检索结果-内蒙古大学图书馆

Shaping History: Advanced Machine Learning Techniques for the Analysis and Dating of Cuneiform Tablets over Three Millennia

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kapon, Danielle Fire, Michael Gordin, Shai Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Be'er Sheva Israel Department of Land of Israel Studies and Archaeology Digital Pasts Lab Ariel University Ariel Israel Digital Humanities and Social Sciences Hub Open University of Israel Ra'anana Israel

Cuneiform tablets, emerging in ancient Mesopotamia around the late fourth millennium BCE, represent one of humanity's earliest writing systems. Historically characterized by wedge-shaped marks on clay tablets, these artifacts provided insight into Mesopotamian civilization across administrative, commercial, legal, literary, and scientific domains. The traditional analysis and dating of these tablets still mainly rely on manual, subjective appreciation of shape and writing style. This approach, however, leads to many uncertainties in pinpointing the exact period the tablets originated from. Recent advances in digitization have revolutionized the study of cuneiform by enhancing accessibility and analytical capabilities. Our research uniquely focuses on the physical shapes of tablets as significant indicators of their historical periods, diverging from most studies that concentrate on textual content. Utilizing an unprecedented dataset of over 94,000 images from the Cuneiform Digital Library Initiative (CDLI) collection, our effort applies deep learning methods to the classification of cuneiform tablets, covering more than 3,000 years of history. By leveraging statistical, computational techniques, and innovative generative modeling through Variational Auto-Encoders (VAEs), we achieve substantial advancements in the automatic classification of these ancient documents, by focusing on the tablets' silhouette as a main predictor. Our classification approach begins with a Decision Tree using the height-to-width ratios of the tablets as the sole predictor which achieved 8% macro F1-score, and culminates with a ResNet50 model, which achieved a 61% macro-F1 score for tablet silhouettes. Additionally, we introduce a novel tool-set, powered by VAEs, to enhance the interpretability of our models and enable researchers to explore the changes in tablet shapes across different eras and genres. This research contributes to the fields of document analysis and diplomatics by demonstra

关键词： Decision trees

Multitask Learning Neural Networks for Pandemic Prediction with Public Stance Enhancement

学校读者我要写书评

暂无评论

Multitask Learning Neural Networks for Pandemic Prediction w...

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Zhong Zhang Feng Xie Xuechen Zhao Bin Zhou Jian Chen Lei Tian School of Computer National University of Defence Technology Changsha China Key Lab. of Software Engineering for Complex Systems National University of Defence Technology Changsha China

State and local governments have imposed health policies to contain the spread of COVID-19 since it had a serious impact on human daily life. However, the public stance on these measures may be time-varying. It is likely to escalate the infection in the area where the public is negative or resistant. To take advantage of the correlation between public stance on health policies and the COVID-19 statistics, we propose a novel framework, Multitask Learning Neural Networks for Pandemic Prediction with Public Stance Enhancement (MP3), which is composed of three modules: (1) Stance awareness module to make stance detection on health policies from users' tweets in social media and convert them into a stance time series. (2) Temporal feature extraction module that applies Convolution Neural Network and Recurrent Neural Network to extract and fuse local patterns and long-term correlations from COVID-19 statistics. Moreover, a Stance Latency-aware Attention is proposed to capture dynamic social effects and fuse them with temporal features. (3) Multi-task prediction module to adopt Graph Convolution Network to model the spread of pandemic and employ multi-task learning to simultaneously predict COVID-19 statistics and the trend of public stance on health policies. The proposed framework outperforms state-of-the-art baselines on both confirmed cases and deaths prediction tasks.

关键词： COVID-19 Correlation Pandemics Social networking (online) Fuses Convolution Multitasking

Pursuit-evasion differential games of players with different speeds in spaces of different dimensions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Shuai Wang, Chen Xie, Guangming The State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing100871 China The National Engineering Research Center of Software Engineering Peking University Beijing100871 China

We study pursuit-evasion differential games between a faster pursuer moving in 3D space and an evader moving in a plane. We first extend the well-known Apollonius circle to 3D space, by which we construct the isochron for the considered two players. Then both cases with and without a static target are considered and the corresponding optimal strategies are derived using the concept of isochron. In order to guarantee the optimality of the proposed strategies, the value functions are given and are further proved to be the solution of Hamilton-Jacobi-Isaacs equation. Simulations with comparison between the proposed strategies and other classical strategies are carried out and the results show the optimality of the proposed strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Game theory

Automated Reuse of Test Cases for Highly Configurable software systems

学校读者我要写书评

暂无评论

Automated Reuse of Test Cases for Highly Configurable Softwa...

Fachtagung des GI-Fachbereichs softwaretechnik, software engineering 2021 - Conference of the GI software engineering Section, SE 2021

作者： Fischer, Stefan Michelon, Gabriela Karoline Ramler, Rudolf Linsbauer, Lukas Egyed, Alexander Hagenberg Austria Johannes Kepler University Institute for Software Systems Engineering Linz Austria LIT Secure and Correct Systems Lab Linz Austria Technische Universität Braunschweig Institute of Software Engineering and Automotive Informatics Braunschweig Germany

ISBN: (纸本)9783885797043

In this work, we report about our research results [Fi20] initially published in the journal Empirical software engineering, volume 25, issue 6, pp. 5295-5332, November 2020, https://***/10.1007/s10664-020-09884-x. We performed experiments on test reusability across configurations of highly configurable software systems. First, we used manually written tests for specific configurations of three configurable systems and investigated how changing configuration options affects these tests. Subsequently, we applied an approach developed for automated reuse, ECCO (Extraction and Composition for Clone-and-Own), to automatically generate tests for new configurations from the existing, manually written tests. The experiments showed that our generated tests had a higher or equal success rate compared to direct reuse and they generally achieved a higher code coverage. It can be concluded that automating the reuse of tests for configurable software can substantially reduce the effort for adapting existing tests and it supports a rigorous testing process. © 2020 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Reusability

Are We Building on the Rock? On the Importance of Data Preprocessing for Code Summarization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Lin Mu, Fangwen Chen, Xiao Wang, Song Wang, Junjie Yang, Ye Li, Ge Xia, Xin Wang, Qing Institute of Software Chinese Academy of Sciences Beijing China Lassonde School of Engineering York University Toronto Canada School of Systems and Enterprises Stevens Institute of Technology HobokenNJ United States Key Lab of High Confidence Software Technology Peking University Beijing China Software Engineering Application Technology Lab Huawei China Laboratory for Internet Software Technologies Institute of Software CAS China University of Chinese Academy of Sciences China Science & Technology on Integrated Information System Laboratory Institute of Software CAS China

Code summarization, the task of generating useful comments given the code, has long been of interest. Most of the existing code summarization models are trained and validated on widely-used code comment benchmark datasets. However, little is known about the quality of the benchmark datasets built from real-world projects. Are the benchmark datasets as good as expected? To bridge the gap, we conduct a systematic research to assess and improve the quality of four benchmark datasets widely used for code summarization tasks. First, we propose an automated code-comment cleaning tool that can accurately detect noisy data caused by inappropriate data preprocessing operations from existing benchmark datasets. Then, we apply the tool to further assess the data quality of the four benchmark datasets, based on the detected noises. Finally, we conduct comparative experiments to investigate the impact of noisy data on the performance of code summarization models. The results show that these data preprocessing noises widely exist in all four benchmark datasets, and removing these noisy data leads to a significant improvement on the performance of code summarization. We believe that the findings and insights will enable a better understanding of data quality in code summarization tasks, and pave the way for relevant research and practice. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

On Automated N-way Program Merging for Facilitating Family-based Analyses of Variant-rich software

学校读者我要写书评

暂无评论

On Automated N-way Program Merging for Facilitating Family-b...

Fachtagung des GI-Fachbereichs softwaretechnik, software engineering 2020 - Conference of the GI Special Interest Group on software engineering, software engineering 2020

作者： Reuling, Dennis Kelter, Udo Bürdek, Johannes Lochau, Malte University of Siegen Software Engineering Group Siegen Germany TU Darmstadt Real-time Systems Lab Darmstadt Germany

ISBN: (纸本)9783885796947

In this work, we report about research results initially published in ACM Transactions on software engineering and Methodology (TOSEM), volume 28 Issue 3, 2019 [Re19]. Nowadays software comes in many different, yet similar variants, often derived from common code via clone-and-own. Family-based-analysis strategies show promising potentials for improving efficiency of quality assurance for variant-rich programs, as compared to variant-by-variant approaches. Unfortunately, these strategies require one superimposed program representation containing all program variants in a syntactically well-formed, semantically sound, and variant-preserving manner, which is hard to obtain manually in practice. In this talk, we present our methodology SiMPOSE for generating superimpositions of program variants to facilitate family-based analyses of variant-rich software. We utilize a novel N-way model-merging methodology for control-flow automaton (CFA) representations of C programs, an abstraction used by many recent software-analysis tools. To cope with the complexity of N-way merging, we use similarity-propagation to reduce the number of N-way matches and enable incremental merging of arbitrary subsets of variants. We apply our SiMPOSE tool to realistic C programs and investigate applicability and efficiency/effectiveness trade-offs of family-based program analyses. Our results reveal efficiency improvements by a factor of up to 2.6 for unit-test generation and 2.4 for model-checking under stable effectiveness, as compared to variant-by-variant. © 2020 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Economic and social effects

Generalized Coverage Criteria for Combinatorial Sequence Testing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Elyasaf, Achiya Farchi, Eitan Margalit, Oded Weiss, Gera Weiss, Yeshayahu Software and Information Systems Engineering Department Ben-Gurion University of the Negev Israel Computer Science Department Ben-Gurion University of the Negev Israel IBM Haifa Research Lab

We present a new model-based approach for testing systems that use sequences of actions and assertions as test vectors. Our solution includes a method for quantifying testing quality, a tool for generating high-quality test suites based on the coverage criteria we propose, and a framework for assessing risks. For testing quality, we propose a method that specifies generalized coverage criteria over sequences of actions, which extends previous approaches. Our publicly available tool demonstrates how to extract effective test suites from test plans based on these criteria. We also present a Bayesian approach for measuring the probabilities of bugs or risks, and show how this quantification can help achieve an informed balance between exploitation and exploration in testing. Finally, we provide an empirical evaluation demonstrating the effectiveness of our tool in finding bugs, assessing risks, and achieving coverage. © 2022, CC BY.

关键词： Risk assessment

Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheriguene, Youssra Jaafar, Wael Yanikomeroglu, Halim Kerrache, Chaker Abdelaziz Laboratoire d'Informatique et de Mathématiques Université Amar Telidji de Laghouat Laghouat Algeria Department of Software and Information Technology Engineering École de Technologie Supérieure MontrealQC Canada Lab Department of Systems and Computer Engineering Carleton University OttawaON Canada

Federated Learning (FL) is a decentralized machine learning (ML) technique that allows a number of participants to train an ML model collaboratively without having to share their private local datasets with others. When participants are unmanned aerial vehicles (UAVs), UAV-enabled FL would experience heterogeneity due to the majorly skewed (non-independent and identically distributed -IID) collected data. In addition, UAVs may demonstrate unintentional misbehavior in which the latter may fail to send updates to the FL server due, for instance, to UAVs' disconnectivity from the FL system caused by high mobility, unavailability, or battery depletion. Such challenges may significantly affect the convergence of the FL model. A recent way to tackle these challenges is client selection, based on customized criteria that consider UAV computing power and energy consumption. However, most existing client selection schemes neglected the participants' reliability. Indeed, FL can be targeted by poisoning attacks, in which malicious UAVs upload poisonous local models to the FL server, by either providing targeted false predictions for specifically chosen inputs or by compromising the global model's accuracy through tampering with the local model. Hence, we propose in this paper a novel client selection scheme that enhances convergence by prioritizing fast UAVs with high-reliability scores, while eliminating malicious UAVs from training. Through experiments, we assess the effectiveness of our scheme in resisting different attack scenarios, in terms of convergence and achieved model accuracy. Finally, we demonstrate the performance superiority of the proposed approach compared to baseline methods. © 2023, CC BY.

关键词： Edge computing

Quality of Service (QoS)-driven Edge Computing and Smart Hospitals: A Vision, Architectural Elements, and Future Directions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Buyya, Rajkumar Srirama, Satish N. Mahmud, Redowan Goudarzi, Mohammad Ismail, Leila Kostakos, Vassilis Lab School of Computing and Information Systems The University of Melbourne Australia School of Computer and Information Sciences The University of Hyderabad India School of Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia Lab Department of Computer Science and Software Engineering National Water and Energy Center United Arab Emirates University United Arab Emirates

The Internet of Things (IoT) paradigm is drastically changing our world by making everyday objects an integral part of the Internet. This transformation is increasingly being adopted in the healthcare sector, where Smart Hospitals are now relying on IoT technologies to track staff, patients, devices, and equipment, both within a hospital and beyond. This paradigm opens the door to new innovations for creating novel types of interactions among objects, services, and people in smarter ways to enhance the quality of patient services and the efficient utilisation of resources. However, the realisation of real-time IoT applications in healthcare and, ultimately, the development of Smart Hospitals are constrained by their current Cloud-based computing environment. Edge computing emerged as a new computing model that harnesses edge-based resources alongside Clouds for real-time IoT applications. It helps to capitalise on the potential economic impact of the IoT paradigm of $11 trillion per year, with a trillion IoT devices deployed by 2025 to sense, manage and monitor the hospital systems in real-time. This vision paper proposes new algorithms and software systems to tackle important challenges in Edge computing-enabled Smart Hospitals, including how to manage and execute diverse real-time IoT applications and how to meet their diverse and strict Quality of Service (QoS) requirements in hospital settings. The vision we outline can help tackle timely challenges that hospitals increasingly face. © 2023, CC BY.

关键词： Internet of things