Exploring Classification Capability of CNN Features

2021 ◽  
pp. 268-282
Author(s):  
Shan Wang ◽  
Yue Wang ◽  
Qilong Zhao ◽  
Zhijiang Yang ◽  
Weiyu Guo ◽  
...  
Keyword(s):  
Classification Capability

Chaotic Liquid State Machine

2015 ◽  
Vol 9 (4) ◽  
pp. 1-20
Author(s):  
Mario Antoine Aoun ◽  
Mounir Boukadoum
Keyword(s):  
Liquid State ◽  
State Machine ◽  
Spiking Neurons ◽  
Signature Verification ◽  
Time Varying ◽  
Plasticity Mechanism ◽  
Online Signature ◽  
Online Signature Verification ◽  
One Class Classifier ◽  
Classification Capability

The authors implement a Liquid State Machine composed from a pool of chaotic spiking neurons. Furthermore, a synaptic plasticity mechanism operates on the connection weights between the neurons inside the pool. A special feature of the system's classification capability is that it can learn the class of a set of time varying inputs when trained from positive examples only, thus, it is a one class classifier. To demonstrate the applicability of this novel neurocomputing architecture, the authors apply it for Online Signature Verification.

Robust and discriminative dictionary learning for face recognition

2018 ◽  
Vol 16 (02) ◽  
pp. 1840004 ◽  
Author(s):  
Guojun Lin ◽  
Meng Yang ◽  
Linlin Shen ◽  
Mingzhong Yang ◽  
Mei Xie
Keyword(s):  
Face Recognition ◽  
Facial Expressions ◽  
Dictionary Learning ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Face Images ◽  
Proposed Model ◽  
Classification Capability ◽  
Discriminative Dictionary Learning

For face recognition, conventional dictionary learning (DL) methods have some disadvantages. First, face images of the same person vary with facial expressions and pose, illumination and disguises, so it is hard to obtain a robust dictionary for face recognition. Second, they don’t cover important components (e.g., particularity and disturbance) completely, which limit their performance. In the paper, we propose a novel robust and discriminative DL (RDDL) model. The proposed model uses sample diversities of the same face image to learn a robust dictionary, which includes class-specific dictionary atoms and disturbance dictionary atoms. These atoms can well represent the data from different classes. Discriminative regularizations on the dictionary and the representation coefficients are used to exploit discriminative information, which improves effectively the classification capability of the dictionary. The proposed RDDL is extensively evaluated on benchmark face image databases, and it shows superior performance to many state-of-the-art dictionary learning methods for face recognition.

scholarly journals A novel bioinformatics approach to identify the consistently well-performing normalization strategy for current metabolomic studies

2019 ◽  
Vol 21 (6) ◽  
pp. 2142-2152 ◽  
Author(s):  
Qingxia Yang ◽  
Jiajun Hong ◽  
Yi Li ◽  
Weiwei Xue ◽  
Song Li ◽  
...  
Keyword(s):  
Biological Variation ◽  
Cubic Splines ◽  
Multiple Criteria ◽  
Technical Error ◽  
Normalization Strategy ◽  
Novel Approach ◽  
Normalization Methods ◽  
Classification Capability ◽  
New Strategies ◽  
Marker Stability

Abstract Unwanted experimental/biological variation and technical error are frequently encountered in current metabolomics, which requires the employment of normalization methods for removing undesired data fluctuations. To ensure the ‘thorough’ removal of unwanted variations, the collective consideration of multiple criteria (‘intragroup variation’, ‘marker stability’ and ‘classification capability’) was essential. However, due to the limited number of available normalization methods, it is extremely challenging to discover the appropriate one that can meet all these criteria. Herein, a novel approach was proposed to discover the normalization strategies that are consistently well performing (CWP) under all criteria. Based on various benchmarks, all normalization methods popular in current metabolomics were ‘first’ discovered to be non-CWP. ‘Then’, 21 new strategies that combined the ‘sample’-based method with the ‘metabolite’-based one were found to be CWP. ‘Finally’, a variety of currently available methods (such as cubic splines, range scaling, level scaling, EigenMS, cyclic loess and mean) were identified to be CWP when combining with other normalization. In conclusion, this study not only discovered several strategies that performed consistently well under all criteria, but also proposed a novel approach that could ensure the identification of CWP strategies for future biological problems.

