Electronics

Research

18 pages, 5268 KiB

Open AccessArticle

Semi-Supervised Gastrointestinal Stromal Tumor Detection via Self-Training

by Qi Yang, Ziran Cao, Yaling Jiang, Hanbo Sun, Xiaokang Gu, Fei Xie, Fei Miao and Gang Gao

Electronics 2023, 12(4), 904; https://doi.org/10.3390/electronics12040904 - 10 Feb 2023

Cited by 1 | Viewed by 1626

Abstract

The clinical diagnosis of gastrointestinal stromal tumors (GISTs) requires time-consuming tumor localization by physicians, while automated detection of GIST can help physicians develop timely treatment plans. Existing GIST detection methods based on fully supervised deep learning require a large amount of labeled data [...] Read more.

The clinical diagnosis of gastrointestinal stromal tumors (GISTs) requires time-consuming tumor localization by physicians, while automated detection of GIST can help physicians develop timely treatment plans. Existing GIST detection methods based on fully supervised deep learning require a large amount of labeled data for the model training, but the acquisition of labeled data is often time-consuming and labor-intensive, hindering the optimization of the model. However, the semi-supervised learning method can perform better than the fully supervised learning method with only a small amount of labeled data because of the full use of unlabeled data, which effectively compensates for the lack of labeled data. Therefore, we propose a semi-supervised gastrointestinal stromal tumor (GIST) detection method based on self-training using the new selection criterion to guarantee the quality of pseudo-labels and adding the pseudo-labeled data to the training set together with the labeled data after linear mixing. In addition, we introduce the improved Faster RCNN with the multiscale module and the feature enhancement module (FEM) for semi-supervised GIST detection. The multiscale module and the FEM can better fit the characteristics of GIST and obtain better detection results. The experiment results showed that our approach achieved the best performance on our GIST image dataset with the joint optimization of the self-training framework, the multiscale module, and the FEM. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

14 pages, 530 KiB

Open AccessArticle

Learning Data-Driven Propagation Mechanism for Graph Neural Network

by Yue Wu, Xidao Hu, Xiaolong Fan, Wenping Ma and Qiuyue Gao

Electronics 2023, 12(1), 46; https://doi.org/10.3390/electronics12010046 - 22 Dec 2022

Cited by 1 | Viewed by 1982

Abstract

A graph is a relational data structure suitable for representing non-Euclidean structured data. In recent years, graph neural networks (GNN) and their subsequent variants, which utilize deep neural networks to complete graph analysis and representation, have shown excellent performance in various application fields. [...] Read more.

A graph is a relational data structure suitable for representing non-Euclidean structured data. In recent years, graph neural networks (GNN) and their subsequent variants, which utilize deep neural networks to complete graph analysis and representation, have shown excellent performance in various application fields. However, the propagation mechanism of existing methods relies on hand-designed GNN layer connection architecture, which is prone to information redundancy and over-smoothing problems. To alleviate this problem, we propose a data-driven propagation mechanism to adaptively propagate information between layers. Specifically, we construct a bi-level optimization objective and use the gradient descent algorithm to learn the forward propagation architecture, which improves the efficiency of learning different layer combinations in multilayer networks. The experimental results of the model on seven benchmark datasets demonstrate the effectiveness of the proposed method. Furthermore, combining this data-driven propagation mechanism with models, such as Graph Attention Networks, can consistently improve the performance of these models. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

14 pages, 2264 KiB

Open AccessArticle

CM-NET: Cross-Modal Learning Network for CSI-Based Indoor People Counting in Internet of Things

by Jing Guo, Xiaokang Gu, Zhengqi Liu, Minghao Ji, Jingwen Wang, Xiaoyan Yin and Pengfei Xu

Electronics 2022, 11(24), 4113; https://doi.org/10.3390/electronics11244113 - 9 Dec 2022

Cited by 1 | Viewed by 2004

Abstract

In recent years, multiple IoT solutions have used computational intelligence technologies to identify people and count them. WIFI Channel State Information (CSI) has recently been applied to counting people with multiple benefits, such as being cost-effective, easily accessible, free of privacy concerns, etc. [...] Read more.

