School of Computer Science and Informatics
Permanent URI for this collection
Browse
Recent Submissions
Item Embargo Self-learning brainstorm optimization for synchronization of operations and maintenance toward dual resource-constrained flexible job shops(Elsevier, 2025-05-10) Yan, Qi; Wang, Hongfeng; Yang, Shengxiang; Fu, YapingIn semi-automated flexible job shop manufacturing scenarios such as furniture customization and circuit board assembly, machine and worker resources need to be flexibly assigned to the processing of each operation, to improve the efficiency of human-machine collaboration and reduce the makespan. Driven by the practical need, the dual resource-constrained flexible job shop scheduling problem (DRCFJSP) has gradually attracted attention from the academic community. However, preventive maintenance (PM) of machines as a key constraint tends to be overlooked in previous research. In this study, a synchronization optimization of the DRCFJSP and PM scheduling is proposed and a joint decision-making model is established, to strike a balance between flexible job shop operations and maintenance. A self-learning brainstorm optimization algorithm (SLBOA) is developed to solve the model. In the SLBOA, an adaptive K-means algorithm based on the silhouette method is employed for flexible clustering, and four global update strategies are adaptively selected using the Q-learning algorithm to facilitate an effective interaction of individuals between different clusters. Furthermore, two knowledge-based local search methods are used to enhance the exploration of elite solutions within the necessary neighborhood structure. Experimental results show that the SLBOA outperforms four state-of-the-art algorithms in solving the proposed DRCFJSP with PM.Item Embargo A prediction approach based on long short-term memory networks for dynamic multi-objective optimization(Elsevier, 2025-04-24) Xu, Biao; Rang, Gejie; Xie, Ruijie; Li, Wenji; Gong, Dunwei; Fan, Zhun; Yang, Shengxiang; He, JieDynamic multiobjective optimization problems (DMOPs) present significant challenges to conventional evolutionary optimization methods because of the continuous changes in their Pareto-optimal sets (PSs) and fronts (PFs). Prediction-driven approaches have demonstrated potential in rapidly adapting to these changes. However, many existing methods depend on linear models to forecast the evolving PSs, which may be restrictive. To counteract this limitation, this research presents a novel dynamic multiobjective evolutionary optimization algorithm that incorporates predictions from long short-term memory (LSTM) networks. Initially, in our methodology, the PS for each problem is segmented into multiple clusters, and the centroid of each cluster is identified. These cluster centroids, representing the PSs across various environmental conditions, are then transformed into a series of time series data. The LSTM network models are subsequently trained on this time series data as input samples. Utilizing these refined models, the centroids of the evolving PSs are predicted with improved precision. Moreover, to enhance the performance of the algorithm, an innovative population-generation strategy is also introduced that guarantees a well-converged and diverse starting population. Our proposed algorithm undergoes rigorous testing using benchmark functions, and the outcomes validate its proficiency in tackling DMOPs, showing superior performance compared to existing state-of-the-art algorithms.Item Embargo Cognitive behavioural characteristics identification for remote user authentication for cybersecurity(Elsevier, 2025-05-01) Orun, A.; Kurugollu, F.; Orun, E.Nowadays cyber-attacks keep threatening global networks and information infrastructures. Day-by-day, the threat is gradually getting more destructive and harder to counter, as the global networks continue to enlarge exponentially with limited security counter-measures. This occurrence urgently demands more sophisticated methods and techniques, such as multi-factor authentication and soft biometrics to respond to evolving threats. This paper is concerned with behavioural soft biometrics and proposes a multidisciplinary remote cognitive observation technique to meet today’s cybersecurity needs. The proposed method introduces a non-traditional “cognitive psychology” and “artificial intelligence” based approach. According to contemporary cognitive psychology research, human cognitive processes can be affected by many different personal factors and emotional states which are specific to an individual. Those factors mainly include personal perception, memory, decision-making, reasoning, learning, etc. In this study we focus on visual (graphical) perception with the support of graphical stimuli environments and investigate how such personal cognitive factors can be exploited within the cybersecurity area for remote user authentication. This technique enables remote access to the cognitive behavioural parameters of an intruder/hacker without any physical contact via online connection, disregarding the distance of the threat. The results show that cognitive stimuli provide crucial information for a behavioural user authentication system to classify the user as “authentic” or “intruder”. The ultimate goal of this work is to develop a supplementary cognitive cyber security tool for “next generation” secure online banking, finance or trade systems.Item Embargo A variable window multi-interval rescheduling optimization algorithm for dynamic flexible job shop problem(Elsevier, 2025-04-21) Guo, Zeyin; Wei, Lixin; Li, Xin; Yang, Shengxiang; Zhang, JinluThe dynamic flexible workshop scheduling problem (DFJSP) requires the generation of new scheduling plans after being subjected to dynamic disturbances. Due to the reconfigurability of chromosomal gene, scheduling schemes have a large search space, which poses challenges for solving scheduling schemes. Therefore, a variable window multi-interval optimization (VWMI) rescheduling algorithm is proposed to solve the DFJSP. A nonlinear adaptive crossover probability and mutation probability function is proposed to address the issue of combinatorial optimization easily getting stuck in local optima. Based on the mapping relationship between individual space and objective space, a spatial joint selection method is proposed to select diverse individuals. Compared with other algorithms in dynamic workshop test cases, the rescheduling strategy achieved 7 optimal performance values in 15 test cases, with a maximum time efficiency improvement of 30.2%. In addition, the VWMI achieved 11 good performances in test cases, outperforming other optimization methods.Item Embargo A grey incidence model with fractional cumulative time delay effects and its applications(Elsevier, 2025-04-18) Sun, Jing; Dang, Yaoguo; Yang, Shengxiang; Wang, Junjie; Cai, YingTo identify the time-delay relationship between sequences more accurately, we propose a grey incidence model for time-delay systems. Before constructing the new model, we first clarify several time-delay relationships, including instantaneous form and cumulative form. Subsequently, the Weibull distribution is initially used to represent multiple types of time-delay effects. To reduce the computational load, the minimum cumulative step size is designed to simplify convolution, which is used to aggregate cumulative time delay effects in our research. This facilitates us to extract discrepancy information using relative angles and distances. To streamline the process of obtaining results, we utilize particle swarm optimization to optimize the self-adaptive parameters of the Weibull distribution and obtain cumulative time-delay information. The proposed model is validated through numerical experiments to analyze the time-delay effects of key influencing factors on air pollution. Finally, a comparative analysis with ten prevailing models demonstrates that our model not only integrates the functionalities of traditional models but also exhibits significant advantages in the detection of continuous time delay.Item Open Access A transformation method of non-cooperative to cooperative behavior by trust propagation in social network group decision making(IEEE, 2025-04-04) Gai, Tiantian; Chiclana, Francisco; Jin, Weidong; Zhou, Mi; Wu, JianIn the consensus reaching process (CRP) of social network group decision making (SN-GDM), the non-cooperative behavior exhibited by experts will hinder the achievement of group consensus. This paper develops a non-cooperative behavior management framework based on trust propagation and dynamic cooperation index under bidirectional feedback context. On the one hand, a trust propagation operator with trust decay is established to enhance the trust relationship between non-cooperative experts; On the other hand, the fuzzy preference relations are utilized as preference expression structure, and the mutual reinforcing effect between consensus and trust is explored to achieve the dynamic enhancement of cooperation index, thereby facilitating the transformation of non-cooperative behavior. Specifically, a cooperation index is formulated to identify the non-cooperation behavior. Subsequently, a non-cooperative behavior transformation method by dynamic cooperation index is investigated. Finally, a bidirectional feedback mechanism is provided for group consensus reaching. This paper provides an innovative strategy for detecting and managing non-cooperative behavior, an illustrative example and some analyses are presented to verify the validity of proposed method.Item Embargo An inter-subgroup compensation mechanism by Nash bargaining game for managing non-cooperative behavior in group decision making(Elsevier, 2025-04-19) Yang, Jie; Wu, Jian; Chiclana, Francisco; Cao, Mingshuo; Yager, Ronald R.Non-cooperative behavior exhibited by DMs when they must make excessive interest compromises hinders the achievement of group consensus. This study develops an inter-subgroup compensation mechanism using the Nash bargaining game under the minimum cost consensus model (MCCM) framework to managing non-cooperative behavior. First, a cooperative acceptability index (CAI) based on compromise limit costs is proposed to objectively identify non-cooperative behavior. By quantifying the acceptable compromise limit costs, the CAI ensures that consensus adjustments remain within acceptable bounds. Then, an inter-subgroup compensation mechanism is designed using the Nash bargaining game