scholarly journals Understanding convolutional neural networks via discriminant feature analysis

2018 ◽  
Vol 7 ◽  
Author(s):  
Hao Xu ◽  
Yueru Chen ◽  
Ruiyuan Lin ◽  
C.-C. Jay Kuo
Keyword(s):  
Feature Representation ◽  
Feature Analysis ◽  
Individual Feature ◽  
Discriminative Ability ◽  
Multiple Features ◽  
Operational Mechanism ◽  
The Past ◽  
Quantitative Metrics ◽  
Cluster Purity ◽  
Good Detection

Trained features of a convolution neural network (CNN) at different convolution layers is analyzed using two quantitative metrics in this work. We first show mathematically that the Gaussian confusion measure (GCM) can be used to identify the discriminative ability of an individual feature. Next, we generalize this idea, introduce another measure called the cluster purity measure (CPM), and use it to analyze the discriminative ability of multiple features jointly. The discriminative ability of trained CNN features is validated by experimental results. Research on CNNs utilizing GCM and CPM tools offers important insights into its operational mechanism, including the behavior of trained CNN features and good detection performance of some object classes that were considered difficult in the past. Finally, the trained feature representation is compared between different CNN structures to explain the superiority of deeper networks.

scholarly journals Evaluating Metrics Applied to the Medical Science Liaison (MSL) Role: A Survey-Based Study of Canadian MSL Leaders

2021 ◽  
Author(s):  
Munaza Saleem ◽  
Lisa Cesario ◽  
Lisa Wilcox ◽  
Marsha Haynes ◽  
Simon Collin ◽  
...  
Keyword(s):  
Health Care ◽  
Health Care Professional ◽  
Online Survey ◽  
Medical Science ◽  
Specialty Care ◽  
Product Lifecycle ◽  
The Past ◽  
Data Analyses ◽  
Quantitative Metrics ◽  
Frequency Of Use

Abstract Introduction Metrics utilized within the Medical Science Liaison (MSL) role are plentiful and traditionally quantitative. We sought to understand the current use and value of metrics applied to the MSL role, including the use of qualitative metrics. Methods We developed a list of 70 MSL leaders working in Canada, spanning 29 companies. Invitations were emailed Jun 16, 2020 and the 25-question online survey was open for 3 weeks. Questions were designed to assess demographics as well as how and why metrics are applied to the MSL role. Data analyses were descriptive. Results Responses were received from 44 leaders (63%). Of the 42 eligible, 45% had ≤ 2 years of experience as MSL leaders and 86% supported specialty care products over many phases of the product lifecycle. A majority (69%) agreed or strongly agreed that metrics are critical to understanding whether an MSL is delivering value, and 98% had used metrics in the past year. The most common reason to use metrics was ‘to show value/impact of MSLs to leadership’ (66%). The most frequently used metric was ‘number of health-care professional (HCP) interactions’, despite this being seen as having moderate value. Quantitative metrics were used more often than qualitative, although qualitative were more often highly valued. Conclusion The data collected show a lack of agreement between the frequency of use for some metrics and their value in demonstrating the contribution of an MSL. Overall, MSL leaders in our study felt qualitative metrics were a better means of showing the true impact of MSLs.

scholarly journals Channel and Spatial Attention Regression Network for Cup-to-Disc Ratio Estimation

Electronics ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 909
Author(s):  
Shuo Li ◽  
Chiru Ge ◽  
Xiaodan Sui ◽  
Yuanjie Zheng ◽  
Weikuan Jia
Keyword(s):  
Spatial Attention ◽  
Structural Changes ◽  
Contextual Information ◽  
Feature Representation ◽  
Feature Maps ◽  
Global Features ◽  
Discriminative Ability ◽  
Deep Learning Network ◽  
Relationship Of ◽  
Cup To Disc Ratio

Cup-to-disc ratio (CDR) is of great importance during assessing structural changes at the optic nerve head (ONH) and diagnosis of glaucoma. While most efforts have been put on acquiring the CDR number through CNN-based segmentation algorithms followed by the calculation of CDR, these methods usually only focus on the features in the convolution kernel, which is, after all, the operation of the local region, ignoring the contribution of rich global features (such as distant pixels) to the current features. In this paper, a new end-to-end channel and spatial attention regression deep learning network is proposed to deduces CDR number from the regression perspective and combine the self-attention mechanism with the regression network. Our network consists of four modules: the feature extraction module to extract deep features expressing the complicated pattern of optic disc (OD) and optic cup (OC), the attention module including the channel attention block (CAB) and the spatial attention block (SAB) to improve feature representation by aggregating long-range contextual information, the regression module to deduce CDR number directly, and the segmentation-auxiliary module to focus the model’s attention on the relevant features instead of the background region. Especially, the CAB selects relatively important feature maps in channel dimension, shifting the emphasis on the OD and OC region; meanwhile, the SAB learns the discriminative ability of feature representation at pixel level by capturing the relationship of intra-feature map. The experimental results of ORIGA dataset show that our method obtains absolute CDR error of 0.067 and the Pearson’s correlation coefficient of 0.694 in estimating CDR and our method has a great potential in predicting the CDR number.

