检索结果-内蒙古大学图书馆

MSMFT: Multi-Stream Multimodal Factorized Transformer for Human Activity Recognition

IEEE Sensors Journal 2025年第6期25卷 10402-10416页

作者： Zhou, Xianfa Yuan, Jiabin Fan, Lili Niu, Xuewei Zha, Keke Liu, Xu Nanjing University of Aeronautics and Astronautics Department of Computer Science and Technology Nanjing210016 China Jinling Institute of Technology Department of Computer Engineering Nanjing211169 China

Existing video-based human activity recognition (HAR) methods are susceptible to challenges such as lighting variations and occlusions in complex environments. Wearable sensors can effectively mitigate these issues. The fusion of the two can reduce environmental impacts, thus enhancing accuracy. However, the heterogeneity between the two data types presents a challenge for fusion. To address this, we propose an architecture called multi-stream multimodal factorized transformer (MSMFT), which leverages the aggregation capabilities of transformers to achieve alignment and fusion of multimodal features without relying on specific feature extractors. First, we designed a statistical feature projection (SFP) method to effectively tokenize wearable sensor data for transformer models. Second, we introduced temporal embedding (TE) to capture local temporal feature variations. Then, we incorporated a factorized transformer architecture that includes temporal and spatial transformer encoders (STEs) to extract global spatiotemporal features fully. Finally, to avoid the issue of modality entanglement caused by deep fusion, we constructed a multi-stream architecture comprising a video stream, wearable sensors stream, and fusion stream. This design allows for the extraction of both independent and interactive modality features. The performance of the MSMFT method was evaluated on three multimodal datasets: UP-Fall, UTD-MHAD, and MMAct. The results show that MSMFT performs better than the state-of-the-art, with a 16.83% improvement in cross-scene F1-score on the MMAct dataset. © 2001-2012 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

CNN-HOG based hybrid feature mining for classification of coffee bean varieties using image processing

引用

Multimedia Tools and Applications 2025年第2期84卷 749-764页

作者： Molla, Yirga Kene Mitiku, Emebet Abeje Department of Computer Science Gafat Institute of Technology Debre Tabor University Debre Tabor Ethiopia Department of Computer Science Faculty of Natural and Computational Science Debark University Debark Ethiopia

Ethiopia, known as the birthplace of coffee, relies on coffee exports as a major source of foreign currency. This research paper focuses on developing a hybrid feature mining technique to automatically classify Ethiopian coffee beans based on their provenance: Harrar, Jimma, Limu, Sidama, and Wellega, which correspond to their botanical origins. A dataset of coffee bean images is collected from various regions through the Ethiopian Commodity Exchange (ECX) in Addis Ababa. The proposed system incorporates preprocessing phases including image resizing, filtering, contrast enhancement, noise removal, grayscale conversion, and segmentation using a combined thresholding and K-means approach for grayscale and RGB images, respectively. Classification is performed using a radial basis function (RBF) kernel function of support vector machine (SVM). To address the color-feature similarity challenge, the study explores merging color and texture features using the histogram of oriented gradients (HOG) local feature descriptor. Performance evaluation is conducted for HOG feature extraction, CNN feature extraction, and a hybrid feature vector (HOG-CNN) using a multi-class SVM classifier, achieving accuracies of 74.17%, 85.83%, and 97.5%, respectively. The deep-shallow-based feature (CNN-HOG) combination demonstrates the highest accuracy of 97.5% in this study. The findings highlight the effectiveness of the proposed hybrid feature mining approach in automatically classifying Ethiopian coffee bean varieties, with potential applications in quality control and traceability within the coffee industry. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Predicting early ASD traits of adults and toddlers using machine learning and deep learning with explainable AI and optimization

引用

Neural Computing and Applications 2025年 1-28页

作者： Rahman, Md. Ashiqur Hossain, Md. Mamun Singh, Sondip Poul Sharmin, Nusrat Dhaka1216 Bangladesh Department of Computer Science and Engineering Military Institute of Science and Technology Dhaka Bangladesh