from the perspective of Kaldor–Hicks improvement. This mechanism enables cooperative DMs to incentivize non-cooperative peers via resource transfers, achieving dual optimization by minimizing collective costs and ensuring individual acceptability. Finally, a community renewal application example and comparison analysis are provided to illustrate the efficacy of the proposed approach.Item Embargo Divide and conquer? A combination of judgments method for comparing DSSs. Pairwise comparison vs. holistic paradigms(Elsevier, 2025-03-26) Saenz-Royo, Carlos; Chiclana, FranciscoDespite the prevalence of Decision Support Systems (DSSs) in the field of decision-making, there is a paucity of research dedicated to the evaluation and comparison of these systems. This paper put forward a novel approach to symbolically encoding a DSS, which enables the generalization of comparisons between DSSs for any distribution of performances of the alternatives. The only hypothesis required in the proposed methodology is that the probability of choosing each alternative is proportional to its latent performance. The approach developed is demonstrated with its application to compare two paradigms commonly employed in DSS: holistic versus pairwise. Using a set of three alternatives, the present study provides mathematical proof that a DSS based on the pairwise comparison paradigm achieves higher expected performance than a DSS based on the holistic evaluation paradigm. This result challenges the emerging preference for holistic evaluation of alternatives and suggests that this result may apply to any number of alternatives.Item Embargo Trust driven group decision making: Research progress and prospects from the perspective of consensus(Elsevier, 2025-04-15) Cao, Mingshuo; Sun, Qi; Chiclana, Francisco; Liu, Yujia; Gai, Tiantian; Yang, Yiling; Wu, JianTrust driven Group Decision Making (TGDM) is a new type of decision making process conducted through trust relationships and information exchange between individuals in the social network environment. By systematically organizing the research progress of TGDM and exploring its future research directions, the GDM research for consensus will be promoted. Firstly, this article combs the development status and research trends in recent years based on bibliometrics methods, and then summarizes and discusses the important literature related to TGDM. Secondly, it defines the scientific research category and basic framework of GDM and TGDM. Thirdly, the basic related concepts of TGDM problems are summarized, and then its characteristics and function are analyzed. Finally, it analyzes the problems and challenges faced by TGDM research and explores future research directions. It finds that many scholars have constructed multi-dimensional TGDM models from different perspectives, which have shown wonderful application performance in fields such as product design, failure mode and effects analysis, meta universe virtual communities, and Water–Energy–Food. In addition, it will be a very promising research direction to in-depth investigate TGDM driven by scene, behavior and decision maker’s personality characteristics.Item Open Access Integrating Large Language Models into Medication Management in Remote Healthcare: Current Applications, Challenges, and Future Prospects(MDPI, 2025-04) Kwan, Ho Yan; Shell, Jethro; Fahy, Conor; Yang, Shengxiang; Xing, YongkangThe integration of large language models (LLMs) into remote healthcare has the potential to revolutionize medication management by enhancing communication, improving medication adherence, and supporting clinical decision-making. This study aims to explore the role of LLMs in remote medication management, focusing on their impact. This paper comprehensively reviews the existing literature, medical LLM cases, and the commercial applications of LLMs in remote healthcare. It also addresses technical, ethical, and regulatory challenges related to the use of artificial intelligence (AI) in this context. The review methodology includes analyzing studies on LLM applications, comparing their impact, and identifying gaps for future research and development. The review reveals that LLMs have shown significant potential in remote medication management by improving communication between patients and providers, enhancing medication adherence monitoring, and supporting clinical decision-making in medication management. Compared to traditional reminder systems, AI reminder systems have a 14% higher rate in improving adherence rates in pilot studies. However, there are notable challenges, including data privacy concerns, system integration issues, and the ethical dilemmas of AI-driven decisions such as bias and transparency. Overall, this review offers a comprehensive analysis of LLMs in remote medication management, identifying both their transformative potential and the key challenges to be addressed. It provides insights for healthcare providers, policymakers, and researchers on optimizing the use of AI in medication management.Item Open Access Methods as a form of engineering knowledge(Cambridge University Press, 2025-05-01) Stacey, Martin; Eckert, Claudia; Pirtle, Zachary; Poznic, Michael; Schuelke-Leech, Beth-Anne; von der Tann, LorettaMethods