检索结果-内蒙古大学图书馆

Report on IWAIT 2020

Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers 2020年第3期74卷 516-519页

作者： Mukai, Nobuhiko Itabashi, Ryunosuke Yagi, Nobuyuki Department of Computer Science Faculty of Information Technology Tokyo City University Tokyo Japan Graduate School of Environmental and Information Studies Tokyo City University Yokohama Japan Department of Information Systems Faculty of Informatics Tokyo City University Yokohama Japan

来源：评论

学校读者我要写书评

暂无评论

SRTRP-Net: A multi-task learning network for segmentation and prediction of stereotactic radiosurgery treatment response in brain metastases

引用

computers in Biology and Medicine 2024年 175卷 108503-108503页

作者： Liu, Xiao Du, Peng Dai, Zhiguang Yi, Rumeng Liu, Weifan Wu, Hao Geng, Daoying Liu, Jie School of Computer and Information Technology Beijing Jiaotong University Beijing100089 China Department of Radiology the Second Affiliated Hospital of Xuzhou Medical University Jiangsu221000 China CSSC Systems Engineering Research Institute Beijing100094 China College of Science Beijing Forestry University Beijing100089 China Huashan Hospital Fudan University Shanghai200020 China

Before the Stereotactic Radiosurgery (SRS) treatment, it is of great clinical significance to avoid secondary genetic damage and guide the personalized treatment plans for patients with brain metastases (BM) by predicting the response to SRS treatment of brain metastatic lesions. Thus, we developed a multi-task learning model termed SRTRP-Net to provide prior knowledge of BM ROI and predict the SRS treatment response of the lesion. In dual-encoder tumor segmentation Network (DTS-Net), two parallel encoders encode the original and mirrored multi-modal MRI images. The differences in the dual-encoder features between foreground and background are enhanced by the symmetrical visual difference block (SVDB). In the bottom layer of the encoder, a transformer is used to extract local contextual features in the spatial and depth dimensions of low-resolution images. Then, the decoder of DTS-Net provides the prior knowledge for predicting the response to SRS treatment by performing BM segmentation. SRS response prediction network (SRP-Net) directly utilizes shared multi-modal MRI features weighted by the signed distance map (SDM) of the masks. The bidirectional multi-dimensional feature fusion module (BMDF) fuses the shared features and the clinical text information features to obtain comprehensive tumor information for characterizing tumors and predicting SRS treatment response. Experiments based on internal and external clinical datasets have shown that SRTRP-Net achieves comparable or better results. We believe that SRTRP-Net can help clinicians accurately develop personalized first-time treatment regimens for BM patients and improve their survival. © 2024

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective

arXiv

引用

arXiv 2022年

作者： Zhang, Wen Chen, Jiaoyan Li, Juan Xu, Zezhong Pan, Jeff Z. Chen, Huajun School of Software Technology Zhejiang University China Department of Computer Science University of Oxford United Kingdom School of Informatics The University of Edinburgh United Kingdom College of Computer Science and Technology Zhejiang University China Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies China Hangzhou Innovation Center Zhejiang University China

Knowledge graph (KG) reasoning is becoming increasingly popular in both academia and industry. Conventional KG reasoning based on symbolic logic is deterministic, with reasoning results being explainable, while modern embedding-based reasoning can deal with uncertainty and predict plausible knowledge, often with high efficiency via vector computation. A promising direction is to integrate both logic-based and embedding-based methods, with the vision to have advantages of both. It has attracted wide research attention with more and more works published in recent years. In this paper, we comprehensively survey these works, focusing on how logics and embeddings are integrated. We first briefly introduce preliminaries, then systematically categorize and discuss works of logic and embedding-aware KG reasoning from different perspectives, and finally conclude and discuss the challenges and further directions. Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Prototype Model of an IoT-based Digital and Smart Door Locking System with Enhanced Security

Prototype Model of an IoT-based Digital and Smart Door Locki...

