检索结果-内蒙古大学图书馆

Enhancing anemia detection through multimodal data fusion: a non-invasive approach using EHRs and conjunctiva images

引用

Discover Artificial Intelligence 2024年第1期4卷 1-19页

作者： Ramzan, Muhammad Saeed, Muhammad Usman Ali, Ghulam School of Computer Science and Engineering Central South University Hunan Changsha410017 China Department of Computer Science University of Okara Punjab Okara56300 Pakistan

Anemia detection using multimodal approaches leverages the integration of multiple data sources, such as imaging, clinical records, and hematological parameters, to improve diagnostic accuracy. Such methods can capture the complex interplay of factors contributing to anemia, providing a more comprehensive assessment than traditional single-modality techniques. In this research, a novel deep learning multi-modal feature fusion approach is proposed for the automated detection of anemia using EHRs (Electronic Health Records), and Conjunctiva image dataset. First, EHR records are preporcessed by selecting the most appropriate features using Random Forest. The features from the conjunctiva images are extracted using RCBAM (Reverse Convolution Block Attention Mechanism). After that, GRAD-Cam algorithm is applied to calculate the pixel percentages of all the features. The output of Random Forest and GRAD-Cam algorithms is concatenated to form a multimodal fusion. The important information from the concatenated features is selected with the help of a professional healthcare consultant. The different experiments are performed on textual and image datasets individually and after concatenating. The results show that the proposed model outperforms from state-of-the-art methods with an accuracy of 95%. Despite challenges such as class imbalance and computational demands, our findings reveal substantial clinical potential, offering a patient-friendly and accessible diagnostic solution. © The Author(s) 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Hybrid brave-hunting optimisation for heart disease detection model with SVM coupled deep CNN

引用

International Journal of Intelligent Information and Database Systems 2025年第1期17卷 92-123页

作者： Tambe, Pravin M. Shrivastava, Manish Department of Computer Science and Engineering Vivekananda Global University Jagatpura Rajasthan Jaipur303012 India

This research proposes a novel hybrid optimisation method called brave-hunting optimisation (BHO) inspired by lion optimisation (LO) and coyote optimisation (CO). The BHO algorithm is employed to fine-tune the SVM parameters, enhancing its classification performance. Simultaneously, a deep CNN model extracts complex and informative features from medical data. The combined approach capitalises on the strengths of both optimisation techniques to create a robust and accurate model for heart disease diagnosis. The performance evaluation of our model is conducted using comprehensive metrics, which achieve an accuracy of 94.89%, an F1-score of 94.48%, a precision of 94.48%, and a recall of 94.58% for a 90 TP. In the context of a ten k-fold evaluation, achieved 94.78% accuracy, 94.36% F1-score, 94.55% precision, and 94.13% recall. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An effective speaker adaption using deep learning for the identification of speakers in emergency situation

引用

Multimedia Tools and Applications 2025年第16期84卷 16945-16969页

作者： Deka, Aniruddha Kalita, Nijara Department of Computer Science and Engineering Assam down town University Assam Guwahati781026 India

Automated speaker identification is an important research topic in recent advanced technologies. This process helps to analyze the speakers in their emergencies. Various existing approaches are used for speaker identification, and the existing systems cannot distinguish background noises such as music and traffic, which can cause signal distortion. Moreover, the existing speaker identification techniques do not have better learning ability and face high computational complexity. Also, they failed to recognize the speaker’s condition because of the inability to extract suitable keywords and noisy speeches. To overcome this issues, the proposed study introduced a new deep-learning mechanism for effective speaker identification in emergency situations. The input audio files are initially collected, and pre-processing is performed to reduce the noise issue using the original speech separation process. The keywords are spotted using the proposed Mel-Frequency Cepstral Coefficients with Binary Weighted Network (MFCC-BWN) from the pre-processed data. This keyword extraction step helps to improve the recognition accuracy because of the significant attributes. Finally, audio files using Adaptive Improved LSTM (AILSTM) identify the speaker’s situation. The simulation result analysis shows that the proposed model outperforms the other comparable methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Loudspeakers

来源：评论

学校读者我要写书评

暂无评论

Development of a machine learning model for predicting abnormalities of commercial airplanes

引用

Data science and Management 2024年第3期7卷 256-265页

作者： Rossi Passarella Siti Nurmaini Muhammad Naufal Rachmatullah Harumi Veny Fara Nissya Nur Hafidzoh Department of Computer Engineering Faculty of Computer ScienceUniversitas Sriwijaya30662Indonesia Intelligent System Research Group(ISysRG) Faculty of Computer ScienceUniversitas Sriwijaya30662Indonesia Department of Informatics Faculty of Computer ScienceUniversitas Sriwijaya30662Indonesia College of Engineering Studies Universiti Teknologi MARA(UiTM)Shah Alam40450Malaysia

