检索结果-内蒙古大学图书馆

Does Thermal Really Always Matter for RGB-T Salient Object Detection?

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cong, Runmin Zhang, Kepu Zhang, Chen Zheng, Feng Zhao, Yao Huang, Qingming Kwong, Sam The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China The Department of Computer Science City University of Hong Kong China The Department of Computer Science and Technology Southern University of Science and Technology Shenzhen518055 China The Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China The City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing RGBT SOD models focus on how to perform cross-modality feature fusion, ignoring whether thermal image is really always matter in SOD task. Starting from the definition and nature of this task, this paper rethinks the connotation of thermal modality, and proposes a network named TNet to solve the RGB-T SOD task. In this paper, we introduce a global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities. In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase. On the one hand, we introduce a semantic constraint provider to enrich the semantics of thermal images in the encoding phase, which makes thermal modality more suitable for the SOD task. On the other hand, we introduce a two-stage localization and complementation module in the decoding phase to transfer object localization cue and internal integrity cue in thermal features to the RGB modality. Extensive experiments on three datasets show that the proposed TNet achieves competitive performance compared with 20 state-of-the-art methods. The code and results can be found from the link of https://***/proj_***. © 2022, CC BY-NC-SA.

关键词： Semantics

Optimal Sensor Placement Using Combinations of Hybrid Measurements for Source Localization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Kang Xu, Sheng Yang, Yuqi Kong, He Ma, Yongsheng Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Computer Science University of Nottingham Nottingham United Kingdom Shenzhen Key Laboratory of Control Theory and Intelligent Systems SUSTech Shenzhen China

This paper focuses on static source localization employing different combinations of measurements, including time-difference-of-arrival (TDOA), received-signal-strength (RSS), angle-of-arrival (AOA), and time-of-arrival (TOA) measurements. Since sensor-source geometry significantly impacts localization accuracy, the strategies of optimal sensor placement are proposed systematically using combinations of hybrid measurements. Firstly, the relationship between sensor placement and source estimation accuracy is formulated by a derived Cramér-Rao bound (CRB). Secondly, the A-optimality criterion, i.e., minimizing the trace of the CRB, is selected to calculate the smallest reachable estimation mean-squared-error (MSE) in a unified manner. Thirdly, the optimal sensor placement strategies are developed to achieve the optimal estimation bound. Specifically, the specific constraints of the optimal geometries deduced by specific measurement, i.e., TDOA, AOA, RSS, and TOA, are found and discussed theoretically. Finally, the new findings are verified by simulation studies. Copyright © 2025, The Authors. All rights reserved.

关键词：

The classical iterative HHL-based hemodynamic simulation quantum linear equation algorithm for abdominal aortic aneurysm

学校读者我要写书评

暂无评论

The European Physical Journal Special Topics 2024年 1-11页

作者： You, Yujie Zhou, Fei Yue, Yimin Qiu, Yue Wang, Xinhang Yu, Yangchao Li, Bing Li, Ran Zhang, Le College of Computer Science Sichuan University Chengdu China Jinan Institute of Quantum Technology Jinan China Jinan Branch Hefei National Laboratory Jinan China West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu People’s Republic of China Med-X Center for Informatics Sichuan University Chengdu People’s Republic of China West China Hospital- SenseTime Joint Lab Chengdu People’s Republic of China Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou China

The abdominal aortic aneurysm (AAA) rupture is an extremely dangerous surgical acute abdominal disease. An important preventive method for AAA rupture is to simulate the hemodynamic parameters of AAA for medical evaluation through computational fluid dynamics. To fill the gap between the application of quantum computing and the field of biomedical engineering, we report a classical iterative HHL-based quantum algorithm for AAA hemodynamic simulation, and provide a Hamiltonian simulation approach for the coefficient matrix of linearized one-dimensional hemodynamic equations. Simulation experiments on IBM’s Qiskit (virtual machine) show that our proposed algorithm cannot only significantly reduce quantum resource consumption, but also improve simulation accuracy compared with the HHL algorithm. In addition, we have established a search-based circuit mapping which considers the hardware structure of the ‘Xiaohong’ quantum computer and selects mapping circuits with lower noise to improve the accuracy of measured results.