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social interaction, communication difficulties, repetitive behaviors, and a range of strengths and differences in cognitive abilities. Early ASD diagnosis using machine learning and deep learning techniques is crucial for preventing its severity and long-term effects. The articles published in this area have only applied different machine learning algorithms, and a notable gap observed is the absence of an in-depth analysis in terms of hyperparameter tuning and the type of dataset used in this context. This study investigated predictive modeling for ASD traits by leveraging two distinct datasets: (i) a raw CSV dataset with tabular data and (ii) an image dataset with facial expression. This study aims to conduct an in-depth analysis of ASD trait prediction in adults and toddlers by doing hyper optimized and interpreting the result through explainable AI. In the CSV dataset, a comprehensive exploration of machine learning and deep learning algorithms, including decision trees, Naive Bayes, random forests, support vector machines (SVM), k-nearest neighbors (KNN), logistic regression, XGBoost, and ANN, was conducted. XGBoost emerged as the most effective machine learning algorithm, achieving an accuracy of 96.13%. The deep learning ANN model outperformed the traditional machine learning algorithms with an accuracy of 99%. Additionally, an ensemble model combining a decision tree, random forest, SVM, KNN, and logistic regression demonstrated superior performance, yielding an accuracy of 96.67%. The XGBoost model, utilized in hyperparameter optimization for CSV data, exhibited a substantial accuracy increase, reaching 98%. For the image dataset, advanced deep learning models, such as ResNet50, VGG16, Boosting, and Bagging, were employed. The bagging model outperformed the others, achieving an impressive accuracy of 99%. Subsequent hyperparameter optimization was conduct

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

A Software Defect Prediction Method Using a Multivariate Heterogeneous Hybrid Deep Learning Algorithm

引用

computers, Materials & Continua 2025年第2期82卷 3251-3279页

作者： Qi Fei Haojun Hu Guisheng Yin Zhian Sun College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China Information Technology Research Department Jiangsu Automation Research InstituteLianyungang222062China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China

Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.

关键词： Software defect prediction multiple heterogeneous data graph convolutional network models based on adjacency and spatial topologies CNN-BiLSTM TabNet

来源：评论

学校读者我要写书评

暂无评论

Stylometry-driven framework for Urdu intrinsic plagiarism detection: a comprehensive analysis using machine learning, deep learning, and large language models

引用

Neural Computing and Applications 2025年第9期37卷 6479-6513页

作者： Manzoor, Muhammad Faraz Farooq, Muhammad Shoaib Abid, Adnan Department of Computer Science University of Management and Technology Lahore Pakistan Department of Data Science Faculty of Computing and Information Technology University of the Punjab Lahore Pakistan

Detecting plagiarism in documents is a well-established task in natural language processing (NLP). Broadly, plagiarism detection is categorized into two types (1) intrinsic: to check the whole document or all the passages have been written by a single author;(2) extrinsic: where a suspicious document is compared with a given set of source documents to figure out sentences or phrases which appear in both documents. In the pursuit of advancing intrinsic plagiarism detection, this study addresses the critical challenge of intrinsic plagiarism detection in Urdu texts, a language with limited resources for comprehensive language models. Acknowledging the absence of sophisticated large language models (LLMs) tailored for Urdu language, this study explores the application of various machine learning, deep learning, and language models in a novel framework. A set of 43 stylometry features at six granularity levels was meticulously curated, capturing linguistic patterns indicative of plagiarism. The selected models include traditional machine learning approaches such as logistic regression, decision trees, SVM, KNN, Naive Bayes, gradient boosting and voting classifier, deep learning approaches: GRU, BiLSTM, CNN, LSTM, MLP, and large language models: BERT and GPT-2. This research systematically categorizes these features and evaluates their effectiveness, addressing the inherent challenges posed by the limited availability of Urdu-specific language models. Two distinct experiments were conducted to evaluate the impact of the proposed features on classification accuracy. In experiment one, the entire dataset was utilized for classification into intrinsic plagiarized and non-plagiarized documents. Experiment two categorized the dataset into three types based on topics: moral lessons, national celebrities, and national events. Both experiments are thoroughly evaluated through, a fivefold cross-validation analysis. The results show that the random forest classifier achieved an ex

