检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Foszner, Pawel Szczęsna, Agnieszka Ciampi, Luca Messina, Nicola Cygan, Adam Bizon, Bartosz Cogiel, Michal Golba, Dominik Macioszek, Elżbieta Staniszewski, Michal Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Institute of Information Science and Technologies National Research Council Pisa Italy QSystems.pro sp. z o.o. Mochnackiego 34 Bytom41-907 Poland Blees sp. z o.o. Zygmunta Starego 24a/10 Gliwice44-100 Poland Department of Transport Systems Traffic Engineering and Logistics Faculty of Transport and Aviation Engineering Silesian University of Technology Katowice Poland

Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or other sensors). The use of simulation tools can significantly reduce the time required to generate scenario-specific crowd datasets, facilitate data-driven research, and next build functional machine learning models. The main goal of this work was to develop an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment, weather conditions, traffic, and the movement and models of individual agents. Finally, three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Sampling and Reduction Methods in Large-Scale Forensic Analysis

Efficient Data Sampling and Reduction Methods in Large-Scale...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Ala Harika Praveen Sharma K Aravinda Amandeep Nagpal Praveen Ali Albawi Institute of Aeronautical Engineering Dundigal Hyderabad Department of Computer Science & Engineering IES Insititute of Technology and Management IES University Bhopal M. P India Department of Electronics and Communication Engineering New Horizon College of Engineering Bangalore Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Greater Noida Uttar Pradesh Radiology Techniques Department College of Medical Technology The Islamic University Najaf

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

In this era of enormous, continuously changing datasets, forensic analysis needs innovative approaches that can adapt to changing data characteristics while maintaining data security. To satisfy this demand, our recommended system includes all algorithms for large forensic investigations. The adaptive stratified sampling algorithm sets the scene. It adjusts strata and sample quantities based on data attributes. The Feature Weighting with Machine Learning Algorithm improves selection by weighting features using machine learning. Based on them, the dynamic cluster-based sampling algorithm organizes data points dynamically. By determining how much information each data point has, the entropy-guided data reduction algorithm improves the framework. The Temporal Correlation Analysis Algorithm finally allows you to view changing data. Tables3 and Tables4 indicate that our approach outperforms others in several key areas. The recommended technique outperforms others in accuracy, memory, F1 score, usability, stability, legal acceptability, ease of application, computing complexity, and freedom. The findings in Figures.6–10 indicate that the proposed framework can balance accuracy and memory, decrease data, and be highly usable, stable, and versatile. Finally, our technology represents a novel technique to conduct large-scale research. It is fast, adaptable, and data-safe. Machine learning, dynamic changes, and temporal variables make our platform robust and comprehensive for current forensic investigations.

关键词： Technological innovation Machine learning algorithms Accuracy Correlation Forensics Heuristic algorithms Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

CrowdSim2: an Open Synthetic Benchmark for Object Detectors

arXiv

引用

arXiv 2023年

Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some state-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment. © 2023, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

On the assessment of face image quality based on handcrafted features

On the assessment of face image quality based on handcrafted...

引用

International Conference of the Biometrics Special Interest Group (BIOSIG)

作者： Olaf Henniger Biying Fu Cong Chen Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science Technical University of Darmstadt Darmstadt Germany

ISBN: (数字)9783885797005

ISBN: (纸本)9781728189277

This paper studies the assessment of the quality of face images, predicting the utility of face images for automated recognition. The utility of frontal face images from a publicly available dataset was assessed by comparing them with each other using commercial off-the-shelf face recognition systems. Multiple face image features delineating face symmetry and characteristics of the capture process were analysed to find features predictive of utility. The selected features were used to build system-specific and generic random forest classifiers.

