Applied Soft Computing最新文献_第2页

Diffusion-based dynamic super-dense candidate boxes with random center points for 3D object detection 三维目标检测中基于扩散的随机中心点动态超密集候选盒

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-21 DOI: 10.1016/j.asoc.2025.113181

Si-Heng He , Zi-Jia Wang , Yuan-Gen Wang , Yicong Zhou , Sam Kwong

{"title":"Diffusion-based dynamic super-dense candidate boxes with random center points for 3D object detection","authors":"Si-Heng He , Zi-Jia Wang , Yuan-Gen Wang , Yicong Zhou , Sam Kwong","doi":"10.1016/j.asoc.2025.113181","DOIUrl":"10.1016/j.asoc.2025.113181","url":null,"abstract":"<div><div>Diffusion models have achieved promising results in image generation, but their applications in 3D object detection still need further exploration. In this paper, we design a novel model DiffCandiDet based on dense heads with Gaussian distributed center points for 3D object detection, which effectively integrates the anchor-based method and the Gaussian random noise-based method to leverage the powerful denoising and reconstruction capabilities of the diffusion model. To achieve the learning balance for multi-class 3D object detection, we propose a Dynamic Super-dense Candidate Boxes (DSCB) strategy. Notably, DiffCandiDet addresses the issue of traditional models struggling to detect pedestrians walking side by side. In addition to Gaussian distribution, we also propose a DSCB strategy based on discrete uniform distribution (DUCandiDet) and continuous uniform distribution (CUCandiDet), to reduce the runtime consumption and enhance the robustness of the model. Extensive experiments show that DiffCandiDet achieves competitive results on both KITTI and Waymo Open Datasets. <strong>DiffCandiDet ranks 1st</strong> on the KITTI validation set in the Car and Pedestrian detection leaderboard. Code is available at <span><span>https://github.com/SiHengHeHSH/DiffCandiDet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"178 ","pages":"Article 113181"},"PeriodicalIF":7.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A comprehensive analysis of Bitcoin volatility forecasting using time-series econometric models 使用时间序列计量经济模型对比特币波动率预测进行全面分析

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-21 DOI: 10.1016/j.asoc.2025.113339

Nrusingha Tripathy , Sarbeswara Hota , Debabrata Singh , Biswa Mohan Acharya , Subrat Kumar Nayak

{"title":"A comprehensive analysis of Bitcoin volatility forecasting using time-series econometric models","authors":"Nrusingha Tripathy , Sarbeswara Hota , Debabrata Singh , Biswa Mohan Acharya , Subrat Kumar Nayak","doi":"10.1016/j.asoc.2025.113339","DOIUrl":"10.1016/j.asoc.2025.113339","url":null,"abstract":"<div><div>The world of cryptocurrency has expanded rapidly over the last ten years, with the most recent advancements witnessed in the last few years as many individuals have realized the importance of storing digital assets online. According to Twitter statistics, there are roughly 1500 tweets on Bitcoin alone per hour, which lends credence to this claim. As a consequence, investors are eager to learn how to make profitable cryptocurrency trades and investments, and the fundamental idea behind digital currencies is growing in acceptance and understanding. This study investigates the notable inefficiencies in the several research efforts that have attempted to create algorithms that can accurately forecast price fluctuations in the Bitcoin market. This work compares different econometric models based on Root Mean Squared Error (RMSE) and Root Mean Squared Percentage Error (RMSPE). The RMSE score of our proposed Threshold Autoregressive Conditional Heteroskedasticity (TARCH) model is 0.065, and an RMSPE score of 0.197, which is minimal compared to other models. The proposed Bootstrap TARCH technique appropriate for simulating the intricate and volatile characteristics of Bitcoin returns.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"178 ","pages":"Article 113339"},"PeriodicalIF":7.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144155112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Q network with action retention for going long and short selling 深度Q网络与行动保留做多和做空

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-21 DOI: 10.1016/j.asoc.2025.113252

