检索结果-内蒙古大学图书馆

34th International Workshop on Machine Learning for signal processing

作者： Brogan, Joel Kotevska, Olivera Torres, Anibely Jha, Sumit Adams, Mark Oak Ridge Natl Lab 1 Bethel Valley Rd Oak Ridge TN 37831 USA

ISBN: (纸本)9798350372267;9798350372250

signal analysis and classification is fraught with high levels of noise and perturbation. computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection;however, these methods aren't designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring. Currently, these models can be brittle, which makes them susceptible to noisy input. This also means they have sub-optimal stability of explanation outputs. Experts and technicians using these models to make decisions in real world scenarios need assurance that a model is performing as it is supposed to. The classification or prediction outputs it generates should be sound and grounded, not likely to change in the presence of shifting noise landscapes. In this work, we explore the idea of neural stochastic Differential Equations (NSDE's) to improve the robustness of models trained to classify time series data and the effect of NSDE's on the explainability of outputs. We then test the effectiveness of these approaches by applying them to a non-intrusive load monitoring (NILM) dataset that consists of simulated harmonic signals injected into a real building.

关键词： signal classification XAI robustness

来源：评论

学校读者我要写书评

暂无评论

Gradient bald vulture optimization enabled multi-objective Unet plus plus with DCNN for prostate cancer segmentation and detection

引用

BIOMEDICAL signal processing AND CONTROL 2024年 87卷

作者： Prasad, Jayashree Rajesh Prasad, Rajesh Shardanand Dhumane, Amol Ranjan, Nihar Tamboli, Mubin MIT Art Design & Technol Univ Sch Comp Comp Sci & Engn Pune 412201 Maharashtra India Pimpri Chinchwad Coll Engn Comp Engn Pune Maharashtra India JSPMs Rajarshi Shahu Coll Engn Informat Technol Pune Maharashtra India Symbiosis Inst Technol Comp Engn Pune Maharashtra India

Prostate cancer (PCa) represents the general type of cancer and is considered the third leading reason of death worldwide. As a combined part of computer-aided detection (CAD) applications, magnetic resonance imaging (MRI) is extensively studied for the precise detection of PCa. However, various issues rely on MRI, which includes the complexity of interpretation and increased time. Thus, deep learning-based tumor detection and segmentation methods attempt to be imperative techniques for radiologists to execute their tasks more precisely. The objective is to present Gradient Bald vulture optimization (GBVO)-based Deep Convolution neural Networks (DCNN) with U-Net++ for segmenting and detecting prostate cancer. Initially, image pre-processing is done using Non-Local Means (NLM) filter. After pre-processing, image segmentation is carried out using the proposed optimized multi-objective Unet++, where the objective function in Unet++ is modified using pixel-wise cross entropy and the Jaccard coefficient. In addition, the training of Unet++ is done using the newly designed Gradient Bald Eagle Optimization (GBEO), which is a combination of stochastic Gradient Descent (SGD) and Bald Eagle optimization (BEO). Finally, cancer detection is done using DCNN. DCNN is trained using GBVO, which is the integration of the African Vultures Optimization Algorithm (AVOA) and GBEO. The proposed method out-performed state-of-the-art techniques. The developed method achieved the highest accuracy of 0.916, a false negative ratio (FNR) of 0.104, a false positive ratio (FPR) of 0.100, and a negative predictive value (NPV) of 0.903.

关键词： Prostate cancer Deep convolution neural network U-Net plus plus Non-local means filter MRI

来源：评论

学校读者我要写书评

暂无评论

A Study on Deep Learning-Based image Target Identification Techniques 5th

A Study on Deep Learning-Based Image Target Identification T...

