检索结果-内蒙古大学图书馆

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Luo, Yin-Jyun Ewert, Sebastian Dixon, Simon Queen Mary Univ London Ctr Digital Music London England Spotify Stockholm Sweden

ISBN: (纸本)9798350344868;9798350344851

Disentangled representation learning seeks to align individual dimensions or separate groups of coordinates of latent factors with attributes of observed data such that perturbing certain latent factors uniquely changes particular attributes. A main challenge in unsupervised disentanglement using autoencoders is that strong regularisation, while necessary for consistent disentanglement, comes at the expense of accurate data reconstruction. To address this, we introduce a teacher-student framework that incorporates a variational sequential autoencoder and a Jacobian constraint that regularises the variation of observations relative to latent factors. In real-world audio recordings of musical instruments, our approach outperforms a state-of-the-art method in both sampling quality and unsupervised pitch-timbre disentanglement.

关键词： Disentangled representation unsupervised learning variational autoencoder music instrument

来源：评论

学校读者我要写书评

暂无评论

Learning Salient Features for Speech Emotion Recognition using Attention-based Residual Bidirectional LSTM with Federated Learning 4

Learning Salient Features for Speech Emotion Recognition usi...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Kaur, Dilsheen Misra, Anuradha Vyas, O.P. Amity University Lucknow Campus Amity School of Engineering and Technology Department of Computer Science and Engineering India Indian Institute of Information Technology Allahabad Department of Information Technology India

ISBN: (纸本)9798350343670

In human communication, expressing human emotion plays an essential role in transferring information to the other individual. The expression forms of human communication are very rich, in different patterns like facial expressions, voice tone, eye contact, body language and laughter. Moreover, the languages used by individuals in the entire world are different, yet without understanding the communication language, the individuals can realize the message that other individuals require to convey as emotional expressions. Among all the human emotional expressions, the conveyed expressions through human voice are experimented with in different studies. However, identifying the emotional situation of the presenter is complicated for the machine learning techniques, which gained more attraction in Speech Emotion Recognition (SER). Here, the SER framework plays an efficient role in different real-world applications in observing human actions, virtual reality, emergency centers and robot communication to observe the emotional phase of the speakers. Thus, an innovative federated learning-based SER is presented in this paper. The essential speech signals are initially collected from the standard database. After that, the collected signal is fed to the feature extraction stage. Here, the deep features in the input signal are obtained by the variational autoencoder (VAE). Further, the deep features obtained from the VAE are passed to the "Attention-based Residual Bidirectional Long Short-Term Memory (A-RBiLSTM)"to identify the emotions in the speech signal. At last, different experimental analyses are executed to observe the effectualness of the implemented framework. © 2024 IEEE.

关键词： Attention-based Residual Bidirectional Long Short-Term Memory Deep Features Feature Extraction Federated Learning Speech Emotion Recognition variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Multi-View Clustering Method of Power Users Based on a variational Automatic Encoder 5

An Efficient Deep Multi-View Clustering Method of Power User...

引用

5th International Conference on Clean Energy and Electric Power Engineering, ICCEPE 2024

作者： Ke, Yang Xiao, Wei Chen, Meng Feng, Yi Wu, Ze Yichang Power Supply Company State Grid Hubei Electric Power Co. Ltd. Hubei Yichang China China Three Gorges University Hubei Key Laboratory of Intelligent Vision-Based Monitoring for Hydroelectric Engineering Hubei Yichang443000 China

ISBN: (纸本)9798350390315

The electricity consumption behavior characteristics of electricity users are reflected in their electricity load data. Therefore, clustering the electricity users into groups and analyzing their characteristics can help power companies obtain a clear insight and a deeper understanding of the user groups and provide more targeted services accordingly. However, due to the large-scale and high-dimensional nature of power load data, traditional clustering methods face certain difficulties in feature extraction. In view of that, this article proposes a deep multi-view clustering method for power users based on a VAE (variational autoencoder). The proposed method first reduces the dimensionality of power load data by distributing the VAE network and then adopts a deep fusion module to achieve deep mining of the reduced data. Finally, it clusters power users using the clustering module. The experimental results demonstrate that the proposed clustering method can achieve optimal performance on both the Calinski Harabasz index and Silhouette score and a suboptimal result on the Davies Bouldin index. The results presented in this study indicate the practical effectiveness of the proposed approach and provide a solid data foundation for more accurate user behavior analysis for power companies. © 2024 IEEE.

关键词： Dual-scale similarity Electricity Load data Multi-view clustering variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

LENS: Predictive Diagnostics for Flexible and Efficient Assessments 23

LENS: Predictive Diagnostics for Flexible and Efficient Asse...

