| 1. |
- Ait-Mlouk, Addi, et al.
(författare)
-
FedQAS : Privacy-Aware Machine Reading Comprehension with Federated Learning
- 2022
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 12:6
-
Tidskriftsartikel (refereegranskat)abstract
- Machine reading comprehension (MRC) of text data is a challenging task in Natural Language Processing (NLP), with a lot of ongoing research fueled by the release of the Stanford Question Answering Dataset (SQuAD) and Conversational Question Answering (CoQA). It is considered to be an effort to teach computers how to "understand" a text, and then to be able to answer questions about it using deep learning. However, until now, large-scale training on private text data and knowledge sharing has been missing for this NLP task. Hence, we present FedQAS, a privacy-preserving machine reading system capable of leveraging large-scale private data without the need to pool those datasets in a central location. The proposed approach combines transformer models and federated learning technologies. The system is developed using the FEDn framework and deployed as a proof-of-concept alliance initiative. FedQAS is flexible, language-agnostic, and allows intuitive participation and execution of local model training. In addition, we present the architecture and implementation of the system, as well as provide a reference evaluation based on the SQuAD dataset, to showcase how it overcomes data privacy issues and enables knowledge sharing between alliance members in a Federated learning setting.
|
|
| 2. |
- Al Khatib, Sultan M., et al.
(författare)
-
Selection of human evaluators for design smell detection using dragonfly optimization algorithm : An empirical study
- 2023
-
Ingår i: Information and Software Technology. - Amsterdam : Elsevier. - 0950-5849 .- 1873-6025. ; 155
-
Tidskriftsartikel (refereegranskat)abstract
- Context: Design smell detection is considered an efficient activity that decreases maintainability expenses and improves software quality. Human context plays an essential role in this domain.Objective: In this paper, we propose a search-based approach to optimize the selection of human evaluators for design smell detection.Method: For this purpose, Dragonfly Algorithm (DA) is employed to identify the optimal or near-optimal human evaluator's profiles. An online survey is designed and asks the evaluators to evaluate a sample of classes for the presence of god class design smell. The Kappa-Fleiss test has been used to validate the proposed approach. Results: The results show that the dragonfly optimization algorithm can be utilized effectively to decrease the efforts (time, cost ) of design smell detection concerning the identification of the number and the optimal or near-optimal profile of human experts required for the evaluation process.Conclusions: A Search-based approach can be effectively used for improving a god-class design smell detection. Consequently, this leads to minimizing the maintenance cost.
|
|
| 3. |
- Alawadi, Sadi, 1983-, et al.
(författare)
-
FedCSD : A Federated Learning Based Approach for Code-Smell Detection
- 2024
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 12, s. 44888-44904
-
Tidskriftsartikel (refereegranskat)abstract
- Software quality is critical, as low quality, or 'Code smell,' increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting 'God Class,' to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model's highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers. © 2013 IEEE.
|
|
| 4. |
- Alawadi, Sadi, 1983-, et al.
(författare)
-
Toward efficient resource utilization at edge nodes in federated learning
- 2024
-
Ingår i: Progress in Artificial Intelligence. - : Springer Science+Business Media B.V.. - 2192-6352 .- 2192-6360. ; 13:2, s. 101-117
-
Tidskriftsartikel (refereegranskat)abstract
- Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However, computational resource constraints and network communication can become a severe bottleneck for larger model sizes typical for deep learning (DL) applications. Edge nodes tend to have limited hardware resources (RAM, CPU), and the network bandwidth and reliability at the edge is a concern for scaling federated fleet applications. In this paper, we propose and evaluate a FL strategy inspired by transfer learning in order to reduce resource utilization on devices, as well as the load on the server and network in each global training round. For each local model update, we randomly select layers to train, freezing the remaining part of the model. In doing so, we can reduce both server load and communication costs per round by excluding all untrained layer weights from being transferred to the server. The goal of this study is to empirically explore the potential trade-off between resource utilization on devices and global model convergence under the proposed strategy. We implement the approach using the FL framework FEDn. A number of experiments were carried out over different datasets (CIFAR-10, CASA, and IMDB), performing different tasks using different DL model architectures. Our results show that training the model partially can accelerate the training process, efficiently utilizes resources on-device, and reduce the data transmission by around 75% and 53% when we train 25%, and 50% of the model layers, respectively, without harming the resulting global model accuracy. Furthermore, our results demonstrate a negative correlation between the number of participating clients in the training process and the number of layers that need to be trained on each client’s side. As the number of clients increases, there is a decrease in the required number of layers. This observation highlights the potential of the approach, particularly in cross-device use cases. © The Author(s) 2024.
|
|
| 5. |
- Alkhabbas, Fahed, et al.
