Search

As the internet and digital technologies revolutionize the healthcare sector, the development of smart hospitals is pivotal for improving medical service efficiency. This research presents a mathematical model for the outpatient scheduling problem and introduces the Graph-based Two-Agent Deep Reinforcement Learning algorithm (GTARS-DRL) to address the escalating demand for medical services and the scarcity of resources. The GTARS-DRL leverages graph neural networks for feature extraction of patient medical activities and applies the PDQPN algorithm to train agents for optimizing patient sequencing and service desk allocation, effectively minimizing wait times. Our experiments indicate that GTARS-DRL outperforms traditional scheduling rules in solution quality and matches the performance of Genetic Algorithms (GA), with a notable advantage in computational efficiency, boasting an ACPU of 0.762 s and an ARPT of 0.327 s. The algorithm's efficacy is further supported by its successful application to larger-scale instances, showcasing its potential for real-world use. This study contributes a novel approach to outpatient scheduling in smart hospitals, providing theoretical backing and practical direction for the optimization of medical resource allocation, and is poised to significantly enhance service efficiency and patient satisfaction. [ABSTRACT FROM AUTHOR]

As customer demands for personalised items continue to grow, flexible material handling systems are becoming indispensable in manufacturing to accommodate the increasing product variety and demand fluctuations. Consequently, the adoption of autonomous mobile robots (AMRs) is on the rise, driven by their capability to autonomously respond to changes in demand. However, the myopic nature of AMRs' autonomous decision-making may limit their ability to consider a system-wide perspective. To address this challenge, we propose an AI-based platform that extracts knowledge from a centralised agent, which makes system-wide decisions offline, and integrates this knowledge into decentralised AMRs operating online. We develop a mixed-integer linear programming model, a genetic algorithm, and a scheduling algorithm to generate centralised solutions. Additionally, we design features to convert these solutions into training instances and employ artificial neural networks to derive knowledge from them. This knowledge is then integrated into each AMR as a protocol. Through experiments, we evaluate the performance of the developed protocol, demonstrating its superiority over other dispatching rules in minimising the total weighted tardiness of transportation requests and the total waiting time of transportation requests at storages. [ABSTRACT FROM AUTHOR]

Variation in sequential task processing times is common in manufacturing systems. This type of disturbance challenges most scheduling methods since they cannot fundamentally change job sequences to adaptively control production performance as jobs enter the system because actual processing times, are not known in advance. Some research literature indicates that simple rules are more suitable than algorithmic scheduling methods for adaptive control. In this work, a ‘state space – average processing time’ (SS-APT) heuristic is proposed and compared to four most commonly used scheduling rules and two well-established heuristics based on Taillard’s benchmarks. It is shown that the adaptive control is made possible under variation in processing times given the flexibility and strong performance of the SS-APT heuristic, especially for work-in-process inventory control. [ABSTRACT FROM AUTHOR]

In the context of Industry 4.0 and intelligent manufacturing, AGVs are widely used in flexible job shop resource transportation, which sharply increases the uncertainty and complexity of the scheduling process. For this reason, an improved double Deep Q Network (DDQN) real-time scheduling method is proposed for the Flexible Job Shop Scheduling Problem with Automated Guided Vehicle (FJSP-AGV) to minimize the makespan. Firstly, the optimization model of the FJSP-AGV is established, and the corresponding constraints and the objective function are defined. Then, the FJSP-AGV is converted into a Markov Decision Process (MDP), in which the state space, action space, and reward function are defined in detail. Next, an improved DDQN is proposed to generate the optimal scheduling policy considering AGV. Finally, the computational experiments are conducted based on data from public benchmarks and the real-world flexible job shop, and the results demonstrate the accuracy and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The evolution of manufacturing systems toward Industry 4.0 and 5.0 paradigms has pushed the diffusion of Machine Learning (ML) in this field. As the number of articles using ML to support manufacturing functions is expanding tremendously, the main objective of this review article is to provide a comprehensive and updated overview of these applications. 114 journal articles have been collected, analysed, and classified in terms of supervision approaches, function, ML algorithm, data inputs and outputs, and application domain. The findings show the fragmentation of the field and that most of the ML-based systems address limited objectives. Some inputs and outputs of the analysed support tools are shared across the reviewed contributions, and their possible combinations have been outlined. The advantages, limitations, and research opportunities of ML support in manufacturing are discussed. The paper outlines that the excessive specialization of the reviewed applications could be overcome by increasing the diffusion of transfer learning in the manufacturing domain. [ABSTRACT FROM AUTHOR]

