检索结果-内蒙古大学图书馆

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Bo Zhang, Bob Zhang, Chengyang Zhou, Minghao Huang, Weiliang Wang, Shihang Wang, Qing Li, Mengran Zhang, Yong Song, Qianqian PAMI Research Group Department of Computer and Information Science University of Macau Taipa China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida Florida United States Faculty of Applied Sciences Macao Polytechnic University Taipa China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong China Department of Cancer Biology Wake Forest School of Medicine Winston SalemNC United States

In the field of image-based drug discovery, capturing the phenotypic response of cells to various drug treatments and perturbations is a crucial step. This process involves transforming high-throughput cellular images into quantitative representations for downstream analysis. However, existing methods require computationally extensive and complex multi-step procedures, which can introduce inefficiencies, limit generalizability, and increase potential errors. To address these challenges, we present PhenoProfiler, an innovative model designed to efficiently and effectively extract morphological representations, enabling the elucidation of phenotypic changes induced by treatments. PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods. It also includes a multi-objective learning module to enhance robustness, accuracy, and generalization in morphological representation learning. PhenoProfiler is rigorously evaluated on large-scale publicly available datasets, including over 230,000 whole-slide multi-channel images in end-to-end scenarios and more than 8.42 million single-cell images in non-end-to-end settings. Across these benchmarks, PhenoProfiler consistently outperforms state-of-the-art methods by up to 20%, demonstrating substantial improvements in both accuracy and robustness. Furthermore, PhenoProfiler uses a tailored phenotype correction strategy to emphasize relative phenotypic changes under treatments, facilitating the detection of biologically meaningful signals. UMAP visualizations of treatment profiles demonstrate PhenoProfiler’s ability to effectively cluster treatments with similar biological annotations, thereby enhancing interpretability. These findings establish PhenoProfiler as a scalable, generalizable, and robust tool for phenotypic learning, offering transformative advancement

关键词： Benchmarking

TIMED AUTOMATA ROBUSTNESS ANALYSIS VIA MODEL CHECKING

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bendík, Jaroslav Sencan, Ahmet Gol, Ebru Aydin Černá, Ivana Max Planck Institute for Software Systems Kaiserslautern Germany Department of Computer Engineering Middle East Technical University Ankara Turkey Faculty of Informatics Masaryk University Brno Czech Republic

Timed automata (TA) have been widely adopted as a suitable formalism to model time-critical systems. Furthermore, contemporary model-checking tools allow the designer to check whether a TA complies with a system specification. However, the exact timing constants are often uncertain during the design phase. Consequently, the designer is often able to build a TA with a correct structure, however, the timing constants need to be tuned to satisfy the specification. Moreover, even if the TA initially satisfies the specification, it can be the case that just a slight perturbation during the implementation causes a violation of the specification. Unfortunately, model-checking tools are usually not able to provide any reasonable guidance on how to fix the model in such situations. In this paper, we propose several concepts and techniques to cope with the above mentioned design phase issues when dealing with reachability and safety specifications. © 2021, CC BY.

关键词： Specifications

Data distribution aware clustering for parallel split learning in healthcare applications

学校读者我要写书评

暂无评论

Future Generation computer systems 2026年 174卷

作者： Md. Tanvir Arafat Md. Abdur Razzaque Abdulhameed Alelaiwi Md. Zia Uddin Mohammad Mehedi Hassan Department of Computer Science and Engineering University of Dhaka Dhaka 1000 Bangladesh Department of Software Engineering King Saud University Riyadh Saudi Arabia SINTEF Digital Oslo Norway Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia

Split learning, a promising approach in privacy-preserving machine learning, decentralizes model training by dividing it among client devices and a central server. However, split learning has exhibited a certain level of slowness in its vanilla approach, mainly due to the serial processing of devices. Recent research endeavors have addressed this challenge by introducing parallelism and thus accelerating the split learning process. However, the existing split learning methodologies often overlook the critical aspect of data distribution among client devices. This paper introduces a Data Distribution Aware Clustering-based Parallel Split Learning (DCSL), a scheme purposefully crafted to address the complexities stemming from non-identically and non-independently distributed (non-IID) data among client devices engaged in the split learning paradigm. In healthcare applications, comprehending the intricacies of data distribution is imperative, particularly given the non-IID nature of medical datasets, to ensure accurate analysis and decision-making. The DCSL leverages a novel clustering technique to create clusters of medical client devices, considering the data distributions of their local datasets, and employs parallel model training within the device clusters. It enhances model convergence and reduces training latency by optimizing the cluster formation. Extensive experiments demonstrate that DCSL outperforms traditional split learning approaches, significantly improving accuracy and reducing training latency across various applications.

关键词：

Chances and Challenges of ChatGPT and Similar Models for Education in M&S

学校读者我要写书评

暂无评论

Chances and Challenges of ChatGPT and Similar Models for Edu...