In recent years, multiple IoT solutions have used computational intelligence technologies to identify people and count them. WIFI Channel State Information (CSI) has recently been applied to counting people with multiple benefits, such as being cost-effective, easily accessible, free of privacy concerns, etc. However, most current CSI-based work is limited to human location-fixed environments since human location-random environments are more complicated. Aiming to fix the problem of counting people in human location-random environments, we propose a solution using deep learning CM-NET, an end-to-end cross-modal learning network. Since it is difficult to count people with CSI straightforwardly, CM-NET approaches this problem using deep learning, utilizing a multi-layer transformer model to automatically extract the correlations between channels and the number of people. Owing to the complexity of human location-random environments, the transformer model cannot extract characteristics describing the number of people. To enhance the feature learning capability of the transformer model, CM-NET takes the feature knowledge learned by the image-based people counting model to supervise the learning process. In particular, CM-NET works with CSI alone during the testing phase without any image information, and ultimately achieves sound results with an average accuracy of 86%. Meanwhile, the superiority of CM-NET has been verified by comparison with the latest available related methods. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

18 pages, 2529 KiB

Open AccessArticle

An Improved Crystal Structure Algorithm for Engineering Optimization Problems

by Wentao Wang, Jun Tian and Di Wu

Electronics 2022, 11(24), 4109; https://doi.org/10.3390/electronics11244109 - 9 Dec 2022

Cited by 5 | Viewed by 1548

Abstract

Crystal Structure Algorithm (CryStAl) is a new meta-heuristic algorithm, and it has been studied by many scholars because of its wide adaptability and the fact that there is no need to set parameters in advance. An improved crystal structure algorithm (GLCryStAl) based on [...] Read more.

Crystal Structure Algorithm (CryStAl) is a new meta-heuristic algorithm, and it has been studied by many scholars because of its wide adaptability and the fact that there is no need to set parameters in advance. An improved crystal structure algorithm (GLCryStAl) based on golden sine operator and Levy flight is designed in this paper. The algorithm makes good use of the relationship between the golden sine operator and the unit circle to make the algorithm exploration space more comprehensive, and then gradually narrows the search space in the iterative process, which can effectively speed up the convergence rate of the algorithm. At the same time, a Levy operator is introduced to help the algorithm effectively get rid of the attraction of local optimal value. To evaluate the performance of GLCryStAl, 12 classic benchmark functions and eight CEC2017 test functions were selected to design a series of comparative experiments. In addition, the experimental data of these algorithms are analyzed using the Wilcoxon and Friedman tests. Through these two tests, it can be found that GLCryStAl has significant advantages over other algorithms. Finally, this paper further tests the optimization performance of GLCryStAl in engineering design. GLCryStAl was applied to optimize pressure vessel design problems and tension/compression spring design problems. The optimization results show that GLCryStAl is feasible and effective in optimizing engineering design. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

14 pages, 3411 KiB

Open AccessArticle

Lightweight Multi-Scale Dilated U-Net for Crop Disease Leaf Image Segmentation

by Cong Xu, Changqing Yu and Shanwen Zhang

Electronics 2022, 11(23), 3947; https://doi.org/10.3390/electronics11233947 - 29 Nov 2022

Cited by 14 | Viewed by 1875

Abstract

Crop disease leaf image segmentation (CDLIS) is the premise of disease detection, disease type recognition and disease degree evaluation. Various convolutional neural networks (CNN) and their modified models have been provided for CDLIS, but their training time is very long. Aiming at the [...] Read more.

Crop disease leaf image segmentation (CDLIS) is the premise of disease detection, disease type recognition and disease degree evaluation. Various convolutional neural networks (CNN) and their modified models have been provided for CDLIS, but their training time is very long. Aiming at the low segmentation accuracy of various diseased leaf images caused by different sizes, colors, shapes, blurred speckle edges and complex backgrounds of traditional U-Net, a lightweight multi-scale extended U-Net (LWMSDU-Net) is constructed for CDLIS. It is composed of encoding and decoding sub-networks. Encoding the sub-network adopts multi-scale extended convolution, the decoding sub-network adopts a deconvolution model, and the residual connection between the encoding module and the corresponding decoding module is employed to fuse the shallow features and deep features of the input image. Compared with the classical U-Net and multi-scale U-Net, the number of layers of LWMSDU-Net is decreased by 1 with a small number of the trainable parameters and less computational complexity, and the skip connection of U-Net is replaced by the residual path (Respath) to connect the encoder and decoder before concatenating. Experimental results on a crop disease leaf image dataset demonstrate that the proposed method can effectively segment crop disease leaf images with an accuracy of 92.17%. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

15 pages, 2213 KiB

Open AccessArticle

Human Perception Intelligent Analysis Based on EEG Signals

by Bingrui Geng, Ke Liu and Yiping Duan

Electronics 2022, 11(22), 3774; https://doi.org/10.3390/electronics11223774 - 17 Nov 2022

Viewed by 1637

Abstract

The research on brain cognition provides theoretical support for intelligence and cognition in computational intelligence, and it is further applied in various fields of scientific and technological innovation, production and life. Use of the 5G network and intelligent terminals has also brought diversified [...] Read more.