Qizhou Sun , Yain-Whar Si

{"title":"Deep Q network with action retention for going long and short selling","authors":"Qizhou Sun , Yain-Whar Si","doi":"10.1016/j.asoc.2025.113252","DOIUrl":"10.1016/j.asoc.2025.113252","url":null,"abstract":"<div><div>In computer-simulated games, the primary objective of adopting reinforcement learning is to achieve victory by attaining the highest hand-crafted reward, considering the optimal state-value functions across the promising trajectories. However, in the context of algorithmic trading, there is no clear goal for hand-crafting an extremely high reward for the state-value function. Besides, the exploration and exploitation of the reinforcement learning could generate a high number of unexpected <em>buy</em> and <em>sell</em> actions. These actions could lead to overlapped transactions which cannot provide a fair reward function. In order to alleviate these problems, we propose a novel trading algorithm named Deep Q Network with Action Retention (DQN-AR). Firstly, the action retention mechanism is proposed to avoid the overlapped transactions. Secondly, the divide-and-conquer approach is employed to break down the profit maximization goal into several sub-goals, with the aim of optimizing the annualized returns from all transactions throughout the entire trading period. Thirdly, we evaluate the effectiveness of the proposed approach by implementing the DQN-AR model for both long and short selling in algorithmic trading. In the experiments, we compare DQN-AR with DQN, Gated-DQN (GDQN), Simple Moving Average (SMA) and Dual Moving Average Crossover (DMAC). The experimental result shows that DQN-AR is superior to DQN, GDQN, SMA and DMAC and achieves the state-of-art trading performance both for long and short positions. In summary, our DQN-AR achieves 15.4% higher profit on average than the second top competitor approach for the long position and 101.03% higher on average for the short position.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"178 ","pages":"Article 113252"},"PeriodicalIF":7.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-individual electrophysiological signal recognition in Clivia biosensors via domain adaptation 基于域适应的Clivia生物传感器跨个体电生理信号识别

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-19 DOI: 10.1016/j.asoc.2025.113323

Chenrui Liu , Ji Qi , Xiuxin Xia , Yicheng Wang , Qiuping Wang , Lingfang Sun , Hong Men

{"title":"Cross-individual electrophysiological signal recognition in Clivia biosensors via domain adaptation","authors":"Chenrui Liu , Ji Qi , Xiuxin Xia , Yicheng Wang , Qiuping Wang , Lingfang Sun , Hong Men","doi":"10.1016/j.asoc.2025.113323","DOIUrl":"10.1016/j.asoc.2025.113323","url":null,"abstract":"<div><div>This study explores the use of Clivia plants as biosensors for environmental monitoring and ecological protection, focusing on the analysis of electrophysiological signals generated under various stress conditions. Plants’ ability to produce real-time electrophysiological signals in response to stressors such as salinity, drought, and pest infestations presents a promising method for precision agriculture and ecological surveillance. However, a key challenge is the significant variability in plant responses and signal distributions across individual plants, which limits the generalizability of models trained on specific plant samples.To address this, we introduce DA-PlantNet, a novel model that leverages domain adaptation techniques to enhance the model's adaptability and transferability across different plant individuals. By minimizing discrepancies in feature distribution between plants, DA-PlantNet effectively differentiates and classifies electrophysiological signals from various Clivia individuals, enabling robust cross-individual classification. We collected signals from Clivia plants under varying soil moisture conditions and analyzed them using DA-PlantNet. Experimental results demonstrate that DA-PlantNet significantly outperforms traditional methods, achieving an accuracy of 95.336 %, precision of 93.853 %, recall of 95.467 %, and an F1-score of 94.047 %, underscoring its robustness and generalization capability.This research introduces a novel approach to enhancing the adaptability and transferability of plant-based biosensor models, paving the way for scalable and reliable applications in precision agriculture and environmental monitoring. DA-PlantNet offers a valuable tool for ecological protection and sustainable agricultural practices, advancing the engineering of plant-based biosensors for real-world applications.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"178 ","pages":"Article 113323"},"PeriodicalIF":7.2,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generative adversarial network based on CNN classifier predicted scores for image style transfer 基于CNN分类器的生成对抗网络预测图像风格迁移得分

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-19 DOI: 10.1016/j.asoc.2025.113303