引用

5th International Conference on 3D Imaging Technologies—Multidimensional signal processing and Deep Learning, 3DIT-MSP and DL 2023

作者： Wang, Yining College of Electronic Information and Optical Engineering Taiyuan University of Technology Shanxi Taiyuan China

ISBN: (纸本)9789819751808

This study aims to explore deep learning-based image target recognition methods to improve the performance of target detection and classification in the field of computer vision. The experiments use satellite-acquired remote sensing images of moving objects, including four target categories such as buses, cars, bicycles and ships. In model training, we performed parameter optimisation by stochastic gradient descent algorithm and set the training period to 12. To validate the model’s effectiveness, we compare the improved R-CNN (Region-based Convolutional neural Network), traditional CNN (Convolutional neural Network) and Faster-RCNN (Faster Region-based Convolutional neural Network) models, and generate confusion matrices to evaluate their performance. The experimental results show that the improved model exhibits excellent performance in recognition of different types of target objects, especially for larger targets. This research provides reliable experimental support for the application of deep learning in the field of image target recognition and is expected to promote further development and innovation in this field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Convolutional-Attentional neural Framework for Structure-Aware Performance-Score Synchronization

引用

IEEE signal processing LETTERS 2022年 29卷 344-348页

作者： Agrawal, Ruchit Wolff, Daniel Dixon, Simon Queen Mary Univ London Ctr Digital Mus London E1 4NS England Inst Res & Coordinat Acoust Mus F-75004 Paris France

Performance-score synchronization is an integral task in signal processing, which entails generating an accurate mapping between an audio recording of a performance and the corresponding musical score. Traditional synchronization methods compute alignment using knowledge-driven and stochastic approaches, and are typically unable to generalize well to different domains and modalities. We present a novel data-driven method for structure-aware performance-score synchronization. We propose a convolutional-attentional architecture trained with a custom loss based on time-series divergence. We conduct experiments for the audio-to-MIDI and audio-to-image alignment tasks pertained to different score modalities. We validate the effectiveness of our method via ablation studies and comparisons with state-of-the-art alignment approaches. We demonstrate that our approach outperforms previous synchronization methods for a variety of test settings across score modalities and acoustic conditions. Our method is also robust to structural differences between the performance and score sequences, which is a common limitation of standard alignment approaches.

关键词： Synchronization Task analysis Convolution computer architecture Hidden Markov models Computational modeling Predictive models Performance-score synchronization audio-to-score alignment convolutional neural networks multimodal data time-series alignment stand-alone self-attention

来源：评论

学校读者我要写书评

暂无评论

Classification of breast mass in two-view mammograms via deep learning

引用

IET image processing 2021年第2期15卷 454-467页

作者： Li, Hua Niu, Jing Li, Dengao Zhang, Chen Taiyuan Univ Technol Coll Informat & Comp Taiyuan Peoples R China Taiyuan Univ Technol Coll Data Sci Taiyuan Peoples R China Shanxi Engn Technol Res Ctr Spatial Informat Netw Taiyuan Peoples R China

Breast cancer is the second deadliest cancer among women. Mammography is an important method for physicians to diagnose breast cancer. The main purpose of this study is to use deep learning to automatically classify breast masses in mammograms into benign and malignant. This study proposes a two-view mammograms classification model consisting of convolutional neural network (CNN) and recurrent neural network (RNN), which is used to classify benign and malignant breast masses. The model is composed of two branch networks, and two modified ResNet are used to extract breast-mass features of mammograms from craniocaudal (CC) view and mediolateral oblique (MLO) view, respectively. In order to effectively utilise the spatial relationship of the two-view mammograms, gate recurrent unit (GRU) structures of RNN is used to fuse the features of the breast mass from the two-view. The digital database for screening mammography (DDSM) be used for training and testing our model. The experimental results show that the classification accuracy, recall and area under curve (AUC) of our method reach 0.947, 0.941 and 0.968, respectively. Compared with previous studies, our method has significantly improved the performance of benign and malignant classification.

关键词： mammography Patient diagnostic methods and instrumentation malignant breast masses neural nets deadliest cancer convolutional neural network craniocaudal view mediolateral oblique view benign classification Biology and medical computing computer vision and image processing techniques Other topics in statistics malignant classification Optical, image and video signal processing cancer recurrent neural network image classification feature extraction biological organs breast cancer X-ray techniques: radiography and computed tomography (biomedical imaging/measurement) medical image processing breast-mass features learning (artificial intelligence) deep learning Probability theory, stochastic processes, and statistics X-rays and particle beams (medical uses) benign breast masses breast mass two-view mammograms classification model recurrent neural nets