The research on brain cognition provides theoretical support for intelligence and cognition in computational intelligence, and it is further applied in various fields of scientific and technological innovation, production and life. Use of the 5G network and intelligent terminals has also brought diversified experiences to users. This paper studies human perception and cognition in the quality of experience (QoE) through audio noise. It proposes a novel method to study the relationship between human perception and audio noise intensity using electroencephalogram (EEG) signals. This kind of physiological signal can be used to analyze the user’s cognitive process through transformation and feature calculation, so as to overcome the deficiency of traditional subjective evaluation. Experimental and analytical results show that the EEG signals in frequency domain can be used for feature learning and calculation to measure changes in user-perceived audio noise intensity. In the experiment, the user’s noise tolerance limit for different audio scenarios varies greatly. The noise power spectral density of soothing audio is 0.001–0.005, and the noise spectral density of urgent audio is 0.03. The intensity of information flow in the corresponding brain regions increases by more than 10%. The proposed method explores the possibility of using EEG signals and computational intelligence to measure audio perception quality. In addition, the analysis of the intensity of information flow in different brain regions invoked by different tasks can also be used to study the theoretical basis of computational intelligence. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

30 pages, 8298 KiB

Open AccessArticle

An Improved Nonlinear Tuna Swarm Optimization Algorithm Based on Circle Chaos Map and Levy Flight Operator

by Wentao Wang and Jun Tian

Electronics 2022, 11(22), 3678; https://doi.org/10.3390/electronics11223678 - 10 Nov 2022

Cited by 19 | Viewed by 3029

Abstract

The tuna swarm optimization algorithm (TSO) is a new heuristic algorithm proposed by observing the foraging behavior of tuna populations. The advantages of TSO are a simple structure and fewer parameters. Although TSO converges faster than some classical meta-heuristics algorithms, it can still [...] Read more.

The tuna swarm optimization algorithm (TSO) is a new heuristic algorithm proposed by observing the foraging behavior of tuna populations. The advantages of TSO are a simple structure and fewer parameters. Although TSO converges faster than some classical meta-heuristics algorithms, it can still be further accelerated. When TSO solves complex and challenging problems, it often easily falls into local optima. To overcome the above issue, this article proposed an improved nonlinear tuna swarm optimization algorithm based on Circle chaos map and levy flight operator (CLTSO). In order to compare it with some advanced heuristic algorithms, the performance of CLTSO is tested with unimodal functions, multimodal functions, and some CEC2014 benchmark functions. The test results of these benchmark functions are statistically analyzed using Wilcoxon, Friedman test, and MAE analysis. The experimental results and statistical analysis results indicate that CLTSO is more competitive than other advanced algorithms. Finally, this paper uses CLTSO to optimize a BP neural network in the field of artificial intelligence. A CLTSO-BP neural network model is proposed. Three popular datasets from the UCI Machine Learning and Intelligent System Center are selected to test the classification performance of the new model. The comparison result indicates that the new model has higher classification accuracy than the original BP model. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

10 pages, 12608 KiB

Open AccessFeature PaperArticle

Estimating Sound Speed Profile by Combining Satellite Data with In Situ Sea Surface Observations

by Zhenyi Ou, Ke Qu, Yafen Wang and Jianbo Zhou

Electronics 2022, 11(20), 3271; https://doi.org/10.3390/electronics11203271 - 11 Oct 2022

Cited by 3 | Viewed by 1532

Abstract

Given that spatiotemporal measurement of the subsurface profile over a wide range are difficult to obtain, surface observations from satellites are often used to estimate the sound speed profile (SSP). This paper proposes a multisource method based on the self-organizing map (SOM) to [...] Read more.