关键词： Faces Training Face recognition Histograms Image quality Testing Forestry

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap with Sensor Networks and Cloud Computing in the Geospatial Web for Optimized Data Services

Bridging the Gap with Sensor Networks and Cloud Computing in...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Veeresh G N. Sreevani Sorabh Lakhanpal Saurabh Sharma B.Ravali Reddy Taqi Mohammed Khattab Al-Rubaye New Horizon College of Engineering Bangalore India Department of CSE(Cyber Security) Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Lloyd Law College Plot No. 11 Knowledge Park II Greater Noida Uttar Pradesh Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Department of Medical Laboratory Technology College of Medical Technologies The Islamic University Najaf Iraq

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

Implementing cloud computing and data networks for local internet services is a priority. This research addresses the issue by introducing a novel approach to enhance the quality of regional internet data services. The proposed technique, Geographical Data Fusion with Dynamic Cloud Resource Allocation (GDF-DCRA), enhances map analytics by combining geographical data fusion with dynamic cloud resource allocation. GDF-DCRA enhances the speed of geospatial analytics by reducing sensor data, efficiently allocating cloud resources, and integrating spatial and temporal data. It consistently outperforms six industry benchmarks in terms of speed, latency, scalability, data accuracy, bandwidth efficiency, fault tolerance, and resource utilisation. Despite the increasing difficulty of working with real-time location data, the proposed approach has the potential to address these challenges.

关键词： Cloud computing Spectral efficiency Soft sensors Web and internet services Data integration Dynamic scheduling Real-time systems Spatial databases Geospatial analysis Resource management

来源：评论

学校读者我要写书评

暂无评论

AI for Cervical Cancer Identification

AI for Cervical Cancer Identification

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： P Arunachalam Gandhiraj V N Deshai A. Mohanarathinam Rajat Kumar Dwibedi Divya Lanka Department of Biomedical Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Chennai Department of Biotechnology Anand Institute of Higher Technology OMR Kazhipattur Chennai Tamil Nadu India Department of IT SRKREC Bhimavaram W.G.Dt A.P Department of Biomedical Engineering Karpagam Academy of Higher Education Coimbatore GR-II Aarupadai Veedu Institute of Technology Vinayaga Mission's Research Foundation Salam Chennai Department of Computer Science and Engineering Sagi Ramakrishnam Raju Engineering College Bhimavaram India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

The chances of avoiding cervical cancer are improved by early detection of abnormal cells in the cervix. Automated methods were created because manual detection, which involves specialized pathologists and is time-consuming and prone to mistake, is not a practical or effective method for detecting abnormal cervical cells. comprehensive analysis of AI-based methods for cervical precancerous cancer detection, screening, and prognosis. Sources and approach of the search: To find publications published up to July 2022, a thorough search of Medline and the science Core Collection site was conducted (to maximize Scopus coverage). Papers using artificial intelligence (AI) models for cervical cancer detection, diagnosis, and prediction will be included in our analysis. The era of lock-in did not exist. According to the disclosure requirements of systematic reviews and meta-analyses, studies on technician iEPI usage were located and evaluated for quality and relevance. Results: 2538 items were found in the first search. After examination, the 117 papers that were included in the review were deemed eligible. On the other hand, it was discovered that pelvic lesions should be checked for tumors and precancerous disorders using AI technology in order to create screening software that runs automatically. The predictive accuracy of the algorithm for cervical cancer ranged from 70% to 100%. This indicates that artificial intelligence (AI) systems can distinguish between benign and malignant cervical cytology with an accuracy range of 80–100%. AI as a clinical diagnostic tool for doctors: The sensitivity of AI in detecting CIN2+ in colposcopy was 71. 9–98. with a specificity of 51 and 22%. 8–96. 2%. This work demonstrates that AI systems can predict the existence of precancerous lesions and cervical cancer using cytology slides in a situation where access to specialized facilities and healthcare is restricted. It's been demonstrated. Artificial intelligence (AI) might be a helpful s

关键词： Accuracy Sensitivity Software algorithms Medical services Software Telecommunication computing Lesions Artificial intelligence Cervical cancer Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Design of a Secure Machine Learning-Based Malware Detection and Analysis Scheme

Design of a Secure Machine Learning-Based Malware Detection ...