Airplanes are a social necessity for movement of humans,goods,and *** are generally safe modes of transportation;however,incidents and accidents occasionally *** prevent aviation accidents,it is necessary to develop a machine-learning model to detect and predict commercial flights using automatic dependent surveillance–broadcast *** study combined data-quality detection,anomaly detection,and abnormality-classification-model *** research methodology involved the following stages:problem statement,data selection and labeling,prediction-model development,deployment,and *** data labeling process was based on the rules framed by the international civil aviation organization for commercial,jet-engine flights and validated by expert commercial *** results showed that the best prediction model,the quadratic-discriminant-analysis,was 93%accurate,indicating a“good fit”.Moreover,the model’s area-under-the-curve results for abnormal and normal detection were 0.97 and 0.96,respectively,thus confirming its“good fit”.

关键词： Automatic dependent surveillance-broadcast data Commercial airplanes accident Data-labeling Machine learning Prediction model

来源：评论

学校读者我要写书评

暂无评论

DisCovHAR: Contrastive Attention for Human Activity Recognition Under Distribution Shifts

引用

IEEE Internet of Things Journal 2025年第12期12卷 21973-21983页

作者： Chen, Luke Odema, Mohanad Al Faruque, Mohammad Abdullah University of California Department of Electrical Engineering and Computer Science IrvineCA92697 United States

Advances in Internet-of-Things (IoT) wearable sensors and Edge-Artificial Intelligence (Edge-AI) have enabled practical realizations of Machine Learning (ML)-enabled mobile sensing applications like Human Activity Recognition (HAR). The effective deployment of these data-driven models necessitates learning robust representations capable of handling prevalent Distribution Shifts (DS), including new users, device positions, rotations, and more. In that respect, Contrastive Learning (CL) has shown promise in learning transformation-invariant features, outperforming traditional HAR methods. However, recent findings reveal that the contrastive loss induces shrinkage and expansion of the feature space which may limit the generalization capacity of the model. To address this, we propose DisCovHAR, a contrastive attention method to selectively apply the contrastive loss to a subset of the feature space through the transformer encoder attention mechanism. Extensive experiments on three HAR datasets (DSADS, PAMAP2, USCHAD) demonstrate its superiority over state-of-the-art methods. Specifically, our approach yields up to 4.47% and 7.82% average accuracy improvements in subject-wise and position-wise generalization settings. Furthermore, DisCov-HAR demonstrates up to 5.07% increased robustness compared to prior methods under multivariate distribution shift scenarios. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CDS: Coupled Data Storage to Enhance Read Performance of 3D TLC NAND Flash Memory

引用

IEEE Transactions on computers 2024年第3期73卷 694-707页

作者： Wu, Wan-Ling Hsieh, Jen-Wei Ku, Hao-Yu National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106 Taiwan

Due to the strong demand of massive storage capacity, the density of flash memory has been improved in terms of technology node scaling, multi-bit per cell technique, and 3D stacking. However, these techniques also degrade read performance and reliability. The long read latency comes from increased data sensing time and time-consuming ECC decoding time. Storing multiple bits per cell results in more read reference voltages and increased latency of identifying appropriate threshold voltages. To deal with error correction, LDPC is widely used in flash memory to provide stronger ECC capability. However, LDPC incurs a long decoding latency when bit errors are numerous. In this work, we propose coupled data storage (CDS) to improve the read performance of 3D NAND flash-memory storage devices. CDS supports two modes to improve read latency: The high read-speed mode is designed to improve data sensing time with reduced voltage states, while the data correction mode is designed to mitigate bit errors and LDPC overhead. Experiment results showed that CDS could reduce 50∼66.6% read latency and 25.7∼27.5% write latency under the high read-speed mode. For the data correction mode, RBER could be decreased by 37∼52% and the lifetime could be prolonged to 1.6 to 3 times. © 1968-2012 IEEE.

关键词： Threshold voltage

来源：评论

学校读者我要写书评

暂无评论

Cost minimization approach with hybrid optimization based task scheduling in Geo-distributed cloud

引用

Australian Journal of Electrical and Electronics engineering 2025年第2期22卷 169-181页

作者： Vasantham, Vijay Kumar Donavalli, Haritha Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur India