L.Mary Gladence , Yi-Wei Lai , Fu-Ti Lee , Mu-Yen Chen , Hsin-Te Wu

{"title":"Generative adversarial network based on CNN classifier predicted scores for image style transfer","authors":"L.Mary Gladence , Yi-Wei Lai , Fu-Ti Lee , Mu-Yen Chen , Hsin-Te Wu","doi":"10.1016/j.asoc.2025.113303","DOIUrl":"10.1016/j.asoc.2025.113303","url":null,"abstract":"<div><div>In recent years, image style transfer has emerged as an increasingly popular research theme in the field of computer vision. Image style transfer seeks to convert the style of an image or mix it with other styles to produce an image with stylistic features not found in the original image. In the past, image style conversion was mainly implemented using feature conversion or filters, processes which require a significant degree of manual design, thus limiting these approaches to performing at most a single style conversion. However, with the development of deep learning technologies, an increasing number of studies have begun to break through these research challenges, achieving significant progress. The study proposes generating image data attribute tags from the classification dataset, constructing a GAN architecture for multi-style conversion tasks, and proposes a Classifier Style Scores GAN (CSS-GAN) model. First, a CNN classifier is used to train on the classification dataset. Once its stability is verified, the classifier is used to make predictions and its output layer features are extracted as attribute labels. These labels are subjected to different types of pre-processing to assess the performance difference between smoothed labels and binary classification labels. Finally, the resulting labels are used to train a multi-style transfer GAN. Experiments are conducted using a facial attribute dataset to compare the labeling method with the proposed model architecture. The results indicate that using classifier-predicted features and applying feature smoothing as attribute labels for training the GAN can effectively enhance the quality and stability of images generated for the style transfer task. Additionally, this approach allows for better control over the degree of transformation and improves the overall performance of style transfer.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"178 ","pages":"Article 113303"},"PeriodicalIF":7.2,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrated RBF networks for periodic extensions for solving boundary value problems 求解边值问题的周期扩展集成RBF网络

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-19 DOI: 10.1016/j.asoc.2025.113238

N. Mai-Duy , Y.T. Gu , K. Le-Cao , C.M.T. Tien

{"title":"Integrated RBF networks for periodic extensions for solving boundary value problems","authors":"N. Mai-Duy , Y.T. Gu , K. Le-Cao , C.M.T. Tien","doi":"10.1016/j.asoc.2025.113238","DOIUrl":"10.1016/j.asoc.2025.113238","url":null,"abstract":"<div><div>In this paper, the radial basis function networks (RBFNs) are trained to extend a non-periodic function to become a periodic one in a rectangular domain, from which Cartesian-grid-based partial-differential-equation (PDE) solvers can be applied. The networks are constructed through integration instead of the usual differentiation. The presence of the integration constants results in a higher dimension space in the hidden layer, which enhances the quality of approximation of the networks. In addition, the resulting integrated basis functions are applied to sinusoidal functions, which guarantees that the approximating function in the extended domain is naturally periodic. With the RBF width, amplitude and phase shift being adjustable parameters, the equations representing the networks are nonlinear and they can be solved by using the Levenberg–Marquardt method. Numerical experiments demonstrate that the iterative convergence is fast, the residual is low and the approximating function in the extension domain possesses a low level of fluctuation. The proposed networks are then utilised in conjunction with some high-order discretisation methods based on RBFs to enable the PDE in a non-rectangular domain to be solved in a rectangular one. The task of discretising a continuous spatial domain is very economical as a simple Cartesian grid can be used to represent the computational/extended domain. Linear and nonlinear problems are considered and the IRBF results are compared with the analytic solutions and numerical results produced by the finite difference and finite element methods. Numerical experiments demonstrate that the high-order discretisation methods are still able to produce their fast rates of convergence.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"177 ","pages":"Article 113238"},"PeriodicalIF":7.2,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Q-learning based arithmetic optimization algorithm for a multi-warehouse joint replenishment and delivery problem 基于q学习的多仓库联合补货配送优化算法

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-18 DOI: 10.1016/j.asoc.2025.113307

Lu Peng , Sirui Wang

引用次数: 0

Offloading-verified framework for adversary detection and mitigation in IoT 卸载验证框架，用于物联网中的攻击检测和缓解

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-17 DOI: 10.1016/j.asoc.2025.113312

Nadhem Ebrahim , Mourad Elloumi , Abdullah Mohammed Alharthi , Fahad S. Altuwaijri , Mohammed Alsaadi

{"title":"Offloading-verified framework for adversary detection and mitigation in IoT","authors":"Nadhem Ebrahim , Mourad Elloumi , Abdullah Mohammed Alharthi , Fahad S. Altuwaijri , Mohammed Alsaadi","doi":"10.1016/j.asoc.2025.113312","DOIUrl":"10.1016/j.asoc.2025.113312","url":null,"abstract":"<div><div>Cyber-physical systems (CPSs) designed for the Internet of Things (IoT) enhanced security and resource infrastructures to support various applications and services, undetected adversaries in the temporarily connected IoT network impose different user and data privacy threats, this research introduces an Offloading-verified Adversary Detection and Mitigation Scheme (OADMS), this proposed scheme coexists with the IoT communication and CPS security infrastructure for adversary detection, conventional behavior-based adversary detection with partial order adversarial network training validates the infrastructure security support against cyber-attacks. The behavior is analyzed for independent and offloaded service exchanges, reducing communication failures and is recurrently analyzed in the detection process until the service termination, communication metrics of the infrastructure units are used to verify adversary and user channel behavior. The learning process recommendations are exploited to validate the channel's reliability through IoT-sharing platforms, and the performance of the proposed system is assessed using communication latency, failure rate, response ratio, and detection factor. The model achieved an excellent detection accuracy rate of 96.8 %.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"177 ","pages":"Article 113312"},"PeriodicalIF":7.2,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep hashing image retrieval based on CNN and visual transformer network 基于CNN和视觉变压器网络的深度哈希图像检索