引用

Communications, Computing, Cybersecurity, and Informatics (CCCI), International Conference on

作者： Pankaj Kumar Mohammad S. Obaidat Piyush Pandey Mohammad Wazid Ashok Kumar Das Devesh Pratap Singh Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India King Abdullah II School of Information Technology The University of Jordan Amman Jordan School of Computing SRM University Jordan University of Science and Technology Beijing Beijing China School of Computing SRM University Kattankulathur TN India Center for Security Theory Algorithmic Research International Institute of Information Technology Hyderabad India

Today's world is rapidly growing towards the advanced concept of technology. Technology nowadays is at its peak of development and has great advantages in all fields of work, whether it is in industrial automation, farming, weather forecasting, or disease detection and control. Despite its great advantages, it does have its negative side because a major population is using technology and general-purpose computing devices (i.e., desktops, laptops, smartphones, tablets, etc.). Therefore, most of their personal data is available online. The data is constantly in danger of getting stolen by malicious actors (i.e., hackers), who can find a way to get their hands on this data and then use it for their personal gain (i.e., money-making). The best-known technique to get this information is by using malware exploitation on the machine of the target. Malware is an executable or a binary that is malicious in nature. It may have various devastating effects, and in order to detect and make the system defensive, we need to propose a scheme to detect the malware in the system, analyze the particular file, and then mitigate it. In this paper, we propose a secure machine learning-based malware detection and analysis scheme (in short, SML-MDA). The conducted security analysis and formal security verification of the proposed SMLMDA prove its security against various types of potential attacks. The proposed SML-MDA is then compared with the other similar competing schemes, and its performance has been found to be better in terms of various performance metrics like accuracy and F1-score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction to: Embeddability of pairs of weighted quasi-arithmetic means into a semiflow

引用

Aequationes mathematicae 2021年第3期95卷 599-600页

作者： Głazowska, Dorota Jarczyk, Justyna Jarczyk, Witold Faculty of Mathematics Computer Science and Econometrics University of Zielona Góra Zielona Góra Poland Institute of Mathematics and Informatics The John Paul II Catholic University of Lublin Lublin Poland

A dumb mistake in the formulation of Theorem 6 has been corrected.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

arXiv

引用

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Trans-DF: A Transfer Learning-based end-to-end Deepfake Detector 5

Trans-DF: A Transfer Learning-based end-to-end Deepfake Dete...

引用

5th IEEE International Conference on Computing Communication and Automation, ICCCA 2020

作者： Patel, Mohil Gupta, Aaryan Tanwar, Sudeep Obaidat, M.S. Institute of Technology Nirma University Department of Computer Science and Engineering Gujarat India University of Sharjah UAE King Abdullah II School of It University of Jordan College of Computing and Informatics Jordan

ISBN: (数字)9781728163246

ISBN: (纸本)9781728163246

With the advent of information and communication technologies, there have been breakthrough developments in the field of Artificial Intelligence (AI). Moreover, increasing computation power and decreasing processing times, new applications are being developed at great speeds. One such application is Deepfakes, which tackles the increased manipulated and forged media content. But these fake images and videos hamper the security and privacy of individuals and can have large-scale religious, communal, or political implications that may prove to be catastrophic for a nation. The face swapped content at times can be identified by human observation, but with the use of Generative adversarial networks (GANs), such forged content can be developed with is hard to be identified even by humans. Hence, detecting such videos and images is a challenging task for researchers. Motivated from these gaps, in this paper, we propose a pipeline for detecting and extracting human faces from videos, process them to extract features from them, and then classify them as real or fake. The results of the proposed model achieved an accuracy of 90.2% for classifying fake images from real ones. © 2020 IEEE.

关键词： Generative adversarial networks

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：