检索结果-内蒙古大学图书馆

IEEE International Conference on Healthcare informatics (ICHI)

作者： Shenghan Zhang Haoxuan Li Ruixiang Tang Sirui Ding Laila Rasmy Degui Zhi Na Zou Xia Hu Department of Computer Science Xi’an Jiaotong-Liverpool University Xi’An China Department of Computer Science Wuhan University Wuhan China Department of Computer Science Rice University Houston USA Department of Computer Science and Engineering Texas A&M University College Station USA UTHealth Houston School of Biomedical Informatics Houston USA Department of Engineering Technology & Industrial Distribution Texas A&M Univerisity College Station USA

Detailed phenotype information is fundamental to accurate diagnosis and risk estimation of diseases. As a rich source of phenotype information, electronic health records (EHRs) promise to empower diagnostic variant interpretation. However, how to accurately and efficiently extract phenotypes from the heterogeneous EHR data remains a challenge. In this work, we present PheME, an Ensemble framework using Multi-modality data of structured EHRs and unstructured clinical notes for accurate Phenotype prediction. Firstly, we employ multiple deep neural networks to learn reliable representations from the sparse structured EHR data and redundant clinical notes. A multi-modal model then aligns multi-modal features onto the same latent space to predict phenotypes. Secondly, we leverage ensemble learning to combine outputs from single-modal models and multi-modal models to improve phenotype predictions. We chose seven diseases to evaluate the phenotyping performance of the proposed framework. Experimental results show that using multi-modal data significantly improves phenotype prediction in all diseases, the proposed ensemble learning framework can further boost the performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic melanoma detection using discrete cosine transform features and metadata on dermoscopic images

引用

Journal of King Saud University - computer and Information Sciences 2024年第2期36卷

作者： Yousefi, Shamim Najjar-Ghabel, Samad Danehchin, Ramin Band, Shahab S. Hsu, Chung-Chian Mosavi, Amir Department of Computer Engineering University of Mohaghegh Ardabili Ardabil Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan John von Neumann Faculty of Informatics Budapest Hungary Ludovika University of Public Service Budapest Hungary

Machine learning contributes in improving the accuracy of melanoma detection. There are extensive studies in classic and deep learning-based approaches for melanoma detection in the literature. Still, they are not accurate or require high learning data. This paper proposes a hybrid mechanism for automated melanoma detection on dermoscopic images based on Discrete Cosine Transform features and metadata. It is composed of three steps. First, extra information/artifacts are deleted;the remaining pixels are standardized for accurate processing. Second, the reliability of the mechanism is improved by the Radon transform, extra data is removed using the Top-hat filter, and the detection rate is increased by Discrete Wavelet Transform and Discrete Cosine Transform. Then, the number of features is reduced by Locality Sensitive Discriminant Analysis. The third step divides the images into learning and test ones to create image-based models using learning data. Finally, the best model is selected based on test data and improved by a metadata-based model. Simulation results show that the decision tree provides the most practical image-based model by improving accuracy and sensitivity. Besides, the comparison results demonstrate that our model improves the F-Value to detect melanoma superior to other approaches. © 2024 The Author(s)

关键词： Artificial intelligence Big data Data science Dermoscopic image Discrete cosine transform features Machine learning Melanoma detection Metadata

来源：评论

学校读者我要写书评

暂无评论

A Development of Object Detection System based on Deep Learning Approach to Support the Laparoscope Manipulating Robot (LMR)

A Development of Object Detection System based on Deep Learn...

引用

2022 International Electrical engineering Congress, iEECON 2022

作者： Sonsilphong, Suphachoke Sonsilphong, Amornthep Hormdee, Daranee Khampitak, Kovit Khon Kaen University Data Science Health Informatics Program Academic Affairs Faculty of Medicine Khon Kaen Thailand Rajamangala University of Technology Isan Department of Electrical Engineering Khon Kean Thailand Khon Kaen University Embedded System RD Group Department of Computer Engineering Faculty of Engineering Khon Kean Thailand Khon Kean University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kean Thailand

