International Journal of System Assurance Engineering and Management最新文献

Decision making problems with ambiguous data often arise in numerous practical fields which can be formulated as optimization models in fuzzy environment. This paper develops a new mathematical model using a proposed methodology to efficiently solve a multi-objective linear fuzzy fractional programming problem in trapezoidal fuzzy environment and generate a set of nondominated solutions. The concept of fuzzy cuts with different degrees of satisfaction is implemented which transforms the fuzzy optimization into an equivalent interval valued optimization. Subsequently, interval valued linear functions approximate the fuzzy valued fractional functions based on Taylor’s series expansion. Finally, a proposed concept using weighting sum approach with varying weight vectors is utilized to design a mathematical model which generates the set of nondominated solutions. Two numerical examples including an existing problem and an additional practical problem in the field of production, are solved for the illustration of the proposed model. The results of the numerical problems are comparatively discussed with graphical analysis to justify the feasibility and applicability of the proposed model.

Community question answering (CQA) sites have become a popular medium for exchanging knowledge with other members of the community. Users can publish questions, answers, and comments on these sites. Furthermore, users of the CQA sites are able to express their thoughts on a post by voting positively or negatively. People anticipate rapid and high-quality answers from these CQA sites, which are often provided by a small group of users known as experts. A large number of queries remain unanswered on these forums, emphasising the scarcity of experts. To address this problem, we presented a methodology for predicting promising expert users for CQA sites. Promising experts are individuals that have just joined the community and have shown glimpses of producing high-quality content to the site. The suggested method looks at the first month of a user’s postings to determine whether or not the individual is a promising expert. The experimental findings revealed that the suggested approach accurately predicts future experts.

Abstract

The construction of information management system is the basis to consider the management level of an enterprise, so the construction of enterprise management information system is an important problem to be solved by enterprises. Using advanced software technology is an important way to improve the level of enterprise management. At the same time, innovative management form is also an important embodiment of enterprise system innovation. The development of cloud platform and Internet of things technology has brought revolutionary impact on enterprise management mode, methods and means. Based on information reconstruction model and Internet of things technology, this paper constructs an enterprise integrated management system, in order to provide reference for the development of enterprises. Novelty of the paper is: (1) Infrastructure level. The comprehensive management informatization is very important to the enterprise management decision-making, which is the key to improve the management level of the enterprise, hence, we use the novel MIS model to make the system efficient. We improve the traditional MIS model to make it fit for the business analytic process. (2) Algorithm design level. The traditional genetic algorithm will converge to a point in the iterative solution, resulting in inbreeding and destroying the diversity of the population. Therefore, the algorithm can only get the internal optimal value and cannot get the global optimal solution. Hence, we consider the novel data analytic model to make the system efficient. We optimize the traditional GA to make it robust for the complex data scenarios. (3) Application level. The business intelligence scenario is considered as the applications. The performance of the proposed pipeline is verified through the experimental analysis, we compare the proposed model with the latest ones and test the performance on regression performance, average response time of the system, number of hits per second of the system and the overall comparison analysis.

Abstract

Dicing saw is a key equipment in chip packaging, in which the servo performance of each axis affects the scribing accuracy. Since the Y-axis is used to locate the micron-level cutting street, its servo positioning accuracy is required to be very high. In this paper, a variable forgetting factor fuzzy iterative learning control (VFF-FILC) with tracking differentiator is proposed for the high-precision localization of the Y-axis electromechanical servo system of the dual-axis wheel dicing saw model 8230 manufactured by Advanced Dicing Technologies. The method combines fuzzy control with iterative learning control to overcome the problem of poor anti-interference ability of traditional PID control. VFF-FILC reduces the overshoot and build-up time, and also improves the tracking performance by adaptively adjusting the learning rate of the ILC algorithm according to the tracking error of the system. To address the problem of noise interference with the Y-axis servo system, tracking differentiator is used to process the input position signal. In order to verify the superiority of the proposed design, it is compared with three conventional controllers in MATLAB/SIMULINK platform and anti-interference experiments are conducted. The results show that the VFF-FILC reduces the rise time by 28.57% and the overshoot by 88.23% compared to the PID controller, which proves the superiority of the proposed method in the Y-axis servo system of the wheel dicing saw.

Abstract

Automatic text summarization (ATS) plays a vital role in condensing original text documents while preserving the most crucial information. Its benefits extend to various domains, including e-Learning systems, where educational content can be summarized to facilitate easier access and comprehension. Multi-document summarization (MDS) techniques enable the creation of concise summaries from groups of related text documents. Leveraging MDS for summarizing learning materials opens new avenues, offering students and teachers reference summaries for enhanced learning experiences. This paper introduces a concept-based Integer Linear Programming model for summarizing learning materials, leveraging a phrase embedding technique. Phrases are treated as fundamental and significant semantic building blocks of sentences, facilitating the comprehension and summarization of documents. Embedding techniques are employed to semantically identify related phrases, eliminate redundancy, and enhance coherence through vector representations. Summaries are generated using the ILP technique, selecting key sentences and reducing redundancy with phrase vectors. The paper proposes sentence reordering techniques based on phrases and sentences to further enhance coherence. The resulting summaries are automatically evaluated using ROUGE metrics, demonstrating the superior performance of the proposed approach compared to various benchmark and baseline methods on both the DUC 2004 benchmark dataset and the newly created educational dataset, EduSumm.

