查看更多>>摘要：Recently, the combination of neural network and attention mechanism is widely employed for electroencephalogram (EEG) emotion recognition (EER) and has achieved remarkable results. Never-theless, most of them ignored the individual information in and within different frequency bands, so they just applied a single-layer attention mechanism to the entire EEG signals, with relatively single feature expression. To overcome the shortcoming, a spatial-frequency convolutional self-attention network (SFCSAN) is proposed in this paper to integrate the feature learning from both spatial and frequency domain of EEG signals. In this model, the intra-frequency band self-attention is employed to learn frequency information from each frequency band, and inter-frequency band mapping further maps them into final attention representation to learn their complementary frequency information. Additionally, a parallel convolutional neural network (PCNN) layer is used to excavate the spatial information of EEG signals. By incorporating spatial and frequency band information, the SFCSAN can fully utilize the spatial and frequency domain information of EEG signals for emotion recognition. The experiments conducted on two public EEG emotion datasets achieved the average accuracy of 95.15%/95.76%/95.64%/95.86% on valence/arousal/dominance/liking label for DEAP dataset, and 93.77%/95.80%/96.26% on valence/arousal/dominance label for DREAMER dataset, which all demonstrate that the proposed method is conducive to enhancing the importing of emotion-salient information and generating better recognition performance. The code of our work is available on "https://github.com/qeebeast7/SFCSAN''. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：The stochastic global optimization (SGO) methods like particle swarm optimization (PSO), genetic algorithm (GA), and cuckoo search (CS) have been widely used in a variety of optimization problems partly because of the ability to find the global optimum. Most existing SGO algorithms are designed for gradient-free problems and ignore the gradient information even if the gradient is readily available, resulting in low efficiency and high computational cost. In this paper, we introduce a hybrid self-adaptive gradient-based cuckoo search (HAGCS) to tackle this limitation. HAGCS first takes a gradient-based local random walk to explore the search space, and then uses gradient-based local optimization (GBLO) to find a local minimum near to the current best solution, which is more efficient and precise than standard CS. Additionally, in order to avoid premature convergence potentially being caused by the use of the gradient, we introduce two novel self-adaptation and diversity promotion strategies onto HAGCS. These help HAGCS find proper control parameters and prevent HAGCS from getting stuck at local minima or stationary points. Lastly, we compare HAGCS with PSO, GA, CS, and 5 refinements of CS on 12 benchmark functions. Compared to the other methods, the experiment results show that the proposed method HAGCS has about 2 times faster convergence speed, higher accuracy, and 27.5% higher success rate of finding the global minimum in high-dimension problems. Even when the dimension of the problem is 1000, HAGCS still offers a success rate of 64% to find the global minima accurately. (C) 2022 Elsevier B.V. All rights reserved.
Gupta, P. K.Siddiqui, Mohammad KhubebHuang, XiaodiMorales-Menendez, Ruben...
10页
查看更多>>摘要：Ever since the outbreak of COVID-19, the entire world is grappling with panic over its rapid spread. Consequently, it is of utmost importance to detect its presence. Timely diagnostic testing leads to the quick identification, treatment and isolation of infected people. A number of deep learning classifiers have been proved to provide encouraging results with higher accuracy as compared to the conventional method of RT-PCR testing. Chest radiography, particularly using X-ray images, is a prime imaging modality for detecting the suspected COVID-19 patients. However, the performance of these approaches still needs to be improved. In this paper, we propose a capsule network called COVID-WideNet for diagnosing COVID-19 cases using Chest X-ray (CXR) images. Experimental results have demonstrated that a discriminative trained, multi-layer capsule network achieves state-of-the-art performance on the COVIDx dataset. In particular, COVID-WideNet performs better than any other CNN based approaches for diagnosis of COVID-19 infected patients. Further, the proposed COVID-WideNet has the number of trainable parameters that is 20 times less than that of other CNN based models. This results in fast and efficient diagnosing COVID-19 symptoms and with achieving the 0.95 of Area Under Curve (AUC), 91% of accuracy, sensitivity and specificity respectively. This may also assist radiologists to detect COVID and its variant like delta. (C)& nbsp;2022 Published by Elsevier B.V.