引用

International Conference on Mathematics, Actuarial science, computer science and Statistics (MACS)

作者： M. Adil Khan Kashif Nisar Ehtisham Lodhi Jawad Khan Muhammad Imran Khan Tariq Rahim Soomro Sana Nisar Department of Computer Science and Technology Chang'an University Xi'an China Victorian Institute of Technology (VIT) Adelaide South Australia The SKL for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department Computer Science Abbottabad University of Science and Technology Havelian KP Pakistan Department of Computer Science Abdul Wali Khan University Mardan Pakistan CCSIS Institute of Business Management Karachi Pakistan Faculty of Computing and Informatics University Malaysia Sabah Jalan UMS Kota Kinabalu Sabah Malaysia

ISBN: (纸本)9781665460729

Biometric-based digital door locking system plays a significant role in providing authentication, reducing the workforce in smart homes, and building automation scenarios. This paper proposes a prototype model of an IoT-based Smart Door Locking System (SDLS) with reliable double-access authentication. The IoT and biometric technology authentication mechanism is adopted to make SDLS more secure and reachable with the alert mechanism on unauthorized access. The SDLS contains a biometric scanner, and a thumb impression is made either from a mobile or a biometric-mounted device on the door and both are connected to the centralized cloud-hosted real-time database. The proposed system was tested in real-time and has shown competitive results compared to other Radio-Frequency Identification (RFID) and password-based door locks. Hence, the overall performance efficiency of SDLS is satisfactory and provides biometric-based remote access to control and monitor door locks with the alert system on unauthorized access.

关键词： Biometrics (access control) Biological system modeling Authentication Prototypes Smart homes Real-time systems Security

来源：评论

学校读者我要写书评

暂无评论

Social and behavioral determinants of health in the era of artificial intelligence with electronic health records: A scoping review

arXiv

引用

arXiv 2021年

作者： Bompelli, Anusha Wang, Yanshan Wan, Ruyuan Singh, Esha Zhou, Yuqi Xu, Lin Oniani, David Kshatriya, Bhavani Singh Agnikula Balls-Berry, Joyce E. Zhang, Rui Department of Pharmaceutical Care & Health Systems University of Minnesota Department of Health Information Management University of Pittsburgh Department of Computer Science University of Minnesota Institute for Health Informatics College of Pharmacy University of Minnesota Carlson School of Business University of Minnesota Department of Computer Science and Mathematics Luther College Department of Health Sciences Research Mayo Clinic Department of Neurology Washington University St. Louis Institute for Health Informatics Department of Pharmaceutical Care & Health Systems University of Minnesota

Background: There is growing evidence that social and behavioral determinants of health (SBDH) play a substantial effect in a wide range of health outcomes. Electronic health records (EHRs) have been widely employed to conduct observational studies in the age of artificial intelligence (AI). However, there has been little research into how to make the most of SBDH information from EHRs. Methods: A systematic search was conducted in six databases to find relevant peer-reviewed publications that had recently been published. Relevance was determined by screening and evaluating the articles. Based on selected relevant studies, a methodological analysis of AI algorithms leveraging SBDH information in EHR data was provided. Results: Our synthesis was driven by an analysis of SBDH categories, the relationship between SBDH and healthcare-related statuses, and several NLP approaches for extracting SDOH from clinical literature. Discussion: The associations between SBDH and health outcomes are complicated and diverse;several pathways may be involved. Using Natural Language Processing (NLP) technology to support the extraction of SBDH and other clinical ideas simplifies the identification and extraction of essential concepts from clinical data, efficiently unlocks unstructured data, and aids in the resolution of unstructured data-related issues. Conclusion: Despite known associations between SBDH and disease, SBDH factors are rarely investigated as interventions to improve patient outcomes. Gaining knowledge about SBDH and how SBDH data can be collected from EHRs using NLP approaches and predictive models improves the chances of influencing health policy change for patient wellness, and ultimately promoting health and health equity. Copyright © 2021, The Authors. All rights reserved.