引用

10th ACM Conference on Learning at Scale (L at S)

作者： Christie, S. Thomas Johnson, Hayden Cook, Carson Gianopulos, Garron Rafferty, Anna N. NWEA St Paul MN 06010 USA NWEA Minneapolis MN USA NWEA Portland OR USA NWEA Raleigh NC USA Carleton Coll Northfield MN USA

ISBN: (纸本)9798400700255

The utility of assessment systems lies in their capacity to transform observations of student behavior into meaningful inferences about learning, knowledge, and skills. Common practice is to use latent variable models and produce scores on scales. However the simplicity of these psychometric models may filter out potentially valuable information present in student behavior. In particular, scale scores are not optimized to support granular instructional decisions. Machine learning offers promising alternatives, but proposed deep learning architectures are not ideally suited for operational testing conditions involving sparse data and shifting category labels for test questions. We present criteria for a model architecture that can leverage the rich, sparse behavioral data made available by modern assessment systems. We argue that behavioral predictions with well-quantified uncertainties are a viable alternative to scale scores for many applications. To satisfy these goals, we propose the LENS model architecture that combines the flexibility of machine learning and the uncertainty quantification of latent variable models to produce high-quality predictive diagnostic claims. Inspired by variational autoencoders, LENS maps student behavior to a latent probability distribution. In addition, LENS performs explicit Bayesian integration of each behavioral observation, allowing the model to incorporate sparse data with informative prior beliefs about students. We then compare the predictive capability of LENS to both latent variable and machine learning approaches. LENS generates competitive or superior predictions of behavior, particularly on sparse data, while requiring fewer modeling assumptions than other options and allowing for easy incorporation of auxiliary behavioral data. We also show how to produce interpretable claims about student behavior at multiple levels of granularity, allowing the same model to serve multiple reporting needs. Finally, we discuss the flexib

关键词： educational assessment deep learning Bayesian inference variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Enhancing Image Classification in Small and Unbalanced Datasets Through Synthetic Data Augmentation 1

引用

13th Workshop on Clinical Image-Based Procedures (CLIP)

作者： de la Fuente, Neil Majo, Mireia Luzko, Irina Cordova, Henry Fernandez-Esparrach, Gloria Bernal, Jorge Comp Vis Ctr Barcelona Spain Univ Autonoma Barcelona Barcelona Spain Hosp Clin Barcelona Barcelona Spain

ISBN: (数字)9783031730832

ISBN: (纸本)9783031730825;9783031730832

Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific variational autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6% increase in global accuracy and precision.

关键词： Synthetic Data Augmentation variational autoencoder Esophagogastroduodenoscopy Image Classification Image Classification

来源：评论

学校读者我要写书评

暂无评论

FMCW Radar Sensing for Indoor Drones Using variational Auto-Encoders

FMCW Radar Sensing for Indoor Drones Using Variational Auto-...

引用

IEEE Radar Conference (RadarConf)

作者： Safa, Ali Verbelen, Tim Catal, Ozan Van de Maele, Toon Hartmann, Matthias Dhoedt, Bart Bourdoux, Andre Katholieke Univ Leuven ESAT Leuven Belgium Univ Ghent IDLab Ghent Belgium Imec B-3001 Leuven Belgium

ISBN: (纸本)9781665436694

This paper investigates unsupervised learning of low-dimensional representations from FMCW radar data, which can be used for multiple downstream tasks in a drone navigation context. To this end, we release a first-of-its-kind dataset of raw radar ADC data recorded from a radar mounted on a flying drone in an indoor environment, together with ground truth detection targets. We show that, by utilizing our learned representations, we match the performance of conventional radar processing techniques while training our models on different input modalities such as range-doppler maps, range-azimuth maps, or raw ADC samples of only two consecutively transmitted chirps.

关键词： Drone navigation deep learning indoor sensing variational autoencoder velocity and angle estimation

来源：评论

学校读者我要写书评

暂无评论

DefWeb: Defending User Privacy against Cache-based Website Fingerprinting Attacks with Intelligent Noise Injection 23

DefWeb: Defending User Privacy against Cache-based Website F...

引用

39th Annual Computer Security Applications Conference (ACSAC)

作者： Son, Seonghun Dipta, Debopriya Roy Gulmezoglu, Berk Iowa State Univ Ames IA 50011 USA

ISBN: (纸本)9798400708862

Cache-based website fingerprinting (WF) attacks violate user privacy where the attacker leverages the shared last-level cache in CPUs and analyzes the fingerprints through machine learning and deep learning models. WF attacks are even applicable in Incognito and anonymized browser platforms, leading to a serious threat to the public. Several defense techniques inject random noise during website rendering to degrade the attack success rate, while these techniques either create large performance overhead or cannot obfuscate the WF dataset entirely when the attacker retrains a new learning model with noisy fingerprints. In this work, we develop a dynamic generative learning-based defense technique, DefWeb, to protect user privacy against cache-based WF attacks by injecting precise noise into the WFs. For this purpose, (i) we train generative neural networks to represent high-dimensional fingerprints in a low-dimension space while creating distinct clusters for each website. (ii) Minimal noise templates are extracted in the low-dimension space to obfuscate the fingerprints efficiently. (iii) We create practical noise templates that can be added to WFs during website rendering by leveraging self-modifying code (SMC). We implement DefWeb in both simulation and real-world setups to degrade the attacker's model accuracy. DefWeb can decrease the model accuracy to 1.1% and 28.8% in simulation and real-world setups, respectively, including Mozilla Firefox, Google Chrome, and Tor browsers. Finally, the performance overhead introduced by DefWeb is only 9.5%, which is considerably lower than previous defense techniques.

