检索结果-内蒙古大学图书馆

PCART: Automated Repair of Python API Parameter Compatibility Issues

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Shuai Xiao, Guanping Wang, Jun Lei, Huashan He, Gangqiang Liu, Yepang Zheng, Zheng The College of Computer Science and Technology The Key Laboratory for Safety-critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing China The Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China The School of Automation Science and Electrical Engineering Beihang University Beijing China

In modern software development, Python third-party libraries play a critical role, especially in fields like deep learning and scientific computing. However, API parameters in these libraries often change during evolution, leading to compatibility issues for client applications reliant on specific versions. Python’s flexible parameter-passing mechanism further complicates this, as different passing methods can result in different API compatibility. Currently, no tool can automatically detect and repair Python API parameter compatibility issues. To fill this gap, we introduce PCART, the first solution to fully automate the process of API extraction, code instrumentation, API mapping establishment, compatibility assessment, repair, and validation. PCART handles various types of Python API parameter compatibility issues, including parameter addition, removal, renaming, reordering, and the conversion of positional to keyword parameters. To evaluate PCART, we construct PCBENCH, a large-scale benchmark comprising 47,478 test cases mutated from 844 parameter-changed APIs across 33 popular Python libraries. Evaluation results demonstrate that PCART is both effective and efficient, significantly outperforming existing tools (MLCatchUp and Relancer) and the large language model ChatGPT (GPT-4o), achieving an F1-score of 96.49% in detecting API parameter compatibility issues and a repair precision of 92.26%. Further evaluation on 30 real-world Python projects from GitHub confirms PCART’s practicality. We believe PCART can significantly reduce the time programmers spend maintaining Python API updates and advance the automation of Python API compatibility issue repair. Copyright © 2024, The Authors. All rights reserved.

关键词： Python

Blockchain and Machine Learning for Fraud Detection: A Privacy-Preserving and Adaptive Incentive Based Approach

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pranto, Tahmid Hasan Hasib, Kazi Tamzid Akhter Md Rahman, Tahsinur Haque, A.K.M. Bahalul Islam, A.K.M. Najmul Rahman, Rashedur M. Department of Electrical and Computer Engineering North South University Dhaka1229 Bangladesh Department of Computer Science and Engineering Brac University Dhaka1212 Bangladesh Software Engineering LENS LUT University Finland

Financial fraud cases are on the rise even with the current technological advancements. Due to the lack of inter-organization synergy and because of privacy concerns, authentic financial transaction data is rarely available. On the other hand, data-driven technologies like machine learning need authentic data to perform precisely in real-world systems. This study proposes a blockchain and smart contract-based approach to achieve robust Machine Learning (ML) algorithm for e-commerce fraud detection by facilitating inter-organizational collaboration. The proposed method uses blockchain to secure the privacy of the data. Smart contract deployed inside the network fully automates the system. An ML model is incrementally upgraded from collaborative data provided by the organizations connected to the blockchain. To incentivize the organizations, we have introduced an incentive mechanism that is adaptive to the difficulty level in updating a model. The organizations receive incentives based on the difficulty faced in updating the ML model. A mining criterion has been proposed to mine the block efficiently. And finally, the blockchain network is tested under different difficulty levels and under different volumes of data to test its efficiency. The model achieved 98.93% testing accuracy and 98.22% Fbeta score (recall-biased f measure) over eight incremental updates. Our experiment shows that both data volume and difficulty level of blockchain impacts the mining time. For difficulty level less than five, mining time and difficulty level has a positive correlation. For difficulty level two and three, less than a second is required to mine a block in our system. Difficulty level five poses much more difficulties to mine the blocks. © 2022, CC BY.

关键词： Smart contract

E-tutor: Comprehensive Student Productivity Management System for Education

学校读者我要写书评

暂无评论

E-tutor: Comprehensive Student Productivity Management Syste...

Advancements in Computing (ICAC), International Conference on

作者： Kumuditha Silva Rashmin Induwara Malshan Wimukthi Sathsarani Poornika Udara Srimath S. Samaratunge Arachchillage Thilini Jayalath Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398106

With the advancement of technology, e-learning has emerged as predominant in the education sector. As students, parents, and educators acknowledged, adopting e-learning can offer several benefits over traditional learning techniques. Since more individuals are becoming acclimated to online learning platforms, these online platforms can provide a simple, instructive, and efficient mode of delivery. This novel approach could be improved with the aid of Artificial Intelligence (AI) to comprehend consumers more thoroughly and provide valuable and better-suited services. Most sectors in education, including universities, swiftly adapted to new educational methodologies because of their flexibility and productivity. Nevertheless, there are some downsides that young demography experiences, such as less instructiveness, distraction due to the absence of teachers, and poor IT literacy. Consequently, these drawbacks would recede the capability of students to assimilate content during the lecture. Therefore, the main objective of this research is to implement an E-learning platform with AI learning analytics to enhance students’ performance regularly while reducing the significant drawbacks of the E-learning platforms. This research consists of students’ focus detection, essay-based answer evaluation, note summarization, mind map generation, and personalized guidance facilities.

关键词： Productivity Performance evaluation Visualization computer aided instruction Electronic learning Demography Education

Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Wan Liu, Gang Chen, Xiaofeng Zhou, Yipeng College of Computer Science and Software Engineering ShenZhen University China Department of Computing Macquarie University Australia

Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

PBF-AMP-Onto: an ontology for powder bed fusion additive manufacturing processes 1

学校读者我要写书评

暂无评论

PBF-AMP-Onto: an ontology for powder bed fusion additive man...

1st International Workshop on Semantic Materials Science: Harnessing the Power of Semantic Web Technologies in Materials Science, SeMatS 2024

作者： Pour, Mina Abd Nikooie Tarafder, Prithwish Wiberg, Anton Li, Huanyu Moverare, Johan Lambrix, Patrick Department of Computer and Information Science Linköping University Linköping Sweden Swedish e-Science Research Centre Linköping University Linköping Sweden Department of Management and Engineering Linköping University Linköping Sweden Wallenberg Initiative Materials Science for Sustainability Linköping University Linköping Sweden Wallenberg AI Autonomous Systems and Software Program Linköping University Linköping Sweden

Additive manufacturing is an innovative production approach aimed at creating products that traditional techniques cannot produce with the desired quality and requirements. Throughout the additive manufacturing process, data is either used (such as materials properties, printer characteristics and settings) or generated (such as monitoring data during printing, slicing strategies setting parameters). However, managing such data with complex relationships remains a significant challenge in both research and industry in the additive manufacturing field. To address this issue, we developed a modular ontology that can be used as the basis for a framework that supports decision-making systems, facilitate semanticsaware data management, and enhance the understanding and optimization of additive manufacturing processes. In this paper we focus on one of the state-of-the-art additive manufacturing approaches, i.e., powder bed fusion. To show the use and the feasibility of our approach, we created a knowledge graph for an actual additive manufacturing experiment based on our ontology, and show how queries relevant to domain experts can be answered using this knowledge graph. © 2024 CEUR-WS. All rights reserved.

关键词： Ontology

A COMPREHENSIVE STUDY ON OCCLUSION INVARIANT FACE RECOGNITION UNDER FACE MASK OCCLUSIONS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hemathilaka, Susith Aponso, Achala Department of Computer Science and Software Engineering University of Westminster London United Kingdom Department of Computer Science Informatics Institute of Technology Colombo Sri Lanka

The face mask is an essential sanitaryware in daily lives growing during the pandemic period and is a big threat to current face recognition systems. The masks destroy a lot of details in a large area of face, and it makes it difficult to recognize them even for humans. The evaluation report shows the difficulty well when recognizing masked faces. Rapid development and breakthrough of deep learning in the recent past have witnessed most promising results from face recognition algorithms. But they fail to perform far from satisfactory levels in the unconstrained environment during the challenges such as varying lighting conditions, low resolution, facial expressions, pose variation and occlusions. Facial occlusions are considered one of the most intractable problems. Especially when the occlusion occupies a large region of the face because it destroys lots of official features. © 2022, CC BY.

关键词： Face recognition

Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Su, Xiaoxin Zhou, Yipeng Cui, Laizhong Lui, John C.S. Liu, Jiangchuan College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Shenzhen University Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong HKSAR Hong Kong School of Computing Science Simon Fraser University Canada

In Federated Learning (FL) paradigm, a parameter server (PS) concurrently communicates with distributed participating clients for model collection, update aggregation, and model distribution over multiple rounds, without touching private data owned by individual clients. FL is appealing in preserving data privacy;yet the communication between the PS and scattered clients can be a severe bottleneck. Model compression algorithms, such as quantization and sparsification, have been suggested but they generally assume a fixed code length, which does not reflect the heterogeneity and variability of model updates. In this paper, through both analysis and experiments, we show strong evidences that variable-length is beneficial for compression in FL. We accordingly present Fed-CVLC (Federated Learning Compression with Variable-Length Codes), which fine-tunes the code length in response of the dynamics of model updates. We develop optimal tuning strategy that minimizes the loss function (equivalent to maximizing the model utility) subject to the budget for communication. We further demonstrate that Fed-CVLC is indeed a general compression design that bridges quantization and sparsification, with greater flexibility. Extensive experiments have been conducted with public datasets to demonstrate that Fed-CVLC remarkably outperforms state-of-the-art baselines, improving model utility by 1.50%-5.44%, or shrinking communication traffic by 16.67%-41.61%. Copyright © 2024, The Authors. All rights reserved.

关键词： Data privacy

Intelligent Phishing Url Detection: A Solution Based on Deep Learning Framework 18

学校读者我要写书评

暂无评论

Intelligent Phishing Url Detection: A Solution Based on Deep...

18th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2021

作者： Butt, Muhammad Hassaan Farooq Li, Jian Ping Saboor, Tehreem Arslan, Muhammad Butt, Muhammad Adnan Farooq University of Electronic Science and Technology of China School of Computer Science and Engineering China Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Department of Computer Science Pakistan COMSATS University Islamabad Pakistan Foundation University Department of Software Engineering Pakistan

ISBN: (纸本)9781665413640

On the Internet, every different day, kinds of attacks are deployed on innocent users. Among all, phishing is the most severe attack in which users lose their credentials or private information and their financial status quickly. The attacker uses their credibility or sensitive information to harm the target or victim. The attacker is clever and uses different strategies to fetch user-sensitive information. The existing techniques fail to overcome these issues to some extent. This work focuses on discovering the essential features that help to differentiate the legitimate and illegitimate URLs. We applied a deep learning technique on the benchmark datasets to identify the pattern of phishing URLs. We used gradient boosted decision trees algorithm to train our model and applied the regular deeply connected neural network layers in various sequences and Adam optimizer. The most found patterns will help the system to detect phishing URLs and avoid phishing. We consider the accuracy, Ff-score, and Root Mean Square Error (RMSE) as our evaluation metrics for model evaluation. The results show that the trained model can achieve an approximately 92% accuracy and 94% f-score. © 2021 IEEE.

关键词： Mean square error

Implementation of Convolutional Neural Networks deep learning approach to Classify Melanoma Skin Cancer

学校读者我要写书评

暂无评论

Implementation of Convolutional Neural Networks deep learnin...

Wireless and Optical Technologies (GCWOT), 2020 Global Conference on

作者： Adnan Afroz Razia Zia Shaheena Noor Andres Ortiz Garcia Sarman Shams Shoaib Mughal Software Enginneering Department Sir Syed University Engineering and Technology Karachi Pakistan Electrical Engineering Department Sir Syed University Engineering and Technology Karachi Pakistan Computer Engineering Department Sir Syed University Engineering and Technology Karachi Pakistan E.T.S Ingenieria De Telecomunicacion Universidad De Malaga Malaga Spain Biomedical Engineering Department Sir Syed University Engineering and Technology Karachi Pakistan Computer Engineering Department Bahria University Karachi Campus

A kind of deadly skin tumor called melanoma is arguably very lethal since it accounts for the majority of skin cancer fatalities. Melanomas are often brown or black in color because melanocyte cells, which produce melanin, are the source of the disease. The DNA of skin cells is damaged by UV light, which is the main cause of melanomas. The analysis of the dermoscopy examination’s findings and comparison with medical sciences are frequently used in the manual diagnosis of melanoma cancer. Human subjectivity has a strong impact on manual detection, which renders it unreliable in some circumstances. In order to classify the outcomes of the dermoscopy test and to determine the results more precisely with a comparatively shorter amount of time, computer-assisted technology is required. Problem statement, planning, execution, and testing are the first steps in the creation of this application. To identify picture data, the research study combines deep machine learning approach using Convolutional Neural Network technique along with LeNet-5 architectural model. With a variable number of training and testing epochs and 44 photos from the training results, the experiment with the best success rate (93% in training and 100% in testing) required 176 images and 100 epochs of training data. Programming language such as Python with utilization of Keras library, which serves as the Tensorflow back-end, were used to construct this application.

关键词： Training Wireless communication Training data Melanoma Manuals Skin Data models