comprise a significant part of the knowledge engineers are taught and that they use in professional practice. But methods have been largely neglected in discussions of the nature of engineering knowledge. In particular, methods prove to be hard to track down in the best known and most influential typology of engineering knowledge, put forward by Walter G. Vincenti in his book What Engineers Know and How They Know It. This paper discusses contemporary views of what engineering methods are and what they contain, how methods (fail to) fit into Vincenti’s analysis, and some characteristics of method knowledge. It argues that methods should be seen as a distinct type of engineering knowledge. While characterizing the knowledge that methods include can be done in different ways for different purposes, the core of method knowledge that does not fit into other categories is explicit ‘how-to’ knowledge of procedures, that draw on other types of knowledge.Item Open Access Channel and space-based joint rate allocation algorithm(IEEE, 2025-03-07) Wang, Dayong; Yuan, Chao; Sun, Yu; Lu, Xin; Guo, Hui; Dufaux, Frederic; Zhu, CeRate control is a critical component for image and video compression Particularly under limited network bandwidth conditions, bitrate control is essential to ensure efficient image transmission by effectively allocation channel resources. In this research, since both Channel and Spatial have relationship with rate allocation, we first propose a joint Channel-wise and Spatial-wise Quantization scheme to determine optimal quantization parameters. Subsequently, we develop a quantization step estimation network to obtain parameters to efficiently allocate rate according to target rate. Experiments demonstrate that our algorithm significantly improve compressed image quality with minimal bitrate distortion and achieve accurate rate control with nearly 3% average bitrate error.Item Open Access A dynamic optimization framework for computation rate maximization in UAV-assisted mobile edge computing(IEEE, 2025-03-10) Chen, Yang; Pi, Dechang; Yang, Shengxiang; Xu, Yue; Wang, Bi; Shou, Qin; Wang, YintongMobile edge computing (MEC) significantly boosts the computing power and reduces the energy consumption of Internet of Things (IoT) devices, serving as a valuable complement to cloud computing. The application of unmanned aerial vehicle (UAV) for MEC systems can effectively alleviate the issue of insufficient or damaged communication facilities in remote areas, further expanding the scope of MEC applications. In this article, we present a system model for UAV-assisted wireless-powered MEC systems in a dynamic environment with the objective of maximizing the computation rate of user devices. Due to the complexity of the optimization objective in dynamic environments, we propose a swarm intelligence-based optimization framework with a mechanism for responding to environmental changes, which is intended to enhance population diversity in both static and dynamic environments with the aim of overcoming premature convergence. We integrate particle swarm optimization and harmony search into the proposed framework, naming them DOPSO and DOHS, respectively. Simulation results for two offloading modes in UAV-assisted MEC systems indicate that the proposed framework significantly outperforms other dynamic optimization algorithms.Item Open Access Combining pathological and cognitive tests scores: A novel data analytics process to improve dementia prediction models(IOS Press, 2024-07-01) Alshehhi, Talib; Ayesh, Aladdin; Yang, Yingjie; Chen, FengThe term ‘dementia’ covers a range of progressive brain diseases from which many elderly people suffer. Traditional cognitive and pathological tests are currently used to detect dementia, however, applications using Artificial Intelligence (AI) methods have recently shown improved results from improved detection accuracy and efficiency. This research paper investigates the efficacy of one type of data analytics called supervised learning to detect Alzheimer’s disease (AD) - a common dementia condition. The aim is to evaluate cognitive tests and common biological markers (biomarkers) such as cerebrospinal fluid (CSF) to develop predictive classification systems for dementia detection. A data analytics process has been proposed, implemented, and tested against real data obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) repository. The models showed good power in predicting AD levels, notably from specified cognitive tests’ scores and tauopathy related features.Item Embargo Adaptive stochastic configuration network based on online active learning for evolving data streams(Elsevier, 2025-03-21) Guo, Yinan; Pu, Jiayang; He, Jiale; Ji, Jianjiao; Yang, ShengxiangStochastic Configuration Networks (SCNs) have exhibited significant potential in data mining, owing to their advantages in fast incremental construction and universal approximation capabilities. However, less researches were done on SCNs-based classification models for concept-drifting data streams. The so-called drifts refer to data distributions changing over time that may degrade the classification performance of SCNs trained on historical data. The previous drift adaptation approach is to discard