检索结果-内蒙古大学图书馆

Developing a CKD prognostic model: Integrating feature extraction and classifiers for early detection

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 106卷

作者： Meena, K. Hema, K. GITAM Bengaluru Campus Dept Comp Sci & Engn Bengaluru Karnataka India

In result of its increase in prevalence, chronic kidney disease remains one of the emerging health concerns. Studies have shown that the average survival period of an individual without the functioning of either kidney is usually 18 days, after which transplants or dialysis have to be resorted to. Therefore, early detection becomes important. Diagnosis using ML and DL methods are quite efficient, but their decision processes are not transparent. In medical diagnosis, Machine Learning and DL techniques offer considerably high accuracy in disease prediction. Besides that, analyzing the influence of feature selection and extraction becomes very important in order to come up with high-quality and consistent *** efficacy of these strategies relies on proper feature selection, extraction, and classifiers. The objective of the research is to propose a novel framework to identify the optimal feature for early prediction of CKD. It uses exhaustive feature selection to identify pertinent features, processed by autoencoders and variational auto encoders for dimensionality reduction. This research paper identifies the better classifiers by comparing various ML algorithms such as GB, XGBoost,DT, RF, LR, and KNN and the DL classifier such as CNN for early CKD prediction, using advanced feature extraction *** conducted extensive experimental analysis using a standard dataset collected from Kaggle. The stated approach effectiveness is assessed using various measures, including accuracy, precision, recall, F1-score, and the Jaccard coefficient.

关键词： Chronic Kidney Disease Diagnosis Feature Selection Feature extraction auto encoder Variational autoencoder Machine learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

DSPCI-MTL: Dynamic split point computing in multi-task learning implementation with collaborative intelligence

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 124卷 404-421页

作者： Sahin, M. Faruk Yeganli, S. Faegheh Kiani, Farzad Istanbul Atlas Univ Dept Comp Engn Istanbul Turkiye Fatih Sultan Mehmet Vakif Univ Data Sci Applicat & Res Ctr VEBIM Istanbul Turkiye Univ British Columbia Dept Comp Sci Vancouver BC Canada

Deep Neural Networks (DNNs) have become a crucial technology in image processing, renowned for their ability to generate effective feature maps. The integration of DNNs within Internet of Things (IoT) environments, particularly in multi-task robots and swarm systems, has positioned them as vital components in various applications. However, their deployment in IoT devices frequently encounters challenges such as limited hardware capabilities, constrained bandwidth, prolonged data transmission times, and image packet loss due to transmission losses. To address these issues, this paper introduces the Multi-Task Learning (MTL) method of Collaborative Intelligence (CI) strategy by dynamically distributing computational tasks among edge devices and cloud. This method addresses the potential performance degradation caused by suboptimal computational splitting points of DNN for multiple tasks (segmentation, classification, depth estimation) and compensates for losses under varying network conditions and data sizes. A key innovation of our methodology is the introduction of a dynamic method to determine split points by computing DNN layers based on real-time bandwidth and data volume. In addition, an auto encoder (AE) architecture is implemented in the cloud to reconstruct image data packets lost during transmission based on feature map similarity measurements. Experimental results show that processing all transactions in the cloud with specific operational parameters reduces processing time by 38 % compared to traditional methods, while dynamically selecting the split point results in gains of up to 61 %. Furthermore, the proposed method achieves efficiency by reducing energy consumption by up to 50 % compared to cloud-only processing. It demonstrates robustness under varying network delays and reduces inference time by up to 47.5 % under low-latency conditions. In this regard, the innovative use of an AE for data loss reconstruction also shows significant potential in comp

关键词： auto encoder Collaborative intelligence Deep neural network IoT Multi-task learning Data reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep intrusion net: an efficient framework for network intrusion detection using hybrid deep TCN and GRU with integral features

引用

WIRELESS NETWORKS 2025年第2期31卷 1255-1278页

作者： Rani, Y. Alekya Reddy, E. Sreenivasa CVR Coll Engn Comp Sci Engn AI & ML Hyderabad India Acharya Nagarjuna Univ Comp Sci Engn Guntur India