ISBN: (纸本)9781665402064

This paper presents the development of an object detection system based on the deep learning approach of computer vision to support the laparoscopic surgical robotic position control system. The system comprises two main phases, the training phase, and the real-time operating phase. In the training phase, a modified YOLOv4 algorithm is proposed to be adopted within the Darknet framework for training the weights of detection models. The best detection model is then selected to be assigned to the object detector in the real-time operating phase. The validation result of the detection model across the experiment datasets is 90% accuracy on average during the training phase. To validate the viability of real-time object detection, the proposed system was implemented in two test-cases of gynecologic surgery with the soft-body cadavers. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

Indoor Channel Characterization with Extremely Large Reconfigurable Intelligent Surfaces at 300 GHz

arXiv

引用

arXiv 2025年

作者： Cardoso, Fabio Matos, Sérgio Pessoa, Luís M. Alexandropoulos, George C. Department of Information Science and Technology University Institute of Lisbon Portugal Instituto de Telecomunicações Portugal INESC TEC Portugal Faculty of Engineering University of Porto Portugal Department of Informatics and Telecommunications National and Kapodistrian University of Athens Greece Department of Electrical and Computer Engineering University of Illinois Chicago IL United States

The technology of Reconfigurable Intelligent Surfaces (RISs) is lately being considered as a boosting component for various indoor wireless applications, enabling wave propagation control and coverage extension. However, the incorporation of extremely large RISs, as recently being considered for ultrahigh capacity industrial environments at subTHz frequencies, imposes certain challenges for indoor channel characterization. In particular, such RISs contribute additional multipath components and their large sizes with respect to the signal wavelength lead to near-field propagation. To this end, ray tracing approaches become quite cumbersome and need to be rerun for different RIS unit cell designs. In this paper, we present a novel approach for the incorporation of RISs in indoor multipath environments towards their efficient channel characterization. An 100×100 RIS design with 2-bit resolution unit cells realizing a fixed anomalous reflection at 300 GHz is presented, whose radar cross section patterns are obtained via full-wave simulations. It is showcased that the RIS behavior can be conveniently approximated by a three-ray model, which can be efficiently incorporated within available ray tracing tools, and that the far-field approximation is valid for even very small distances from the RIS. © 2025, CC BY-NC-ND.

关键词： Radar reflection

来源：评论

学校读者我要写书评

暂无评论

Head Pose Feature for Prediction Pedestrian Intention to Crossing the Road Using LSTM

Head Pose Feature for Prediction Pedestrian Intention to Cro...

引用

IEEE Region 10 International Conference TENCON

作者： Hanugra Aulia Sidharta Muhammad Ilham Perdana Eko Mulyanto Yuniarno Berlian Al Kindhi Mauridhi Hery Purnomo Department of Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Informatics Universitas Muhammadiyah Malang Malang Indonesia Department of Electrical Automation Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Electrical Engineering Department of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia

Understanding pedestrian behaviour when crossing the road is an important key to the development of autonomous vehicles. Because pedestrians are considered Vul-nerable Road Users (VRUs), they are likely to be killed if they are involved in an accident. To ensure their safety, it is then necessary to predict the pedestrian's intention based on their behaviour. In this experiment, we propose head pose observation for predicting their intention, by observing pedestrians' head pose data, we can then predict their intention to cross the road. To achieve this purpose, we use human head detector and head pose extraction feature, and the resulting yaw, pitch and roll as three head pose features. To select the most optimal feature is important for predicting pedestrian intention, then we make 7 combination scenarios based on these three features and compare it with the same model. Based on this scenario, it is proved that all these three data are optimal to observe pedestrian intention. There are three behavioural annotation that have been used, there are crossing, not crossing and will crossing. We derive will crossing from the annotation looking and not crossing while waiting at the roadside. Prediction of pedestrian behaviour is done by using LSTM model, and the resulting precision on crossing and not crossing with 0.98, while will crossing is 0.94.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clinical resistance predictors to first-line VEGFR-TKI monotherapy for metastatic renal cell carcinoma: a retrospective multicenter real-life case series