关键词： Records management

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach of “KNN LSTM” for detection of Brain Tumour in MR images

Hybrid Machine Learning Approach of “KNN LSTM” for detecti...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： G. Uganya Shruthi V Kulkarni Vani Valsaraj Anuja Govindrao Gunale D. Rajalakshmi B Srividhya Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of AIML HKBK College of Engineering opposite manyata tech park Nagawara Bengaluru Karnataka Department of Computer Engineering UPL University of Sustainable Technology Block no 402 Ankleshwar-Valia Road Vataria Gujarat Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Chennai Department of ComputerApplication Faculty of Humanities and Sciences SRM Institute Of Science and Technology Chengalpattu Tamil Nadu

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Now a days, more existing techniques are available to found tumours on brain from MR images. But still the researchers are concentrated on to detect the brain tumour accurately with less time. So, this work proposed the hybrid machine learning algorithm of “K-Nearest Neighbour - Long Short-Term Memory” (“KNN-LSTM”) with increased ‘accuracy’, ‘sensitivity’, ‘specificity’, with less ‘time consumption’. In this work, the brain tumour is identified by predicting the MR images from huge dataset with usage of machine learning approach of “KNN-LSTM”. Brain tumour detection is difficult when to compare the abnormal and typical tissues of large capacity. In order to enable a speedy recovery following therapy, brain tumours should be identified as soon as feasible. If the brain tumour is discovered early on, patients can benefit from improved care. Due to the irregular spreading of the abrasions, brain tumours are still difficult to identify even with intensive study. Sometimes the tiny tumours look like normal, but it is challenging to find it. So, the techniques are need to increase the classification accuracy, and selecting the useful features. This paper proposes a hybrid machine learning model “KNN-LSTM” for categorizing the tumours with predicting through MR images. MRI brain imaging collection is used for our experimentation. The “KNN” algorithm usage is to extract the important characteristics from pictures once the data has been pre-processed effectively. The proposed work predicts the brain tumour with 99.15% of ‘accuracy’, 98% of ‘sensitivity’, 97.12% of ‘specificity’ and testing time consumption of 0.5 minutes.

关键词： Machine learning algorithms Accuracy Sensitivity Magnetic resonance imaging Machine learning Nearest neighbor methods Brain modeling Long short term memory Tumors Testing

来源：评论

学校读者我要写书评

暂无评论

A set of distinct facial traits learned by machines is not predictive of appearance bias in the wild

引用

AI and Ethics 2021年第3期1卷 249-260页

作者： Steed, Ryan Caliskan, Aylin Heinz College of Information Systems & Public Policy Carnegie Mellon University Pittsburgh USA Department of Computer Science George Washington University Washington USA

Research in social psychology has shown that people’s biased, subjective judgments about another’s personality based solely on their appearance are not predictive of their actual personality traits. But researchers and companies often utilize computer vision models to predict similarly subjective personality attributes such as “employability”. We seek to determine whether state-of-the-art, black box face processing technology can learn human-like appearance biases. With features extracted with FaceNet, a widely used face recognition framework, we train a transfer learning model on human subjects’ first impressions of personality traits in other faces as measured by social psychologists. We find that features extracted with FaceNet can be used to predict human appearance bias scores for deliberately manipulated faces but not for randomly generated faces scored by humans. Additionally, in contrast to work with human biases in social psychology, the model does not find a significant signal correlating politicians’ vote shares with perceived competence bias. With Local Interpretable Model-Agnostic Explanations (LIME), we provide several explanations for this discrepancy. Our results suggest that some signals of appearance bias documented in social psychology are not embedded by the machine learning techniques we investigate. We shed light on the ways in which appearance bias could be embedded in face processing technology and cast further doubt on the practice of predicting subjective traits based on appearances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive congestion control in IoT networks: Leveraging one-way delay for enhanced performance

引用

Heliyon 2024年第22期10卷 e40266页

作者： Verma, Lal Pratap Kumar, Gyanendra Khalaf, Osamah Ibrahim Wong, Wing-Keung Hamad, Abdulsattar Abdullah Rawat, Sur Singh Department of Computer and Communication Engineering Manipal University Jaipur Jaipur 303007 India Department of IoT and Intelligent Systems Manipal University Jaipur Jaipur 303007 India Department of Solar Al-Nahrain Research Center for Renewable Energy Al-Nahrain University Jadriya Baghdad Iraq Asia University Taiwan University of Samarra College of Education Department of Physics Iraq Department of Computer Science and Engineering J.S.S. Academy of Technical Education Noida 201301 India