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-17 DOI: 10.1016/j.asoc.2025.113244

Shuli Cheng , Xingming Xiao , Liejun Wang

{"title":"Deep hashing image retrieval based on CNN and visual transformer network","authors":"Shuli Cheng , Xingming Xiao , Liejun Wang","doi":"10.1016/j.asoc.2025.113244","DOIUrl":"10.1016/j.asoc.2025.113244","url":null,"abstract":"<div><div>Deep hashing technology can achieve unified representation of multimedia technology, which is widely used in fields such as smart agriculture, smart transportation, and public safety. However, the current deep hashing methods cannot achieve efficient fusion of global and local information, and the learning ability of hash code representation needs to be further strengthened. In this paper, we propose a deep hashing retrieval algorithm based on integrated CNN and visual Transformer(ICVT) network. Firstly, we propose a lightweight nonlinear spatial group enhancement (NSGE) module, which is integrated with the Transformer through a parallel architecture and introduces a self-attention mechanism to enhance the spatial distribution of semantic features through the similarity between local and global features. The CNN representation capability of feature maps is improved to enhance the spatial distribution of semantic features within each feature semantic group. Secondly, we propose a margin contrast loss function to optimize the hash code parameters, which is used to improve the retrieval accuracy of the algorithm for multi-label datasets. Finally, extensive experiments on CIFAR-10, NUS-WIDE, and ImageNet datasets demonstrate that ICVT has superior retrieval performance compared with the currently popular algorithms, especially on CIFAR-10, where the mAP performance reaches 97.5%.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"177 ","pages":"Article 113244"},"PeriodicalIF":7.2,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

EEG microstates classification empowered with optimum-path forest using different distance measurements 利用不同距离测量的最优路径森林对EEG微状态进行分类

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-05-17 DOI: 10.1016/j.asoc.2025.113253

Raniere R. Guimarães , Leandro A. Passos , David W. Kuster , Ani Dong , Victor Hugo C. de Albuquerque

{"title":"EEG microstates classification empowered with optimum-path forest using different distance measurements","authors":"Raniere R. Guimarães , Leandro A. Passos , David W. Kuster , Ani Dong , Victor Hugo C. de Albuquerque","doi":"10.1016/j.asoc.2025.113253","DOIUrl":"10.1016/j.asoc.2025.113253","url":null,"abstract":"<div><div>Electroencephalography (EEG) is considered one of the most important tests for neurological disease diagnosis, whose signals comprise microstate information regarding the spatiotemporal characteristics of human brain activity. However, interpreting and identifying such signals denotes a complex and time-consuming activity, thus motivating the use of automated approaches like machine learning techniques in many studies. Recent research has presented several techniques for detecting neurological disorders through analyzing EEG microstates. However, this area has room for advancements and improvements, using distinct methods and more in-depth scrutiny. Therefore, this paper proposes a new method for EEG signal classification through microstate analysis for diagnosing neurological diseases using a graph-based algorithm, namely the Optimum-Path Forest (OPF) classifier. Experiments were conducted over features extracted from EEG microstates obtained from the Temple University Hospital Abnormal EEG Corpus (TUAB) and the Schizophrenia EEG datasets. Such features are further processed using principal component analysis, t-distributed stochastic neighbor embedding, and uniform manifold approximation and projection dimensionality reduction techniques to improve computational efficiency and increase the classifier’s performance. Furthermore, this work evaluates 44 distance measurements in OPF’s graph modeling context. Finally, the experimental results show that with a reduced set of features extracted from the microstates and an appropriate distance measure, it is possible to obtain accuracy values equivalent to 100% with low processing time compared to raw data. In addition, the <span><math><mi>k</mi></math></span>-nearest neighbors and support vector machine classifiers were used to compare the experimental results.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"177 ","pages":"Article 113253"},"PeriodicalIF":7.2,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0