In recent times, the several cyber attacks are occurred on the network and thus, essential tools are needed for detecting intrusion over the network. Moreover, the network intrusion detection systems become an important tool thus, it has the ability to safeguard the source data from all malicious activities or threats as well as protect the insecurity among individual privacy. Moreover, many existing research works are explored to detect the network intrusion model but it fails to protect the target network efficiently based on the statistical features. A major issue in the designed model is regarded as the robustness or generalization that has the capability to control the working performance when the data is attained from various distributions. To handle all the difficulties, a new meta-heuristic hybrid-based deep learning model is introduced to detect the intrusion. Initially, the input data is garnered from the standard data sources. It is then undergone the pre-processing phase, which is accomplished through duplicate removal, replacing the NAN values, and normalization. With the resultant of pre-processed data, the auto encoder is utilized for extracting the significant features. To further improve the performance, it requires choosing the optimal features with the help of an Improved chimp optimization algorithm known as IChOA. Subsequently, the optimal features are subjected to the newly developed hybrid deep learning model. The hybrid model is built by incorporating the deep temporal convolution network and gated recurrent unit, and it is termed as DINet, in which the hyper parameters are tuned by an improved IChOA algorithm for attaining optimal solutions. Finally, the proposed detection model is evaluated and compared with the former detection approaches. The analysis shows the developed model is suggested to provide 97% in terms of accuracy and precision. Thus, the enhanced model elucidates that to effectively detect malware, which tends to improve data

关键词： Intrusion detection Deep intrusion net Improved chimp optimization algorithm Deep temporal convolution network Gated recurrent unit auto encoder Detected intrusion outcomes

来源：评论

学校读者我要写书评

暂无评论

Improving Bird Vocalization Recognition in Open-Set Cross-Corpus Scenarios With Semantic Feature Reconstruction and Dual Strategy Scoring

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1515-1519页

作者： Xie, Jiangjian Wang, Yingqi Qian, Xinyuan Zhang, Junguo Schuller, Bjorn W. Beijing Forestry Univ State Key Lab Efficient Prod Forest Resources Beijing 100083 Peoples R China Univ Sci & Technol Beijing Dept Comp Sci & Technol Beijing 100083 Peoples R China Imperial Coll London GLAM London SW7 2AZ England Tech Univ Munich CHI D-80333 Munich Germany MCML D-85748 Munich Germany MDSI D-85748 Munich Germany

automated recognition of bird vocalizations (BVs) is essential for biodiversity monitoring through passive acoustic monitoring (PAM), yet deep learning (DL) models encounter substantial challenges in open environments. These include difficulties in detecting unknown classes, extracting species-specific features, and achieving robust cross-corpus recognition. To address these challenges, this letter presents a DL-based open-set cross-corpus recognition method for BVs that combines feature construction with open-set recognition (OSR) techniques. We introduce a three-channel spectrogram that integrates both amplitude and phase information to enhance feature representation. To improve the recognition accuracy of known classes across corpora, we employ a class-specific semantic reconstruction model to extract deep features. For unknown class discrimination, we propose a Dual Strategy Coupling Scoring (DSCS) mechanism, which synthesizes the log-likelihood ratio score (LLRS) and reconstruction error score (RES). Our method achieves the highest weighted accuracy among existing approaches on a public dataset, demonstrating its effectiveness for open-set cross-corpus bird vocalization recognition.

关键词： Index Terms -Bird vocalizations recognition open-set cross-corpus cross-corpus phase characteristics phase characteristics auto encoder auto encoder auto encoder

来源：评论

学校读者我要写书评

暂无评论

TFF-Codec: A High Fidelity End-to-End Neural Audio Codec

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2025年第6期44卷 4013-4032页

作者： Zhao, Yuhao Jia, Maoshen Ru, Jiawei Wang, Lizhong Wen, Liang Beijing Univ Technol Sch Informat Sci & Technol Beijing 100124 Peoples R China Samsung R&D Inst China Beijing Beijing 100028 Peoples R China

Audio Coding has made significant progress with the development of deep neural networks. Recently, neural speech codecs based on vector quantized variational autoencoder have become increasingly popular among researchers due to their elegant design and superior performance, but their application to high bitrate audio coding has not been further expanded. In this paper, we propose a novel high fidelity end-to-end neural audio codec called time frequency fusion codec (TFF-Codec), which is capable of high-quality reconstruction of 32 kHz audio in the time-frequency domain at 48 and 64 kbps. In this paper, a dual-path time-frequency filtering module is proposed to capture the local structure of the spectrogram and the long-term time dependence between consecutive frames. The architecture of the proposed codec is composed of encoder, the time-frequency filtering module, vector quantizer and decoder. First, the input audio is fed into the encoder to obtain its potential representation. Then, it is modeled in the frequency domain in the time-frequency filtering module. Subsequently, it is further compressed by a vector quantizer. Finally, the reconstructed audio is obtained by the decoder. We also use a combination of multiple loss functions in TFF-Codec to ensure that the reconstructed audio is balanced in terms of objective metrics and subjective listening experience. To evaluate the performance of TFF-Codec, comparative experiments are conducted with the traditional audio codec Opus and several recent neural audio codecs. Both subjective and objective evaluation tests demonstrate the superiority of our proposed method.