Given that spatiotemporal measurement of the subsurface profile over a wide range are difficult to obtain, surface observations from satellites are often used to estimate the sound speed profile (SSP). This paper proposes a multisource method based on the self-organizing map (SOM) to improve the estimation of the SSP by merging surface observations with satellite data. Surface observations from the Kuroshio Extension Observatory (KEO) were used to supplement satellite observations (anomalies in the measured sea level and sea surface temperature) to this end. Different combinations of the surface parameters were assessed, their errors were analyzed, and differences between the results before and after the multisource parameters were used are discussed. The proposed method significantly increased the accuracy of estimating the SSP when the parameters obtained from in situ measurements were used, with a root mean square error of 2.18 m/s, less than a third of the error obtained when only satellite observations were used. The proposed method provides a new approach to determining an accurate three-dimensional structure of the sound speed when various surface observations are available. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

13 pages, 464 KiB

Open AccessArticle

Transformer-Based Distillation Hash Learning for Image Retrieval

by Yuanhai Lv, Chongyan Wang, Wanteng Yuan, Xiaohao Qian, Wujun Yang and Wanqing Zhao

Electronics 2022, 11(18), 2810; https://doi.org/10.3390/electronics11182810 - 6 Sep 2022

Cited by 2 | Viewed by 2355

Abstract

In recent years, Transformer has become a very popular architecture in deep learning and has also achieved the same state-of-the-art performance as convolutional neural networks on multiple image recognition baselines. Transformer can obtain global perceptual fields through a self-attention mechanism and can enhance [...] Read more.

In recent years, Transformer has become a very popular architecture in deep learning and has also achieved the same state-of-the-art performance as convolutional neural networks on multiple image recognition baselines. Transformer can obtain global perceptual fields through a self-attention mechanism and can enhance the weights of unique discriminable features for image retrieval tasks to improve the retrieval quality. However, Transformer is computationally intensive and finds it difficult to satisfy real-time requirements when used for retrieval tasks. In this paper, we propose a Transformer-based image hash learning framework and compress the constructed framework to perform efficient image retrieval using knowledge distillation. By combining the self-attention mechanism of the Transformer model, the image hash code is enabled to be global and unique. At the same time, this advantage is instilled into the efficient lightweight model by knowledge distillation, thus reducing the computational complexity and having the advantage of an attention mechanism in the Transformer. The experimental results on the MIRFlickr-25K dataset and NUS-WIDE dataset show that our approach can effectively improve the accuracy and efficiency of image retrieval. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

13 pages, 2218 KiB

Open AccessArticle

Multi-Scale Convolution-Capsule Network for Crop Insect Pest Recognition

by Cong Xu, Changqing Yu, Shanwen Zhang and Xuqi Wang

Electronics 2022, 11(10), 1630; https://doi.org/10.3390/electronics11101630 - 20 May 2022

Cited by 13 | Viewed by 2487

Abstract

Accurate crop insect pest identification in fields is useful to control pests and beneficial to agricultural yield and quality. However, it is a difficult and challenging problem due to the crop insect pests being small with various sizes, postures, shapes, and disorganized backgrounds. [...] Read more.

Accurate crop insect pest identification in fields is useful to control pests and beneficial to agricultural yield and quality. However, it is a difficult and challenging problem due to the crop insect pests being small with various sizes, postures, shapes, and disorganized backgrounds. Multi-scale convolution-capsule network (MSCCN) is constructed for crop insect pest identification. It consists of a multi-scale convolution module, capsule network (CapsNet) module, and SoftMax classification module. Multi-scale convolution is used to extract the multi-scale discriminative features, CapsNet is employed to encode the hierarchical structure of the size-variant insect pests in the crop images, and Softmax is adopted for insect pest identification. MSCCN combines the advantages of convolutional neural network (CNN), CapsNet, and multi-scale CNN, and can learn multi-scale robust features from pest images of different shapes and sizes for pest recognition and identify various morphed pests. Experimental results on the crop pest image dataset show that this method has a good recognition rate of 91.4%. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

13 pages, 970 KiB

Open AccessArticle

Few-Shot Learning with Collateral Location Coding and Single-Key Global Spatial Attention for Medical Image Classification

by Wenjing Shuai and Jianzhao Li

Electronics 2022, 11(9), 1510; https://doi.org/10.3390/electronics11091510 - 9 May 2022

Cited by 8 | Viewed by 2470

Abstract

Humans are born with the ability to learn quickly by discerning objects from a few samples, to acquire new skills in a short period of time, and to make decisions based on limited prior experience and knowledge. The existing deep learning models for [...] Read more.

