Publications

Shared transportation involves vehicles, drivers, and customers, the interactions among which could have potential long-term impacts on the business. Machine learning techniques, and their integration with existing models, have proved to significantly improve results. Availability of extensive unstructured textual data has fostered research in text generation and mining. Cognizance and analysis of such data has become crucial for modern commercial applications. Thus, in this article, sentiment analysis, using natural language processing, is used to quantify raw customer feedback, to obtain drivers' ratings and perform driver selection. Selection of the best drivers for ferrying riders is desired and modeled accordingly. An integrated vehicle routing problem with generalized fuzzy travel durations, and uncertain pick-up and drop demands, is modeled and solved using a hybrid genetic algorithm. Fuzzy simulations in a credibilistic environment are employed to evaluate the cost function. Performance of selected drivers is used to update driver ratings for the subsequent run, and the process is repeated multiple times. The results obtained authenticate the purpose of this article, and comparative analysis is performed to further corroborate the model's capability. An additional case of triangular fuzzy ratings is also illustrated, and its impact on the model discussed. Suggestions for driver classification are also provided for personnel management.

Rule–based fuzzy models have modular architectures and come with well-developed design methodologies such that they can build accurate models with good interpretabilities in system modeling. However, a large amount of private data needs to be used for statistical analysis and forecasting in rule–based fuzzy models. The purpose of this study is to build an intelligent model with high accuracy and versatility under the premise of data privacy and model security. To mitigate the risk of malicious attacks on privacy data during the analysis process, we have employed highly regarded differential privacy techniques to devise a novel rule-based fuzzy modeling approach. We propose a function approximation mechanism to reconstruct the objective function and add a perturbation mechanism to the objective function in Takagi-Sugeno rules model. Taking into account the delicate balance between data privacy and utility, we have innovatively introduced a Takagi-Sugeno rule-based model based on differential privacy. This model is applicable to both linear and nonlinear systems, offering protection to sensitive data privacy and model security within the system. We investigate the relationship between the interpretability of the model and the degree of privacy protection. By constructing a reasonable rule base, we achieve higher accuracy than other system modeling methods based on differential privacy. This paper compares the influence of the number of rules on differential privacy, and considers the algorithm performance under various noise distributions. It is shown that the Takagi-Sugeno rules model based on differential privacy has a strong ability to predict and analyze data.

Evaluating the holistic privacy risk (HPR) presented by a smart home ecosystem (SHE), encompassing both internal and external entities that may be targeted by different adversaries seeking to compromise users' privacy, can enhance the comprehensive understanding of the privacy risk landscape within the SHE. This matter is influenced by the complexity of risk surroundings, the diverse perspectives of users toward privacy, and the lack of historical data. Unfortunately, existing literature falls short in addressing these factors. To fill the gap, this article develops an innovative capability-oriented model that accommodates epistemic uncertainty and wisdom of crowds (WoC), designed to assist smart home device manufacturers in accurately assessing HPR posed by their SHEs. The model presents a method for representing subjective judgments that captures epistemic uncertainty and a technique for weighting individual judgments to mitigate overconfidence bias, thus effectively harnessing WoC. In addition, this model features two specialized methods: one for quantifying HPR and another for prioritizing associated single risks, both tailored to operate effectively within uncertain context. These innovative methods are versatile and can be applied to various risk assessment scenarios, especially where historical data are not available. The practicality and effectiveness of our model are demonstrated through a detailed case study.

Software repositories contain a wealth of information about the aspects related to software development process. For this reason, many studies analyze software repositories using methods of data analytics with a focus on clustering. Software repository clustering has been applied in studying software ecosystems such as GitHub, defect and technical debt prediction, software remodularization. Although some interesting insights have been reported, the considered studies exhibited some limitations. The limitations are associated with the use of individual clustering methods and manifesting in the shortcomings of the obtained results. In this study, to alleviate the existing limitations we engage multiple cluster validity indices applied to multiple clustering methods and carry out consensus clustering. To our knowledge, this study is the first to apply the consensus clustering approach to analyze software repositories and one of the few to apply the consensus clustering to software metrics. Intensive experimental studies are reported for software repository metrics data consisting of a number of software repositories each described by software metrics. We revealed seven clusters of software repositories and relate them to developers’ activity. It is advocated that the proposed clustering environment could be useful for facilitating the decision making process for business investors and open-source community with the help of the Gartner’s hype cycle.