检索结果-内蒙古大学图书馆

A Multibranch LSTM-Attention Ensemble classification Network for Sensor Drift Compensation

IEEE SENSORS JOURNAL 2024年第16期24卷 25830-25841页

作者： Liang, Zhifang Chen, Dongming Yang, Liu Chen, Yilin Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China

Sensor drift has been one of the challenging problems in the development of electronic noses (E-noses), which can seriously affect the recognition accuracy of the sensor. In this article, a multibranch long short-term memory-attention ensemble classification network (MLAEC-Net) is proposed to address this problem. The framework simulates the working principle of the animal olfactory system and uses a multibranch structure to allow each branch to capture different features and attributes of the data. It combines the long short-term memory (LSTM) network and the attention mechanism to deal with long-term dependencies and extract key features. Furthermore, the framework improves the generalization ability and prediction accuracy of the overall model through the integration of classifiers. In addition, for E-nose systems with different numbers of sensors, it is only necessary to simply adjust the number of branches, providing excellent flexibility and generalizability to adapt to different sensor arrays and datasets. We validate the effectiveness of the MLAEC-Net framework by conducting experiments on two publicly available datasets. The experimental results show that the MLAEC-Net framework proposed in this article achieves significant advantages with better performance and robustness compared with other state-of-the-art approaches.

关键词： Long short term memory Logic gates Sensors Feature extraction Adaptation models Ensemble learning classification algorithms Attention mechanism classifier ensemble drift compensation electronic nose (E-nose)

来源：评论

学校读者我要写书评

暂无评论

QChi: A Faster classification Algorithm Based on Wang-Mendel Algorithm

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2024年第4期32卷 2261-2271页

作者： Jara, Leonardo Gonzalez, Antonio Perez, Raul Univ Granada DaSCI Andalusian Res Inst Dept Comp Sci & Artificial Intelligence Granada 18012 Spain

To address learning problems in which many examples and variables are involved, the use of algorithms that are capable of processing the data using simple and efficient techniques is required. The Wang and Mendel algorithm applied to classification (also known as the Chi algorithm) satisfies these properties in many cases. However, in particularly complex problems, such as those provided by big data, it has become necessary to use architectures for parallel processing, such as MapReduce, whose base algorithm is just this algorithm. The use of these architectures is necessary because the bottleneck of the algorithm is the calculation of the weight of the rules. This calculation requires, for each selected rule, to consider the adaptation of all the examples with this rule. Although this calculation is polynomial-order, in problems with many examples and where many rules are generated, it is very time consuming. In this article, we propose Quick Chi (QChi), a new algorithm based on the Wang-Mendel algorithm that uses, among other changes to make it efficient, a new way of calculating the weights of the rules that is much less computationally expensive. The reduction in learning time is so significant that it allows the algorithm to tackle big data problems without parallel processing structures. In addition to the description of the algorithm, this article checks experimentally on a wide variety of problems, including those that other authors have used as big data problems that this algorithm drastically reduces the learning time while maintaining the classification performance.

关键词： classification algorithms Proposals Complexity theory Big Data Training Inference algorithms Linguistics Big data fast fuzzy inference fuzzy rule-based classification systems fuzzy rule learning Wang-Mendel method

来源：评论

学校读者我要写书评

暂无评论

NeuroSOFM-Classifier: Nanoscale FeFETs Based Low Power Neuromorphic Architecture for classification Using Continuous Real-Time Unsupervised Clustering

引用

IEEE TRANSACTIONS ON NANOTECHNOLOGY 2024年 23卷 124-131页

作者： Barve, Siddharth Jha, Rashmi Univ Cincinnati Elect & Comp Engn Cincinnati OH 45221 USA

Supervised machine learning techniques are becoming subject of significant interest in data analysis. However, the high memory bandwidth requirement of current implementations, scarcity of labeled data, and dynamic environments in many applications prevent implementation of supervised machine learning techniques. In this work, we propose a neuromorphic architecture implementing the self-organizing feature map algorithm using nanoscale ferroelectric field-effect transistors (FeFETs) and complementary metal-oxide-semiconductor (CMOS) technology to produce a semi-supervised NeuroSOFM-Classifier. A best matching input (BMI) identifier circuit allows for very few labeled samples to be used to provide supervised class labels for each hardware neuron in the NeuroSOFM-Classifier. The NeuroSOFM-Classifier architecture can then be used to inference or classify the new data in real-time. This NeuroSOFM-Classifier, trained on just 2% of the labeled data, is capable of classifying COVID-19 patient chest x-rays with an average accuracy of 83%.

关键词： FeFETs Neurons Neuromorphics Logic gates Field effect transistors classification algorithms Topology Neural network hardware ferroelectric devices unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

CRE-TSCAE: A Novel classification Model Based on Stacked Convolutional Autoencoder for Dual-Target RSVP-BCI Tasks

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2024年第7期71卷 2080-2094页

作者： Chen, Hongying Wang, Dan Xu, Meng Chen, Yuanfang Beijing Univ Technol Beijing Peoples R China Beijing Univ Technol Beijing 100022 Peoples R China Beijing Machine & Equipment Inst Beijing 100854 Peoples R China

Objective: The Rapid Serial Visual Presentation (RSVP) paradigm facilitates target identification in a rapid picture stream, which is applied extensively in military target surveillance and police monitoring. Most researchers concentrate on the single target RSVP-BCI whereas the study of dual-target is scarcely conducted, limiting RSVP application considerably. Methods: This paper proposed a novel classification model named Common Representation Extraction-Targeted Stacked Convolutional Autoencoder (CRE-TSCAE) to detect two targets with one nontarget in RSVP tasks. CRE generated a common representation for each target class to reduce variability from different trials of the same class and distinguish the difference between two targets better. TSCAE aimed to control uncertainty in the training process while requiring less target training data. The model learned a compact and discriminative feature through the training from several learning tasks so as to distinguish each class effectively. Results: It was validated on the World Robot Contest 2021 and 2022 ERP datasets. Experimental results showed that CRE-TSCAE outperformed the state-of-the-art RSVP decoding algorithms and the Average ACC was 71.25%, improving 6.5% at least over the rest. Conclusion: It demonstrated that CRE-TSCAE showed a strong ability to extract discriminative latent features in detecting the differences among two targets with nontarget, which guaranteed increased classification accuracy. Significance: CRE-TSCAE provided an innovative and effective classification model for dual-target RSVP-BCI tasks and some insights into the neurophysiological distinction between different targets.

关键词： Feature extraction Task analysis Brain modeling classification algorithms Electroencephalography Convolution Training Autoencoder classification Rapid Serial Visual Presentation (RSVP) feature extraction

来源：评论

学校读者我要写书评

暂无评论

Automatic Estuarine Fish Species classification System Based on Deep Learning Techniques

引用

IEEE ACCESS 2024年 12卷 140412-140438页

作者： Tejaswini, H. Manohara Pai, M. M. Pai, Radhika M. Manipal Acad Higher Educ Manipal Inst Technol Dept Informat & Commun Technol Manipal 576104 Karnataka India Manipal Acad Higher Educ Manipal Inst Technol Dept Data Sci & Comp Applicat Manipal 576104 Karnataka India

Fish classification (FC) is crucial in various domains, including fishery management and ecological research. Traditional FC methods rely mainly on morphological criteria such as body shape and patterns. Although these methods are useful, they require expert knowledge and are prone to subjective interpretation. Recent advances in technology and the availability of datasets have allowed deep learning (DL) techniques to be used in fish species classification. These methods automatically extract relevant features from fish images and categorize them into species groupings. Traditional DL models, however, have difficulties capturing long-range dependencies and require fixed input sizes, making them less adaptive when working with images with varying proportions. The Vision Transformer (ViT) addresses these constraints by utilizing the transformer model's self-attention mechanisms. So, in this study, a ViT is used to solve the FC problem. The performance of ViT is assessed against pre-trained models, VGG16, VGG19, DenseNet121, ResNet50v2, InceptionV3, InceptionResNetV2, and Xception. The experiments make use of a curated Estuarine Fish species dataset (EFD). In this study, ViT outperformed state-of-the-art literature by achieving 99.04% and 100% accuracy without and with augmentation, respectively. The presented research is tailored to the task of recognizing estuarine fish species that are useful in the aquaculture domain. Additionally, our research aligns with the objectives of Sustainable Development Goals (SDGs) 2 and 14. This emphasises the broader societal and environmental implications of our work, emphasizing its potential to positively impact food security and aquaculture ecosystem sustainability.

关键词： Fish Biological system modeling Accuracy Aquaculture Production Feature extraction Deep learning classification algorithms Ecology Visualization deep learning estuarine fish dataset fish classification vision transformers

来源：评论

学校读者我要写书评

暂无评论

Improving Safety for Disabled and Elderly Individuals: A Multimodal classification Approach Based on Support Vector Machine for Alert Systems Within Smart Homes

引用

IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE 2024年第9期27卷 54-62页

作者： Parsafar, Parsa Baban, Payam Qaderi Nasiri, Adel Univ Mazandaran Comp Engn Babolsar Iran Sahand Univ Technol Tabriz Power Syst Engn Tabriz Iran Islamic Azad Univ Qazvin Branch Fac Elect Biomed & Mechatron Engn Tehran Iran Pooya Co Tehran Iran Babol Noshirvani Univ Technol Dept Elect & Comp Engn Babol Iran

This article investigates the detection of disabled and elderly individuals' activity within smart homes by monitoring residents' behavior in the home environment. The ultimate objective is to construct a comprehensive behavioral model by leveraging data stored in the building management system's database, frequently gathered through the sensors outlined in the paper. This model will be employed for an alarm and notification system, fulfilling the safety of the residents. More precisely, our advanced intelligent system is adept at discerning the specific activities of a resident among seven distinct conditions. These conditions encompass a range of daily actions, including toilet or bathroom use, eating, resting, sleeping, communication, dressing and danger. For instance, the proposal is exploited to track sleeping habits, which provide an expressive, yet indirect, health-related indicator. The system achieves this by analyzing temporal data gathered from both the resident's body and various sensors strategically placed throughout the home and the pre-established behavioral model. The discussion revolves around employing well-suited sensors on the residents' bodies to monitor the vital signs, accurate data processing techniques within the proposed system implemented in the building, and also an efficient and accurate behavior classification. Extensive research was conducted in three distinct stages. The paper focuses on the selection of sensors and processing techniques, with a particular emphasis on the activities performed by disabled and elderly individuals in smart homes. The collected data was classified and processed utilizing Support Vector Machine (SVM) algorithms. Lastly, the optimal kernel and SVM training rule were determined through the implementation of the Particle Swarm Optimization (PSO) algorithm, resulting in the formation of the final pattern for storage in the building management system's database.

关键词： Support vector machines Training Accuracy Smart homes Sensor systems classification algorithms Safety Older adults Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

A Flat-Hierarchical Approach Based on Machine Learning Model for e-Commerce Product classification

引用

IEEE ACCESS 2024年 12卷 72730-72745页

作者： Cotacallapa, Harold Saboya, Nemias Canas Rodrigues, Paulo Salas, Rodrigo Linkolk Lopez-Gonzales, Javier Univ Peruana Union Fac Ingn & Arquitectura Lima 15464 Peru Univ Fed Bahia Dept Stat BR-40110909 Salvador Brazil Univ Valparaiso Escuela Ingn C Biomed Valparaiso 2362905 Chile Millennium Inst Intelligent Healthcare Engn iHealt Santiago 7820436 Chile Univ Peruana Union Escuela Posgrad Lima 15464 Peru

Within the e-commerce sphere, optimizing the product classification process assumes pivotal importance, owing to its direct influence on operational efficiency and profitability. In this context, employing machine learning algorithms stands out as a premier solution for effectively automating this process. The design of these models commonly adopts either a flat or local (hierarchical) approach. However, each of them exhibits significant limitations. The regional approach introduces taxonomic inconsistencies in predictions, whereas the flat approach becomes inefficient when dealing with extensive datasets featuring high granularity. Therefore, our research introduces a solution for hierarchical product classification based on a Machine Learning model that integrates flat and local (hierarchical) classification approaches using a 4-level electronic product dataset obtained from a renowned e-commerce platform in Latin America. In pursuit of this goal, a comparative analysis of seven machine learning algorithms, including Multinomial Naive Bayes, Linear Support Vector Classifier, Multinomial Logistic Regression, Random Forest, XGBoost, FastText, and Voting Ensemble, was conducted. This hybrid approach model performs better than models using a single approach. It surpassed the top-performing flat approach model by 0.15% and outperformed the leading local approach (Local Classifier per Level) model by 4.88%, as measured by the weighted F1-score. Additionally, this paper contributes to the academic community by presenting a significant Spanish-language dataset comprising over one million products and discussing the preprocessing techniques tailored for the dataset. It also addresses the study's inherent limitations and potential avenues for future exploration in this field.

关键词： Electronic commerce classification algorithms Machine learning algorithms Bayes methods Support vector machines Random forests Performance evaluation Data models South America Logistic regression Inventory management Product delivery Machine learning e-commerce hierarchical product classification local classifier per level ensemble

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Melanocytic Nevi classification Algorithm by Leveraging Physiologic-Inspired Knowledge and Channel Encoded Information

引用

IEEE ACCESS 2024年 12卷 113072-113086页

作者： Sun, Qilin Tang, Yaoqi Wang, Siqi Chen, Jun Xu, Hui Ling, Yuye Shanghai Jiao Tong Univ Shanghai Peoples Hosp 9 Sch Med Dept Dermatol Shanghai 200011 Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China

Melanocytic nevi (MN), which are the most prevalent benign skin tumors, can be classified into three subtypes based on the depth of the nevus cell nests: junctional, compound, and intradermal nevi. Among these subtypes, intradermal nevi pose a lower risk of malignancy, whereas junctional nevi carry a higher risk of malignancy. To facilitate early stage diagnosis, mitigate unnecessary biopsies, and reduce medical costs, this paper presents the first study on the classification of benign melanocytic nevi. We propose an algorithm that utilizes depth-relevant, channel-specific, and channel-shared information from dermoscopy images. This approach draws inspiration from the physical principles underlying dermoscopy imaging and the physiological essence of nevi. We employed CNN and transformer blocks to capture local and long-range contextual information. In addition, our physiology-inspired module focuses on learning depth-related features from the color channels. To assess the performance of our proposed method, we curated a dataset of dermoscopic images of MN and compared it with two human experts as well as classic CNN and Transformer baseline models. Our results showed that the proposed automated method achieved an average accuracy of 70.23%, surpassing the best-performing baseline by 3.6%, and outperforming human experts by nearly 20%. Furthermore, we conducted an ablation study to confirm the effectiveness of our algorithm and to analyze its clinical significance.

关键词： Lesions Skin Feature extraction Transformers Convolutional neural networks classification algorithms Melanoma Deep learning Medical diagnosis Melanocytic nevi dermoscopy classification deep learning assistant diagnostic system

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based classification and Detection of the Smart Home Automation Rules Conflicts

引用

IEEE ACCESS 2024年 12卷 85072-85088页

作者： Ansari, Adeeb Mansoor Nazir, Mohammed Mustafa, Khurram Jamia Millia Islamia Dept Comp Sci New Delhi India

Smart homes are the most adaptable and utilized application of the IoT. Smart homes enable end users to define and control the automation remotely by defining automation rules. The automation rules interaction results in the defined tasks and activities but also delivers unwanted interactions, which show adverse effects. Their interactions may consist of chained and covert rules interaction, which are hard to trace and identify. Attackers' malicious apps installed in smart homes may leverage rules' adverse effects to compromise smart home security and harm users, such as opening the window at night or when no one is home. To address such issues, we developed an ontology of smart home automation rules to identify such interactions. Prior works failed to provide the complete classification and could not identify all possible rule conflicts. In this work, we proposed the classification of automation rule interactions into five categories and recognized the potential rule conflicts. In addition, the ontology can examine rules interactions against the defined safety policies, providing an extra layer of security. The ontology will aid the designers in better understanding and developing a robust security mechanism at the design phase to resist rules interaction conflicts and their adverse effects. We examine this work on the thirty-five rules formed in the light of prior work test cases and validation. The results show that the proposed work is promising and can efficiently identify all the rule interaction conflicts in the smart home.

关键词： Automation Ontologies Safety Actuators Temperature sensors classification algorithms Smart home ontology automation rules rule conflict conflict classification security

来源：评论

学校读者我要写书评

暂无评论

EnsCL-CatBoost: A Strategic Framework for Software Requirements classification

引用

IEEE ACCESS 2024年 12卷 127614-127628页

作者： Abbas, Jalil Zhang, Cheng Luo, Bin Anhui Univ Sch Comp Sci & Technol Hefei 230039 Anhui Peoples R China

Accurate classification of software requirements, distinguishing between functional and non-functional aspects, is crucial for developing reliable and efficient software systems. However, existing methods often struggle with insufficient semantic understanding and managing diverse software requirements. In this study, we introduce an innovative framework named EnsCL-CatBoost (Ensembled Contrastive Learning with CatBoost) to address these challenges by enhancing classification accuracy and robustness. Our method uses a weighted ensemble of Doc2Vec, Word2Vec, and FastText, leveraging their strengths for richer semantic representation. Unlike conventional strategies, we incorporate contrastive learning with the InfoNCE loss function, boosting discriminative power by clustering similar samples and distancing dissimilar ones, thus enhancing robustness and model generalization. To tackle class imbalance, we integrate SMOTE-Tomek links into the embedding process, achieving balanced class distribution before classification. Additionally, our evaluation extends beyond test datasets to new, unlabeled datasets, demonstrating practical applicability in real-world scenarios. We compare our framework's performance with five machine learning classifiers which we trained using traditional embedding techniques. The results show that our method significantly outperforms others, achieving 94% accuracy. Our research transparently presents tool-based results, highlighting the transformative potential of automation in software requirement classification and setting a new benchmark for practical deployment in diverse environments, paving the way for future research in the field.

关键词： Accuracy Feature extraction classification algorithms Support vector machines Contrastive learning Software algorithms Software performance Machine learning Software requirements classification SMOTE-Tomek EnsCL-CatBoost weighted ensemble machine learning classifiers contrastive learning

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：