检索结果-内蒙古大学图书馆

Enhanced Emotion-Aware Conversational Agent: Analyzing User Behavioral Status for Tailored Reponses in Chatbot Interactions

引用

IEEE ACCESS 2025年 13卷 19770-19787页

作者： Abinaya, S. Ashwin, K. S. Alphonse, A. Sherly Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India

While chatbots are increasingly popular for communication, their effectiveness is limited by their difficulty in understanding users' emotions. To address this, this study proposes a new hybrid chatbot model called "TEBC-Net" (Text Emotion Bert CNN Network), which combines text and video analysis to interpret user emotions and generate more empathetic responses. At the core of TEBC-Net is a multi-modal emotion analysis system. One component uses Bidirectional Encoder Representations from Transformers (BERT), a well-regarded model in natural language processing (NLP), achieving an 87.21% accuracy rate in detecting emotional cues from text inputs. The second component captures users' facial expressions through webcam footage. It begins by detecting faces using a pre-trained classifier like Haarcascade. Then, to improve emotion recognition, it preprocesses the image through brightness adjustments and contrast enhancement with Automatic CLAHE and dual gamma correction. This processed image is analyzed by a Convolutional Neural Network (CNN) model trained specifically for emotion recognition, reaching 74.14% accuracy by assigning probabilities to different emotions. By integrating insights from both text and video analysis, TEBC-Net gains a comprehensive understanding of the user's emotional state and intent. This combined data then informs the chatbot's response generation module, enabling it to craft responses that are both empathetic and more directly aligned with the user's emotional needs.

关键词： Chatbots Emotion recognition Encoding Bidirectional control Convolutional neural networks Accuracy Faces classification algorithms Transformers Training Chatbot bidirectional encoder representations from transformers natural language processing emotion recognition automatic CLAHE with dual gamma correction convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

PIDDN: Pair-Image-Based Defect Detection Network With Template for PCB Inspection

引用

IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY 2025年第4期15卷 830-841页

作者： Jiang, Qixing Wu, Xiaojun Zhou, Jinghui Cheng, Jun Harbin Inst Technol Shenzhen Sch Mech Engn & Automat Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China

The detection of defects has consistently posed a significant obstacle in the domain of machine vision, particularly in the context of the production of printed circuit board (PCB) components. To advance this technology, we present pair-image-based defect detection network (PIDDN), a novel framework that enables precise detection of object bounding boxes by utilizing a pair of images, with one designated as a template. The PIDDN approach involves the utilization of a Siamese neural network to simultaneously encode the features of the pair image, followed by the implementation of a template feature fusion network (TFFN) for integration. In addition, we introduce a template feature rectification module (TFRM) that aligns the feature maps of the pair-images attentively. We evaluate PIDDN on the DeepPCB dataset, and it achieves an impressive mean average precision (mAP) score of 99.6%. Furthermore, we present PairPCB, a complex and realistic dataset collected from real-world PCB production scenarios, to validate the effectiveness of template images. Extensive experiments demonstrate that PIDDN outperforms mainstream object detection algorithms with a 4.1% improvement in mAP. Code will be available at: https://***/QixingJiang/PIDDN.

关键词： Feature extraction Defect detection Printed circuits Object detection Production Manufacturing Accuracy Head classification algorithms Training machine vision printed circuit board (PCB) Siamese network template images

来源：评论

学校读者我要写书评

暂无评论

ADS-YOLO: A Multi-Scale Feature Extraction Remote Sensing Image Object Detection Algorithm Based on Dilated Residuals

引用

IEEE ACCESS 2025年 13卷 26225-26234页

作者： Li, Jianying Chen, Yajun Niu, Meiqi Cai, Wenhao Qiu, Xiaoyang China West Normal Univ Sch Elect Informat Engn Nanchong 637009 Peoples R China

Object detection in remote sensing images is of significant research value in fields such as environmental monitoring and urban planning. However, the large variation in object sizes, along with challenges such as small and densely packed objects, makes this task particularly challenging. To address these issues, we propose an algorithm for multi-scale feature extraction in remote sensing image detection using dilated residuals (ADS-YOLO). Firstly, to address the challenges of scale variation and small target size, the Dilation-wise Residual (DWR) design is employed to form the C2f_DWR module, which restructures the bottleneck structure within the C2f segment to facilitate the extraction and fusion of multi-scale contextual information, thus reducing the difficulty associated with target scale variation. Secondly, inspired by the Adown subsampling convolution module from YOLOv9, we use it to replace the convolutions in the Backbone, enabling the model to capture finer image details at higher levels, while maintaining accuracy and reducing computational load. Lastly, to address the issue of dense targets, we design the Soft-NMS-ShapeIoU module to improve the consistency of bounding boxes and target shapes, while also suppressing adjacent boxes. Experimental results demonstrate that, on the publicly available remote sensing image datasets DIOR, RSOD, and NWPU VHR-10, the proposed ADS-YOLO model outperforms other state-of-the-art methods by a significant margin.

关键词： Feature extraction Remote sensing Convolution YOLO Semantics classification algorithms Accuracy Shape Sensors Image segmentation Object detection remote sensing images deep learning multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Instance Selection With Multiple Partial Adaptive Classifiers for Domain Adaptation

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2025年第1期29卷 46-60页

作者： Nguyen, Bach Hoai Xue, Bing Andreae, Peter Zhang, Mengjie Victoria Univ Wellington Ctr Data Sci & Artificial Intelligence Wellington 6140 New Zealand Victoria Univ Wellington Sch Engn & Comp Sci Wellington 6140 New Zealand

Domain adaptation reuses the knowledge learned from an existing (source) domain to classify unlabeled data from another related (target) domain. However, the two domains have different data distributions. Common approaches to bridge the two distributions are selecting/reweighting instances, building domain-invariant feature subspaces, or directly building adaptive classifiers. Recent domain adaptation work has shown that combining the above first two approaches before applying the third approach achieves better performance than performing each approach individually. However, most existing instance selection approaches are based on a ranking mechanism, ignore interdependences between instances, and require a predefined number of selected instances. Furthermore, adaptive classifiers are sensitive to their parameters which are challenging to optimize due to the lack of target labeled instances. This article introduces a novel evolutionary instance selection approach for domain adaptation. We propose a compacted representation and an efficient fitness function for particle swarm optimization to automatically determine the number of selected instances while considering the interdependencies among instances. This article also proposes to use multiple partial classifiers to build a more reliable and robust adaptive classifier. The results show that evolutionary instance selection selects better instances than the ranking approach. In cooperation with multiple partial classifiers, the proposed algorithm achieves better performance than nine state-of-the-art and well-known domain adaptation approaches.

关键词： classification algorithms Task analysis Optimization Contracts Buildings Standards Particle swarm optimization classification domain adaptation evolutionary computation (EC) particle swarm optimization (PSO) transfer learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Flight Condition Recognition Performance Through Functional Similarity

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 4270-4283页

作者： Leoni, Jessica Villa, Eugenia Cazzulani, Gabriele Baldi, Andrea Mariani, Ugo Tanelli, Mara Politecn Milan I-20133 Milan Italy Politecn Milan Dept Mech Engn Appl Mech I-20133 Milan Italy Leonardo Helicopters I-21017 Samarate Italy

Flight condition recognition (FCR) is pivotal for aviation safety, enabling the recognition of the real usage spectrum, and thus, adapting and optimizing the maintenance schedule defined at design time. However, as the spectrum of flight regimes expands, recognition accuracy becomes complex. With increasing regimes, classifier representations overlap due to synthesized indicators summarizing multivariate time-series behaviors. Neglecting temporal dependencies and dynamic behaviors impairs classifier performance, particularly for specific regimes, limiting the expansion of the recognized set. In this article, we propose a functional similarity index to address this challenge, aiding analysts in identifying similar regimes and improving classification performance. To define such index, we rely on functional data analysis to capture regime dynamics, enhancing both performance and behavior analysis. The designed similarity index offers dual benefits: it investigates supervised FCR classifier outcomes and guides a closed-loop feature selection procedure to enhance recognition performance. This process eliminates the need for direct supervised classifier retraining, using the similarity index as a gauge to estimate the classifier's capability to distinguish critical regimes given a specific features set. When applied to extensive data collected during load survey flights performed by two Leonardo helicopter models, our method provides insights into results assessed by a state-of-the-art FCR supervised classifier. It identifies critical regimes and identifies informative features to include in the set to enhance recognition. This versatile framework has the potential to significantly enhance operational efficiency and aviation system safety, thereby fortifying overall operational capabilities.

关键词： Indexes Helicopters Maintenance Monitoring Feature extraction Accuracy Heuristic algorithms Expert systems classification algorithms Surveys Functional analysis helicopter maintenance signal processing temporal databases

来源：评论

学校读者我要写书评

暂无评论

Intelligent Sleep Apnea Detection by Advanced ML Using Single-Lead EEG Signal Data

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 3859-3866页

作者： Khan, Atiya Biswas, Saroj Kr. Chunka, Chukhu Baruah, Barnana Natl Inst Technol Dept Comp Sci & Engn Silchar 788010 Assam India Assam Kaziranga Univ Dept Comp Sci Jorhat 785006 Assam India

Obstructive sleep apnea (OSA) is a common sleep disorder that causes repeated disruptions in breathing during sleep. The traditional method to diagnose OSA is polysomnography, which is complex and time-consuming and requires an overnight stay in a sleep lab. However, electroencephalography (EEG) sensor-based methods offer the possibility of simpler, in-home testing, improving accessibility and patient comfort. This article proposes an intelligent expert system for the OSA detection (IESOSAD) model. The proposed model aims to efficiently detect apnea utilizing single-lead EEG data and ensemble learning algorithms. The IESOSAD model begins by analyzing the C4-A1 channel of the EEG signal and uses discrete wavelet transform (DWT) with a Daubechies-8 wavelet (db8) to decompose it into subbands. Statistical features (Sfs) are then extracted from these subbands to create a dataset for further analysis. Furthermore, the dataset undergoes preprocessing with a Gaussian filter for feature smoothing and isolation forest (IF) for anomaly detection, leading to enhanced data quality. Subsequently, the artificial bee colony (ABC) feature selection algorithm is applied to eliminate irrelevant features. The final stage of the IESOSAD model involves classification using an Extremely Randomized Trees classifier. The IESOSAD model's performance is rigorously evaluated under holdout, tenfold, and fivefold cross-validation (CV) using a comprehensive set of metrics, including precision, recall, accuracy, F1-score, and ROC AUC curve. The results demonstrate that IESOSAD achieves the highest accuracy of 88.12%, surpassing other state-of-the-art machine and ensemble learning algorithms. Moreover, IESOSAD has outperformed benchmark OSA detection models by a significant margin, facilitating a more streamlined and reliable OSA detection system.

关键词： Brain modeling Feature extraction Electroencephalography Sleep apnea Accuracy Support vector machines Electrocardiography Discrete wavelet transforms Data models classification algorithms Artificial bee colony (ABC) discrete wavelet transform (DWT) electroencephalography (EEG) Gaussian filter isolation forest (IF) obstructive sleep apnea (OSA)

来源：评论

学校读者我要写书评

暂无评论

Optimization of Financial Asset Allocation and Risk Management Strategies Combining Internet of Things and Clustering algorithms

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第4期12卷 3654-3669页

作者： Lyu, Sijun Jiao, Zhi St Marys Univ Econ Dept Halifax NS B3H 3C3 Canada Univ Sydney Econ Sydney NSW 2008 Australia Hubei Hongtai Grp Fac Dept Financial Dev Wuhan 430071 Hubei Peoples R China

This study proposes a new method for optimizing household financial asset allocation (FAA) and developing scientific risk control strategies by integrating Internet of Things (IoT) data and clustering algorithms. IoT technology is utilized to collect real-time data, including macroeconomic indicators, market dynamics, and investor behavior. The data comes from national statistical offices, financial market trading platforms, and social media. The optimized K-means++ clustering algorithm is used for asset classification. Moreover, its performance is evaluated through indexes, such as the silhouette coefficient, adjusted rand index (ARI), Davies-Bouldin index (DBI), and mutual information (MI). The results show that the K-means++ algorithm outperforms these indexes, especially in terms of silhouette coefficient (0.62), ARI (0.75), and MI (0.80). In terms of asset allocation optimization, the proportion of stock products and wealth management products has increased to 4.94% and 12.34%, indicating an improvement in asset diversification and risk diversification. Risk assessment reveals that Internet financial behavior and economic development level have a marked impact on asset allocation. For example, the asset allocation of households with active Internet financial behavior is more diversified. The cash deposit ratio in the eastern region is 79.32%, lower than the 86.08% in the western region. This study provides effective methods for managing household financial assets, which can help improve household wealth management, enhance risk management capabilities, and promote the development of financial technology.

关键词： Resource management Clustering algorithms Internet of Things Risk management Real-time systems classification algorithms Heuristic algorithms Investment Accuracy Optimization Asset optimization clustering algorithms financial asset allocation (FAA) Internet of Things (IoT) data risk management

来源：评论

学校读者我要写书评

暂无评论

Learning the Optimal Discriminant SVM With Feature Extraction

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第4期47卷 2897-2911页

作者： Zhang, Junhong Lai, Zhihui Kong, Heng Yang, Jian Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China BaoAn Cent Hosp Shenzhen Dept Breast & Thyroid Surg Shenzhen 518100 Peoples R China Nanjing Univ Sci & Technol Key Lab Intelligent Percept & Syst High Dimens Inf Minist Educ Nanjing 210094 Peoples R China

Subspace learning and Support Vector Machine (SVM) are two critical techniques in pattern recognition, playing pivotal roles in feature extraction and classification. However, how to learn the optimal subspace such that the SVM classifier can perform the best is still a challenging problem due to the difficulty in optimization, computation, and algorithm convergence. To address these problems, this paper develops a novel method named Optimal Discriminant Support Vector Machine (ODSVM), which integrates support vector classification with discriminative subspace learning in a seamless framework. As a result, the most discriminative subspace and the corresponding optimal SVM are obtained simultaneously to pursue the best classification performance. The efficient optimization framework is designed for binary and multi-class ODSVM. Moreover, a fast sequential minimization optimization (SMO) algorithm with pruning is proposed to accelerate the computation in multi-class ODSVM. Unlike other related methods, ODSVM has a strong theoretical guarantee of global convergence, highlighting its superiority and stability. Numerical experiments are conducted on thirteen datasets and the results demonstrate that ODSVM outperforms existing methods with statistical significance.

关键词： Support vector machines Feature extraction Optimization classification algorithms Convergence Vectors Principal component analysis Minimization Representation learning Training Support vector machine subspace learning joint learning framework

来源：评论

学校读者我要写书评

暂无评论

FSRS: A Frequency Space Random Search Approach for Efficient Opaque-Box Adversarial Attacks

引用

IEEE TRANSACTIONS ON RELIABILITY 2025年

作者： Tsai, Min Han Huang, Qi Xian Sun, Hung Min Natl Tsing Hua Univ Inst Informat Syst & Applicat Hsinchu 300044 Taiwan Natl Tsing Hua Univ Dept Comp Sci Hsinchu 300044 Taiwan

The imperative of ensuring machine learning safety has escalated concomitantly with its pervasive deployment. Among the myriad of potential threats, adversarial examples represent a particularly insidious form of attack, wherein malefactors introduce meticulously engineered perturbations to a model's input, thereby skewing its output. Recent developments have underscored the feasibility of such attacks even in the absence of intimate knowledge regarding the model's architecture, leveraging the model's output to iteratively refine these perturbations. Notwithstanding, the opacity inherent in opaque-box models-characterized by the unavailability of gradient information-necessitates a prodigious number of queries to mount a successful attack, thereby diminishing their efficacy. In response to these challenges, this study introduces the frequency space random search (FSRS) attack methodology. Distinct from conventional opaque-box strategies that operate within the spatial domain, the FSRS method innovatively manipulates the low-frequency domain, thereby curtailing the requisite search space. Furthermore, it harnesses the inherent efficiencies of random search algorithms to minimize the query footprint. Empirical validation of our approach reveals its superior performance in terms of query efficiency and success rate, all the while ensuring minimal perceptual distortion when benchmarked against contemporary opaque-box adversarial techniques.

关键词： Perturbation methods Frequency-domain analysis Discrete wavelet transforms Optimization Signal processing algorithms classification algorithms Sun Safety Computational modeling Machine learning algorithms Adversarial attacks deep learning discrete wavelet transform (DWT) random search

来源：评论

学校读者我要写书评

暂无评论

Learning From Crowds by Class-Specific Instance Weighting

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年

作者： Ji, Qiang Jiang, Liangxiao Zhang, Wenjun Li, Chaoqun China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China China Univ Geosci Sch Math & Phys Wuhan 430074 Peoples R China

In crowdsourcing scenarios, we can acquire each instance's multiple noisy label set from crowd workers and then infer its integrated label via label integration. To further enhance the quality of integrated labels, some noise correction algorithms have been proposed in recent years. Most of them aim to partition the dataset into a clean set and a noise set, followed by training one or multiple classifiers on the clean set to rectify the instances in the noise set. However, they overlook the fact that the class distribution of the clean set is often inconsistent with that of the noise set, resulting in the subpar correction performance of trained classifiers. To mitigate this inconsistency, this paper proposes a class-specific instance weighting-based noise correction (CIWNC) algorithm. In CIWNC, each class's weight is computed based on the class distribution of the clean set firstly. Subsequently, a class-specific weight is computed for each instance using the weight of the class that its integrated label belongs to, as well as its multiple noisy label set. Finally, a classifier is trained on the instance weighted clean set to rectify the instances in the noise set. Experimental results on 34 simulated and two real-world datasets demonstrate that CIWNC outperforms existing state-of-the-art noise correction algorithms significantly.

关键词： Noise classification algorithms Noise measurement Crowdsourcing Prediction algorithms Clustering algorithms Supervised learning Training Inference algorithms Partitioning algorithms Crowdsourcing learning noise correction instance weighting class-specific instance weighting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：