IEEE Transactions on Emerging Topics in Computational Intelligence最新文献

{"title":"Personalized Exercise Group Assembly Using a Two Archive Evolutionary Algorithm","authors":"Yifei Sun;Yifei Cao;Ziang Wang;Sicheng Hou;Weifeng Gao;Zhi-Hui Zhan","doi":"10.1109/TETCI.2024.3514976","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3514976","url":null,"abstract":"Traditional exercise recommendation algorithms generate exercise groups according to the features of exercises for all students. However, as different students may have different knowledge proficiencies, this article focuses on the personalized exercises group assembly (PEGA) to select exercises for each student based on their knowledge proficiencies, which is formulated as a constrained multi-objective problem. In order to solve the constrained multi-objective PEGA problem efficiently, this paper proposes a two archives evolutionary algorithm (TAEA) with three novel designs. Firstly, as the number of exercises is very large in PEGA, the traditional binary-number encoding method will result in high consumption in both memory and computation. To this end, a new integer-number encoding (INE) method is designed for solution representation. It saves memory for exercise subset representation, speeds up evaluations, and generates solutions that satisfy some constraints. Secondly, based on the INE method, the TAEA adopts two archives name convergence-oriented archive (CA) and diversity-oriented archive (DA). The CA ensures the convergence, driving force, and feasibility of the solutions. The DA aims to provide as diverse a solution as possible, including exploration of infeasible regions. Thirdly, a classification-based offspring co-reproduction strategy is proposed to solve the issue of too much infeasible space exploration. Experimental results show that our INE method can help to reduce the running time and improve the optimization results. The effectiveness of the TAEA is demonstrated by comparing it with some recent existing algorithms.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 3","pages":"2572-2583"},"PeriodicalIF":5.3,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PFPS: Polymerized Feature Panoptic Segmentation Based on Fully Convolutional Networks","authors":"Shucheng Ji;Xiaochen Yuan;Junqi Bao;Tong Liu;Yang Lian;Guoheng Huang;Guo Zhong","doi":"10.1109/TETCI.2024.3515004","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3515004","url":null,"abstract":"Panoptic segmentation requires the prediction of a pixel-level mask with a category label in an image. In recent years, panoptic segmentation has been gaining more attention since it can help us understand objects and the environment in many fields, such as medical images, remote sensing images, and autonomous driving. However, existing panoptic segmentation methods are usually challenging for multi-scale object segmentation and boundary localization. In this paper, we propose a Polymerized Feature Panoptic Segmentation (PFPS) to enhance the network's feature representation ability by polymerizing the extracted stage features. Specifically, we propose a Generalization-Enhanced Stage Feature Generation Module (GSFGM) to extract and enhance the stage features. In the GSFGM, a novel Sampled and Concated Feature Generation (SCFG) is designed as an individual component, which polymerizes the convoluted backbone features to enhance multi-scale feature representation. Thereafter, we propose a Stage Feature Re-weight Module (SFRM) to ensure the network can learn efficient information from the massive channels. Moreover, we further propose a Unified Encoder Module (UEM) to provide spatial information and compress the high-dimensional features by coordinating convolution operations and channel attention. To demonstrate the superiority of the proposed PFPS, we conduct experiments on the COCO-2017 and the Cityscapes validation datasets. The experimental results indicate that the PFPS achieves a better performance in PQ of 43.0%, SQ of 80.4%, RQ of 51.9%, PQ^th of 48.6%, SQ^th of 82.6%, RQ^th of 58.1%, PQ^st of 34.6% on COCO-2017 validation dataset, while PQ of 61.7%, and PQ^st of 67.9% on Cityscapes validation dataset.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 3","pages":"2584-2596"},"PeriodicalIF":5.3,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Bit Mixed-Precision Quantization and Acceleration of CNN for FPGA Deployment","authors":"JianRong Wang;Zhijun He;Hongbo Zhao;Rongke Liu","doi":"10.1109/TETCI.2024.3510295","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3510295","url":null,"abstract":"Nowadays, the deployment of intelligent networks on hardware devices for real-time applications is gaining popularity in both academia and industry. However, on-chip resources and power consumption are usually limited, making quantization a crucial step due to its ability to reduce the computational footprint. To this point, mixed-precision bit-width allocation for weights is an effective way to reduce the overall memory footprint while maximizing model accuracy, which can generally be divided into two schemes: per-layer quantization and per-channel quantization. However, the latter has a