all the hidden nodes of SCNs, and then learn a new model with new instances, in which the valuable historical information cannot be fully utilized. In addition, labeling all newly-arrived instances is time-consuming and impractical. To address these issues, an adaptive stochastic configuration network embedding online active learning is proposed. Crucially, a query strategy is developed to select representative instances for labeling based on the change degree of instances density and their uncertainty. An online update mechanism is employed to incrementally update the network's output parameters instance by instance. To rationally forget the outdated information and learn new concepts, a dynamic adjustment mechanism adaptively adds or prunes nodes in the SCN model. Experimental results for nine datasets confirm that our algorithm outperforms six popular ones on classification accuracy.Item Metadata only Analysis of Objective Functions for Ribonucleic Acid Multiple Sequence Alignment Fusion Based on Harmony Search Algorithm(American Scientific Publishing Group, 2025) Saif, Mubarak; Abdullah, Rosni; Omar, Mohd. Adib Hj.; Ahmed, Abdulghani Ali; Omar, Nurul Aswa; Mostafa, Salama A.Four kinds of smaller molecules known as ribonucleotide bases-adenine (A), cytosine (C), guanine (G), and uracil (U) combine to form the linear molecule known as ribonucleic acid (RNA). Aligning multiple sequences is a fundamental task in bioinformatics. This paper studies the correlation of different objective functions applying to RNA multiple sequence alignment (MSA) fusion generated by the Harmony search-based method. Experiments are performed on the BRAliBase dataset containing different numbers of test groups. The correlation of the alignment score and the quality obtained is compared against coffee, sum-of-pairs (SP), weight sum-of-pairs (WSP), NorMD, and MstatX. The results indicate that COFFEE and SP objective functions achieved a correlation coefficient (R²) of 0.96 and 0.92, respectively, when compared to the reference alignments, demonstrating their effectiveness in producing high-quality alignments. In addition, the sum-of-pairs takes less time than the COFFEE objective function for the same number of iterations on the same RNA benchmark.Item Embargo Assessing numerical error bound of classic grey prediction model: An application to the transport performance of China’s civil aviation industry(Elsevier, 2025-03-07) Chong Li; Liu, S. F.; Yang, YingjieAlthough grey system models have been developed and applied successfully to various socio-economic and engineering problems for several decades, the algorithm stability problem of these models has never been investigated. This paper introduces a method to estimate the error bounds of algorithms used in the classic grey prediction model. To reduce the complex calculation in finding the model error bounds, equivalent but simple estimation models are presented. An algebraic optimization technique for the solution processes of the proposed mathematic models is then provided. The backward error bound model is then extended to the other two commonly used linear regression forecasting models and the similarities and differences between them are explored. Finally, the proposed method is applied to the prediction of four key transportation performance indicators for China’s civil aviation industry. The case study considers not only the traditional accuracy criteria, but also the stability of prediction results in model optimization. The robustness of prediction methods with different types of noise interference and weighting preference scenarios are tested. It is found that model solving methods influence the error bounds, but smaller prediction errors do not necessarily guarantee better backward stability or applicability of the prediction model. Methods described in this paper make it possible to measure numerically the accuracy of any alleged solution of the classic grey prediction model and other linear regression models and provide an objective, quantitative approach to evaluating the effectiveness of information processing in different sample disturbances situations.Item Metadata only A data-driven approach to student support using formative feedback and targeted interventions(Routledge, 2025-03-26) Coupland, Simon; Fahy, Conor; Stuart, Graeme; Allman, ZoeDe Montfort University (DMU) has approximately 30,000 registered students, primarily at its Leicester campus in the United Kingdom (UK) but also at campuses internationally, as well as UK-based and transnational education partners. Based in Leicester, DMU’s community was particularly hit by the impact of COVID-19, with Leicester being the first city to be placed in local lockdown, extending the period of lockdown beyond the broader national experience. The approaches described in this case study were motivated by the need to capture information about student progress in the lockdown-necessitated online environment but have been equally impactful in in-person classroom teaching. In the subject area of computer games programming (CGP) at levels 5 and 6, students are required to use theoretical underpinning to develop solutions to practical problems, often demonstrating mastery of learning through completing