Humans are born with the ability to learn quickly by discerning objects from a few samples, to acquire new skills in a short period of time, and to make decisions based on limited prior experience and knowledge. The existing deep learning models for medical image classification often rely on a large number of labeled training samples, whereas the fast learning ability of deep neural networks has failed to develop. In addition, it requires a large amount of time and computing resource to retrain the model when the deep model encounters classes it has never seen before. However, for healthcare applications, enabling a model to generalize new clinical scenarios is of great importance. The existing image classification methods cannot explicitly use the location information of the pixel, making them insensitive to cues related only to the location. Besides, they also rely on local convolution and cannot properly utilize global information, which is essential for image classification. To alleviate these problems, we propose a collateral location coding to help the network explicitly exploit the location information of each pixel to make it easier for the network to recognize cues related to location only, and a single-key global spatial attention is designed to make the pixels at each location perceive the global spatial information in a low-cost way. Experimental results on three medical image benchmark datasets demonstrate that our proposed algorithm outperforms the state-of-the-art approaches in both effectiveness and generalization ability. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

15 pages, 2924 KiB

Open AccessArticle

Evolutionary Optimization Based Set Joint Integrated Probabilistic Data Association Filter

by Shuang Liang, Yun Zhu and Hao Li

Electronics 2022, 11(4), 582; https://doi.org/10.3390/electronics11040582 - 15 Feb 2022

Cited by 2 | Viewed by 1758

Abstract

The joint integrated probabilistic data association (JIPDA) algorithm is widely used for the automatic tracking of multiple targets, but it has the well-known problem of track coalescence. By optimizing the posterior density, the accuracy of the target state estimation can be improved. Motivated [...] Read more.

The joint integrated probabilistic data association (JIPDA) algorithm is widely used for the automatic tracking of multiple targets, but it has the well-known problem of track coalescence. By optimizing the posterior density, the accuracy of the target state estimation can be improved. Motivated by this idea, we developed a novel evolutionary optimization based joint integrated probabilistic data association (EOJIPDA) filter to overcome the coalescence problem of the JIPDA filter. The trace for the covariance matrix of the posterior density is used as the objective function for the above optimization problem. It is shown that the accuracy of the target state estimation can be improved by reducing the trace. Evolutionary optimization was employed to minimize the trace and optimize the posterior density. More specifically, we enumerated all the possible permutations of the targets and assign a unique index to each permutation. The resulting indices were randomly assigned to all possible association hypothesis events. Each assignment indicated one possible gene in the evolutionary algorithm. This process was repeated several times to arrive at the initial population. An illustrative example shows that the EOJIPDA filter can effectively improve the accuracy of state estimation. Numerical studies are presented for two challenging multi-target tracking scenarios with clutter and missed detections. The experimental results demonstrate that the EOJIPDA filter provides better tracking accuracy than traditional coalescence-avoiding methods. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

17 pages, 1071 KiB

Open AccessFeature PaperArticle

A Novel Progressive Image Classification Method Based on Hierarchical Convolutional Neural Networks

by Cheng Li, Fei Miao and Gang Gao

Electronics 2021, 10(24), 3183; https://doi.org/10.3390/electronics10243183 - 20 Dec 2021

Cited by 3 | Viewed by 3288

Abstract

Deep Neural Networks (DNNs) are commonly used methods in computational intelligence. Most prevalent DNN-based image classification methods are dedicated to promoting the performance by designing complicated network architectures and requiring large amounts of model parameters. These large-scale DNN-based models are performed on all [...] Read more.

Deep Neural Networks (DNNs) are commonly used methods in computational intelligence. Most prevalent DNN-based image classification methods are dedicated to promoting the performance by designing complicated network architectures and requiring large amounts of model parameters. These large-scale DNN-based models are performed on all images consistently. However, since there are meaningful differences between images, it is difficult to accurately classify all images by a consistent network architecture. For example, a deeper network is fit for the images that are difficult to be distinguished, but may lead to model overfitting for simple images. Therefore, we should selectively use different models to deal with different images, which is similar to the human cognition mechanism, in which different levels of neurons are activated according to the difficulty of object recognition. To this end, we propose a Hierarchical Convolutional Neural Network (HCNN) for image classification in this paper. HCNNs comprise multiple sub-networks, which can be viewed as different levels of neurons in humans, and these sub-networks are used to classify the images progressively. Specifically, we first initialize the weight of each image and each image category, and these images and initial weights are used for training the first sub-network. Then, according to the predicted results of the first sub-network, the weights of misclassified images are increased, while the weights of correctly classified images are decreased. Furthermore, the images with the updated weights are used for training the next sub-networks. Similar operations are performed on all sub-networks. In the test stage, each image passes through the sub-networks in turn. If the prediction confidences in a sub-network are higher than a given threshold, then the results are output directly. Otherwise, deeper visual features need to be learned successively by the subsequent sub-networks until a reliable image classification result is obtained or the last sub-network is reached. Experimental results show that HCNNs can obtain better results than classical CNNs and the existing models based on ensemble learning. HCNNs have 2.68% higher accuracy than Residual Network 50 (Resnet50) on the ultrasonic image dataset, 1.19% than Resnet50 on the chimpanzee facial image dataset, and 10.86% than Adaboost-CNN on the CIFAR-10 dataset. Furthermore, the HCNN is extensible, since the types of sub-networks and their combinations can be dynamically adjusted. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