scholarly journals On containment and syncretism in English preterites and participles

2019 ◽  
Vol 4 (1) ◽  
pp. 54
Author(s):  
Luke Adamson
Keyword(s):  
Feature Representation ◽  
Distributed Morphology ◽  
Past Participle ◽  
Virtual Absence ◽  
The Past ◽  
The Relationship

This study explores Bobaljik’s (2012) suggestion that in English, the feature representation of the preterite contains the representation of the past participle. While containment analyses in both Distributed Morphology (DM) and Nanosyntax capture the virtual absence of ABA patterns of syncretism for the order BASE-PARTICIPLE-PRETERITE, I demonstrate that they face empirical challenges when the exponence of the suffixes is considered. After evaluating an alternative feature decomposition, I show how a DM containment approach can derive the facts for both base and suffix alternations with the aid of impoverishment, which also helps to explain counterexamples to *ABA in this domain. Lastly, I offer cautionary discussion about the relationship between containment structures and deriving *ABA.

ACPred-Fuse: fusing multi-view information improves the prediction of anticancer peptides

2019 ◽  
Vol 21 (5) ◽  
pp. 1846-1855 ◽  
Author(s):  
Bing Rao ◽  
Chen Zhou ◽  
Guoying Zhang ◽  
Ran Su ◽  
Leyi Wei
Keyword(s):  
Anticancer Activity ◽  
Large Scale ◽  
Representation Learning ◽  
Feature Representation ◽  
Accurate Identification ◽  
Discriminative Ability ◽  
Anticancer Peptides ◽  
Probabilistic Information ◽  
Feature Descriptors ◽  
Comparison Results

Abstract Fast and accurate identification of the peptides with anticancer activity potential from large-scale proteins is currently a challenging task. In this study, we propose a new machine learning predictor, namely, ACPred-Fuse, that can automatically and accurately predict protein sequences with or without anticancer activity in peptide form. Specifically, we establish a feature representation learning model that can explore class and probabilistic information embedded in anticancer peptides (ACPs) by integrating a total of 29 different sequence-based feature descriptors. In order to make full use of various multiview information, we further fused the class and probabilistic features with handcrafted sequential features and then optimized the representation ability of the multiview features, which are ultimately used as input for training our prediction model. By comparing the multiview features and existing feature descriptors, we demonstrate that the fused multiview features have more discriminative ability to capture the characteristics of ACPs. In addition, the information from different views is complementary for the performance improvement. Finally, our benchmarking comparison results showed that the proposed ACPred-Fuse is more precise and promising in the identification of ACPs than existing predictors. To facilitate the use of the proposed predictor, we built a web server, which is now freely available via http://server.malab.cn/ACPred-Fuse.

scholarly journals Performing Arts and BarkaNaach of Dangaura Tharus as Folk Drama

2021 ◽  
Vol 3 (1) ◽  
pp. 26-33
Author(s):  
Megh Prasad Kharel
Keyword(s):  
Cultural Identity ◽  
Cultural Memory ◽  
Performing Arts ◽  
Musical Instruments ◽  
Community Based ◽  
Multiple Features ◽  
The Past ◽  
Rural Farmers ◽  
Folk Drama ◽  
Basic Features

This article examines different elements of folk drama in the BarkaNaach of Dangaura Tharus. It attempts to present the multiple features of the folk drama in the folk community. Based on the basic features of vernacular theatre, the study spotlights the key dramatic elements like ritual rule, context, narrative, stage and setting, characters and semiotic implication, song, dance and language as well as musical instruments and costumes in the presentation of BarkaNaach. The analysis of such drama in the light of elementary facet underlines the multiple sides of folklore as it embodies the cultural identity and value of Tharus. In doing so, I also argue that its theatrical aspects like plot and storyline are not unfamiliar to the rural farmers. Consequently, the study concludes that ritualistic performance of folk drama does not bring the unexpected happening, but it is repeated with their routinized act of cultural memory whatever performed in the past days of the ancestral force.

scholarly journals IR-MF-SVMe: Image Retrieval using Multiple Features Extraction with Support Vector Machine ensemble

2021 ◽  
Vol 15 ◽  
pp. 1781-1789
Author(s):  
Nayak K., Venkataravana ◽  
J. S. Arunalatha ◽  
K. R. Venugopal
Keyword(s):  
Support Vector Machines ◽  
Image Retrieval ◽  
Feature Representation ◽  
Gabor Wavelet ◽  
Support Vector ◽  
Shape Information ◽  
Discriminative Performance ◽  
Multiple Features ◽  
Vector Machines ◽  
The Individual