large searching space, making it hard to obtain optimal solutions, so currently most research focuses on the former scheme. Additionally, there is almost no research targeting the design and optimization of FPGA accelerator structures for per-channel quantization. Motivated by these considerations, this paper first proposes a mixed-precision bit allocation method, called Hierarchical Bit Programming (HBP), which reduces the magnitude of the search space by applying group optimization on channel dimension and consequently reduce the computational complexity of the solving process. Then a loop optimization strategy is presented based on quantization manner, and models are established to evaluate FPGA performance and resource requirement, enabling the evaluation and analysis of accelerator performance bottlenecks and optimization boundaries in the early phase of system design. Based on the optimization results, a hardware accelerator design structure is presented. Several mainstream CNN models are used for evaluation, and on-board tests are conducted on the Zynq MPSoC XCZU15EG FPGA platform. The experiment results show that our HBP method could achieve an improvement of more than 2% on accuracy compared with other related methods. Compared with CPU and GPU, the proposed FPGA accelerator yields speedups of 28.8%, 46.2%, 31.0%, and 35.9% in energy efficiency on VGG-16, ResNet18, ResNet34, and ResNet50, respectively, and the processing latency could be 25% lower than state-of-the-art methods.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 3","pages":"2597-2617"},"PeriodicalIF":5.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bayesian Inference of Hidden Markov Models Through Probabilistic Boolean Operations in Spiking Neuronal Networks","authors":"Ayan Chakraborty;Saswat Chakrabarti","doi":"10.1109/TETCI.2024.3502472","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3502472","url":null,"abstract":"Recurrent neural networks (RNN) have been extensively used to address the problem of Bayesian inference of a hidden Markov model (HMM). However, such artificial neural architectures are prone to computationally exhaustive training procedures and high energy dissipation. Spiking neural networks (SNNs) are recently explored for performing similar tasks. An interesting problem on Bayesian inference of hidden Markov models (HMM) on SNN paradigm is addressed in this paper. A population based stochastic temporal encoding (PSTE) scheme has been introduced to establish that a spiking neuron behaves as a probabilistic Boolean operator. Using this property the posterior of a hidden state is mapped to probability of firing a logic <inline-formula><tex-math>$HIGH$</tex-math></inline-formula> by a spiking neuron. Two new algorithms are presented for fixing synaptic strengths denoted by a random variable <inline-formula><tex-math>$q$</tex-math></inline-formula>. The first algorithm uses a sigmoidal relationship from pre-statistical analysis to select the values of <inline-formula><tex-math>$q$</tex-math></inline-formula> such that the probability of a neuron producing a logic HIGH becomes equal to the posterior probability of a hidden state. The second algorithm considers data for appropriately determining <inline-formula><tex-math>$q$</tex-math></inline-formula> through in-network-training. It has been demonstrated that Bayesian inference of both two-state HMMs as well as multi-state HMMs are implementable using the concept of PSTE. Two examples are presented, one on inferring the trend of a time series and the other related to deciphering the correct digit of a seven segment LED display with noisy bits. Our framework has performed very closely with traditional Bayesian inference (difference in accuracy <inline-formula><tex-math>$&lt; 2%$</tex-math></inline-formula>) and traditional RNNs.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 3","pages":"2618-2632"},"PeriodicalIF":5.3,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MSE-GCN: A Multiscale Spatiotemporal Feature Aggregation Enhanced Efficient Graph Convolutional Network for Dynamic Sign Language Recognition","authors":"Neelma Naz;Hasan Sajid;Sara Ali;Osman Hasan;Muhammad Khurram Ehsan","doi":"10.1109/TETCI.2024.3509500","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3509500","url":null,"abstract":"Graph convolution networks have emerged as an active area of research for skeleton-based sign language recognition (SLR). One essential problem in this approach is to efficiently extract the most discriminative features capable of modeling short-range and long-range spatial and temporal information over all skeleton joints while ensuring low inference costs. To address this issue, we propose a novel multi-scale efficient graph convolutional network (MSE-GCN) for skeleton-based SLR. The proposed network makes use of separable convolution layers set in a multi-scale setting and embedded in a multi branch (MB) network along with an early fusion scheme, resulting in an accurate, computationally efficient, and faster system. In addition, we have proposed a novel hybrid attention module, named Spatial Temporal Joint Part attention (ST-JPA) to distinguish the most important body parts as well as most informative joints in the specific frames from the whole sign sequence. The performance of proposed network (MSE-GCN) is evaluated on five challenging sign language datasets, WLASL-100, WLASL-300, WLASL-1000, MINDS-Libras, and LIBRAS-UFOP achieving state-of-the-art (SOTA) accuracies of 85.27%, 81.59%, 71.75%, 97.442 ± 1.01%, and 88.59±3.60%, respectively while incurring lower computational costs.