Air pollution is now one of the world's most serious environmental problems. It represents a significant hazard to both health and the climate. Urban air quality is steadily declining, affecting not only the air itself but also impacting the quality of water and land. This paper explores the utilization of machine learning-based algorithms for analysis and prediction of air quality in smart cities. In this paper, smart cities for which air quality index (AQI) is calculated are Ahmedabad, Delhi, Lucknow, Gurugram, and Mumbai. The comparative analysis of different Machine Learning algorithms such as Random Forest Regression (RF), Decision Tree Regression, Linear regression, XgBoost and proposed hybrid model which is combination of Random forest and Xgboost model, have been discussed in the paper. The analysis has been carried out using a machine learning-based algorithm to determine which pollutant is the primary source of pollution in a smart city so that preventative steps can be implemented to reduce air pollution.

In an era where the relentless evolution of cyber threats necessitates the perpetual advancement of security measures, the detection of obfuscated malware has emerged as a formidable challenge. The clandestine tactics employed by malicious actors demand innovative solutions that transcend conventional approaches. In this context, this research present a groundbreaking research endeavor that redefines the frontiers of obfuscated malware detection using artificial intelligence. In this research, a comprehensive methodology is introduced that combines three pivotal feature selection techniques: correlation analysis, mutual information, and principal component analysis. This hybrid approach not only enhances the discrimination of meaningful features but also ensures the efficiency and effectiveness of the feature subset, thus mitigating the curse of dimensionality. To harness the full potential of these meticulously selected features, an array of ensemble-based machine learning algorithms, including AdaBoost, stacking, random forest, bagging, and voting, is deployed. Amongst these, our findings demonstrate that AdaBoost emerges as the preeminent choice, achieving unprecedented levels of performance. The outcomes underscore the profound impact of our research in the realm of obfuscated malware detection, a paradigm shift that reimagines the very essence of security. In a world where cybersecurity challenges continually escalate, our research represents a pivotal milestone in the unceasing battle to safeguard digital landscapes. It is an exultant testament to the boundless potential of innovative feature selection techniques and the supremacy of AdaBoost within the domain of malware detection.

The perishable nature of food signifies that managing raw material inventory is a crucial aspect of the food industry. The present study focuses on the reliability assessment of a food industrial system, considering the synchronization of its raw material inventory and its food processing module. The raw material inventory encounters two distinct types of failures: one arises from the shortage of raw material, while the other stems from malfunctions in the inventory’s cooling system. An inspection is conducted to detect the type of failure in the raw material inventory. Two types of repairmen, namely operator and fitter, are employed to address the failures occurring in both the raw material inventory and the food processing module. The semi-Markov process and regenerative point technique are deployed for the dual purpose of evaluating the reliability indices and conducting availability sensitivity analysis so as to provide guidance to the manufacturers for enhancing the processing of production lines.

A charge scheduling strategy is a robust approach to schedule the charging strategies in electric vehicles (EVs) from a broad perspective with the aim of evading the overloading of charging stations and enhancing energy efficiency. However, devising an effective charging scheduling schemefor attaining optimal energy consumption still prevails as a complicated problem, particularly while considering the synchronized behavior of both charging stations as well as EVs. Here, a robust QoS-based charge scheduling approach was developed, which exploits the vehicular Adhoc networks (VANETs) with the improved functionalities for enabling communication between the vehicle-traffic server, road-side units (RSUs), and various EVs on roads. An optimal routing is performed by the Fractional-social sky driver (Fractional SSD), which is devised by the incorporation of the Fractional calculus (FC) and social sky driver (SSD) optimization. Here, the multi-objectives, namely, distance, battery power, and predicted traffic density are considered where the traffic density is effectively predicted using deep recurrent neural network (Deep RNN). Then, the charge scheduling process is executed by the utilization of the developed optimization technique called Fractional-social water cycle algorithm (Fractional SWCA)-based scheduling algorithm by taking into account the QoS-based fitness objective, likepriority, response time, and latency. Moreover, the proposed Fractional SWCA is developed by the integration of fractional SSD and water cycle algorithm (WCA). The performance of the devisedscheme is evaluated withmeasures, like metrics, delay, traffic density, fitness, total trip time, percentage of successful allocation, and power with the values of 8.429 min, 4.8 per lane, 24.571, 49.421 min, 94.494%, and 14,135.72 J.

In this research work, two Back to Back connected 2-level voltage source inverters (BBC-VSI) under three phase three wire weak utility grid is examined. Generally, the challenges addressed in the modern utility grid are end users’ nonlinear loads and dependency on conventional energy sources. The end users’ nonlinear loads generate power quality (PQ) issues and dependency on conventional energy sources raises environment pollution and economic crises. The BBC-VSI based distribution static compensator (DSTATCOM) topology consists of two voltage source inverters (VSIs) supplied by a distributed energy resources (DERs) supported common DC-link capacitor. A sparse least mean squares (SLMS) technique is selected for generating the pulses IGBTs. The SLMS technique offers high estimation speed, less than one cycle weight convergence, fast transient response and small error in steady state over conventional technique. A holistic comparison is performed between the BBC-VSI and VSI using the field programmable gate arrays (FPGA) SPARTAN-6 control board regarding optimal power flow control, which shows the BBC-VSI is competitive. Also, it is authenticated under different conditions like source current shaping before and after compensation, source power failure, DER power fluctuation, nonlinear load variation, etc., which are naturally encountered in a modern utility grid.