In the fourth industrial revolution, artificial intelligence and machine learning (ML) have increasingly been applied to manufacturing, particularly additive manufacturing (AM), to enhance processes and production. This study provides a comprehensive review of the state-of-the-art achievements in this domain, highlighting not only the widely discussed supervised learning but also the emerging applications of semi-supervised learning and reinforcement learning. These advanced ML techniques have recently gained significant attention for their potential to further optimize and automate AM processes. The review aims to offer insights into various ML technologies employed in current research projects and to promote the diverse applications of ML in AM. By exploring the latest advancements and trends, this study seeks to foster a deeper understanding of ML's transformative role in AM, paving the way for future innovations and improvements in manufacturing practices. [ABSTRACT FROM AUTHOR]

The detection of the vertical profiles of atmospheric variables or aerosols is a vital component in the accurate calculation of the atmospheric boundary layer height (ABLH). In many existing techniques, the precise ABLH detection has poor resource consumption, heterogeneous IoT conditions, lack of interoperability, and online and offline analyzers overdue are impacted by the processing of high streaming data from the ceilometer. Hence, a novel Edge AI cosmos blockchain distributed network is proposed to eliminate the efficient lowering parameters to provide a user-scalable networking based on a deep learning algorithm, in which the cosmos ledger blockchain method gets the data without affecting its precision or specificity, eliminates interoperability, increases usability. Moreover, the existing techniques has no real-time adjustment when processing the high streaming data. Hence, a model Real-time batch scheduling technique has been introduced to reduce a significant amount of computing power. In existing techniques, the scheduling process is very complicated as the ABLH layer attribution, precipitation, lofted aerosol layers, low aerosol conditions, and clouds. To overcome these issues, a gubernatorial algorithm is used to detect the ABLH value hourly which is gathered and stored data in a very optimized and efficient manner. Overall, the proposed technique compares effective data management and produces a computer environment which is optimal for ABLH. [ABSTRACT FROM AUTHOR]

With the advent of the socio-technical manufacturing paradigm, the way in which rescheduling decisions are taken at the shop floor has radically changed in order to guarantee highly efficient production under increasingly dynamic conditions. To cope with uncertain production environments, a drastic increase in the type and degree of automation used at the shop floor for handling unforeseen events and unplanned disturbances is required. In this work, the on-line rescheduling task is modelled as a closed-loop control problem in which an artificial autonomous agent implements a control policy generated off-line using a schedule simulator to learn schedule repair policies directly from high-dimensional sensory inputs. The rescheduling control policy is stored in a deep neural network, which is used to select repair actions in order to achieve a small set of repaired goal states. The rescheduling agent is trained using Proximal Policy Optimisation based on a wide variety of simulated transitions between schedule states using colour-rich Gantt chart images and negligible prior knowledge as inputs. An industrial example is discussed to highlight that the proposed approach enables end-to-end deep learning of successful rescheduling policies to encode task-specific control knowledge that can be understood by human experts. [ABSTRACT FROM AUTHOR]

With a high percentage of distributed new energy sources connected to the power system, the power grid needs to reserve a larger margin to deal with the uncertainty of renewable energy outputs, leading to an increase in the cost of controlling the margins for the safe operation of the power grid. In order to reduce costs and increase efficiency, a quantitative assessment of new energy output uncertainty is needed. In this paper, a quantitative assessment method of new energy output uncertainty based on the prediction error is proposed, which makes use of a graph database to efficiently obtain massive new energy historical data, uses the clustering in quest (CLIQUE) algorithm to cluster the new energy historical data, and calculates the renewable energy real power confidence interval based on a given new energy power prediction, taking account of the impact of prediction errors caused by the new energy uncertainty and realizing the quantitative description of new energy output uncertainty. Finally, the method is calculated and analyzed together with the actual example data to verify the practical effect of the method. [ABSTRACT FROM AUTHOR]