关键词：

Patients’ and Health Care Professionals’ Expectations of Virtual Therapeutic Agents in Outpatient Aftercare: Qualitative Survey Study

学校读者我要写书评

暂无评论

JMIR Formative Research 2025年 9卷 e59527页

作者： Immel, Diana Hilpert, Bernhard Schwarz, Patricia Hein, Andreas Gebhard, Patrick Barton, Simon Hurlemann, René Department of Psychiatry School of Medicine and Health Sciences Carl von Ossietzky Universität Oldenburg Oldenburg Germany Affective Computing Group Deutsches Forschungszentrum für Künstliche Intelligenz GmbH German Research Center for Artificial Intelligence Kaiserslautern Germany Leiden Institute of Advanced Computer Science Leiden University Snellius Gebouw Leiden Netherlands Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Assistance Systems and Medical Device Technology Department for Health Services Research School of Medicine & Health Sciences Carl von Ossietzky Universität Oldenburg Oldenburg Germany

Background: Depression is a serious mental health condition that can have a profound impact on the individual experiencing the disorder and those providing care. While psychotherapy and medication can be effective, there are gaps in current approaches, particularly in outpatient care. This phase is often associated with a high risk of relapse and readmission, and patients often report a lack of support. Socially interactive agents represent an innovative approach to the provision of assistance. Often powered by artificial intelligence, these virtual agents can interact socially and elicit humanlike emotions. In health care, they are used as virtual therapeutic assistants to fill gaps in outpatient aftercare. Objective: We aimed to explore the expectations of patients with depression and health care professionals by conducting a qualitative survey. Our analysis focused on research questions related to the appearance and role of the assistant, the assistant-patient interaction (time of interaction, skills and abilities of the assistant, and modes of interaction) and the therapist-assistant interaction. Methods: A 2-part qualitative study was conducted to explore the perspectives of the 2 groups (patients and care providers). In the first step, care providers (n=30) were recruited during a regional offline meeting. After a short presentation, they were given a link and were asked to complete a semistructured web-based questionnaire. Next, patients (n=20) were recruited from a clinic and were interviewed in a semistructured face-to-face interview. Results: The survey findings suggested that the assistant should be a multimodal communicator (voice, facial expressions, and gestures) and counteract negative self-evaluation. Most participants preferred a female assistant or wanted the option to choose the gender. In total, 24 (80%) health care professionals wanted a selectable option, while patients exhibited a marked preference for a female or diverse assistant. Regrading

关键词： artificial intelligence depression digital health care digital intervention digital technology e-mental health major depressive disorder mental disorder mental illness outpatient aftercare public health socially interactive agent suicidal ideation suicide prevention virtual therapeutic assistant

Quantification of Honey Adulteration Using a Planar Microstrip Metamaterial-Motivated Sensor and Software-Defined Radio

学校读者我要写书评

暂无评论

IEEE Sensors Journal 2025年

作者： Hasar, Ugur C. Hasar, Hafize Kaya, Yunus Ozturk, Hamdullah Korkmaz, Huseyin Kosunalp, Selahattin Iliev, Teodor Islam, Mohammad Tariqul Nayyeri, Vahid Ramahi, Omar Mustafa Gaziantep University Department of Electrical and Electronics Engineering Gaziantep27310 Turkey Directorate of Provincial Agriculture and Forestry Ministry of Agriculture and Forestry of the Republic of Turkey Gaziantep Turkey Bayburt University Department of Electronics and Automation Bayburt69010 Turkey Gaziantep Islam Science and Technology University Department of Electrical and Electronics Engineering Gaziantep27010 Turkey Bandırma Onyedi Eylül University Department of Computer Technologies Bandırma10200 Turkey University of Ruse "Angel Kanchev" Department of Telecommunication Ruse7017 Bulgaria Faculty of Engineering and Built Environment Department of Electrical Electronic and Systems Engineering Bangi43600 Malaysia Iran University of Science and Technology School of Advanced Technologies Tehran*** Iran University of Waterloo Department of Electrical and Computer Engineering ON WaterlooN2L 3G1 Canada