关键词： Audio codec End to end neural network auto encoder High fidelity audio generation

来源：评论

学校读者我要写书评

暂无评论

Data Privacy Preservation and Authentication Scheme for Secured IoMT Communication Using Enhanced Heuristic Approach with Deep Learning

引用

CYBERNETICS AND SYSTEMS 2024年

作者： Bhasha, Shaik Jhani Panda, Sunita GITAM Deemed Be Univ EECE Rudraram 502329 Telangana India GITAM Deemed Be Univ Bengaluru 561203 Karnataka India

Internet of Medical Things (IoMT) is a promising field that is widely used in healthcare applications nowadays. The IoMT is an extension of the Internet of Things (IoT) that is utilized for the processing, generation, collection, and evaluation of medical data. However, the most concerning issue in IoMT is regarding the privacy and protection of the IoMT data. Because privacy preservation of information is the major concern in IoT-based healthcare systems. Hence, there is a need for a trustworthy end-to-end system, which can tolerate even insider attacks. The core aim of this research work is to promote the latest secure technique for transmitting the data from sink nodes to the server and also to ensure the security level of communication between them. Here, the gathered sink node is authenticated by deep hybrid methods of combining the auto encoder (AE) and Bidirectional Long Short-Term Memory (BiLSTM). This hybrid model is named as auto encoder-Bidirectional Long Short-Term Memory (AE-Bi-LSTM), in which the parameters are tuned by the Improved Chimp Optimization Algorithm (IChoA). Hence, data privacy preservation makes to secure communication in the networks. The proposed privacy-prevention model is utilized for maintaining communication between sink nodes and servers. The communication is done through three different steps (a) Sanitation, (b) Optimal key generation, and (c) Restoration. Moreover, from the overall result analysis, the accuracy and precision rate of the designed IChoA-AE-Bi-LSTM approach are 95.58 and 91.93%. The experimental analysis shows that the designed model offers a better authentication scheme and guarantees data privacy than traditional models. Moreover, applying a high amount of energy will reduce the lifetime of the sensor nodes. Here, privacy preservation is a challenging task due to fraudulent attacks from third-party service providers. In the future, advanced techniques will be implemented with lightweight encoded mechanisms.

关键词： auto encoder bidirectional long short-term memory data privacy preservation improved chimp optimization algorithm internet of things internet of medical things sink node authentication scheme

来源：评论

学校读者我要写书评

暂无评论

The implementation of deep clustering for SuperDARN backscatter echoes

引用

ADVANCES IN SPACE RESEARCH 2024年第1期74卷 243-254页

作者： Kong, Xing Liu, Erxiao Shi, Shengsheng Chen, Fengjv Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310018 Peoples R China Chinese Acad Sci State Key Lab Space Weather Beijing 100190 Peoples R China

The collection of SuperDARN ionospheric echo data to make ionospheric convection maps is of great significance for Space Weather research. The ionospheric echoes for SuperDARN are generally mixed with scatter from the ground or sea surface, thus the clustering analysis of SuperDARN backscatter echoes is important. In this paper, the first implementation of deep clustering based on the graph automatic encoder network is efficiently realized for classifying the SuperDARN data. In addition, the model is compared with the traditional algorithm and machine learning clustering algorithms. Application of the model to sample data reveals that the deep clustering algorithm can capture the structural characteristics of the echoes and improve the accuracy of echo clustering and classifying. (c) 2024 COSPAR. Published by Elsevier B.V. All rights reserved.

关键词： Space Weather SuperDARN Graph Clustering auto encoder K-means

来源：评论

学校读者我要写书评

暂无评论

Adaptive graph clustering based on feature adversarial and graph transformer

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 281卷

作者： Zhang, Weitong Zhu, Xuerong Shang, Ronghua Ren, Jinhong Jiao, Licheng Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Minist Educ Xian 710071 Shaanxi Peoples R China

Most of the existing graph clustering methods do not fully utilize the graph's structural and attribute information. In addition, there is a lack of adaptive fusion mechanisms to integrate and refine the complementarity between the graph structural and the graph attribute information. This makes it difficult to learn distributionally consistent representations, thus affecting the performance of graph clustering. To overcome the above problems, in this article, an adaptive graph clustering method based on feature adversarial and graph transformer (FTAGC) is proposed. First, a feature adversarial auto-encoder module (FAAE) is designed. The node representation features are obtained by using an auto-encoder (AE) to learn the graph attribute information. These features and the prior distribution are then fed into a discriminator for adversarial learning. This process enhances the representation performance of the AE, ensuring that the attribute-level node representation features learned by the FAAE match the prior distribution. Second, a graph transformer auto-encoder module (GTAE) is designed. It learns the graph's local features using a linear structure. The self-attention mechanism captures the dependency between the graph's local features and global structure, so as to learn the global structure-level node representation features. Finally, a dual-source feature adaptive fusion (DFAF) module is proposed. The attention module adaptively calculates weights for the weighted fusion of attribute-level and structure-level dual-source features learned from FAAE and GTAE branches. This operation achieves convergent representation learning, resulting in the final node representation features, which will be utilized in the downstream clustering task. In the meantime, self-supervised learning constrains the cross-module information of FAAE, GTAE, and DFAF. It directs the unified optimization of graph representation learning and the graph clustering assignments, in order to accom

