Energy-efficient production scheduling research has received much attention because of the massive energy consumption manufacturing process. In this article, we study an energy-efficient job-shop problem with sequence-dependent setup time, aiming to minimize makespan, total tardiness and simultaneously. To effectively evaluate select solutions for a multiobjective optimization nature, novel fitness evaluation mechanism (FEM) based on fuzzy relative entropy (FRE) is developed. FRE...

Numerous studies on mental depression have found that tweets posted by users with major depressive disorder could be utilized for detection. The potential of sentiment analysis detecting through an social media messages has brought increasing attention to this field. In article, we propose 90 unique features as input a machine learning classifier framework using texts. Derived from combination feature extraction approaches lexicons and textual contents, these are able provide impressive...

Financial news disclosures provide valuable information for traders and investors while making stock market investment decisions. Essential but challenging, the prediction problem has attracted significant attention from both researchers practitioners. Conventional machine learning models often fail to interpret content of financial due complexity ambiguity natural language used in news. Inspired by success recurrent neural networks (RNNs) sequential data processing, we propose an ensemble...

Digital Twins (DTs) are dynamic digital representations of physical objects and systems, including their associated processes environments. Using real-time data analytics, modelling, simulation 'what-if' scenarios, they can enable valuable understanding decision-support for managing a system. One potential application DTs is the management natural landscapes. However, despite critical impact humans on environment, none environment found in literature include human systems that environment....

Purpose Despite the widespread use of mobile government (m-government) services in developed countries, adoption and acceptance m-government among citizens developing countries is relatively low. The purpose this study to explore most critical determinants a country context. Design/methodology/approach unified theory technology (UTAUT) extended with perceived mobility communication (MCS) was used as theoretical framework. Data collected from 216 users across Bangladesh analyzed two stages....

We present an evolutionary game model that integrates the concept of tags, trust and migration to study how in social physical groups influence cooperation decisions. All agents have a tag, they gain or lose other tags as interact with agents. This different determines their players groups. In contrast models literature, our does not use determine cooperation/defection decisions agents, but rather Agents decide whether cooperate defect based purely on learning (i.e. imitation from others)....

Residuary resistance prediction is an important initial step in the process of designing a sailing yacht. Being able to predict residuary accurately crucial for calculating required propulsive power and ensuring good performance This paper presents two- layer Wang-Mendel (WM) fuzzy approach improve approximation ability WM model this task. Unlike traditional method, which consequent its rules set, our proposed corresponds rule base. We apply top-down method fuzzy-rule clustering construct...

We propose a multi-classifier ensemble model based on particle swarm optimization (PSO) for the evaluation of personal credit risk in peer-to-peer (P2P) lending platforms. In proposed method, we consider differences and complementarity base classifiers' performance use PSO to optimize their weights. Experimental results show that our P2P scoring outperforms both single other benchmark models. Among examined variants, with 100 particles is best.

This paper presents a symbiotic organism search (SOS)-based support vector regression (SVR) ensemble for predicting the printed circuit board (PCB) cycle time of surface-mount-technology (SMT) production lines. Being able to predict PCB accurately is essential optimising SMT schedule. Although machine simulator can be reliably used single-type production, it time-consuming and often inaccurate applied highly mixed orders in multiple flexible Due dynamic changes both lines, there diverse set...

This paper presents an implementation on modelling the database security using agent-based simulation (ABS). While ABS has been widely used for social simulations since 1990s, not many previous studies have tried simulating scenarios in more technical domains and it is main objective of this work to fill gap. We develop a program that includes permission rules immediate fixing corrupted data. show when privileges are selectively granted based certain regulations, can be dramatically...

In the big data era, machine learning algorithms are extensively used for sentiment polarity prediction. However, identifying correct algorithm and its parameter settings problem at hand can be a difficult task. We propose system based on Particle Swarm Optimisation (PSO) to find best optimise parameters The system's design consists of two layers, namely multi-PSO layer knockout layer. From experimental results, we that each PSO in could classifiers processed. Overall, is able determine...

Migration is one of the many responses humans and societies make to ongoing demographic, economic, societal environmental changes. In this work, we use agent-based modeling (ABM) study dynamics migration flows across provinces cities in Mekong Delta, Vietnam. The strength ABM that it allows a bottom-up approach focuses on how individuals decisions complex system comprising various factors. Outputs our model are automatically calibrated with actual data using genetic algorithm. This automated...

The Travelling Salesman Problem (TSP), one of the most famous combinatorial optimisation problems, has been widely studied for half a century now. state-of-the-art solutions proposed in recent years seem to have focused on nature-inspired algorithms. While good performance reported many these algorithms, they are considerably expensive terms computation. In this paper, we describe hybrid solution based nearest neighbour algorithm and progressive improvement algorithm. is simple search that...

Abstract The interior search algorithm (ISA) is an optimization inspired by esthetic techniques used for design and decoration. has only one parameter, controlled θ , uses evolutionary boundary constraint handling (BCH) strategy to keep itself within admissible solution space while approaching the optimum. We apply ISA find optimal weight of truss structures with frequency constraints. Sensitivity ISA's performance parameter BCH investigated considering different values techniques. This...