查看更多>>摘要：Rapid, accurate and robust detection of looming objects in cluttered moving backgrounds is a significant and challenging problem encountered when designing robotic visual systems to perform collision detection and avoidance tasks. Inspired by the neural circuit involved in the elementary motion vision of the mammalian retina, this study proposes a bioinspired approach-sensitive neural network (ASNN). The three main contributions of this work are as follows. First, a direction-selective visual processing module is built based on the spatiotemporal energy framework, which can estimate motion direction accurately via only two mutually perpendicular spatiotemporal filtering channels. Second, a novel approach-sensitive neural network is modeled as a push-pull structure formed by ON and OFF pathways, which responds strongly to approaching motion, but is insensitive to lateral motion. Finally, a method of direction-selective inhibition is introduced, which is able to effectively suppress translational backgrounds. Extensive synthetic and real robotic experiments indicate that the proposed model is able to not only detect collisions accurately and robustly in cluttered and dynamic backgrounds but also extract additional information on the approaching object, such as position and direction, which is critical for guiding rapid decision making. (C)& nbsp;2022 Published by Elsevier B.V.
查看更多>>摘要：Currently, processing time, energy consumption and processing quality are three significant optimization objectives for manufacturing process. The variety of optimization objectives and the constraints of processes make the production scheduling an NP-hard problem. To improve processing quality, feedback processing is requisite in productive process, but the nonlinearity of feedback process causes further scheduling complexity. The purpose of this research is to realize the multi-objective optimization scheduling of manufacturing process with feedback process. To solve these problems, a virtual workflow modeling method for parallel manufacturing process of manifold varieties of jobs is proposed in this study, and based on the models, a Multi-Objective Virtual Workflow Scheduling Algorithm (MOVWSA) is contributed. In MOVWSA, the genetic evolution based on two-dimensional chromosome coding and weighted elite retention metrics is employed to select processing equipment for processes, and a sequence-selective strategy is proposed to specify processing order and starting time of each process. It is shown from the comparative test results on flexible job shop scheduling benchmark instances (MK01-MK10) that the proposed MOVWSA can provide more dominant static solutions for multi-objective optimization scheduling. The simulation test illustrates that MOVWSA with virtual workflow modeling is capable of dynamically adjusting the processing plans when reprocessing events occur to ensure the stability of processing with makespan and energy consumption. Consequently, the method contributed in this paper achieves the static and dynamic multi-objective optimization scheduling for manufacturing process with nonlinear feedback process by the two mechanisms of virtual modeling and evolutionary optimization. (C)& nbsp;2022 Published by Elsevier B.V.
查看更多>>摘要：With the advent of AI, the internet of things (IoT) and human-centric computing (HCC), the world has witnessed a rapid proliferation of smart homes (SH). However, implementing a robust security system for residents of SH remains a daunting task. The existing smart homes incorporate security provisions such as biometric verification, activity tracking, and facial recognition. Integrating multi-sensor devices, networking systems and data storage facilities escalate the lifecycle costs of these systems. Facial emotions convey important cues on behaviour and intent that can be used as non-invasive feedback for contextual threat analysis. The early mitigation of a hostile situation, such as a fight or an attempted intrusion, is vital for the SH residents' safety. This research proposes a real-time facial emotion-based security framework called iSecureHome for smart homes using a CMOS camera, which is triggered by a passive infrared (PIR) motion sensor. The impact of chromatic and achromatic features on facial Emotion Recognition (ER), as well as skin colour-based biases in current ER algorithms, are also investigated. A time-bound facial emotion decoding strategy is presented in iSecureHome that is based on EmoFusioNet-a deep fusion-based model-to predict the security concerns in the vicinity of a given residence. EmoFusioNet utilises stacked and late fusion methodologies to ensure a colourneutral and equitable ER system. Initially, the stacked model synchronously extracts the chromatic and achromatic facial features using deep CNNs, and their predictions are then fed into the late fusion component. After that, a regularised multi-layer perceptron (R-MLP) is trained to fuse the results of stacked CNNs , generate final predictions. Experimental results suggest that the proposed fusion methodology augments the ER model and achieves the final train and test accuracy of 98.48% and 98.43%, respectively. iSecureHome also comprises a multi-threaded decision-making framework for threat analysis with efficient performance and minimal latency.