引用

Journal of Cancer Metastasis and Treatment 2023年第1期9卷 445-458页

作者： Gaetano Pezzicoli Silvana Quaglini Valentina Tibollo Melissa Bersanelli Camillo Porta Mimma Rizzo Department of Interdisciplinary Medicine University of Bari"Aldo Moro"Bari 70124Italy Department of Electrical Computer and Biomedical EngineeringUniversity of PaviaPavia 27100Italy Laboratory of Informatics and Systems Engineering for Clinical Research Scientific Clinical Institute Maugeri(ICS Maugeri)Pavia 27100Italy Medical Oncology Unit University Hospital of ParmaParma 43121Italy Division of Translational Oncology Scientific Clinical Institute Maugeri(ICS Maugeri)Pavia 27100Italy Medical Oncology Unit University Hospital-Polyclinic of BariBari 70124Italy

Aim:For many years,systemic treatment of metastatic Renal Cell Carcinoma(mRCC)was based on sequential targeted agent *** this real-life case series,we evaluated easily accessible clinical factors useful for disease course ***:We exploited patients'clinical pathological characteristics and systemic treatment outcomes in a real-world population of 365 mRCC patients who received sequential monotherapies in the targeted therapy era,and we identified an early progressors subpopulation,resistant to first-line VEGFR-TKI monotherapy in less than 6 ***:Early progressors(n=124)show a far worse OS compared with patients progressing beyond the sixth month of therapy(13.5 vs.44.8 months,P-value<0.0001,HR=0.41,95%CI:0.29-0.53).However,these patients did not show far worse performance in second and third-line settings compared to first-line *** the univariate analysis,IMDC risk class,sarcomatoid features,and Systemic Inflammation Index(SII)were correlated with first-line therapy Progression-Free Survival(PFS1).In multivariate analysis,variables correlated with first-line outcome were IMDC risk class,histotype,and number of metastatic sites at the ***:Real-world data can contribute to developing easy-to-use prognostic factors associated with refractory disease that could support clinicians in identifying the most appropriate treatment strategy for each patient.

关键词： Renal cell carcinoma targeted therapy tyrosine kinase inhibitor drug resistance early progressor rapidly progressive prognostic factor real-world data

来源：评论

学校读者我要写书评

暂无评论

Advancements in Repetitive Action Counting: Joint-Based PoseRAC Model With Improved Performance

arXiv

引用

arXiv 2023年

作者： Chen, Haodong Zendehdel, Niloofar Leu, Ming C. Moniruzzaman, Md Yin, Zhaozheng Hajmohammadi, Solmaz Department of Mechanical and Aerospace Engineering Missouri University of Science and Technology United States Department of Biomedical Informatics Department of Computer Science Stony Brook University United States Peloton Interactive United States

Repetitive counting (RepCount) is critical in various applications, such as fitness tracking and rehabilitation. Previous methods have relied on the estimation of red-green- and-blue (RGB) frames and body pose landmarks to identify the number of action repetitions, but these methods suffer from a number of issues, including the inability to stably handle changes in camera viewpoints, over-counting, under-counting, difficulty in distinguishing between sub-actions, inaccuracy in recognizing salient poses, etc. In this paper, based on the work done by [1], we integrate joint angles with body pose landmarks to address these challenges and achieve better results than the state-of-the-art RepCount methods, with a Mean Absolute Error (MAE) of 0.211 and an Off-By-One (OBO) counting accuracy of 0.599 on the RepCount data set [2]. Comprehensive experimental results demonstrate the effectiveness and robustness of our method. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Method for Software Defect Prediction Targeting Ranking

An Ensemble Learning Method for Software Defect Prediction T...

引用

2025 2nd International Conference on Algorithms, Software engineering and Network Security (ASENS)

作者： Xiaowei Zhao Lu Lu Weibiao Chen Jiahao Cheng Xinyan Yi School of Computer Science and Engineering South China University of Technology Guangzhou China Digital Research Department China Southern Power Grid Guangzhou China Pengcheng Laboratory Shenzhen China College of Mathematics and Informatics South China Agricultural University Guangzhou China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Software defects pose a significant threat to system stability and user experience. Traditional defect prediction methods often fall short in practical testing scenarios. In response to this, we propose SeDI (Semantics-Enhanced DT-NN Integration), an ensemble learning approach for ordinary software defect prediction. SeDI integrates static software metrics with deep semantic features extracted from abstract syntax trees, leveraging a gradient boosting ranking model and a Multi-layer Perceptron to enhance ranking accuracy. The model's performance is evaluated using FPA and PD20 metrics, demonstrating superior ranking accuracy and improved performance in the top 20% of predicted modules.