This chapter is a continuation of the chapter titled "Intelligent Model of Scheduling RFACs - Part I: Methodology and Strategy" with the emphasis on application of the developed methodology to the scheduling of the RFACs. Based on the methodology and strategy presented in Part I, a new model for multi-objective scheduling problems in RFACs was developed. This model was based on combining a fuzzy-based mathematical model with simulation software tools. In this chapter, a hypothetical case study of RFACs is presented to prove the effectiveness of the developed methodology, and then compare the results that are obtained by the new methodology with the common scheduling rules. Simulation results show that the performance of the proposed methodology outperforms the most popular scheduling rules from literature. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to develop a method based on artificial intelligence capable of predicting the due date (DD) of job shops in real-time, aiming to assist in the decision-making process of industries. Design/methodology/approach: This paper chooses to use the methodological approach Design Science Research (DSR). The DSR aims to build solutions based on technology to solve relevant issues, where its research results from precise methods in the evaluation and construction of the model. The steps of the DSR are identification of the problem and motivation, definition of the solution's objectives, design and development, demonstration, evaluation of the solution and the communication of results. Findings: Along with this work, it is possible to verify that the proposed method allows greater accuracy in the DD definition forecasts when compared to conventional calculations. Research limitations/implications: Some limitations of this study can be pointed. It is possible to mention questions related to the tasks to be informed by users, as they could lead to problems in the performance of the artifact as the input data may not be correctly posted due to the misunderstanding of the question by part of the users. Originality/value: The proposed artifact is a method capable of contributing to the development of the manufacturing industry to improve the forecast of manufacturing dates, assisting in making decisions related to production planning. The use of real production data contributed to creating, demonstrating and evaluating the artifact. This approach was important for developing the method allowing more reliability. [ABSTRACT FROM AUTHOR]

Research on Artificial Intelligence (AI) in communication research is gaining broader interest. This interdisciplinary interest has yet to be supported by a systematic scholarly definition and by a holistic theoretical framework in communication research. First, combining prior theoretical efforts from diverse disciplines in the social sciences, especially journalism and communication, this study introduces a wide-ranging working AI scholarly definition in communication research as the tangible real-world capability of non-human machines or artificial entities to perform, task solve, communicate, interact, and act logically as it occurs with biological humans. We also propose its theoretical operationalization based on two dimensions: level of performance and level of autonomy, advancing an elementary conceptual framework drawing on AI's levels of potential actions or performance the AI may accomplish, including 1) performing tasks, 2) taking decisions, and 3) making predictions; as well as AI's level of autonomy, or the agency results contingent on the degrees of human input, interaction, or supervision involved. [ABSTRACT FROM AUTHOR]

This research combines deep neural network (DNN) and Markov decision processes (MDP) for the dynamic dispatching of re-entrant production systems. In re-entrant production systems, jobs enter the same workstation multiple times and dynamic dispatching oftentimes aims to dynamically assign different priorities to various job groups to minimise weighted cycle time or maximise throughput. MDP is an effective tool for dynamic production control, but it suffers from two major challenges in dynamic control problems. First, the curse of dimensionality limits the computational performance of solving large MDP problems. Second, a different model should be built and solved after system configuration is changed. DNN is used to overcome both challenges by learning directly from optimal dispatching policies generated by MDP. Results suggest that a properly trained DNN model can instantly generate near-optimal dynamic control policies for large problems. The quality of the DNN solution is compared with the optimal dynamic control policies through the standard K-fold cross-validation test and discrete event simulation. On average, the performance of the DNN policy is within 2% of optimal in both tests. The proposed artificial intelligence algorithm illustrates the potential of machine learning methods in manufacturing applications. [ABSTRACT FROM AUTHOR]

As one of the most complex parts in manufacturing systems, scheduling plays an important role in the efficient allocation of resources to meet individual customization requirements. However, due to the uncertain disruptions (e.g., task arrival time, service breakdown duration) of manufacturing processes, how to respond to various dynamics in manufacturing to keep the scheduling process moving forward smoothly and efficiently is becoming a major challenge in dynamic manufacturing scheduling. To solve such a problem, a wide spectrum of artificial intelligence techniques have been developed to (1) accurately construct dynamic scheduling models that can represent both personalized customer needs and uncertain provider capabilities and (2) efficiently obtain a qualified schedule within a limited time. From these two perspectives, this article systemically makes a state-of-the-art literature survey on the application of these artificial intelligence techniques in dynamic manufacturing modeling and scheduling. It first introduces two types of dynamic scheduling problems that consider service-and task-related disruptions in the manufacturing process, respectively, followed by a bibliometric analysis of artificial intelligence techniques for dynamic manufacturing scheduling. Next, various kinds of artificial-intelligence-enabled schedulers for solving dynamic scheduling problems including both directed heuristics and autonomous learning methods are reviewed, which strive not only to quickly obtain optimized solutions but also to effectively achieve the adaption to dynamics. Finally, this article further elaborates on the future opportunities and challenges of using artificialintelligence- enabled schedulers to solve complex dynamic scheduling problems. In summary, this survey aims to present a thorough and organized overview of artificial-intelligence-enabled dynamic manufacturing scheduling and shed light on some related research directions that are worth studying in the future. [ABSTRACT FROM AUTHOR]

Container virtualization technology represented by Docker has been widely used in the industry due to its advantages of lightweight, fast deployment, and easy portability. This paper considers the scenarios of AI-based IoT applications based on container technology in a cloud-edge collaborative environment, and proposes a container-based task scheduling algorithm. Using priority-aware greedy strategy, a new scheduling algorithm named PGT has been proposed which adopts the multi-criteria approach Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The containers in cloud servers and edge servers are managed in a uniform platform, and IoT application services are deployed in containers. The task with smaller deadline constraint is scheduled first due to its higher priority. Then, multiple indicators are considered comprehensively, such as task response time, energy consumption, task execution cost, to find the optimal container to execute task. Through varying the number of edge servers and the number of tasks, the simulation results in a cloud-edge collaborative environment indicate that the proposed scheduling approach outperforms the four baseline algorithms in improving QoS satisfaction rate, energy consumption, penalty cost and total violation time. [ABSTRACT FROM AUTHOR]

The fourth industrial revolution, Industry 4.0, has brought internet, artificial intelligence (AI), and machine learning (ML) concepts into manufacturing. There is an immediate need to understand the capabilities of AI and ML and how they can be implemented in manufacturing domains. This article presents a detailed survey of AI algorithms and their use in manufacturing. The article treats casting, forming, machining, welding, additive manufacturing (AM), and supply chain management (SCM) as six manufacturing verticals. The horizontals in each vertical are the descriptions including, the evolution of each process from the mechanization era to the present-day scenario, and developments in the automation of processes by processing signal and image information and applying ML and AI algorithms. The evolution of robotics and cloud-based technologies is also discussed. The critical review gives a realistic view of manufacturing automation and benefits of AI. Further, the article discusses several manufacturing use cases where AI and ML algorithms are deployed. As a future research direction, human-like intelligence is introduced highlighting the necessity of cognitive skills in manufacturing. In a nutshell, a reader can logically explain why, when, and how far AI will define complete manufacturing. [ABSTRACT FROM AUTHOR]

Recently, artificial intelligence, data-driven techniques, cyber-physical systems, and cloud and cognitive computation have further stimulated research and applications of monitoring, optimization, and control techniques. Complex industrial automation systems and processes, such as chemical processes, manufacturing systems, wireless network systems, power and energy systems, smart grids and so forth, have greatly contributed to our daily life. As a result, there has been increasing demand in the complex industries to develop reliable condition-monitoring techniques to monitor real-time system status and promote advanced optimization algorithms and resilient control methods to ensure the desired control and operation performance. Han et al., proposed a novel optimization algorithm, by combining a simulated annealing algorithm-based Hopfield neural network algorithm and local scheduling rules, to solve the flexible flow shop scheduling problem with a public buffer [[23]]. [Extracted from the article]

Stroke occurs when a brain's blood artery ruptures or the brain's blood supply is interrupted. Due to rupture or obstruction, the brain's tissues cannot receive enough blood and oxygen. Stroke is a common cause of mortality among older people. Hence, loss of life and severe brain damage can be avoided if stroke is recognized and diagnosed early. Healthcare professionals can discover solutions more quickly and accurately using artificial intelligence (AI) and machine learning (ML). As a result, we have shown how to predict stroke in patients using heterogeneous classifiers and explainable artificial intelligence (XAI). The multistack of ML models surpassed all other classifiers, with accuracy, recall, and precision of 96%, 96%, and 96%, respectively. Explainable artificial intelligence is a collection of frameworks and tools that aid in understanding and interpreting predictions provided by machine learning algorithms. Five diverse XAI methods, such as Shapley Additive Values (SHAP), ELI5, QLattice, Local Interpretable Model-agnostic Explanations (LIME) and Anchor, have been used to decipher the model predictions. This research aims to enable healthcare professionals to provide patients with more personalized and efficient care, while also providing a screening architecture with automated tools that can be used to revolutionize stroke prevention and treatment. [ABSTRACT FROM AUTHOR]

In recent years, deep learning models have been more and more widely used in various fields and have become a research hotspot for various tasks in artificial intelligence, but there are significant limitations in non-convex optimization problems. As a model training strategy for non-convex optimization, curriculum learning advocates that models learn in the order of easier to more difficult data, mimicking the basic idea of gradual human learning as they learn curriculum. This strategy has been widely used in the fields of computer vision, natural language processing, and reinforcement learning; it can effectively solve the non-convex optimization problem and improve the generalization ability and convergence speed of models. This paper first introduces the application of curriculum learning at three major levels: data, task, and model, and summarizes the evaluators designed using curriculum learning methods in various domains, including difficulty evaluators, training schedulers, and loss evaluators, which correspond to the three stages of difficulty evaluation, training schedule, and loss evaluation in the application of curriculum learning to model training. We also discuss how to choose an appropriate evaluation system and the differences between terms used in different types of research. Finally, we summarize five methods similar to curriculum learning in the field of machine learning and provide a summary and outlook of the curriculum learning evaluation system. [ABSTRACT FROM AUTHOR]

At present, the old production management mode has become a stumbling block to the development of enterprises, and the high-end manufacturing technology is still not mature enough. This research mainly discusses the intelligent manufacturing management system based on data mining in artificial intelligence energy-saving resources. The enterprise business management system cannot accurately and timely grasp the actual situation of the production site, and the accuracy and feasibility of the upper-level planning cannot be guaranteed. At the same time, on-site personnel and equipment cannot get practical production plans and production instructions in time, resulting in product backlogs and excessive inventory. On the other hand, equipment is idle and resources are wasted, and the workshop scheduling system loses the corresponding scheduling role. The development of this system is mainly composed of front-end technology, back-end technology and front-end and back-end interaction technology. The interface design of the front end is mainly completed by the windows form application in c#. The interaction between the front and back ends is mainly realized by programming in each control of the form application. Back-end technology is the core content of the system, mainly including two key technologies: mixed programming of C #. Net and MATLAB and C # connecting SQL Server database. The system mainly includes five sub-functional modules: order management, material management, mixed model assembly line balance, assembly line logistics scheduling and system management. Order management and material management are the basis of the system, which provides parameter input for the balance of assembly line and logistics scheduling. The balance of mixed model assembly line is the core function of the system. The balance of mixed model assembly line is carried out by calling the intelligent algorithm written in MATLAB, and the optimal assembly scheme of workstation is displayed to the front end of the system, which reflects the intelligent characteristics of production control system for intelligent manufacturing. The logistics scheduling of assembly line takes the balance result of mixed model assembly line as the premise, takes the balance result as the task sequence input of logistics scheduling, and optimizes the operation efficiency of logistics system (driving path and running time of AGV). The operation results show that the comprehensive energy consumption of 10,000 yuan industrial output value is 401.19 kg standard coal/10,000 yuan, a year-on-year decrease of 6.96%. This study is helpful to the fine management of manufacturing industry. [ABSTRACT FROM AUTHOR]

The analytical evaluation of production system performance measures is a difficult task. Over the years, various methods have been developed to solve specific cases of very short production lines. However, formulae for estimating the mean production rate (throughput) are lacking. Recent developments in artificial intelligence simplify their use in the solution of symbolic regression problems. In this work, we use genetic programming (GP) to obtain approximate formulae for calculating the throughput of short reliable approximately balanced production lines, for which the processing times are exponentially distributed. A hybrid GP&GA scheme reduces the search space, in which GP uses genetic algorithms (GA) as a search engine. The scheme produces polynomial formulae for throughput estimation for the first time. To train the GP algorithm we use MARKOV, an accurate algorithm for calculating numerically the exact throughput of short exponential production lines. A few formulae, not previously reported in the literature, are presented. These formulae give close results to the exact results from the MARKOV algorithm, for short (up to five stations) reliable approximately balanced production lines without intermediate buffers. Also, the robustness of these formulae is satisfactory. In addition, the proposed hybrid GP&GA scheme is useful for design/production engineers to adjust the formulae to other ranges of the mean processing rates; the algorithms are quickly retrained to generate a new approximate formula. [ABSTRACT FROM AUTHOR]

A flexible manufacturing system (FMS) due to its ability of being flexible in nature is concerned with automatic production of different parts in medium range. In short, it can be regarded as an automated manufacturing system. In this paper, an insight on previous work in the area of FMS modelling has been provided with an overview of research and development for better understanding of FMS. It serves as a medium for investigation of work that are accomplished by using different modelling techniques in FMS like mathematical, artificial intelligence, hierarchical, multi criteria decision-making method, Petri Nets and simulation. This paper will help researchers who are keen to do research in the area of FMS modelling, by highlighting contribution of available techniques in the field of FMS. It will also help them in deciding which modelling techniques can be used for a given problem. At last, comparison of different parameters considered in the recent papers of modelling FMS has been provided in the form of Table, along with a clear vision related to those works that still need to be investigated. [ABSTRACT FROM AUTHOR]

No-show appointments in healthcare is a problem faced by medical centers around the world, and understanding the factors associated with no-show behavior is essential. In recent decades, artificial intelligence has taken place in the medical field and machine learning algorithms can now work as an efficient tool to understand the patients' behavior and to achieve better medical appointment allocation in scheduling systems. In this work, we provide a systematic literature review (SLR) of machine learning techniques applied to no-show appointments aiming at establishing the current state-of-the-art. Based on an SLR following the PRISMA procedure, 24 articles were found and analyzed, in which the characteristics of the database, algorithms and performance metrics of each study were synthesized. Results regarding which factors have a higher impact on missed appointment rates were analyzed too. The results indicate that the most appropriate algorithms for building the models are decision tree algorithms. Furthermore, the most significant determinants of no-show were related to the patient's age, whether the patient missed a previous appointment, and the distance between the appointment and the patient's scheduling. [ABSTRACT FROM AUTHOR]

Industrial control systems play a central role in today's manufacturing systems. Ongoing trends towards more flexibility and sustainability, while maintaining and improving production capacities and productivity, increase the complexity of production systems drastically. To cope with these challenges, advanced control algorithms and further developments are required. In recent years, developments in Artificial Intelligence (AI)-based methods have gained significantly attention and relevance in research and the industry for future industrial control systems. AI-based approaches are increasingly explored at various industrial control systems levels ranging from single automation devices to the real-time control of complex machines, production processes and overall factories supervision and optimization. Thereby, AI solutions are exploited with reference to different industrial control applications from sensor fusion methods to novel model predictive control techniques, from self-optimizing machines to collaborative robots, from factory adaptive automation systems to production supervisory control systems. The aim of the present perspective paper is to provide an overview of novel applications of AI methods to industrial control systems on different levels, so as to improve the production systems' self-learning capacities, their overall performance, the related process and product quality, the optimal use of resources and the industrial systems safety, and resilience to varying boundary conditions and production requests. Finally, major open challenges and future perspectives are addressed. [ABSTRACT FROM AUTHOR]

Evolutionary Algorithms (EAs) has attracted significantly attention with respect to complexity scheduling problems, which is referred to evolutionary scheduling. However, EAs differ in the implementation details and the nature of the particular scheduling problem applied. In order to have an effective implementation of EAs for production scheduling, this paper focuses on making a survey of researches based on using hybrid EAs. Starting from scheduling description, we identify the classification and graph representation of scheduling problems. Then, we present the various representations, hybridisation techniques and machine-learning techniques to enhancing EAs. Finally, we also present successful applications in manufacturing. [ABSTRACT FROM AUTHOR]

Compared with the traditional assembly line, seru production can reduce worker(s) and decrease makespan. However, when the two objectives are considered simultaneously, Pareto-optimal solutions may save manpower but increase makespan. Therefore, we formulate line-seru conversion towards reducing worker(s) without increasing makespan and develop exact and meta-heuristic algorithms for the different scale instances. Firstly, we analyse the distinct features of the model. Furthermore, according to the feature of the solution space, we propose two exact algorithms to solve the small to medium-scale instances. The first exact algorithm searches the solution space from more workers to fewer workers. The second exact algorithm searches the solution space from fewer workers to more workers. The two exact algorithms search a part of solution space to obtain the optimal solution of reducing worker(s) without increasing makespan. According to the variable length of the feasible solutions, we propose a variable-length encoding heuristic algorithm for the large-scale instances. Finally, we use the extensive experiments to evaluate the performance of the proposed algorithms and to investigate some managerial insights on when and how to reduce worker(s) without increasing makespan by line-seru conversion. [ABSTRACT FROM AUTHOR]

This article outlines the proposed open-radio access network (O-RAN) deployment for fifth-generation (5G) wireless networks. O-RAN seeks to supplant hardware-specific radio access network (RAN) components with generic hardware, specialized software, and open signaling interfaces. The virtualization and network slicing features of 5G allow for software to replace previously hardware-specific functions. The software further provides faster analytics, thus supporting 5G's latency requirements and advanced usage scenarios (i.e., enhanced mobile broadband, massive machine type communications, and ultra-reliable low latency communications). Furthermore, as software annexes control of the RAN, there is the freedom to integrate artificial intelligence/machine learning algorithms into RAN management (particularly at the user plane). This integration is one of the goals of O-RAN. Finally, relying on generic hardware and specialized, open-source software eliminates reliance upon specific device manufacturers. This article will provide questions regarding O-RAN's future, with a focus on 5G network device security. [ABSTRACT FROM AUTHOR]

The shift of traditional mass-producing industries towards mass customisation practices is nowadays evident. However, if not implemented properly, mass customisation can lead to disturbances in material flow and severe reduction in productivity. Moreover, manufacturing enterprises often face the challenge of manufacturing highly customized products in small lot sizes. One solution to adapt to the ever-changing demands, which increases resource flexibility, lies in the digitization of the manufacturing systems. Furthermore, the distributed manufacturing environment and the ever-increasing product variety and complexity result in reduced time-to market, ubiquitous data access and sharing and adaptability and responsiveness to changes. These requirements can be achieved through smart manufacturing tools and especially Wireless Sensor Networks (WSN). Thus, the aim of this position paper is to summarize the design and development of solutions based on cutting-edge technologies such as Cloud Computing, Artificial Intelligence (AI), Internet of Things (IoT), Simulation, 5G, and so on. Concretely, the first part discusses the development of a Cloud-based production planning and control system for discrete manufacturing environments. The proposed approach takes into consideration capacity constraints, lot sizing and priority control in a "bucket-less" manufacturing environment. Then, an open and interoperable Internet of Things platform is discussed, which is enhanced by innovative tools and methods that transform them into Cyber-Physical Systems (CPS), supporting smart customized shopping, through gathering customers' requirements, adaptive production, and logistics of vending machines replenishment and Internet of Things and Wireless Sensor Networks for Smart Manufacturing. To that end, all the proposed methodologies are validated using data derived from Computer Numerical Control (CNC) machine building industry, from European Metal-cutting and mold-making SMEs, from white goods industry and SMEs that produces solar panels. [ABSTRACT FROM AUTHOR]

This paper proposes a bi-criteria nonlinear fluctuation smoothing rule to further improve the performance of job scheduling in a wafer fabrication factory (wafer fab). The rule is based on the well-known fluctuation smoothing rules. First, the remaining cycle time of a job is estimated by applying the self-organization map–fuzzy back propagation network approach to improve the estimation accuracy. Second, two nonlinear forms of the fluctuation smoothing rules are obtained to enhance the balance and responsiveness. Third, the two nonlinear fluctuation smoothing rules are merged into a bi-criteria rule for considering two performance measures (average cycle time and cycle time variation) at the same time. Finally, the content of the bi-criteria rule can be tailored for the wafer fab and be scheduled with an adjustable factor. To evaluate the effectiveness of the proposed methodology, a production simulation was conducted. According to the experimental results, the proposed methodology outperformed some of the existing approaches by reducing the average cycle time and cycle time variation at the same time. In addition, the experimental results showed that the bi-criteria rule made it possible to improve one performance measure without raising the expense of another one. [ABSTRACT FROM AUTHOR]

Decentralised scheduling with dispatching rules is applied in many fields of production and logistics, especially in highly complex manufacturing systems. Since dispatching rules are restricted to their local information horizon, there is no rule that outperforms other rules across various objectives, scenarios and system conditions. In this paper, we present an approach to dynamically adjust the parameters of a dispatching rule depending on the current system conditions. The influence of different parameter settings of the chosen rule on the system performance is estimated by a machine learning method, whose learning data is generated by preliminary simulation runs. Using a dynamic flow shop scenario with sequence-dependent set-up times, we demonstrate that our approach is capable of significantly reducing the mean tardiness of jobs. [ABSTRACT FROM PUBLISHER]

Artificial intelligence (AI) is expected to bring greater efficiency in radiology by performing tasks that would otherwise require human intelligence, also at a much faster rate than human performance. In recent years, milestone deep learning models with unprecedented low error rates and high computational efficiency have shown remarkable performance for lesion detection, classification, and segmentation tasks. However, the growing field of AI has significant implications for radiology that are not limited to visual tasks. These are essential applications for optimizing imaging workflows and improving noninterpretive tasks. This article offers an overview of the recent literature on AI, focusing on the musculoskeletal imaging chain, including initial patient scheduling, optimized protocoling, magnetic resonance imaging reconstruction, image enhancement, medical image-to-image translation, and AI-aided image interpretation. The substantial developments of advanced algorithms, the emergence of massive quantities of medical data, and the interest of researchers and clinicians reveal the potential for the growing applications of AI to augment the day-to-day efficiency of musculoskeletal radiologists. [ABSTRACT FROM AUTHOR]

In this article, we encompass an analysis of the recent advances in parallel genetic algorithms (PGAs). We have selected these algorithms because of the deep interest in many research fields for techniques that can face complex applications where running times and other computational resources are greedily consumed by present solvers, and PGAs act then as efficient procedures that fully use modern computational platforms at the same time that allow the resolution of cutting-edge open problems. We have faced this survey on PGAs with the aim of helping newcomers or busy researchers who want to have a wide vision on the field. Then, we discuss the most well-known models and their implementations from a recent (last six years) and useful point of view: We discuss on highly cited articles, keywords, the venues where they can be found, a very comprehensive (and new) taxonomy covering different research domains involved in PGAs, and a set of recent applications. We also introduce a new vision on open challenges and try to give hints that guide practitioners and specialized researchers. Our conclusion is that there are many advantages to using these techniques and lots of potential interactions to other evolutionary algorithms; as well, we contribute to creating a body of knowledge in PGAs by summarizing them in a structured way, so the reader can find this article useful for practical research, graduate teaching, and as a pedagogical guide to this exciting domain. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is a rapidly growing field that has the potential to revolutionize various aspects of human life. In the field of nuclear medicine (NM) and molecular imaging, AI can be integrated to improve precision medicine by assisting with tasks such as image planning, interpretation, diagnosis, and prediction of therapy response. AI can also be used for administrative purposes, such as patient admission and appointment scheduling. Additionally, AI has the potential to optimize workflows, improve image quality, and reduce radiation exposure in NM and PET imaging. However, it is important for medical imaging professional societies to establish guidelines and standards for the safe and effective use of AI in this field. Educational programs are also necessary to ensure clinicians and technologists are knowledgeable about AI and its potential applications in NM and molecular imaging. [Extracted from the article]

Earlier studies indicated that using multiple dispatching rules (MDRs) for the various zones in the system can enhance the production performance to a greater extent than using a single dispatching rule (SDR) over a given scheduling interval for all the machines in the system, since MDRs employ the multi-pass simulation approach for real-time scheduling (RTS). However, if a classical machine learning approach is used, an RTS knowledge base (KB) can be developed by using the appropriate MDRs strategy (this method is called an intelligent multi-controller in this paper) as obtained from training examples. The main disadvantage of using MDRs is that the classes (scheduling decision variables) to which training examples are assigned must be provided. Hence, developing an RTS KB using the intelligent multi-controller approach becomes an intolerably time-consuming task because MDRs for the next scheduling period must be determined. To address this issue, we proposed an intelligent multi-controller incorporating three main mechanisms: (1) simulation-based training example generation mechanism, (2) data pre-processing mechanism and (3) SOM-based real time MDRs selection mechanism. Under various performance criteria over a long period, the proposed approach yields better system performance than the machine learning-based RTS using the SDR approach and heuristic individual dispatching rules. [ABSTRACT FROM AUTHOR]

This paper evaluates several artificial intelligence heuristics for a simultaneous Kanban controlling and scheduling on a flexible Kanban system. The objective of the problem is to minimise a total production cost that includes due date penalty, inventory, and machining costs. We show that the simultaneous Kanban controlling and scheduling is critical in minimising the total production cost (approximately 30% cost reduction over scheduling without a Kanban controlling). To identify the most effective search method for the simultaneous Kanban controlling and scheduling, we evaluated widely known artificial intelligence heuristics: genetic algorithm, simulated annealing, tabu search, and neighbourhood search. Computational results show that the tabu search performs the best in terms of solution quality. The tabu search also requires a much less computational time than the genetic algorithm and the simulated annealing. To further improve the solution quality and computational time for a simultaneous Kanban controlling and scheduling on a flexible Kanban system, we developed a two-stage tabu search. At the beginning of the tabu search process, an initial solution is constructed by utilising the customer due date information given by a decision support system. The two-stage tabu search performs better than the tabu search with a randomly generated initial solution in both the solution quality and computational time across all problem sizes. The difference in the solution quality is more pronounced at the early stages of the search. [ABSTRACT FROM AUTHOR]