To manage the huge data, cloud computing necessitates a significant number of disc I/O, network bandwidth and CPU cycles. To handle the massive volumes of data, the programming paradigm known as data flow integrates the tasks to a graph structure. Task scheduling is one of the main areas of current study that primarily aims to allocate the tasks to resources. It is essential to organise the tasks in a way which saves time and makes the most use of available resources. In recent years, scholars have offered different job scheduling techniques. This work intends to introduce a novel cost minimisation for big data processing with respect to task allocation or scheduling. Initially, the big data is processed under Map Reduce framework. This allocation processes is taken as the optimisation issue, which is solved under the consideration of minimisation factors like execution cost, makespan, communication cost, and energy consumption and risk. For solving this issue, a new hybrid optimisation algorithm known as Hybrid bald eagle and Archimedes Optimisation algorithm (HBE-ArCA) is developed. The betterment of HBE-ArCA is proven regarding cost, makespan and so on. ©, Engineers Australia.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

A Low Resource Multi-lingual Simultaneous Script Identification and Text Recognition Model

引用

SN computer science 2024年第6期5卷 740页

作者： Mukherjee, Jayati Roy, Utpal Computer Science and Engineering Academy of Technology Department of computer and system sciences Visva-bharati

In this paper, we have proposed a multi-task learning model for multi-lingual Optical Character Recognition. Our model does the script identification and text recognition simultaneously of offline machine printed documents. We have extracted the spatial and temporal features of a line image by the combination of several CNN and BLSTM layers. The feature is shared between the script identification and text recognition modules. Fully connected layer and softmax identify the script. The identified script works as a case selector for the text recognizer which is a CTC layer. Finally, the text is identified by the text recognizer. The model is applied to two public datasets: ISIDDI, RETAS containing Bengali degraded, and English pages. We have created a dataset of Devnagari/Hindi and Tamil scripts to test our model. The model has achieved 99.2% accuracy for script recognition. The achieved text recognition accuracy on the scripts Bengali, English, Hindi, and Tamil are respectively 91.68%, 97.07%, 95.68% and 92.27%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Multi-task learning Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Privacy Comparison for Bitcoin Light Client Implementations 6

Privacy Comparison for Bitcoin Light Client Implementations

引用

6th Conference on Advances in Financial Technologies, AFT 2024

作者： Kotzer, Arad Rottenstreich, Ori The Department of Computer Science Technion Haifa Israel The Department of Computer Science The Department of Electrical and Computer Engineering Technion Haifa Israel

ISBN: (纸本)9783959773454

Light clients implement a simple solution for Bitcoin’s scalability problem, as they do not store the entire blockchain but only the state of particular addresses of interest. To be able to keep track of the updated state of their addresses, light clients rely on full nodes to provide them with the required information. To do so, they must reveal information about the addresses they are interested in. This paper studies the two most common light client implementations, SPV and Neutrino with regards to their privacy. We define privacy metrics for comparing the privacy of the different implementations. We evaluate and compare the privacy of the implementations over time on real Bitcoin data and discuss the inherent privacy-communication tradeoff. In addition, we propose general techniques to enhance light client privacy in the existing implementations. Finally, we propose a new SPV-based light client model, the aggregation model, evaluate it, and show it can achieve enhanced privacy than in the existing light client implementations. © Arad Kotzer and Ori Rottenstreich.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Per-user network access control kernel module with secure multifactor authentication

引用

Journal of Supercomputing 2024年第1期80卷 970-1008页

作者： Cheng, Sheng-Tzong Horng, Gwo-Jiun Hsu, Chih-Wei Su, Z.-Yu Department of Computer Science and Information Engineering National Cheng Kung University Tainan701 Taiwan Department of Computer Science and Information Engineering Southern Taiwan University of Science and Technology Tainan Taiwan

Network attacks, such as botnets stealing sensitive data, constitute a critical concern for administrators in the Internet area. Such attacks can be prevented using a network access control (NAC) scheme. However, existing NAC mechanisms all rely on the user account mechanism provided by the operating system. Herein, we propose a protocol involving a Linux security module for user-based NAC. The module requires neither user accounts nor secure user space;it loads signed rules and keys for a user from a USB security key, securely authenticates the user, and controls network permissions directly from the Linux kernel. Moreover, we present extensions for the protocol, developed using additional authentication methods and devices (such as a smartphone), to prevent man-in-the-middle, replay, and phishing attacks. The protocol can securely authenticate users from kernel space by using USB security keys and a user smartphone despite an insecure user space, is resistant to various attacks, and can guarantee that authorized users obtain their corresponding network privileges. At the same time, the analysis of Linux operating system security enhancement technology is proposed to achieve the goal of trusting machines. Through the use of empirical algorithm analysis, enhanced virtualization technology, and other methods, the risk of hacker intrusion on information platforms is reduced in multiple aspects, and management mechanisms are used to set and use resource permissions. On the other hand, after mastering the key technologies for network blocking development in the core layer of the system, there is also an opportunity to independently build modules for the security core of operating systems in special fields and future 5G/6G SDNs. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Network security

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：