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Image Retrieval in Cloud Servers with TN-AGW: A Secure and Efficient Approach

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 459-473页

作者： Ponnuviji, N.P. Nirmala, G. Kokila, M. L. Sworna Priyadharshini, S. Indra Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Thiruvallur India Department of Computer Science and Engineering RMD Engineering College Chennai India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nādu Kattankulathur Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The increasing use of cloud-based image storage and retrieval systems has made ensuring security and efficiency crucial. The security enhancement of image retrieval and image archival in cloud computing has received considerable attention in transmitting data and ensuring data confidentiality among cloud servers and users. Various traditional image retrieval techniques regarding security have developed in recent years but they do not apply to large-scale environments. This paper introduces a new approach called Triple network-based adaptive grey wolf (TN-AGW) to address these challenges. The TN-AGW framework combines the adaptability of the Grey Wolf Optimization (GWO) algorithm with the resilience of Triple Network (TN) to enhance image retrieval in cloud servers while maintaining robust security measures. By using adaptive mechanisms, TN-AGW dynamically adjusts its parameters to improve the efficiency of image retrieval processes, reducing latency and utilization of resources. However, the image retrieval process is efficiently performed by a triple network and the parameters employed in the network are optimized by Adaptive Grey Wolf (AGW) optimization. Imputation of missing values, Min–Max normalization, and Z-score standardization processes are used to preprocess the images. The image extraction process is undertaken by a modified convolutional neural network (MCNN) approach. Moreover, input images are taken from datasets such as the Landsat 8 dataset and the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset is employed for image retrieval. Further, the performance such as accuracy, precision, recall, specificity, F1-score, and false alarm rate (FAR) is evaluated, the value of accuracy reaches 98.1%, the precision of 97.2%, recall of 96.1%, and specificity of 917.2% respectively. Also, the convergence speed is enhanced in this TN-AGW approach. Therefore, the proposed TN-AGW approach achieves greater efficiency in image retrieving than other existing

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing brain tumour classification and detection using CNN 4th

Enhancing brain tumour classification and detection using CN...

引用

4th International Conference on Computational Methods in science and technology, ICCMST 2024

作者： Jaleel, D. Abdul Darshan, D. Sai Kumar, K. V. Dheeraj Faizan, Syed Kumar, T. Hemanth Department of Computer Science and Technology Madanapalle Institute of Technology and Science Andhra Pradesh India Department of Computer Science and Technology Madanapalle Institute of Technology and Science India

ISBN: (纸本)9781032911571

Accurate class and early detection of mind tumour is of maximum significance to facilitate powerful treatment planning to improve affected person consequences. This work offers a novel technique makes use of convolutional neural community (CNNs) for correct and efficient brain tumour characterization and detection. Our approach calls for cautious curation of numerous and appreciably annotated statistics units, ensuring a complete image of tumour kinds and stages The CNN machine is intended for scientific imaging demanding situations, with two convolutional and pooling layers including hierarchically extraction talents it is critical for accurate detection accuracy, to optimize version parameters for high accuracy and hold them in thoughts in tumour class. Through the evaluation metrics of precision, F1 score, consider, and accuracy, ourself determine the general performance of the model on an independent dataset, highlighting its ability to generalize to different information. This evaluation gives a innovative technique to improving mind tumour diagnosis and patient care, laying the basis for adaptation, validation in large contexts, and capacity integration into medical settings. © 2025 the Author(s).

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm-optimized k-nearest Neighbors and Support Vector Machines for Breast Cancer Detection in Resource-constrained Environments

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第3期52卷 848-861页

作者： Alemu, Abebe Girma, Anteneh Abebe, Mesfin Srinivasagan, Ramasamy Adama Science and Technology University Adama Ethiopia Computer Science/Cyber-Security department University of the District of Columbia WashingtonDC United States Computer Science and Engineering department Adama Science and Technology University Adama Ethiopia Computer Engineering department CCSIT King Faisal University Al Hufuf Saudi Arabia

Breast cancer poses a significant global threat, highlighting the urgent need for early detection to reduce mortality rates. Researchers are working to minimize the occurrence of false positives and false negatives, thereby improving the efficiency of breast cancer detection models. To achieve this, they employ advanced techniques such as artificial intelligence, machine learning, deep learning, and computational intelligence. Support vector machines (SVM) and k-nearest neighbors (KNN) are two popular lightweight machine-learning techniques.;however, their effectiveness depends on proper feature selection and parameter tuning. Genetic algorithm optimization provides a solution by intelligently selecting relevant features and fine-tuning parameters, which enhances classification accuracy for early diagnosis. This study demonstrates the effectiveness of a hybrid computational intelligence model that utilizes genetic algorithms for feature selection. The proposed GAKNN-SVM model shows superior performance in detecting breast tumors, utilizing the Wisconsin Breast Cancer Diagnostic Dataset. The results indicate significant improvements, with accuracy, sensitivity, and specificity rates reaching 98.25%, 98.15%, and 98.41%, respectively, based on 171 test samples. Overall, genetic algorithms and machine learning approaches hold great promise for improving breast cancer detection accuracy, ultimately leading to better diagnostic outcomes and reduced mortality rates, especially in resource-constrained environments. © (2025), (International Association of Engineers). All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Exploring image data association: A hybrid mining approach

引用

Multimedia Tools and Applications 2025年第9期84卷 5725-5740页

作者： Parashar, Nishtha Tiwari, Akhilesh Gupta, Rajendra Kumar Department of Computer Science and Engineering Madhav Institute of Technology & Science M.P. Gwalior India Department of Information Technology Madhav Institute of Technology & Science M.P. Gwalior India

In this paper, a new approach for mining image association rules is presented, which involves the fine-tuned CNN model, as well as the proposed FIAR and OFIAR algorithms. Initially, the image transactional database is generated using feature vectors obtained from the fine-tuned CNN architecture. The proposed FIAR algorithm is used to generate hash-indexed image association rules, which are further optimized using the proposed OFIAR algorithm. This methodology combines the strengths of the CNN model to extract histogram features from images, the FIAR algorithm to efficiently mine frequent image itemsets, and the OFIAR algorithm to optimize image association rules. The proposed methodology can be used to discover hidden relationships among images, leading to new insights in image processing and analysis. Efficient results were obtained with a minimum support of 0.50 and a minimum confidence of 0.50. Experiments were performed on the fruits image dataset consisting of 2618 images from six different classes, and the results show that image mining is feasible and can produce strong optimized image association rules that can be further used for classification purposes. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

AfriSign: African sign languages machine translation

引用

Discover Artificial Intelligence 2025年第1期5卷 1-16页

作者： Takyi, Kate Gyening, Rose-Mary Owusuaa Mensah Gueuwou, Shester Msouobu Nyarko, Marco Stanley Adade, Richard Borkor, Reindorf Nartey Boadu-Acheampong, Samuelson Israel Tabari, Linus Department of Computer Science Kwame Nkrumah University of Science and Technology Kumasi Ghana Department of Disability and Rehabilitation Studies Kwame Nkrumah University of Science and Technology Kumasi Ghana Department of Mathematics Kwame Nkrumah University of Science and Technology Kumasi Ghana

Research on sign language translation is ongoing with a high social inclusive goal of crossing the bridge between people with hearing disability using sign language as their basic way to communicate to others who do not understand sign language. Hundreds of different sign languages exist instead of a single universal sign language. Research on translating sign languages from high-income nations has grown significantly, but little is known about translating sign languages from Africa. In this paper, we curate a novel video-to-text African sign languages translation dataset containing sign language videos of Bible verses from six (6) different African countries. We experimented with competitive machine translation and sign language translation techniques on our dataset, including the application of transformers to sign language translation, multilingual training, and cross-transfer learning. We evaluated them in terms of accuracy and precision. The results from our experiments prove that having one Multilingual model for all the languages tends to be a better choice when deployed in real system in terms of memory usage with an accuracy of 94.6% and precision of 97.3%. These results give headway for more multilingual models to be developed to enhance inclusion for the deaf community and bridge the gap between the hearing and the deaf in Africa. © The Author(s) 2025.

关键词： Machine translation

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：