17 pages, 847 KiB

Open AccessArticle

Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism

by Fei Xie, Panpan Zhang, Tao Jiang, Jiao She, Xuemin Shen, Pengfei Xu, Wei Zhao, Gang Gao and Ziyu Guan

Electronics 2021, 10(24), 3103; https://doi.org/10.3390/electronics10243103 - 13 Dec 2021

Cited by 7 | Viewed by 2547

Abstract

Computational intelligence has been widely used in medical information processing. The deep learning methods, especially, have many successful applications in medical image analysis. In this paper, we proposed an end-to-end medical lesion segmentation framework based on convolutional neural networks with a dual attention [...] Read more.

Computational intelligence has been widely used in medical information processing. The deep learning methods, especially, have many successful applications in medical image analysis. In this paper, we proposed an end-to-end medical lesion segmentation framework based on convolutional neural networks with a dual attention mechanism, which integrates both fully and weakly supervised segmentation. The weakly supervised segmentation module achieves accurate lesion segmentation by using bounding-box labels of lesion areas, which solves the problem of the high cost of pixel-level labels with lesions in the medical images. In addition, a dual attention mechanism is introduced to enhance the network’s ability for visual feature learning. The dual attention mechanism (channel and spatial attention) can help the network pay attention to feature extraction from important regions. Compared with the current mainstream method of weakly supervised segmentation using pseudo labels, it can greatly reduce the gaps between ground-truth labels and pseudo labels. The final experimental results show that our proposed framework achieved more competitive performances on oral lesion dataset, and our framework further extended to dermatological lesion segmentation. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

13 pages, 2343 KiB

Open AccessArticle

Multipopulation Particle Swarm Optimization for Evolutionary Multitasking Sparse Unmixing

by Dan Feng, Mingyang Zhang and Shanfeng Wang

Electronics 2021, 10(23), 3034; https://doi.org/10.3390/electronics10233034 - 5 Dec 2021

Cited by 5 | Viewed by 2491

Abstract

Recently, the multiobjective evolutionary algorithms (MOEAs) have been designed to cope with the sparse unmixing problem. Due to the excellent performance of MOEAs in solving the NP hard optimization problems, they have also achieved good results for the sparse unmixing problems. However, most [...] Read more.

Recently, the multiobjective evolutionary algorithms (MOEAs) have been designed to cope with the sparse unmixing problem. Due to the excellent performance of MOEAs in solving the NP hard optimization problems, they have also achieved good results for the sparse unmixing problems. However, most of these MOEA-based methods only deal with a single pixel for unmixing and are subjected to low efficiency and are time-consuming. In fact, sparse unmixing can naturally be seen as a multitasking problem when the hyperspectral imagery is clustered into several homogeneous regions, so that evolutionary multitasking can be employed to take advantage of the implicit parallelism from different regions. In this paper, a novel evolutionary multitasking multipopulation particle swarm optimization framework is proposed to solve the hyperspectral sparse unmixing problem. First, we resort to evolutionary multitasking optimization to cluster the hyperspectral image into multiple homogeneous regions, and directly process the entire spectral matrix in multiple regions to avoid dimensional disasters. In addition, we design a novel multipopulation particle swarm optimization method for major evolutionary exploration. Furthermore, an intra-task and inter-task transfer and a local exploration strategy are designed for balancing the exchange of useful information in the multitasking evolutionary process. Experimental results on two benchmark hyperspectral datasets demonstrate the effectiveness of the proposed method compared with the state-of-the-art sparse unmixing algorithms. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

15 pages, 2311 KiB

Open AccessArticle

Reliable Memory Model for Visual Tracking

by Daohui Ge, Ruyi Liu, Yunan Li and Qiguang Miao

Electronics 2021, 10(20), 2488; https://doi.org/10.3390/electronics10202488 - 13 Oct 2021

Cited by 1 | Viewed by 1528

Abstract

Effectively learning the appearance change of a target is the key point of an online tracker. When occlusion and misalignment occur, the tracking results usually contain a great amount of background information, which heavily affects the ability of a tracker to distinguish between [...] Read more.