a single, large piece of coursework over a medium-long timeframe, usually three–five months. Through the learning and assessment journey, students plan, meet, and reprioritise a series of dynamic sub-objectives. This all takes place during weekly timetabled workshops where most of the valuable learning occurs. These are student- and assessment-centred learning environments where learners, facilitated by tutors, incrementally develop their coursework projects. These workshops are natural opportunities to monitor engagement and to provide instant, formative feedback personalised to the learner and directly related to assessment. CGP as a discipline attracts students with a wide range of learning preferences and differences; the classical approach of 1–1 in-person tutoring may not be the best approach for these students (Amoako et al., 2013). Additionally, the temporary move to online teaching necessitated by the COVID-19 pandemic meant this established approach was not possible. Continual support and feedback are critical in an online setting and facilitated through sustained interaction between tutor and learner (Gikandi et al., 2011). Maintaining this interactivity is important, and it has been observed that continual documentation and sharing of learner-created artefacts is a key feature of meaningful interactivity (Gikandi & Morrow, 2016). In response the CGP team have developed a suite of innovative tools and processes to facilitate the real-time monitoring of student progress through using digital artefacts and the metadata associated with these digital artefacts. This approach provides students with timely formative feedback at key milestones in their progress and facilitates interventions for students requiring additional support to fully engage for best attainment. This approach is grounded in constructivist theories of learning. The individual learner is at the centre of the process, and the feedback process is an iterative, continuous part of learning (Carless et al., 2011; Molloy, 2014).Item Embargo Single batch-processing machine scheduling problem with interval grey processing time(Elsevier, 2025-01-03) Xie, Naiming; Yihang Qin; Nanlei Chen; Yang, YingjieThis paper investigates a single batch-processing machine scheduling problem with uncertain processing time. The uncertain processing time is characterized by interval grey number. A grey mixed integer linear programming model is established to formulate this uncertain scheduling problem to minimize the makespan. To solve this problem, a genetic algorithm with targeted population generation and neighbourhood search is designed. The results of experiments demonstrate that the proposed algorithm has excellent performance in both efficiency and stability. The resulting scheduling scheme can be shown through the Gantt chart with interval grey processing time, offering a novel approach for visualizing scheduling schemes with uncertain processing time.Item Embargo Research on tomato disease image recognition method based on DeiT(Elsevier, 2024-10-30) Sun, Changxia; Song, Zhengdao; Li, Yong; Liu, Qian; Si, Haiping; Yang, Yingjie; Cao, QingTomatoes, globally cultivated and economically significant, play an essential role in both commerce and diet. However, the frequent occurrence of diseases severely affects both yield and quality, posing substantial challenges to agricultural production worldwide. In China, where tomato cultivation is carried out on a large scale, disease prevention and identification are increasingly critical for enhancing yield, ensuring food safety, and advancing sustainable agricultural practices. As agricultural production scales and the demand for efficient methodologies grows, traditional disease recognition methods no longer meet current needs. The agricultural sector's move towards more modern and scalable production methods necessitates more effective and precise disease recognition technologies to support swift decision-making and timely preventive actions. To address these challenges, this paper proposes a novel tomato disease recognition method that integrates the data-efficient image transformers (DeiT) model with strategies like exponential moving average (EMA) and self-distillation, named EMA-DeiT. By leveraging deep learning technologies, this method significantly improves the accuracy of disease recognition. The enhanced EMA-DeiT model demonstrated exemplary performance, achieving a 99.6 % accuracy rate in identifying ten types of tomato leaf diseases within the PlantVillage public dataset and 98.2 % on the Dataset of Tomato Leaves, which encompasses six disease types. In generalization tests, it achieved 97.1 % accuracy on the PlantDoc dataset and 97.6 % on the Tomato-Village dataset. Utilizing the improved DeiT model, a comprehensive tomato disease recognition system was developed, featuring modules for image collection, disease detection, and information display. This system facilitates an integrated process from image collection to intelligent disease analysis, enabling agricultural workers to promptly understand and respond to disease occurrences. This system holds significant practical value for implementing precision agriculture and enhancing the efficiency of agricultural production.