This work presents the application of a planar microstrip metamaterial (MM)- motivated sensor in the form of a split-ring resonator (SRR) for the detection and quantification of water adulteration in honey samples. The proposed sensor utilizes inexpensive software-defined radio (SDR) measurements, offering a cost-effective solution. Unlike previous MM sensors employing SRR configuration, our proposed MM-motivated sensor is integrated with a microstrip feedline and an additional vertical bar, enhancing its sensing capability. To enable accurate measurements, a simple calibration procedure based on baseline normalization is implemented, allowing for amplitude-only transmission measurements (|S21|) using the SDR. A special sample holder was designed to increase repeatability of measurements. We separately employ two post-processing techniques, namely the rolling average (RA) approach and the Savitzky-Golay (SG) filter, to effectively eliminate ripples in the measured |S21| data obtained from the SDR. For validation and evaluation of the proposed sensor and post-processing techniques, measurements of flower honey samples with water adulteration levels (δ) up to 10% (mass-to-mass basis) were also performed using a vector network analyzer. The resonance frequency of |S21| is utilized as the basis for analysis. We establish a metric function (linear function) that correlates the shift in resonance frequency with the δ. It is observed that this function fits to measured resonance frequency values with an R2 value greater than 0.96 for both post-processing techniques with or without the sample holder. By inverting this function, we can predict δ with considerable accuracy for a given resonance frequency by using another linear function. It is observed that percentage variations between predicted and measured δ values are between 1.54% and 6.46% for testing samples with δ = 5% and δ = 7%. © 2001-2012 IEEE.

关键词： Adulteration honey metamaterials microwaves planar structures rolling average Savitzky-Golay filter sensors water

Dominant Defect and Microstructure Transformation Engineering for Highly Efficient Low-Bandgap Stannite Solar Cells

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Yu, Zixuan Li, Shuoren Li, Chuanhao Huang, Sihao Wang, Yonghao Su, Zhenghua Liang, Guangxing Yan, Chang Guangdong Guangzhou511400 China Institute of Thin Film Physics and Applications Shenzhen Key Laboratory of Advanced Thin Films and Applications Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province State Key Laboratory of Radio Frequency Heterogeneous Integration College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518060 China Guangdong Guangzhou511400 China Guangdong-Hong Kong Joint Laboratory for Carbon Neutrality Jiangmen Laboratory of Carbon Science and Technology Guangdong Province Jiangmen529199 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong999077 Hong Kong

To meet the requirements of high-efficiency multi-junction tandem, it is imperative to seek cost-effective low-bandgap bottom subcell candidates. The bandgap of Cu2ZnSn(S,Se)4 (CZTSSe) can be effectively narrowed by Cd alloying with the lowest achievable bandgap of 0.87 eV after 60% Zn substitution by Cd. However, the low-bandgap Cu2CdZnSn(S,Se)4 (CCZTSSe) is not efficient, majorly owing to the poor crystallinity of thin films and severe non-radiative recombination. Herein, we report an effective approach to enhance the crystallinity of CCZTSSe via in situ Na-addition in the bottom precursor. Sodium attracts Se within the bottom layers, facilitating the grain growth. Electrical properties are promoted accordingly, with the reduced interface defect densities, modified grain boundaries and superior Ohmic contact at the back interface. The most significant improvement is the dominant defect transformation, from detrimental deep CuCd to benign shallow VCu. These advances enable non-radiative recombination to be greatly suppressed both at the interface and in the bulk. Eventually, an efficiency of 10.48% has been achieved, which is the highest reported efficiency for stannite solar cells. This is a significant step forward on the road to applying CCZTSSe in future tandem technologies. © 2024, The Authors. All rights reserved.

关键词： Grain boundaries

Hybrid Recommendation System for Young Football Athletes Customized Training

学校读者我要写书评

暂无评论

Hybrid Recommendation System for Young Football Athletes Cu...

Future of Information and Communication Conference, FICC 2020

作者： Matos, Paulo Rocha, João Gonçalves, Ramiro Santos, Filipe Abreu, David Soares, Hugo Martins, Constantino Computer Science Department Engineering Institute - Polytechnic of Porto Porto Portugal Trás-os-Montes e Alto Douro University Vila Real Portugal GECAD Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Porto Portugal INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal

ISBN: (纸本)9783030394448

Information and communication technologies (ICTs) are been increasingly used in sports over the past decades, especially in professional football, with the goal of enhancing preparation and improve the athletes’ performance. Training programs, however, are not accessible for young and amateur athletes. Most of the systems available, don’t have learning skills to adjust, develop and find new suggestions for training, specifically designed for each athlete. In this paper we present the Smart Coach architecture and user adaptation model and describe our hybrid recommendation system to help the development of young athletes. It simplifies the relationship between the team’s technical staff leaders and their young athletes, enhancing the counselling of the young person and their development as an athlete. The system allows performance evaluation for young athletes utilizing various measurements. The match information is captured intuitively and adaptively by acquaintances, relatives and staff, using a comfortable smartphone interface. © Springer Nature Switzerland AG 2020.