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 4","pages":"2979-2994"},"PeriodicalIF":5.3,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Non-Homogeneous Granulation-Aided Density-Based Deep Feature Clustering for Far Infrared Sign Language Images","authors":"Pritam Paral;Saibal Ghosh;Sankar K. Pal;Amitava Chatterjee","doi":"10.1109/TETCI.2024.3510292","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3510292","url":null,"abstract":"In image clustering applications, deep feature clustering has recently demonstrated impressive performance, which employs deep neural networks for feature learning that favors clustering exercises. In this context, density-based methods have emerged as the preferred choice for the clustering mechanism within the framework of deep feature clustering. However, as the performance of these clustering algorithms is primarily effective on the low-dimensional feature data, deep feature learning models play a crucial role here. With far infrared (FIR) thermal imaging systems working in real-world scenarios, the images captured are largely affected by blurred edges, background noise, thermal irregularities, few details, etc. In this work, we demonstrate the effectiveness of granular computing-based techniques in such scenarios, where the input data contains indiscernible image regions and vague boundary regions. We propose a novel adaptive non-homogeneous granulation (ANHG) technique here that can adaptively select the smallest possible size of granules within a purview of unequally-sized granulation, based on a segmentation assessment index. Proposed ANHG in combination with deep feature learning helps in extracting complex, indiscernible information from the image data and capturing the local intensity variation of the data. Experimental results show significant performance improvement of the density-based deep feature clustering method after the incorporation of the proposed granulation scheme.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 2","pages":"1269-1280"},"PeriodicalIF":5.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Light Image Enhancement Network Based on Multi-Scale Residual Feature Integration","authors":"Shuying Huang;Hebin Liu;Yong Yang;Weiguo Wan","doi":"10.1109/TETCI.2024.3508834","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3508834","url":null,"abstract":"Owing to insufficient light, images captured in low-light environment have a series of image degradation problems such as low visibility, color deviation, and noise. To address these problems, an image enhancement network based on multi-scale residual feature integration (IEN-MRFI) is proposed, which includes two modules: a shallow feature extraction module (SFEM) and a multi-scale feature integration module (MFIM). First, the SFEM is constructed for extracting multi-scale shallow features through three-scale convolutional layers and smooth convolution residual blocks (SCRBs). The constructed SCRB runs through the entire network to extract features and avoid gridding artifacts. Then, the MFIM is constructed by cascading multiple feature integration residual blocks to fuse the shallow and deep features of the same scale. Finally, the fused features are passed through a convolutional layer to obtain an enhanced result. In addition, to improve the generalization ability of our network, this study constructs an outdoor dataset for the training of the low-light image enhancement network. Experiments on indoor and outdoor images show that the enhancement results of our method can provide more accurate color saturation and richer details than those of some state-of-the-art methods. We intend to make the constructed dataset public after our paper is accepted for publication.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 4","pages":"2965-2978"},"PeriodicalIF":5.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolutionary Optimization for Proactive and Dynamic Computing Resource Allocation in Open Radio Access Network","authors":"Gan Ruan;Leandro L. Minku;Zhao Xu;Xin Yao","doi":"10.1109/TETCI.2024.3499997","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3499997","url":null,"abstract":"In Open Radio Access Network (O-RAN), intelligent techniques are urged to achieve the automation of the computing resource allocation, so as to save computing resources and increase their utilization rate, as well as decrease the network delay. However, the existing formulation of this problem as an optimization problem defines the capacity utility of resource in an inappropriate way and it tends to cause much delay. Moreover, the only algorithm proposed to solve this problem is a greedy search algorithm, which is not ideal as it could get stuck into local optima. To overcome these