关键词： Accuracy Source coding Semantics Predictive models Feature extraction Software User experience Ensemble learning Software measurement Testing

来源：评论

学校读者我要写书评

暂无评论

Concepts and Experiments on Psychoanalysis Driven Computing

arXiv

引用

arXiv 2022年

作者： Gadalla, Minas Nikoletseas, Sotiris de Amazonas, José Roberto A. Rolim, José D.P. Department of Computer Engineering & Informatics University of Patras Greece University of Patras and CTI Greece Department of Computer Architecture Technical University of Catalonia - UPC Barcelona Spain University of Geneva Switzerland

This research investigates the effective incorporation of the human factor and user perception in text-based interactive media. In such contexts, the reliability of user texts is often compromised by behavioural and emotional dimensions. To this end, several attempts have been made in the state of the art, to introduce psychological approaches in such systems, including computational psycholinguistics, personality traits and cognitive psychology methods. In contrast, our method is fundamentally different since we employ a psychoanalysis-based approach;in particular, we use the notion of Lacanian discourse types, to capture and deeply understand real (possibly elusive) characteristics, qualities and contents of texts, and evaluate their reliability. As far as we know, this is the first time computational methods are systematically combined with psychoanalysis. We believe such psychoanalytic framework is fundamentally more effective than standard methods, since it addresses deeper, quite primitive elements of human personality, behaviour and expression which usually escape methods functioning at "higher", conscious layers. In fact, this research is a first attempt to form a new paradigm of psychoanalysis-driven interactive technologies, with broader impact and diverse applications. To exemplify this generic approach, we apply it to the case-study of fake news detection;we first demonstrate certain limitations of the well-known Myers-Briggs Type Indicator (MBTI) personality type method, and then propose and evaluate our new method of analysing user texts and detecting fake news based on the Lacanian discourses psychoanalytic approach. © 2022, CC BY.

关键词： Cognitive systems

来源：评论

学校读者我要写书评

暂无评论

An Integrated Dynamic Graph Convolutional Network (ID-GCN) for Load Forecasting of Electric Vehicle Charge

An Integrated Dynamic Graph Convolutional Network (ID-GCN) f...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Djamel Eddine Mekkaoui Abdelkarim Smaili Bowen Feng Mohamed Amine Midoun Mohamed Zakariya Talhaoui Yanming Shen School of Computer Science and Technology Dalian University of Technology Dalian China School of Software Dalian University of Technology Dalian China School of Informatics University of Edinburgh Edinburgh UK Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

Forecasting energy load is a complex task in intelligent energy systems, especially with the rise of electric vehicles (EVs). Accurate EV load forecasting relies on analyzing historical data and properly integrating relevant factors. Graph convolutional networks (GCNs) have recently gained attention for time series forecasting. In this context, we propose the Integrated Dynamic Graph Convolutional Network (ID-GCN). It comprises of the Features Extraction Unit (FE), the Dynamic Graph Convolutional Networks Unit (DGCN), and the Transformer block for the output gate. The FE block processes and depicts the historical energy consumption, while the DGCN, a dynamic application of graph network, uses user transition flow to learn transition distribution and the stations' spatial representation to generate the adjacency matrix. This approach provides thorough spatial analysis and learning of the charging network and node interconnection, leading to accurate forecasts of complex EV charging demands. The ID-GCN model has been proven to outperform traditional and recent spatiotemporal forecasting methods regarding predictive accuracy for short-and long-term forecasts. This is demonstrated through comprehensive testing on real-world datasets, including detailed energy load analyses, load duration, and user transition patterns.

关键词： Energy consumption Accuracy Graph convolutional networks Load forecasting Predictive models Iron Electric vehicle charging Vehicle dynamics Forecasting Load modeling

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：