Effectively learning the appearance change of a target is the key point of an online tracker. When occlusion and misalignment occur, the tracking results usually contain a great amount of background information, which heavily affects the ability of a tracker to distinguish between targets and backgrounds, eventually leading to tracking failure. To solve this problem, we propose a simple and robust reliable memory model. In particular, an adaptive evaluation strategy (AES) is proposed to assess the reliability of tracking results. AES combines the confidence of the tracker predictions and the similarity distance, which is between the current predicted result and the existing tracking results. Based on the reliable results of AES selection, we designed an active–frozen memory model to store reliable results. Training samples stored in active memory are used to update the tracker, while frozen memory temporarily stores inactive samples. The active–frozen memory model maintains the diversity of samples while satisfying the limitation of storage. We performed comprehensive experiments on five benchmarks: OTB-2013, OTB-2015, UAV123, Temple-color-128, and VOT2016. The experimental results show that our tracker achieves state-of-the-art performance. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

16 pages, 1201 KiB

Open AccessArticle

Efficient Opponent Exploitation in No-Limit Texas Hold’em Poker: A Neuroevolutionary Method Combined with Reinforcement Learning

by Jiahui Xu, Jing Chen and Shaofei Chen

Electronics 2021, 10(17), 2087; https://doi.org/10.3390/electronics10172087 - 28 Aug 2021

Cited by 4 | Viewed by 5627

Abstract

In the development of artificial intelligence (AI), games have often served as benchmarks to promote remarkable breakthroughs in models and algorithms. No-limit Texas Hold’em (NLTH) is one of the most popular and challenging poker games. Despite numerous studies having been conducted on this [...] Read more.

In the development of artificial intelligence (AI), games have often served as benchmarks to promote remarkable breakthroughs in models and algorithms. No-limit Texas Hold’em (NLTH) is one of the most popular and challenging poker games. Despite numerous studies having been conducted on this subject, there are still some important problems that remain to be solved, such as opponent exploitation, which means to adaptively and effectively exploit specific opponent strategies; this is acknowledged as a vital issue especially in NLTH and many real-world scenarios. Previous researchers tried to use an off-policy reinforcement learning (RL) method to train agents that directly learn from historical strategy interactions but suffered from challenges of sparse rewards. Other researchers instead adopted neuroevolutionary (NE) method to replace RL for policy parameter updates but suffered from high sample complexity due to the large-scale problem of NLTH. In this work, we propose NE_RL, a novel method combing NE with RL for opponent exploitation in NLTH. Our method contains a hybrid framework that uses NE’s advantage of evolutionary computation with a long-term fitness metric to address the sparse rewards feedback in NLTH and retains RL’s gradient-based method for higher learning efficiency. Experimental results against multiple baseline opponents have proved the feasibility of our method with significant improvement compared to previous methods. We hope this paper provides an effective new approach for opponent exploitation in NLTH and other large-scale imperfect information games. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

13 pages, 2713 KiB

Open AccessArticle

Evolutionary Multiobjective Optimization with Endmember Priori Strategy for Large-Scale Hyperspectral Sparse Unmixing

by Zhao Wang, Jinxin Wei, Jianzhao Li, Peng Li and Fei Xie

Electronics 2021, 10(17), 2079; https://doi.org/10.3390/electronics10172079 - 27 Aug 2021

Cited by 9 | Viewed by 1801

Abstract

Mixed pixels inevitably appear in the hyperspectral image due to the low resolution of the sensor and the mixing of ground objects. Sparse unmixing, as an emerging method to solve the problem of mixed pixels, has received extensive attention in recent years due [...] Read more.