关键词： Graph clustering Feature adversarial Adaptive feature fusion Graph attention auto encoder

来源：评论

学校读者我要写书评

暂无评论

An Attribute-wise Attention model with BiLSTM for an efficient Fake News Detection

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第13期83卷 38109-38126页

作者： Merryton, Adline Rajasenah Augasta, M. Gethsiyal Manonmaniam Sundarnar Univ Sarah Tucker Coll Tirunelveli 627012 Tamil Nadu India Manonmaniam Sundaranar Univ Kamaraj Coll Thoothukudi Tamil Nadu India

Nowadays, fake news propaganda is the main threat to society, as it has the potential to misdirect public behaviour and provoke violence and extremism. Recently, to prevent the spread of misinformation, researchers have devised various fake news detection models with deep learning techniques. This research aims to develop a unique deep architecture to capture the basic insights about the document in the form of a summarised feature vector representation for better fake news detection. The proposed model, namely AA-BiLSTM includes Bi-directional Long Short-Term Memory (Bi-LSTM) and an attribute-wise attention mechanism based on Convolutional Neural Network (CNN) as the CNN models extract higher-level features using convolutional layers and average pooling layers. Moreover, this model suitably pays attention to the word or sentence based on the dependent attribute by applying the attention mechanism after the fusing process. The performance of the proposed AA-BiLSTM has been experimentally evaluated on four benchmark datasets, namely Kaggle fake_real_news [2022], Kaggle fake_real_news [2016], ISOT and Liar datasets, and compared with the existing state-of-the-art fake news detection methods. For the Kaggle fake_real_news 2016 and ISOT fake news datasets, the AA-BiLSTM algorithm achieved an accuracy of more than 99%. In the Liar dataset, the AA-BiLSTM method surpassed all basic models with an accuracy of 60.31%.

关键词： Natural Language Processing Bi-LSTM CNN Attention Mechanism Fake News Detection auto encoder

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based deep learning for massive multiple-input multiple-output uplink under high-power amplifier non-linearities

引用

IET COMMUNICATIONS 2023年第2期17卷 162-170页

作者： Cherif, Maha Arfaoui, Ahlem Bouallegue, Ridha Univ Catthage SupCom InnovCOM Atiana 2083 Tunisia

In this paper, the authors study the compensation of high-power amplifier (HPA) non-linear distortion in the multi-user (MU) massive multiple-input multiple-output (MIMO) systems and focus on uplink transmission, where the base station (BS) uses a large antenna array. First, the authors present a non-linear distortion iterative cancellation (NDIC) algorithm-based MMSE and approximate message passing (AMP) at the receiver level, in order to estimate and mitigate jointly a non-linear distortion and the channel noise. Second, the authors propose a novel distortion cancellation technique based on deep learning. At this level, the authors first introduce a multilayer neural network, trained in the Levenberg-Marquardt algorithm by eliminating HPA non-linearities on the 'Pre distortion' transmitter and 'Post distortion' receiver side. Next, the authors developed a novel end-to-end (E2E) learning approach for the joint transmitter and non-coherent receiver in the Rayleigh fading channel. The basic idea lies in the use of deep neural networks (DNNs), auto encoder (AE) for unknown channels, where DNNs are applied to perform several functions and modules existing in the transmission chain. The simulation results demonstrate the strong potential of the proposed approach E2E in terms of improving the link quality and symbol error rate (SER) compared to other compensation techniques presented in this work.

关键词： HPA nonlinearities interference suppression fading channels high-power amplifier nonlinear distortion NDIC algorithm-based MMSE approximate message passing Communication channel equalisation and identification Antenna arrays uplink transmission iterative methods autoencoder-based deep learning multiuser massive multiple-input multiple-output systems Neural nets message passing massive multiple-input multiple-output uplink distortion cancellation technique end-to-end learning approach base station least mean squares methods receiver level multilayer neural network Rayleigh channels neural nets Radio links and equipment deep learning (artificial intelligence) Modulation and coding methods antenna arrays Levenberg-Marquardt algorithm Electromagnetic compatibility and interference nonlinear distortion iterative cancellation algorithm-based MMSE auto encoder wireless channels MIMO communication Interpolation and function approximation (numerical analysis) high-power amplifier nonlinearities error statistics Other topics in statistics noncoherent receiver Amplifiers power amplifiers E2E learning approach

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：