关键词： Recommender systems

StairwayGraphNet for inter- And intra-modality multi-resolution brain graph alignment and synthesis

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mhiri, Islem Mahjoub, Mohamed Ali Rekik, Islem Basira Lab Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey Université de Sousse Ecole Nationale d'Ingénieurs de Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia

Synthesizing multimodality medical data provides complementary knowledge and helps doctors make precise clinical decisions. Although promising, existing multimodal brain graph synthesis frameworks have several limitations. First, they mainly tackle only one problem (intra- or inter-modality), limiting their generalizability to synthesizing inter- and intra-modality simultaneously. Second, while few techniques work on super-resolving low-resolution brain graphs within a single modality (i.e., intra), inter-modality graph super-resolution remains unexplored though this would avoid the need for costly data collection and processing. More importantly, both target and source domains might have different distributions, which causes a domain fracture between them. To fill these gaps, we propose a multi-resolution StairwayGraphNet (SG-Net) framework to jointly infer a target graph modality based on a given modality and super-resolve brain graphs in both inter and intra domains. Our SG-Net is grounded in three main contributions: (i) predicting a target graph from a source one based on a novel graph generative adversarial network in both inter (e.g., morphological-functional) and intra (e.g., functional-functional) domains, (ii) generating high-resolution brain graphs without resorting to the time consuming and expensive MRI processing steps, and (iii) enforcing the source distribution to match that of the ground truth graphs using an inter-modality aligner to relax the loss function to optimize. Moreover, we design a new Ground Truth-Preserving loss function to guide both generators in learning the topological structure of ground truth brain graphs more accurately. Our comprehensive experiments on predicting target brain graphs from source graphs using a multi-resolution stairway showed the outperformance of our method in comparison with its variants and state-of-the-art method. SG-Net presents the first work for graph alignment and synthesis across varying modalities and r

关键词： Graphic methods

Dynamical causality under invisible confounders

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Jinling Zhang, Shao-Wu Zhang, Chihao Huang, Weitian Shi, Jifan Chen, Luonan MOE Key Laboratory of Information Fusion Technology School of Automation Northwestern Polytechnical University Xi’an710072 China Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Shanghai200031 China NCMIS CEMS RCSDS Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Mathematics Sciences University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Institute of Intelligence Science and Technology Hengqin Guangdong Zhuhai519031 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China State Key Laboratory of Medical Neurobiology MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University Shanghai200032 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences Hangzhou310024 China

Causality inference is prone to spurious causal interactions, due to the substantial confounders in a complex system. While many existing methods based on the statistical methods or dynamical methods attempt to address misidentification challenges, there remains a notable lack of effective methods to infer causality, in particular in the presence of invisible/unobservable confounders. As a result, accurately inferring causation with invisible confounders remains a largely unexplored and outstanding issue in data science and AI fields. In this work, we propose a method to overcome such challenges to infer dynamical causality under invisible confounders (CIC method) and further reconstruct the invisible confounders from time-series data by developing an orthogonal decomposition theorem in a delay embedding space. The core of our CIC method lies in its ability to decompose the observed variables not in their original space but in their delay embedding space into the common and private subspaces respectively, thereby quantifying causality between those variables both theoretically and computationally. This theoretical foundation ensures the causal detection for any high-dimensional system even with only two observed variables under many invisible confounders, which is actually a long-standing problem in the field. In addition to the invisible confounder problem, such a decomposition actually makes the intertwined variables separable in the embedding space, thus also solving the non-separability problem of causal inference. Extensive validation of the CIC method is carried out using various real datasets, and the experimental results demonstrates its effectiveness to reconstruct real biological networks even with unobserved confounders. © 2024, CC BY-NC-ND.

关键词： Time series