Image representation is a widespread strategy of image retrieval based on appearance, shape information. The traditional feature representation methods ignore hidden information that exists in the dataset samples; it reduces the discriminative performance of the classifier and excludes various geometric and photometric variations consideration in obtaining the features; these degrade retrieval performance. Hence, proposed multiple features fusion and Support Vector Machines Ensemble (IR-MF-SVMe); an Image Retrieval framework to enhance the performance of the retrieval process. The Color Histogram (CH), Color Auto-Correlogram (CAC), Color Moments (CM), Gabor Wavelet (GW), and Wavelet Moments (WM) descriptors are used to extract multiple features that separate the element vectors of images in representation. The multi-class classifier is constructed with the aggregation of binary Support Vector Machines, which decrease the count of false positives within the interrelated semantic classes. The proposed framework is validated on the WANG dataset and results in the accuracy of 84% for the individual features and 86% for the fused features related to the state-of-the-arts.

scholarly journals Siamese High-Level Feature Refine Network for Visual Object Tracking

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1918 ◽  
Author(s):  
Md. Maklachur Rahman ◽  
Md Rishad Ahmed ◽  
Lamyanba Laishram ◽  
Seock Ho Kim ◽  
Soon Ki Jung
Keyword(s):  
Visual Tracking ◽  
Feature Representation ◽  
Visual Object ◽  
Target Feature ◽  
Discriminative Ability ◽  
Visual Object Tracking ◽  
Discrimination Ability ◽  
Proposed Model ◽  
Real Time Tracking ◽  
High Level

Siamese network-based trackers are broadly applied to solve visual tracking problems due to its balanced performance in terms of speed and accuracy. Tracking desired objects in challenging scenarios is still one of the fundamental concerns during visual tracking. This research paper proposes a feature refined end-to-end tracking framework with real-time tracking speed and considerable performance. The feature refine network has been incorporated to enhance the target feature representation power, utilizing high-level semantic information. Besides, it allows the network to capture the salient information to locate the target and learns to represent the target feature in a more generalized way advancing the overall tracking performance, particularly in the challenging sequences. But, only the feature refine module is unable to handle such challenges because of its less discriminative ability. To overcome this difficulty, we employ an attention module inside the feature refine network that strengths the tracker discrimination ability between the target and background. Furthermore, we conduct extensive experiments to ensure the proposed tracker’s effectiveness using several popular tracking benchmarks, demonstrating that our proposed model achieves state-of-the-art performance over other trackers.

scholarly journals Pedestrian and Vehicle Detection in Autonomous Vehicle Perception Systems—A Review

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7267
Author(s):  
Luiz G. Galvao ◽  
Maysam Abbod ◽  
Tatiana Kalganova ◽  
Vasile Palade ◽  
Md Nazmul Huda
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Vehicle Detection ◽  
Weather Conditions ◽  
Detection Performance ◽  
The Past ◽  
Perception System ◽  
Good Detection

Autonomous Vehicles (AVs) have the potential to solve many traffic problems, such as accidents, congestion and pollution. However, there are still challenges to overcome, for instance, AVs need to accurately perceive their environment to safely navigate in busy urban scenarios. The aim of this paper is to review recent articles on computer vision techniques that can be used to build an AV perception system. AV perception systems need to accurately detect non-static objects and predict their behaviour, as well as to detect static objects and recognise the information they are providing. This paper, in particular, focuses on the computer vision techniques used to detect pedestrians and vehicles. There have been many papers and reviews on pedestrians and vehicles detection so far. However, most of the past papers only reviewed pedestrian or vehicle detection separately. This review aims to present an overview of the AV systems in general, and then review and investigate several detection computer vision techniques for pedestrians and vehicles. The review concludes that both traditional and Deep Learning (DL) techniques have been used for pedestrian and vehicle detection; however, DL techniques have shown the best results. Although good detection results have been achieved for pedestrians and vehicles, the current algorithms still struggle to detect small, occluded, and truncated objects. In addition, there is limited research on how to improve detection performance in difficult light and weather conditions. Most of the algorithms have been tested on well-recognised datasets such as Caltech and KITTI; however, these datasets have their own limitations. Therefore, this paper recommends that future works should be implemented on more new challenging datasets, such as PIE and BDD100K.

An Algorithm of early Smoke Detection Based on Multiple Features

2012 ◽  
Vol 457-458 ◽  
pp. 1254-1257
Author(s):  
Ming Xin Jiang ◽  
Xing Yang Cai ◽  
Hong Yu Wang
Keyword(s):  
Diffusion Process ◽  
False Alarm ◽  
False Alarm Rate ◽  
Detection Algorithm ◽  
Time Requirement ◽  
Dynamic Features ◽  
Smoke Detection ◽  
Multiple Features ◽  
Color Distribution ◽  
Good Detection

An early smoke detection algorithm based on Codebook model and multiple features is presented in this paper. First, the foreground is obtained by using the Codebook algorithm. Second, the model of color distribution and the model of shape feathers of smoke are applied to detect the suspected smoke area in the foreground. Finally, the false alarm rate is reduced effectively by using dynamic features in the diffusion process of smoke. Experimental results show that our algorithm has good detection performance and achieves real-time requirement which is very important for real application.

Sign in / Sign up

Export Citation Format

Share Document