Simulation Winter Conference

作者： Andreas Tolk Philip Barry Margaret L. Loper Ghaith Rabadi William T. Scherer Levent Yilmaz Modeling and Analysis Innovation Center The MITRE Corporation Charlottesville VA USA Mission Analysis Group L3Harris Corporation Herndon VA USA Georgia Tech Research Institute Georgia Institute of Technology Atlanta GA USA University of Central Florida School of Modeling Simulation and Training Orlando FL USA Department of Systems and Information Engineering University of Virgina Charlottesville VA USA Samuel Ginn College of Engineering Computer Science and Software Engineering Auburn University Auburn AL USA

This position paper summarizes the inputs of a group of experts from academia and industry presenting their view on chances and challenges of using ChatGPT within Modeling and Simulation education. The experts also address the need to evaluate continuous education as well as education of faculty members to address scholastic challenges and opportunities while meeting the expectation of industry. Generally, the use of ChatGPT is encouraged, but it needs to be embedded into an updated curriculum with more emphasis on validity constraints, systems thinking, and ethics.

关键词：

An Empirical Study on Secure Usage of Mobile Health Apps: The Attack Simulation Approach

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Aljedaani, Bakheet Ahmad, Aakash Zahedi, Mansooreh Babar, M. Ali Computer Science Department Aljumum University College Umm Alqura University Makkah Saudi Arabia School of Computing and Communications Lancaster University Leipzig Germany School of Computing and Information Systems University of Melbourne Australia CREST – the Centre for Research on Engineering Software Technologies University of Adelaide Australia Australia

Context: Mobile applications (mobile apps for short) have proven their usefulness in enhancing service provisioning across a multitude of domains that range from smart healthcare, to mobile commerce, and areas of context-sensitive computing. In smart healthcare context, mobile health (mHealth) apps - representing a specific genre of mobile apps that manage health-critical information - face some critical challenges relating to security and privacy of device and user data. In recent years, a number of empirically grounded, survey-based studies have been conducted to investigate secure development and usage of mHealth apps. However, such studies rely on self-reported behaviors documented via interviews or survey questions that lack a practical, i.e. action-based approach to monitor and synthesise users’ actions and behaviors in security critical scenarios. Objective and Method: Our objective was to conduct an empirical study - engaging participants with attack simulation scenarios and analyse their actions - for investigating the security awareness of mHealth app users via action-based research. To conduct the study, we simulated some common security attack scenarios in mHealth context and engaged a total of 105 app users (14 countries across 5 continents) to monitor their actions and analyse their behavior. We analysed users' data with statistical analysis including reliability and correlations tests, descriptive analysis, and qualitative data analysis (i.e., thematic analysis method) for the open-ended questions. Results: Our results indicate that whilst the minority of our participants perceived access permissions positively, the majority had negative views by indicating that such an app could violate or cost them to lose privacy. Users provide their consent, granting permissions, without a careful review of privacy policies that leads to undesired or malicious access to health critical data. The results also indicated that 73.3% of our participants had denied at l

关键词： mHealth

Text-based automatic personality prediction: A bibliographic review

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Feizi-Derakhshi, Ali-Reza Feizi-Derakhshi, Mohammad-Reza Ramezani, Majid Nikzad-Khasmakhi, Narjes Asgari-Chenaghlu, Meysam Akan, Taymaz Ranjbar-Khadivi, Mehrdad Zafarni-Moattar, Elnaz Jahanbakhsh-Naghadeh, Zoleikha Computerized Intelligence Systems Laboratory Department of Computer Engineering University of Tabriz Tabriz Iran Department of Software Engineering Ayvansaray University Istanbul Turkey Clinical Informatics Louisiana State University Health Sciences Center Shreveport Shreveport United States Department of Computer Engineering Shabestar Branch Islamic Azad University Shabestar Iran Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Computer Engineering Naghadeh Branch Islamic Azad University Naghadeh Iran

Personality detection is an old topic in psychology and Automatic Personality Prediction (or Perception) (APP) is the automated (computationally) forecasting of the personality on different types of human generated/exchanged contents (such as text, speech, image, video). The principal objective of this study is to offer a shallow (overall) review of natural language processing approaches on APP since 2010. With the advent of deep learning and following it transfer-learning and pre-trained model in NLP, APP research area has been a hot topic, so in this review, methods are categorized into three;pre-trained independent, pre-trained model based, multimodal approaches. Also, to achieve a comprehensive comparison, reported results are informed by datasets. © 2021, CC BY-NC-SA.

关键词： Forecasting

Deep learning approach for forecasting athletes' performance in sports tournaments 20

学校读者我要写书评

暂无评论

Deep learning approach for forecasting athletes' performance...