关键词： Cache-based Attack Noise Injection Website Fingerprinting Generative Learning variational autoencoder Web Security

来源：评论

学校读者我要写书评

暂无评论

Echocardiography Segmentation With Enforced Temporal Consistency

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2022年第10期41卷 2867-2878页

作者： Painchaud, Nathan Duchateau, Nicolas Bernard, Olivier Jodoin, Pierre-Marc Univ Sherbrooke Dept Comp Sci Sherbrooke PQ J1K 2R1 Canada Univ Claude Bernard Lyon 1 Univ Lyon INSA Lyon UJM St EtienneCNRSInsermCREATIS UMR 5220U1294 F-69621 Lyon France Inst Univ France IUF F-75005 Paris France

Convolutional neural networks (CNN) have demonstrated their ability to segment 2D cardiac ultrasound images. However, despite recent successes according to which the intra-observer variability on end-diastole and end-systole images has been reached, CNNs still struggle to leverage temporal information to provide accurate and temporally consistent segmentation maps across the whole cycle. Such consistency is required to accurately describe the cardiac function, a necessary step in diagnosing many cardiovascular diseases. In this paper, we propose a framework to learn the 2D+time apical long-axis cardiac shape such that the segmented sequences can benefit from temporal and anatomical consistency constraints. Our method is a post-processing that takes as input segmented echocardiographic sequences produced by any state-of-the-art method and processes it in two steps to (i) identify spatio-temporal inconsistencies according to the overall dynamics of the cardiac sequence and (ii) correct the inconsistencies. The identification and correction of cardiac inconsistencies relies on a constrained autoencoder trained to learn a physiologically interpretable embedding of cardiac shapes, where we can both detect and fix anomalies. We tested our framework on 98 full-cycle sequences from the CAMUS dataset, which are available alongside this paper. Our temporal regularization method not only improves the accuracy of the segmentation across the whole sequences, but also enforces temporal and anatomical consistency.

关键词： Image segmentation Shape Echocardiography Annotations Encoding Magnetic resonance imaging Cardiac function Deep learning CNN variational autoencoder cardiac segmentation ultrasound left ventricle myocardium

来源：评论

学校读者我要写书评

暂无评论

Design of anomaly detection research model for multi-dimensional temporal data 4

Design of anomaly detection research model for multi-dimensi...

引用

4th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)

作者： Wang, Shuai Jiang, Yan Shenyang Univ Technol Sch Software Shenyang Liaoning Peoples R China

ISBN: (纸本)9798350375084;9798350375077

In the production and daily life of various industries in today's society, it is often necessary to arrange a large number of sensors to collect data on a scheduled basis. However, due to factors such as collection errors, sensor failures, network transmission anomalies, and human influence, the obtained multidimensional temporal data may exhibit anomalies. In order to better analyze multidimensional temporal data, understand patterns, trends, and correlations in observed phenomena, and help people better analyze problems and make decisions, a design scheme for anomaly detection models that have always been oriented towards multidimensional temporal data is proposed. This scheme utilizes Convolutional Neural Networks (CNN) to extract local features, Long Short Term Memory Networks (LSTM) to store and extract time-series data features, combined with attention mechanisms to enhance feature extraction capabilities, and uses variational autoencoder (VAE) for anomaly detection, significantly improving the accuracy and efficiency of detection. Through experimental verification, this method performs well in practical applications and has broad application prospects.

关键词： component: Multidimensional Temporal Data Ab normal Detection Convolutional Neural Networks Long Short-term Memory Network variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Balancing Class Distribution in Microarray Analysis Using GenAI 4th

Balancing Class Distribution in Microarray Analysis Using Ge...

引用

4th International Conference on Intelligent Systems and Pattern Recognition-ISPR

作者： Anurekha, G. Amutha, S. Nivethika, K. Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept Comp Sci & Engn Chennai Tamil Nadu India

ISBN: (纸本)9783031821554;9783031821561

Microarrays are sophisticated datasets that have a substantial number of features and a limited number of samples. This can lead to a class imbalance problem. Balancing class distribution is an important research domain. In this paper, a novel variational auto encoder model is proposed for class imbalance mitigation. The proposed model employs an adversarial loss function to generate simulated data. The proposed model is evaluated using the autism gene expression dataset. The obtained experimental results prove that the data generated from the proposed model have obtained noteworthy results compared with the original dataset by employing three different classifiers.

关键词： Class imbalance Deep learning Microarray Simulated data variational autoencoder

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：