With the exploding number of IoT devices generating vast data volumes, there is a growing risk of significant performance degradation without efficient congestion management. To tackle this challenge, efficient regulation and supervision are essential for managing congestion in IoT networks. This research work introduces a One-Way-Delay (OWD)-based congestion control (CC) method that estimates data transmission delays of the communication path and adjusts network traffic accordingly. The proposed method enhances IoT device performance by continuously monitoring OWD along the transmission path to identify and mitigate congestion. Comparative analysis with existing methods demonstrates that the proposed approach more effectively utilizes network resources, reduces congestion, and improves throughput while ensuring fairness and reliability within the IoT infrastructure. The experimental simulations show that the proposed OWD-based method outperforms well-established TCP variants such as BBR, TCP Cubic, HTCP, and New Reno, achieving average throughput improvements ranging from 4.1 % to 22.7 %. The proposed method also maintains fairness in mixed-traffic environments and effectively manages congestion in complex network topologies. © 2024

关键词： Congestion control Congestion window IoT TCP Transport layer

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning based Semantic Communication for Wireless Image Transmission

Contrastive Learning based Semantic Communication for Wirele...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Shunpu Tang Qianqian Yang Lisheng Fan Xianfu Lei Yansha Deng Arumugam Nallanathan Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Zhejiang University School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Mobile Communications Southwest Jiaotong University Chengdu China Department of Engineering Kings College London London U.K. School of Electronic Engineering and Computer Science Queen Mary University of London London U.K.

Recently, semantic communication has been widely applied in wireless image transmission systems as it can prioritize the preservation of meaningful semantic information in images over the accuracy of transmitted symbols, leading to improved communication efficiency. However, existing semantic communication approaches still face limitations in achieving considerable inference performance in downstream AI tasks like image recognition, or balancing the inference performance with the quality of the reconstructed image at the receiver. Therefore, this paper proposes a contrastive learning (CL)-based semantic communication approach to overcome these limitations. Specifically, we regard the image corruption during transmission as a form of data augmentation in CL and leverage CL to reduce the semantic distance between the original and the corrupted reconstruction while maintaining the semantic distance among irrelevant images for better discrimination in downstream tasks. Moreover, we design a two-stage training procedure and the corresponding loss functions for jointly optimizing the semantic encoder and decoder to achieve a good trade-off between the performance of image recognition in the downstream task and reconstructed quality. Simulations are finally conducted to demonstrate the superiority of the proposed method over the competitive approaches. In particular, the proposed method can achieve up to 56% accuracy gain on the CIFAR10 dataset when the bandwidth compression ratio is 1/48.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Criteria Decision Making for Machine Learning Algorithms Using AHP-VIKOR techniques: Case Study Adult Autism Diagnosis

Multi-Criteria Decision Making for Machine Learning Algorith...

引用

International Conference on Engineering Technology and their Applications (IICETA)

作者： Mustafa Mohammed Jassim Manar Hassan Ali Amer S. Elamer Mustafa Musa Jaber Mohammed Q. Mohammed Ahmed Alkhayyat Department of Medical Instruments Engineering Techniques Al-Farahidi University Baghdad Iraq Iraqi Commission for Computers and Informatics Informatics Institute for Postgraduate Studies Baghdad Iraq Department of Computer Science Dijlah University Collage Baghdad Department of Information Technology Al-Esraa University College Baghdad College of Technical Engineering The Islamic University Najaf Iraq

ISBN: (数字)9781665472159

ISBN: (纸本)9781665472166

autism spectrum disorder is known as a neurodevelopmental disorder with sensory problems. Many infected adults die frequently due to the psychological conditions they live in. Machine learning helps doctors detect cases of autism spectrum disorders in adults. It has proven very successful in this field. In this study, after pre-processing and solving the data class imbalance problem the data we proposed to use MCDM methods to know prioritization and the best method to diagnose autism between four algorithms (SVM, Random Forest, Neural Network, and KNN), after obtaining the classification results we utilized AHP method to assign weights to each classification performance metrics based on expert assessment then he used both the obtained weights and the classification results to enter them into the VIKOR method to make a decision based on the weighted table where we would get the ranking of the algorithms. The random Forest method scores the best in this classification for diagnosing autism, with an accuracy rate of 0.9957 and sensitivity 0.9841.

关键词： Support vector machines Autism Machine learning algorithms Sensitivity Neural networks Psychology Medical services

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：