13th International Conference on Intelligent systems: Theories and Applications, SITA 2020

作者： El-Kassabi, Hadeel T. Khalil, Khaled Serhani, M. Adel Computer Science and Software Engineering Cit Uae University Al-Ain United Arab Emirates Department of Mechanical and Industrial Engineering University of Toronto Toronto Canada Information Systems and Security Cit Uae University Al-Ain United Arab Emirates

ISBN: (纸本)9781450377331

Sports and international tournaments have gained world attention in the past decade. Enhancing sports activities and promoting sports to participate in international events competitions and tournaments play a substantial role in the development and advancement of nations around the globe. In this paper we applied different deep learning models for predicting athletes' performance in tournaments to help them improve their results. We propose a deep learning selection algorithm to evaluate the effectiveness of the athletes' current training by predicting their race results upon completing each additional training which potentially improves their performance. We gathered public training data for athletes who participated in the 2017 Boston Marathon within a five-month window prior to the race. Deep learning models were applied and evaluated to predict marathon finishing times. These include Recurrent Neural Networks (RNN) Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU). Results show that Deep Learning models give improved race time prediction accuracy over the baseline machine learning model such as standard Linear Regression (LR). © 2020 ACM.

关键词： Sports

Independent and Identically Distributed (IID) Data Assessment in Federated Learning

学校读者我要写书评

暂无评论

Independent and Identically Distributed (IID) Data Assessmen...

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Mohamad Arafeh Ahmad Hammoud Hadi Otrok Azzam Mourad Chamseddine Talhi Zbigniew Dziong Department of Software Engineering Ecole de Technologie Superieure (ETS) Montreal QC Canada Department of Electrical Engineering Ecole de Technologie Superieure (ETS) Montreal Canada Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE Department of Computer science and Mathematics Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi UAE

ISBN: (纸本)9781665435413

Federated learning extends the centralized machine learning architecture by enabling data privacy for its providers. The distributed structure of the emerged federated architecture imposes a problem of the data being not independent and identically distributed (non-IID), which drastically affects the performance of the learning process. While the majority of the recent works in the federated learning domain have accepted this limitation, only a few scholars addressed the non-IID problem straightforwardly. Nevertheless, these works lack the fundamental analysis of the data’ IIDness, and/or contradict the privacy feature of the federated learning paradigm. In this paper, we focus on evaluating the harmony of the participants by studying their data distribution and calculating their level of compatibility. The devised tool, in this work, is an assessment technique integrated within the federated learning framework to analyze the data distribution among the trainers. Our proposed method is proven by experimenting with several scenarios, and results show that our utility can fairly assess the selected participants before initiating the learning process.

关键词： Data privacy Federated learning Distributed databases Coherence Global communication Convergence

Artificial intelligence for modelling infectious disease epidemics

学校读者我要写书评

暂无评论

Nature 2025年第8051期638卷 623-635页

作者： Kraemer, Moritz U. G. Tsui, Joseph L.-H. Chang, Serina Y. Lytras, Spyros Khurana, Mark P. Vanderslott, Samantha Bajaj, Sumali Scheidwasser, Neil Curran-Sebastian, Jacob Liam Semenova, Elizaveta Zhang, Mengyan Unwin, H. Juliette T. Watson, Oliver J. Mills, Cathal Dasgupta, Abhishek Ferretti, Luca Scarpino, Samuel V. Koua, Etien Morgan, Oliver Tegally, Houriiyah Paquet, Ulrich Moutsianas, Loukas Fraser, Christophe Ferguson, Neil M. Topol, Eric J. Duchêne, David A. Stadler, Tanja Kingori, Patricia Parker, Michael J. Dominici, Francesca Shadbolt, Nigel Suchard, Marc A. Ratmann, Oliver Flaxman, Seth Holmes, Edward C. Gomez-Rodriguez, Manuel Schölkopf, Bernhard Donnelly, Christl A. Pybus, Oliver G. Cauchemez, Simon Bhatt, Samir Pandemic Sciences Institute University of Oxford Oxford United Kingdom Department of Biology University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of California Berkeley Berkeley CA United States UCSF UC Berkeley Joint Program in Computational Precision Health Berkeley CA United States Division of Systems Virology Department of Microbiology and Immunology The Institute of Medical Science The University of Tokyo Tokyo Japan Section of Epidemiology Department of Public Health University of Copenhagen Copenhagen Denmark Oxford Vaccine Group University of Oxford and NIHR Oxford Biomedical Research Centre Oxford United Kingdom Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom School of Mathematics University of Bristol Bristol United Kingdom MRC Centre for Global Infectious Disease Analysis School of Public Health Imperial College London London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Doctoral Training Centre University of Oxford Oxford United Kingdom Institute for Experiential AI Northeastern University MA Boston Thailand Santa Fe Institute Santa Fe NM United States World Health Organization Regional Office for Africa Brazzaville Congo WHO Hub for Pandemic and Epidemic Intelligence Health Emergencies Programme World Health Organization Berlin Germany Centre for Epidemic Response and Innovation (CERI) School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa African Institute for Mathematical Sciences (AIMS) South Africa Muizenberg Cape Town South Africa Genomics England London United Kingdom Scripps Research La Jolla CA United States Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland The Ethox Centre Nuffield

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (AI) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of AI systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in AI can accelerate breakthroughs in answering key epidemiological questions and we discuss specific AI methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of AI for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of AI applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in AI. © Springer Nature Limited 2025.

关键词：