tumors. We hypothesize that machine learning can stratify cells by their TERTp mutation status using DAPI fluorescence images since the STAR-FISH technique can be costly and inaccessible for some healthcare facilities. In this study, we present a machine learning-based approach to recognize nuclei harboring TERTp mutations solely based on the DAPI fluorescence images of GBM tissues. The proposed pipeline integrates a convolutional neural network (CNN)-based deep learning model to segment cells, extract hand-engineered features, and feed them into fully connected (FC) layers within the neural network or other machine learning classifiers to identify TERTp mutant cells. This approach involves extracting DAPI features, including both morphological and textural image features, followed by an ensemble of machine learning modules to predict TERTp mutant cells. We evaluate our approach on a cohort of 18 patients (70 pairs of DAPI and STAR-FISH processed images). Our experimental results show that the FC layers within the neural network achieve the highest AUC, F1-Score, and recall of 0.77, 0.69, and 0.86, respectively, with the integrated CNN model achieving a Dice score of 0.83, accurately segmenting cells. Our work is one of the earliest attempts that we are aware of to use machine-learning models for TERTp mutation identification using DAPI fluorescence images. Our results indicate the possibility of improved GBM diagnosis accuracy. To improve patient diagnosis and treatment planning for GBM, future research aims will expand the cohort and enhance the models to provide more precise and diagnostically valuable models for the interpretation o

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Data-driven soft sensing towards quality monitoring of industrial pasteurization processes

Data-driven soft sensing towards quality monitoring of indus...

引用

International Conference on Distributed Computing in Sensor Systems (DCOSS)

作者： Gabriel Filios Andreas Kyriakopoulos Stavros Livanios Fotis Manolopoulos Sotiris Nikoletseas Stefanos H. Panagiotou Paul Spirakis Computer Engineering and Informatics Department University of Patras Greece Computer Technology Institute and Press “Diophantus” (CTI) Greece Heineken Patras Plant Greece Department of Computer Science University of Liverpool UK

ISBN: (数字)9781665495127

ISBN: (纸本)9781665495134

In the food and beverage industry many foods, beers and soft drinks usually need to get pasteurized, a process that holds a significant role in the quality and taste of the final product but is difficult to monitor due to the process nature. Soft sensing techniques, also called virtual sensing or surrogate sensing, can be leveraged to monitor the product quality, by using information available from other measurements and process parameters to calculate an estimation of the quantity of interest. In this paper, we develop a soft sensing methodology that is based on machine learning algorithms for continuous, end-to-end estimation of the temperature of products during the pasteurization process, with the vision to serve as an intermediate step towards monitoring live the final quality of the pasteurized products. This work studies a real beer pasteurization process in collaboration with Heineken’s plant in Patras, Greece and the results demonstrate notable performance in temperature prediction accuracy, with average root mean square error (RMSE) of 1.85°C in the test sets. Thus, we claim that it is possible to obtain measurements quite similar to the ones by the respective physical sensors with sufficient accuracy, and our methodology can be considered as a virtual low-cost solution for monitoring product quality in legacy pasteurizer operation.

关键词： Temperature measurement Temperature sensors Machine learning algorithms Soft sensors Estimation Product design Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Automated Diagnosis of Heart-Lung Diseases in Chest X-ray Images 5

Automated Diagnosis of Heart-Lung Diseases in Chest X-ray Im...

引用

5th International Conference on engineering technology and its Applications, IICETA 2022

作者： Alslatie, Mohammad Alquran, Hiam Mustafa, Wan Azani Abu-Qasmieh, Isam Alqudah, Ali Mohammad Alkhayyat, Ahmed The Institute of Biomedical Technology King Hussein Medical Center Royal Jordanian Medical Service Amman Jordan Yarmouk University Biomedical Systems and Medical Informatics Engineering Irbid Jordan Arau Faculty of Electrical Engineering Technology Perlis Malaysia University of Manitoba Biomedical Engineering Program Department of Electrical and Computer Engineering Canada The Islamic University Faculty of Engineering Najaf Iraq

ISBN: (纸本)9781665472159

The state of the art of artificial intelligence (AI) for various medical imaging applications leads to enhanced accuracy, analysis, visualization, and interpretation of chest Xray (CXR) images for diagnosis. Many diseases are diagnosed based on CXR images. In this paper, two types of abnormalities are diagnosed based on AI techniques. The two classes are atelectasis and cardiomegaly. The acquired images are segmented to localize the chest region and then enhanced using gray-level transformation methods. The enhanced images are passed to two pretrained convolutional neural networks (CNNs): shuffle and mobile net. The transfer learning approach is utilized in this stage. The automated features are extracted from the last fully connected layer. Each CNN deserves to have the two most representative features for the two classes. These four features are passed to support the vector machine classifier. The training accuracy reached 100% and the test accuracy was 96.7%. The proposed method can be extended to be a milestone in the classification of all heart-lung diseases that can be diagnosed using chest X-ray images. © 2022 IEEE.

关键词： Convolutional neural networks

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：