Mixed pixels inevitably appear in the hyperspectral image due to the low resolution of the sensor and the mixing of ground objects. Sparse unmixing, as an emerging method to solve the problem of mixed pixels, has received extensive attention in recent years due to its robustness and high efficiency. In theory, sparse unmixing is essentially a multiobjective optimization problem. The sparse endmember term and the reconstruction error term can be regarded as two objectives to optimize simultaneously, and a series of nondominated solutions can be obtained as the final solution. However, the large-scale spectral library poses a challenge due to the high-dimensional number of spectra, it is difficult to accurately extract a few active endmembers and estimate their corresponding abundance from hundreds of spectral features. In order to solve this problem, we propose an evolutionary multiobjective hyperspectral sparse unmixing algorithm with endmember priori strategy (EMSU-EP) to solve the large-scale sparse unmixing problem. The single endmember in the spectral library is used to reconstruct the hyperspectral image, respectively, and the corresponding score of each endmember can be obtained. Then the endmember scores are used as a prior knowledge to guide the generation of the initial population and the new offspring. Finally, a series of nondominated solutions are obtained by the nondominated sorting and the crowding distances calculation. Experiments on two benchmark large-scale simulated data to demonstrate the effectiveness of the proposed algorithm. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

15 pages, 759 KiB

Open AccessArticle

Evolutionary Convolutional Neural Network Optimization with Cross-Tasks Transfer Strategy

by Zhao Wang, Di Lu, Huabing Wang, Tongfei Liu and Peng Li

Electronics 2021, 10(15), 1857; https://doi.org/10.3390/electronics10151857 - 2 Aug 2021

Cited by 5 | Viewed by 2929

Abstract

Convolutional neural networks (CNNs) have shown great success in a variety of real-world applications and the outstanding performance of the state-of-the-art CNNs is primarily driven by the elaborate architecture. Evolutionary convolutional neural network (ECNN) is a promising approach to design the optimal CNN [...] Read more.

Convolutional neural networks (CNNs) have shown great success in a variety of real-world applications and the outstanding performance of the state-of-the-art CNNs is primarily driven by the elaborate architecture. Evolutionary convolutional neural network (ECNN) is a promising approach to design the optimal CNN architecture automatically. Nevertheless, most of the existing ECNN methods only focus on improving the performance of the discovered CNN architectures without considering the relevance between different classification tasks. Transfer learning is a human-like learning approach and has been introduced to solve complex problems in the domain of evolutionary algorithms (EAs). In this paper, an effective ECNN optimization method with cross-tasks transfer strategy (CTS) is proposed to facilitate the evolution process. The proposed method is then evaluated on benchmark image classification datasets as a case study. The experimental results show that the proposed method can not only speed up the evolutionary process significantly but also achieve competitive classification accuracy. To be specific, our proposed method can reach the same accuracy at least 40 iterations early and an improvement of accuracy for 0.88% and 3.12% on MNIST-FASHION and CIFAR10 datasets compared with ECNN, respectively. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

16 pages, 4516 KiB

Open AccessArticle

Efficiently Mastering the Game of NoGo with Deep Reinforcement Learning Supported by Domain Knowledge

by Yifan Gao and Lezhou Wu

Electronics 2021, 10(13), 1533; https://doi.org/10.3390/electronics10131533 - 24 Jun 2021

Cited by 8 | Viewed by 4276

Abstract

Computer games have been regarded as an important field of artificial intelligence (AI) for a long time. The AlphaZero structure has been successful in the game of Go, beating the top professional human players and becoming the baseline method in computer games. However, [...] Read more.

Computer games have been regarded as an important field of artificial intelligence (AI) for a long time. The AlphaZero structure has been successful in the game of Go, beating the top professional human players and becoming the baseline method in computer games. However, the AlphaZero training process requires tremendous computing resources, imposing additional difficulties for the AlphaZero-based AI. In this paper, we propose NoGoZero+ to improve the AlphaZero process and apply it to a game similar to Go, NoGo. NoGoZero+ employs several innovative features to improve training speed and performance, and most improvement strategies can be transferred to other nonspecific areas. This paper compares it with the original AlphaZero process, and results show that NoGoZero+ increases the training speed to about six times that of the original AlphaZero process. Moreover, in the experiment, our agent beat the original AlphaZero agent with a score of 81:19 after only being trained by 20,000 self-play games’ data (small in quantity compared with 120,000 self-play games’ data consumed by the original AlphaZero). The NoGo game program based on NoGoZero+ was the runner-up in the 2020 China Computer Game Championship (CCGC) with limited resources, defeating many AlphaZero-based programs. Our code, pretrained models, and self-play datasets are publicly available. The ultimate goal of this paper is to provide exploratory insights and mature auxiliary tools to enable AI researchers and computer-game communities to study, test, and improve these promising state-of-the-art methods at a much lower cost of computing resources. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Applications of Computational Intelligence

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (20 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI