检索结果-内蒙古大学图书馆

Swin Transformer and Momentum Contrast (MoCo) in Leukemia Diagnostics: A New Paradigm in AI-Driven Blood Cell Cancer Classification

引用

IEEE Access 2025年 13卷 82441-82466页

作者： Jain, Eshika Kaushik, Pratham Kukreja, Vinay Ati, Modafar Hariharan, Shanmugasundaram Ahuja, Vandana Bhattacherjee, Abhishek Kumar Kaushal, Rajesh Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Punjab Rajpura140401 India Abu Dhabi University Computer Science and Information Technology College of Engineering Abu Dhabi United Arab Emirates Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Telangana Hyderabad501218 India Swami Vivekanand Institute of Engineering and Technology Department of Computer Science and Engineering Punjab Banur140601 India Lovely Professional University Department of Computer Science Engineering Punjab Phagwara144411 India Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Applications Punjab Rajpura140401 India

Acute Lymphoblastic Leukemia (ALL) is a fast-growing blood cancer that requires prompt diagnosis for effective treatment. Automated image diagnostics offer potential solutions but often lack clinical robustness. Despite their widespread use in medical imaging, Convolutional Neural Networks (CNNs) struggle to differentiate morphologically similar ALL subtypes due to limited context and feature discrimination. Moreover, integrating contrastive self-supervised learning with hierarchical attention-based models remains underexplored in hematologic malignancy classification. This study aims to develop a robust, automated classification model for ALL subtypes using peripheral blood smear images, employing advanced feature extraction through the Swin Transformer framework, combined with Momentum Contrast (MoCo) for contrastive learning and a Bidirectional Encoder Transformer for classification. The Swin Transformer’s patch-based embedding and multi-level attention enhance feature discrimination across ALL subtypes, while MoCo generates distinct embeddings, minimizing overlap between cell types. BiET is employed to classify the refined feature vectors, leveraging self-attention mechanisms to improve classification accuracy. The model achieved an overall classification accuracy of 92.5%, with the precision of 90.3%, a recall of 91.1%, and an F1-score of 90.7% across four classes (Benign, Malignant Early Pre-B, Malignant Pre-B, and Malignant Pro-B). Class-specific performance metrics indicate that Malignant Pre-B achieved the highest F1-score of 92.4%. The MoCo framework reduced contrastive loss from 0.5 to 0.097 for benign cells, enhancing feature discrimination. An ablation study revealed that omitting the dynamic queue decreased accuracy by 5%, underscoring its importance for effective feature learning. This approach can be extended to other hematologic malignancies, with potential for further improvement using larger datasets and real-time diagnostic workflows to support p

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A New Approach to Determine Feasible Operating Region of Unbalanced Distribution Networks with Distributed Photovoltaics

引用

IEEE Transactions on Power Delivery 2025年第3期40卷 1493-1504页

作者： Prasad, Manorath Rather, Zakir Hussain Razzaghi, Reza Doolla, Suryanarayana Indian Institute of Technology Bombay Department of Energy Science and Engineering Mumbai India Monash University Department of Electrical and Computer Systems Engineering Melbourne Australia

Amidst rising distributed generation and its potential role in grid management, this article presents a new realistic approach to determine the operational space and flexibility potential of an unbalanced active distribution network. The feasible operating region of an active distribution network is constituted by its range of active-reactive power exchanges with the bulk power system without breaching network constraints. This study explores the potential of highly penetrated single- and three-phase distributed photovoltaics and voltage-sensitive loads to determine the feasible operating region at different operating points. The cumulative response of Volt-Var controlled distributed photovoltaics and voltage-sensitive loads determines the power flow at the bulk power system-active distribution network interconnection, ensuring feasibility with respect to voltage magnitude and unbalance constraints. Further, the correspondence of feasible operating region with the tap-settings of substation transformer enables a novel feature to traverse throughout the available operating region and facilitate bulk power system-active distribution network power coordination. Additionally, a nodal sensitivity-based adjustable Volt-Var control scheme is proposed for distributed photovoltaics, improving the feasible operating region. The proposed strategy is validated on bulk power systemactive distribution network integrated test system. Bulk power system: IEEE-9 bus system-Active distribution network: (highly unbalanced IEEE-13 bus distribution system (medium voltage) + modified CIGRE low voltage system). © 1986-2012 IEEE.

关键词： Power distribution networks

来源：评论

学校读者我要写书评

暂无评论

Unlocking Eye Gestures with Earable Inertial Sensing for Accessible HCI 17

Unlocking Eye Gestures with Earable Inertial Sensing for Acc...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Chugh, Garvit Chakraborty, Suchetana Chakraborty, Sandip Indian Institute of Technology Department of Computer Science and Engineering Jodhpur India Indian Institute of Technology Department of Computer Science and Engineering Kharagpur India

ISBN: (纸本)9798331531195

Eye gestures are widely used in many applications, including device control, biometrics, visual analytics, and health-care, like Alzheimer's, accessibility, etc. The conventional method for eye gesture detection needs visual information processing devices or smart glasses to capture the movement patterns of the eyeballs. In this paper, we present a novel framework that utilizes inertial measurement unit (IMU) sensors embedded in earable devices for real-time eye gesture detection, which can work as a complementary to visual information processing devices. The framework translates specific eye movements into actionable commands, enabling hands-free interaction for users with limited mobility. Through extensive experimentation with 14 participants across diverse activities such as sitting, walking, running, and driving, the framework demonstrated high accuracy in eye gesture recognition, achieving a macro F1 score of 0.85 on our self-collected dataset. © 2025 IEEE.

关键词： Eye movements

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

Real-Time Elderly Fall Detection as Ambient Intelligence in Old Age Homes 3

Real-Time Elderly Fall Detection as Ambient Intelligence in ...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Shabadi, Laxmi Chaitra, M. Monik, L. Pavan, S.G. Deekshith, R.K. Narayan, Laxmi Sjb Institute of Technology Department of Computer Science and Engineering Bangalore India Bnm Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331515911

The rapid expansion of autonomous technologies, the rise of computer vision, and edge computing present exciting opportunities in healthcare monitoring systems. Fall prevention is especially important for the elderly because falls from this age group often result in fatalities and serious injuries. Fall detection devices that can quickly recognize falls and alert emergency services have become more and more popular as a result. The primary goal of the project is to increase elderly home safety by implementing an ambient intelligence-based automated emergency recognition system. We present a unique method for fall posture detection utilizing an intelligence surveillance camera and a class of efficient models called MobileNets for mobile and embedded vision applications. A real-time embedded solution persuaded from 'edge AI' is implemented using the state-of-the-art Object detection: single shot detector (SSD) Mobile Net V2 and Internet of things embedded GPU platform NVIDIA's Jetson Nano. © 2025 IEEE.

关键词： Ambient intelligence

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern

引用

Neural Computing and Applications 2025年第1期37卷 263-281页

作者： Sekhar, J.C. Josephson, P. Joel Chinnasamy, A. Maheswari, M. Sankar, S. Kalangi, Ruth Ramya Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Electronics and Communication Engineering Malla Reddy Engineering College Telangana Hyderabad India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vijayawada India

Researchers have recently created several deep learning strategies for various tasks, and facial recognition has made remarkable progress in employing these techniques. Face recognition is a noncontact, nonobligatory, acceptable, and harmonious biometric recognition method with a promising national and social security future. The purpose of this paper is to improve the existing face recognition algorithm, investigate extensive data-driven face recognition methods, and propose a unique automated face recognition methodology based on generative adversarial networks (GANs) and the center symmetric multivariable local binary pattern (CS-MLBP). To begin, this paper employs the center symmetric multivariant local binary pattern (CS-MLBP) algorithm to extract the texture features of the face, addressing the issue that C2DPCA (column-based two-dimensional principle component analysis) does an excellent job of removing the global characteristics of the face but struggles to process the local features of the face under large samples. The extracted texture features are combined with the international features retrieved using C2DPCA to generate a multifeatured face. The proposed method, GAN-CS-MLBP, syndicates the power of GAN with the robustness of CS-MLBP, resulting in an accurate and efficient face recognition system. Deep learning algorithms, mainly neural networks, automatically extract discriminative properties from facial images. The learned features capture low-level information and high-level meanings, permitting the model to distinguish among dissimilar persons more successfully. To assess the proposed technique’s GAN-CS-MLBP performance, extensive experiments are performed on benchmark face recognition datasets such as LFW, YTF, and CASIA-WebFace. Giving to the findings, our method exceeds state-of-the-art facial recognition systems in terms of recognition accuracy and resilience. The proposed automatic face recognition system GAN-CS-MLBP provides a solid basis for a

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

DELTa: Dynamic Energy-and-Latency-aware Task scheduling for Fog-Cloud Paradigm

引用

IEEE Access 2025年 13卷 74617-74633页

作者： Mahapatra, Abhijeet Pradhan, Rosy Majhi, Santosh K. Mishra, Kaushik Department of Computer Science & Engineering Odisha Burla768018 India Sikkim Manipal University Sikkim Manipal Institute of Technology Department of Artificial Intelligence and Data Science Sikkim India Department of Electrical Engineering Odisha Burla768018 India Department of Computer Science and Information Technology Chhattisgarh Bilaspur495009 India Manipal Academy of Higher Education Manipal Institute of Technology Bengaluru Department of Computer Science and Engineering Manipal India

The rapid proliferation of IoT devices like smartphones, smartwatches, etc. has significantly elevated the quantity of data requiring execution. It poses challenges for centralized Cloud computing servers, such as latency overhead and increased consumption of energy. To address this, Fog computing has been incorporated in this research as a complementary paradigm to the Cloud-based computing model. It thereby reduces the huge distance between end-user IoT gadgets and the Cloud computing servers. In order to improve the latency and waiting time this research employs a Multi-Level Queue (MLQ) for classifying tasks based on their priority. For parallel processing, a Self-adaptive Fuzzy C-means++ (SaFCm++) approach has been applied to cluster the Fog computing nodes depending on the heterogeneity of the computational nodes. For efficient scheduling, a Dynamic Energy-and-Latency-aware Task scheduling (DELTa) approach has been proposed to optimize latency, makespan, and utilization of resources. Extensive simulations are carried out for different test cases considering task and machine heterogeneity, followed by a statistical analysis. The overall improvements of the proposed method over other baselines are 9.75% for makespan, 64.59% for service latency, 13.90% for resource utilization, and 12.75% for energy consumption. The proposed energy-efficient scheduling method effectively manages diverse tasks and resources, enhancing task processing efficiency while minimizing energy consumption and maximizing resource utilization. Furthermore, the value of the Friedman statistics FF for the proposed model is estimated at 5.44, which shows superiority over the crucial value for four methodologies and four evaluation matrices. © 2013 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Function Scheduling with Data Security in Serverless Computing Systems 17

Function Scheduling with Data Security in Serverless Computi...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Saha, Srestha Pandey, Arvind Addya, Sourav Kanti Brata Nath, Shubha Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India National Institute of Technology Karnataka Department of Computer Science and Engineering Surathkal India

ISBN: (纸本)9798331531195

In serverless computing, the service provider takes full responsibility for function management. However, serverless computing has many challenges regarding data security and function scheduling. To address these challenges, we have proposed a system to secure the data of an end-user. We also aim to meet the quality of service (QoS) for the end-user requests. This work presents a Simulated Annealing-based optimization algorithm for function placement. Also, we have Hyperledger Fabric, a blockchain framework in the system architecture for securing the data of an end-user. We have conducted experiments in Amazon Elastic Compute Cloud (EC2) taking virtual machine instances. The experiments in Amazon EC2 indicate that the proposed system secures the data and enhances the end-user's QoS. © 2025 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Innovative Video Classification Method based on Deep Learning Approach

引用

Recent Patents on engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham science Publishers.

关键词： Convolutional neural networks

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：