查看更多>>摘要：Nowadays, scientific research, industry, and many other fields are greedy regarding computing resources. Therefore, Cloud Computing infrastructures are now attracting pervasive interest thanks to their excellent hallmarks such as scalability, high performance, reliability, and the pay-per-use strategy. The execution of these high-performant applications on such kind of computing environments in respect of optimizing many conflicting objectives brings us to a challenging issue commonly known as the multi-objective workflows scheduling on large scale distributed systems. Having this in mind, we outline in the present paper our proposed approach called Genetically-modified Multi-objective Particle Swarm Optimization (GMPSO) for scheduling application workflows on hybrid Clouds in the context of high-performance computing in an attempt to optimize Makespan and Cost. The GMPSO consists of incorporating genetic operations into the Multi-objective Particle Swarm Optimization to enhance the resulting solutions. To achieve this, we have designed a novel solution encoding that represents the task ordering, the task mapping and the resource provisioning processes of the workflow scheduling problem in hybrid Clouds. In addition, a set of particular adaptive evolutionary operators have been designed. Conducted simulations lead to significant results compared with a set of well-performed algorithms such NSGA-II, OMOPSO and SMPSO, especially, for the most-demanding workload of workflows. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：The prediction of algal bloom is one of the important links in eutrophication prevention. Chlorophyll a concentration is the indicating variable of algal bloom, and its time series is non-stationary and nonlinear, which brings challenges to its effective prediction. Although the current algae growth model (AGM) can directly describe the algal bloom dynamics, the fixed parameters limit the adaptability of the model. If the fixed parameters are dynamically adjusted, the trend of chlorophyll a concentration can be better captured. Therefore, the adaptive dynamic programming (ADP) approach is used to optimize the parameters of the AGM. The ADP contains an action network and a critic network by echo state network, where the action network is used to output the increment value of the fixed parameters, and the critic network is used to approximate the performance index function. In this paper, the input of the action network uses the time series features extracted by the relevant variables, so that the time-varying parameters of the AGM have better dynamic characteristics. We verify the effectiveness of the proposed model through the dataset of the North Canal and Taihu Lake, and the convergence analysis proves the theoretical reliability. In this way, the improved mechanism model with timevarying parameters not only maintains the better interpretability of the original AGM, but also further enhances the prediction accuracy and adaptability by extracting inherent interactive features from the relevant variables.
查看更多>>摘要：In this paper, a multi/many-objective optimization algorithm assisted by radial basis function is proposed based on reference vectors to solve computationally expensive optimization. According to the iteration, a set of candidates are first determined by the reference vectors guided evolutionary algorithm in a sub-cycle. Based on the candidate pool, a refinement regeneration strategy and a dynamic exploration strategy are required. The refinement regeneration strategy is adopted to update the reference vectors derived from three types of reference vectors (i.e., the coarse reference vectors, the random reference vectors, and the refined reference vectors). The dynamic exploration strategy aims to determine the infilling samples from the candidate pool, considering space-infilling characteristics in the design space and convergence in the objective space. By repeatedly selecting candidates, the refinement regeneration strategy, as well as the dynamic exploration strategy, the final Pareto-optimal solutions can be yielded when the termination condition is satisfied. To verify the effectiveness of the proposed algorithm in addressing low/high-dimensional multi/many-objective optimization, the algorithm is compared with three state-of-the-art surrogate-assisted evolutionary algorithms in terms of numerous benchmark problems and an engineering problem. According to the corresponding results, the competitiveness of the proposed algorithm is verified. (C) 2022 Elsevier B.V. All rights reserved.
Charkari, Nasrollah MoghadamDaneshyar, Seyed Abbas
24页
查看更多>>摘要：Moving object tracking is one of the applied fields in artificial intelligence and robotic. The main objective of object tracking is to detect and locate targets in video frames of real scenes. Although various methods have been proposed for object tracking so far, tracking in challenging conditions remains an open issue. Recently, different evolutionary and heuristics algorithms like swarm intelligence have been used to address the tracking challenges, which have shown promising performance. In this paper, a new approach based on modified biogeography based optimization (mBBO) method is introduced. The BBO algorithm includes migration and mutation steps. In the migration phase, the search space is properly explored by sharing information between habitats and weaker solutions to improve their position. On the other hand, the mutation phase leads to diversity and change in solutions. In this algorithm, the elitist method has been also used to keep better solutions. The performance of modified BBO tracker has been evaluated on benchmark video datasets and compared with several other tracking methods. Experimental results demonstrate that the proposed method estimates the location of targets with high accuracy and achieves better performance and robustness compared to other trackers.(c) 2022 Published by Elsevier B.V.
NSTL
Elsevier