来源：评论

学校读者我要写书评

暂无评论

Rag-bull rider optimisation with deep recurrent neural network for epileptic seizure detection using electroencephalogram

引用

IET signal processing 2021年第2期15卷 122-140页

作者： Johnrose, Prabin Jose Muniasamy, Sundaram Georgepeter, Jaffino Kamaraj Coll Engn & Technol Dept Elect & Commun Engn Madurai Tamil Nadu India VSB Engn Coll Dept Elect & Commun Engn Karur India Aditya Coll Engn Dept Elect & Commun Engn Surampalem India

Electroencephalogram (EEG) signal is mostly utilised to monitor epilepsy to revitalize the close loop brain. Several classical methods devised to identify seizures rely on visual analysis of EEG signals which is a costly and complex task if channel count increases. A novel method, namely, a rag-Rider optimisation algorithm (rag-ROA) is devised for training a deep recurrent neural network (Deep RNN) to discover epileptic seizures. Here the input EEG signals are splitted to different channels wherein each channel undergoes feature extraction. The features like Holoentropy, relative energy, fluctuation index, tonal power ratio, spectral features along with the proposed Taylor-based delta amplitude modulation spectrogram (Taylor-based delta AMS) are mined from each channel. The proposed Taylor-based delta AMS is designed by integrating the delta AMS and Taylor series. The probabilistic principal component analysis (PPCA) is employed to reduce the feature dimension. The dimensionally reduced feature vector is classified with Deep RNN using rag-ROA, which is designed by integrating rag-bull rider along with the four other riders available in the Rider optimisation algorithm (ROA). Thus, the resulted output of the proposed rag-ROA-based deep RNN is employed for EEG seizure detection. The proposed rag-ROA-based Deep RNN showed improved results with maximal accuracy of 88.8%, maximal sensitivity of 91.9%, and maximal specificity of 89.9% than the existing methods, such as Wavelet + SVM, HWPT + RVM, MVM-FzEN, and EWT + RF, using the TUEP dataset.

关键词： deep recurrent neural network computer vision and image processing techniques medical signal detection Probability theory, stochastic processes, and statistics spectral features Biology and medical computing rag-ROA-based deep RNN EEG signals brain feature dimension Bioelectric signals classical methods signal processing and detection electroencephalography recurrent neural nets Taylor-based delta AMS principal component analysis Digital signal processing rag-Rider optimisation algorithm Electrical activity in neurophysiological processes complex task electroencephalogram signal rag-bull rider optimisation feature extraction signal detection rag-ROA-based Deep RNN EEG seizure detection spectral analysis Electrodiagnostics and other electrical measurement techniques riders medical signal processing epileptic seizures dimensionally reduced feature vector epileptic seizure detection probabilistic principal component analysis channel count increases neurophysiology Taylor-based delta amplitude modulation spectrogram support vector machines signal classification costly task Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Improving Robustness of Spectrogram Classifiers with neural stochastic Differential Equations

Improving Robustness of Spectrogram Classifiers with Neural ...

引用

IEEE Workshop on Machine Learning for signal processing

作者： Joel Brogan Olivera Kotevska Anibely Torres Sumit Jha Mark Adams Oak Ridge National Laboratory Oak Ridge TN USA

ISBN: (数字)9798350372250

ISBN: (纸本)9798350372267

signal analysis and classification is fraught with high levels of noise and perturbation. computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, these methods aren't designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring. Currently, these models can be brittle, which makes them susceptible to noisy input. This also means they have sub-optimal stability of explanation outputs. Experts and technicians using these models to make decisions in real world scenarios need assurance that a model is performing as it is supposed to. The classification or prediction outputs it generates should be sound and grounded, not likely to change in the presence of shifting noise landscapes. In this work, we explore the idea of neural stochastic Differential Equations (NSDE's) to improve the robustness of models trained to classify time series data and the effect of NSDE's on the explainability of outputs. We then test the effectiveness of these approaches by applying them to a non-intrusive load monitoring (NILM) dataset that consists of simulated harmonic signals injected into a real building.

关键词： Training Load monitoring Accuracy stochastic processes Differential equations Robustness Stability analysis Mathematical models Spectrogram Load modeling

来源：评论

学校读者我要写书评

暂无评论

Enhancing Arabic Text Classification: A Comparative Study of Machine Learning and Deep Learning Approaches 12

Enhancing Arabic Text Classification: A Comparative Study of...

