Purpose -The purpose of this paper is to outline the main features concerning the optimization of printed circuit board (PCB) fabrication by improving the manufacturing process productivity. Design/methodology/approach -The author explored two different approaches to increase the manufacturing process productivity of PCBs. The first approach involved optimization of the PCB manufacturing process as a whole. The second approach was based on increasing the process productivity at the operational level. Findings -To reduce the total manufacturing time, two heuristic algorithms for solving flowshop scheduling problems were designed. These algorithms were used for the computation of an optimal PCB manufacturing schedule. The case study shows both mono-and bi-criteria optimization of the PCBs manufacturing. Research limitations/implications -While the input data used in the case study were based on random numbers, the mathematical considerations drew only the main directions for manufacturing process optimization. Originality/value -The paper shows two original heuristic algorithms for solving the flowshop scheduling problem, with high performance according to the best heuristics in the field. Besides their performances, these algorithms have the advantage of simplicity and ease of implementation on a computer. Using these algorithms, the optimal schedule for the PCB manufacturing process was calculated. For the case of the bi-criteria optimization, the study of points which belong to the Pareto-optimal set are presented.

Objective: Brain-computer interfaces (BCIs) allow subjects with sensorimotor disability to interact with the environment. Non-invasive BCIs relying on EEG signals such as event-related potentials (ERPs) have been established as a reliable compromise between spatio-temporal resolution and patient impact, but limitations due to portability and versatility preclude their broad application. Here we describe a deep-learning augmented error-related potential (ErrP) discriminating BCI using a consumer-grade portable headset EEG, the Emotiv EPOC+. Approach: We recorded and discriminated ErrPs offline and online from 14 subjects during a visual feedback task. Main results: We achieved online discrimination accuracies of up to 81%, comparable to those obtained with professional 32/64-channel EEG devices via deep-learning using either a generative-adversarial network or an intrinsic-mode function augmentation of the training data and minimalistic computing resources. Significance: Our BCI model has the potential of expanding the spectrum of BCIs to more portable, artificial intelligence-enhanced, efficient interfaces accelerating the routine deployment of these devices outside the controlled environment of a scientific laboratory.

PurposeThe purpose of this paper is to demonstrate the optimization of printed circuit board (PCB) manufacturing by improving drilling process productivity.Design/methodology/approachTwo different ways are explored to increase the productivity of the PCB drilling operation. The first way involves the minimization of the cutting‐tool path length. The second way to achieve the objective explores the efficiency of processing stacked PCBs.FindingsTo reduce the tool path length between the holes of a PCB, a heuristic hybrid algorithm to solve the traveling salesman problem (TSP) is briefly described. Also, a mathematical model to calculate the total processing time is proposed. Based on this model, the paper shows the optimal number of stacked PCBs that can be profitably processed, while high processing productivity does not always mean high number of stacked PCBs.Research limitations/implicationsThe paper does not treat the optimization of the drilling process parameters, even if reduction of the drilling time using optimized cutting parameters also represents an efficient method for improving the productivity.Originality/valueThe paper shows the influence of the algorithm performance for solving the TSP on the processing time minimization, by decreasing the component of drill movement time along the drill path between holes. Additionally, the conditions in which stacking a specific number of PCBs is advantageous are also investigated. Furthermore, the paper shows how to determine the optimum number of stacked PCBs.

Abstract.Numerous studies have suggested the use of decoded error potentials in the brain to improve human-computer communication.Together with state-of-the-art scientific equipment, experiments have also tested instruments with more limited performance for the time being, such as Emotiv EPOC. This study presents a review of these trials and a summary of the results obtained. However, the level of these results indicates a promising prospect for using this headset as a human-computer interface for error decoding.

The adaptive distance between the neighbourhood's makespans influences the local search to explore the non-investigated areas of the solutions space. A Tabu Search with the intensive concentric exploration over non-explored areas is proposed as an alternative solution to the simplest Tabu Search with the random shifting of two jobs indexes operation for Permutation Flow Shop Problem (PFSP) with the makespan minimization criteria.