issues, a new formulation that better describes the problem is proposed. In addition, an evolutionary algorithm (EA) is designed to find a resource allocation scheme to proactively and dynamically deploy the computing resource for processing upcoming traffic data. A multivariate long short-term memory model is used in the proposed EA to predict future traffic data for the production of deployment scheme. As a global search approach, the EA is less likely to get stuck in local optima than greed search, leading to better solutions. Experimental studies carried out on real-world datasets and artificially generated datasets with different scenarios and properties have demonstrated the significant superiority of our proposed EA over a baseline greedy algorithm under all parameter settings. Moreover, experimental studies with all afore-mentioned datasets are performed to compare the proposed EA and two variants under different parameter settings, to demonstrate the impact of different algorithm choices.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 1","pages":"1001-1018"},"PeriodicalIF":5.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient Multi-View Clustering via Essential Tensorized Bipartite Graph Learning","authors":"Wanrong Gu;Junlong Guo;Haiyan Wang;Guangyu Zhang;Bin Zhang;Jiazhou Chen;Hongmin Cai","doi":"10.1109/TETCI.2024.3502459","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3502459","url":null,"abstract":"Multi-view spectral clustering has garnered significant attention for its capacity to integrate intrinsic feature information from multiple perspectives, resulting in improved performance. However, the oversight of inter-view correlations has led to suboptimal outcomes. Furthermore, the conventional method of constructing an <inline-formula><tex-math>$N times N$</tex-math></inline-formula> graph in multi-view clustering imposes a substantial time burden when dealing with large-scale scenarios. To address these challenges, this paper presents an efficient multi-view clustering approach via <italic>E</i>ssential <italic>T</i>ensorized <italic>B</i>ipartite <italic>G</i>raph <italic>L</i>earning (ETBGL). Specifically, ETBGL utilizes the low-rank tensor Schatten <inline-formula><tex-math>$p$</tex-math></inline-formula>-norm to capture inter-view similarity, effectively capturing high-order correlation information embedded in multiple views. Simultaneously, by incorporating bipartite graph learning, ETBGL efficiently mitigates the computational demands and spatial complexity associated with tensor operations. Additionally, we introduce the <inline-formula><tex-math>$ell _{2,1}$</tex-math></inline-formula>-norm of tensor as a sparse penalty to the error term, with the aim of filtering out noise and preserving shared information, thus enhancing clustering robustness. We solve our objective by an efficient algorithm that is time-economical and has good convergence. Comprehensive evaluations on diverse datasets demonstrate the exceptional performance of our proposed model.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 4","pages":"2952-2964"},"PeriodicalIF":5.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Streamlined and Resource-Efficient Estimation of Epistemic Uncertainty in Deep Ensemble Classification Decision via Regression","authors":"Jordan F. Masakuna;Djeff K. Nkashama;Arian Soltani;Marc Frappier;Pierre M. Tardif;Froduald Kabanza","doi":"10.1109/TETCI.2024.3508846","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3508846","url":null,"abstract":"Ensemble deep learning (EDL) has emerged as a leading tool for epistemic uncertainty quantification (UQ) in predictive modelling. Our study focuses on the utilization of EDL, composed of auto-encoders (AEs) for out-of-distribution (OoD) detection. EDL offers straightforward interpretability and valuable practical insights. Conventionally, employing multiple AEs in an ensemble requires regular training for each model whenever substantial changes occur in the data, a process that can become computationally expensive, especially when dealing with large ensembles. To address this computational challenge, we introduce an innovative strategy that treats ensemble UQ as a regression problem. During initial training, once the uncertainty distribution is established, we map this distribution to one ensemble member. This approach ensures that during subsequent trainings and inferences, only one ensemble member and the regression model are needed to predict uncertainties, eliminating the need to maintain the entire ensemble. This streamlined approach is particularly advantageous for systems with limited computational resources or situations that demand rapid decision-making, such as alert management in cybersecurity. Our evaluations on five benchmark OoD detection data sets demonstrate that the uncertainty estimates obtained with our proposed method can, in most cases, align with the uncertainty distribution learned by the ensemble, all while significantly reducing the computational resource requirements.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 4","pages":"2940-2951"},"PeriodicalIF":5.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}