(författare)
-
ART4FL : An Agent-based Architectural Approach for Trustworthy Federated Learning in the IoT
- 2023
-
Ingår i: 8th International Conference on Fog and Mobile Edge Computing, FMEC 2023. - : Institute of Electrical and Electronics Engineers (IEEE). - 9798350316971 - 9798350316988 ; , s. 270-275
-
Konferensbidrag (refereegranskat)abstract
- The integration of the Internet of Things (IoT) and Machine Learning (ML) technologies has opened up for the development of novel types of systems and services. Federated Learning (FL) has enabled the systems to collaboratively train their ML models while preserving the privacy of the data collected by their IoT devices and objects. Several FL frameworks have been developed, however, they do not enable FL in open, distributed, and heterogeneous IoT environments. Specifically, they do not support systems that collect similar data to dynamically discover each other, communicate, and negotiate about the training terms (e.g., accuracy, communication latency, and cost). Towards bridging this gap, we propose ART4FL, an end-to-end framework that enables FL in open IoT settings. The framework enables systems’ users to configure agents that participate in FL on their behalf. Those agents negotiate and make commitments (i.e., contractual agreements) to dynamically form federations. To perform FL, the framework deploys the needed services dynamically, monitors the training rounds, and calculates agents’ trust scores based on the established commitments. ART4FL exploits a blockchain network to maintain the trust scores, and it provides those scores to negotiating agents’ during the federations’ formation phase. © 2023 IEEE.
|
|
| 6. |
- Alkharabsheh, Khalid, et al.
(författare)
-
A comparison of machine learning algorithms on design smell detection using balanced and imbalanced dataset : A study of God class
- 2022
-
Ingår i: Information and Software Technology. - : Elsevier B.V.. - 0950-5849 .- 1873-6025. ; 143
-
Tidskriftsartikel (refereegranskat)abstract
- Context: Design smell detection has proven to be a significant activity that has an aim of not only enhancing the software quality but also increasing its life cycle. Objective: This work investigates whether machine learning approaches can effectively be leveraged for software design smell detection. Additionally, this paper provides a comparatively study, focused on using balanced datasets, where it checks if avoiding dataset balancing can be of any influence on the accuracy and behavior during design smell detection. Method: A set of experiments have been conducted-using 28 Machine Learning classifiers aimed at detecting God classes. This experiment was conducted using a dataset formed from 12,587 classes of 24 software systems, in which 1,958 classes were manually validated. Results: Ultimately, most classifiers obtained high performances,-with Cat Boost showing a higher performance. Also, it is evident from the experiments conducted that data balancing does not have any significant influence on the accuracy of detection. This reinforces the application of machine learning in real scenarios where the data is usually imbalanced by the inherent nature of design smells. Conclusions: Machine learning approaches can effectively be used as a leverage for God class detection. While in this paper we have employed SMOTE technique for data balancing, it is worth noting that there exist other methods of data balancing and with other design smells. Furthermore, it is also important to note that application of those other methods may improve the results, in our experiments SMOTE did not improve God class detection. The results are not fully generalizable because only one design smell is studied with projects developed in a single programming language, and only one balancing technique is used to compare with the imbalanced case. But these results are promising for the application in real design smells detection scenarios as mentioned above and the focus on other measures, such as Kappa, ROC, and MCC, have been used in the assessment of the classifier behavior. © 2021 The Authors
|
|
| 7. |
- Alkharabsheh, Khalid, et al.
(författare)
-
Analysing Agreement Among Different Evaluators in God Class and Feature Envy Detection
- 2021
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 9, s. 145191-145211
-
Tidskriftsartikel (refereegranskat)abstract
- The automatic detection of Design Smells has evolved in parallel to the evolution of automatic refactoring tools. There was a huge rise in research activity regarding Design Smell detection from 2010 to the present. However, it should be noted that the adoption of Design Smell detection in real software development practice is not comparable to the adoption of automatic refactoring tools. On the basis of the assumption that it is the objectiveness of a refactoring operation as opposed to the subjectivity in definition and identification of Design Smells that makes the difference, in this paper, the lack of agreement between different evaluators when detecting Design Smells is empirically studied. To do so, a series of experiments and studies were designed and conducted to analyse the concordance in Design Smell detection of different persons and tools, including a comparison between them. This work focuses on two well known Design Smells: God Class and Feature Envy. Concordance analysis is based on the Kappa statistic for inter-rater agreement (particularly Kappa-Fleiss). The results obtained show that there is no agreement in detection in general, and, in those cases where a certain agreement appears, it is considered to be a fair or poor degree of agreement, according to a Kappa-Fleiss interpretation scale. This seems to confirm that there is a subjective component which makes the raters evaluate the presence of Design Smells differently. The study also raises the question of a lack of training and experience regarding Design Smells.
|
|
| 8. |
- Alkharabsheh, Khalid, et al.
(författare)
-
Prioritization of god class design smell : A multi-criteria based approach
- 2022
-
Ingår i: JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES. - Amsterdam : Elsevier. - 1319-1578 .- 2213-1248. ; 34:10, s. 9332-9342
-
Tidskriftsartikel (refereegranskat)abstract
- Context: Design smell Prioritization is a significant activity that tunes the process of software quality enhancement and raises its life cycle.Objective: A multi-criteria merge strategy for Design Smell prioritization is described. The strategy is exemplified with the case of God Class Design Smell.Method: An empirical adjustment of the strategy is performed using a dataset of 24 open source projects. Empirical evaluation was conducted in order to check how is the top ranked God Classes obtained by the proposed technique compared against the top ranked God class according to the opinion of developers involved in each of the projects in the dataset.Results: Results of the evaluation show the strategy should be improved. Analysis of the differences between projects where respondents answer correlates with the strategy and those projects where there is no correlation should be done.
|
|
| 9. |
- Awaysheh, Feras M., et al.
(författare)
-
FLIoDT : A Federated Learning Architecture from Privacy by Design to Privacy by Default over IoT
- 2022
-
Ingår i: 2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC). - Piscataway, N.J. : IEEE. - 9798350334524 ; , s. 1-6
-
Konferensbidrag (refereegranskat)abstract
- The Internet of Things (IoT) realized exponential growth of smart devices with decent capabilities, promising an era of Edge Intelligence. This paradigm creates a timely need to shift many computations closer to the data source at the network's edge. Data privacy is paramount, as security breaches can severely impact such an environment with its vast attack surface. The advent of Federated learning (FL), a privacy-by-design with decentralized machine learning (ML), enables participants to collaboratively train a model without sharing their sensitive data. Nevertheless, privacy implications are a glaring concern and perrier for widening the utilization of FL approaches and their mass adoption over IoT applications. This paper introduces the notion of FL over the Internet of Disconnected Things (FLIoDT), a functionality separation of concerns following the air-gapped networks. FLIoDT provides a practical methodology to mitigate Data threats/attacks in the FL domain. FLIoDT proves a practical architectural approach to mitigate several attacks in an Edge environment. Data dredging and adversarial attacks, like data poisoning, to name some. This study investigates human activity recognition of health monitoring patient data over edge computing to validate FLIoDT. © 2022 IEEE.
|
|
| 10. |
- Awaysheh, F. M., et al.
(författare)
-
Security by Design for Big Data Frameworks Over Cloud Computing
- 2022
-
Ingår i: IEEE transactions on engineering management. - : Institute of Electrical and Electronics Engineers (IEEE). - 0018-9391 .- 1558-0040. ; 69:6, s. 3676-3693
-
Tidskriftsartikel (refereegranskat)abstract
- Cloud deployment architectures have become a preferable computation model of Big Data (BD) operations. Their scalability, flexibility, and cost-effectiveness motivated this trend. In a such deployment model, the data are no longer physically maintained under the user’s direct control, which raises new security concerns. In this context, BD security plays a decisive role in the widespread adoption of cloud architectures. However, it is challenging to develop a comprehensive security plan unless it is based on a preliminary analysis that ensures a realistic secure assembly and addresses domain-specific vulnerabilities. This article presents a novel security-by-design framework for BD frameworks deployment over cloud computing (BigCloud). In particular, it relies on a systematic security analysis methodology and a completely automated security assessment framework. Our framework enables the mapping of BigCloud security domain knowledge to the best practices in the design phase. We validated the proposed framework by implementing an Apache Hadoop stack use case. The study findings demonstrate its effectiveness in improving awareness of security aspects and reducing security design time. It also evaluates the strengths and limitations of the proposed framework, from which it highlights the main existing and open challenges in the BigCloud-related area.
|
|