引用

12th IEEE International Symposium on signal, image, Video, and Communications, ISIVC 2024

作者： Akhadam, Idriss Ayyad, Habib Hassan 2 University Mathematics Computer Science & Applications Laboratory Mohammedia Morocco

ISBN: (纸本)9798350385267

This paper presents a comprehensive pipeline that integrates machine learning (ML) and deep learning (DL) methods for Arabic text classification, achieving high accuracy. Our approach includes a detailed preprocessing phase,that involves tokenization, removal of non-Arabic words, stop words, punctuation, normalization of the Hamza character, and an optional stemming process. We utilize Bag of Words (BOW) and Term Frequency-Inverse Document Frequency (TF-IDF) for feature selection. Various ML and DL algorithms have been explored using the AL-Khaleej database, which contains 45500 arabic news documents. Performance evaluation on the testing set focuses on accuracy, precision, recall, and F1-score metrics. Our findings reveal that Logistic Regression and stochastic Gradient Descent (SGD) classifiers perform robustly with both feature extraction methods, achieving 97% accuracy. Linear Support Vector Classifier (SVC) shows a slight improvement with TF-IDF. Stemming's impact varies, with SVC improving to 98% accuracy without stemming using BOW. The Convolutional neural Network (CNN) models, particularly with word-level representation, achieve superior accuracy of 97%, indicating their effectiveness in capturing contextual nuances and semantic relationships. Our pipeline not only accurately classifies Arabic texts but also provides insights into the efficacy of preprocessing and feature selection techniques in Arabic language processing. The success of our pipeline underscores its potential as a pivotal contribution to the advancement of Arabic text classification. © 2024 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Detection of Motion Vector-Based Stegomalware in Video Files 1

引用

International Conference on computer vision and Machine Intelligence, CVMI 2022

作者： Nair, Sandra V. S. Arun Raj Kumar, P. Department of Computer Science and Engineering National Institute of Technology Calicut Kozhikode India

ISBN: (数字)9789811978678

ISBN: (纸本)9789811978661

Cybercriminals are increasingly using steganography to launch attacks on devices. The cyberattack is more threatening as steganography hides the embedded malware, if any, making it harder to detect by various anti-virus tools. Such malware is called stegomalware. Since video files are larger and have a complex structure, they also have a high capacity for hiding malware. Motion vector (MV)-based steganography techniques do not cause much distortion in video files. Therefore, it remains to be one of the leading video steganography techniques. This paper deals with a lightweight solution for MV-based stegomalware detection in video files. Our model is compatible with state-of-the-art video coding standards having variable macroblock sizes and different motion vector resolutions. The proposed method obtained an accuracy of 95.8% on testing H.264 videos with various embedding rates. The 81-D spatial and temporal features result in the high performance of the proposed model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

IMPROVING ROBUSTNESS OF SPECTROGRAM CLASSIFIERS WITH neural stochastic DIFFERENTIAL EQUATIONS

arXiv

引用

arXiv 2024年

作者： Brogan, Joel Kotevska, Olivera Torres, Anibely Jha, Sumit Adams, Mark Oak Ridge National Laboratory 1 Bethel Valley Road Oak RidgeTN37831 United States

signal analysis and classification is fraught with high levels of noise and perturbation. computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection;however, these methods aren’t designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring. Currently, these models can be brittle, which makes them susceptible to noisy input. This also means they have sub-optimal stability of explanation outputs. Experts and technicians using these models to make decisions in real world scenarios need assurance that a model is performing as it is supposed to. The classification or prediction outputs it generates should be sound and grounded, not likely to change in the presence of shifting noise landscapes. In this work, we explore the idea of neural stochastic Differential Equations (NSDE’s) to improve the robustness of models trained to classify time series data and the effect of NSDE’s on the explainability of outputs. We then test the effectiveness of these approaches by applying them to a non-intrusive load monitoring (NILM) dataset that consists of simulated harmonic signals injected into a real building. © 2024, CC BY-NC-ND.

关键词： Spectrographs

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：