scholarly journals Identification of CTQs for Complex Products Based on Mutual Information and Improved Gravitational Search Algorithm

2015 ◽  
Vol 2015 ◽  
pp. 1-6 ◽  
Author(s):  
Huaqiang Wang ◽  
Lijun Liang ◽  
Zhanwen Niu ◽  
Zhen He
Keyword(s):  
Mutual Information ◽  
Search Algorithm ◽  
Gravitational Search Algorithm ◽  
Hybrid Approach ◽  
Data Sets ◽  
Complex Products ◽  
Information Relevance ◽  
Tenfold Cross Validation ◽  
Gravitational Search ◽  
Classification Capability

The identification of CTQs for complex products is the first step to implement quality control. To improve the efficiency and accuracy of CTQs identification, we propose a novel hybrid approach based on mutual information and improved gravitational search algorithm, which has advantages of filter and wrapper. At first, the information relevance and redundancy are measured by mutual information. Then, the improved gravitational search algorithm is used to search the CTQs. Experimentation is carried out using 2 UCI data sets, and the classification capability of CTQs is tested by SVM and tenfold cross validation. The results show that the presented method is verified to be effective and practically applicable.

scholarly journals Constructing decision rules from naive bayes model for robust and low complexity classification

2021 ◽  
Vol 7 (1) ◽  
pp. 76
Author(s):  
Nabeel Hashim Al-Aaraji ◽  
Safaa Obayes Al-Mamory ◽  
Ali Hashim Al-Shakarchi
Keyword(s):  
Naive Bayes ◽  
Decision Rules ◽  
Low Complexity ◽  
Naïve Bayes ◽  
Bayes Model ◽  
Coverage Accuracy ◽  
Rule Set ◽  
Classification Tasks ◽  
M Estimate ◽  
Classification Capability

A large spectrum of classifiers has been described in the literature. One attractive classification technique is a Naïve Bayes (NB) which has been relayed on probability theory. NB has two major limitations: First, it requires to rescan the dataset and applying a set of equations each time to classify instances, which is an expensive step if a dataset is relatively large. Second, NB may remain challenging for non-statisticians to understand the deep work of a model. On the other hand, Rule-Based classifiers (RBCs) have used IF-THEN rules (henceforth, rule-set), which are more comprehensible and less complex for classification tasks. For elevating NB limitations, this paper presents a method for constructing a rule-set from the NB model, which serves as RBC. Experiments of the constructing rule-set have been conducted on (Iris, WBC, Vote) datasets. Coverage, Accuracy, M-Estimate, and Laplace are crucial evaluation metrics that have been projected to rule-set. In some datasets, the rule-set obtains significant accuracy results that reach 95.33 %, 95.17% for Iris and vote datasets, respectively. The constructed rule-set can mimic the classification capability of NB, provide a visual representation of the model, express rules infidelity with acceptable accuracy; an easier method to interpreting and adjusting from the original model. Hence, the rule-set will provide a comprehensible and lightweight model than NB itself.

scholarly journals Improved Faster R-CNN Traffic Sign Detection Based on a Second Region of Interest and Highly Possible Regions Proposal Network

Sensors ◽  
2019 ◽  
Vol 19 (10) ◽  
pp. 2288 ◽  
Author(s):  
Faming Shao ◽  
Xinqing Wang ◽  
Fanjie Meng ◽  
Jingwei Zhu ◽  
Dong Wang ◽  
...  
Keyword(s):  
A Priori ◽  
Region Of Interest ◽  
Traffic Sign ◽  
Detection Systems ◽  
Proposal A ◽  
Sign Detection ◽  
Priori Information ◽  
Small Targets ◽  
Traffic Sign Detection ◽  
Classification Capability

Traffic sign detection systems provide important road control information for unmanned driving systems or auxiliary driving. In this paper, the Faster region with a convolutional neural network (R-CNN) for traffic sign detection in real traffic situations has been systematically improved. First, a first step region proposal algorithm based on simplified Gabor wavelets (SGWs) and maximally stable extremal regions (MSERs) is proposed. In this way, the region proposal a priori information is obtained and will be used for improving the Faster R-CNN. This part of our method is named as the highly possible regions proposal network (HP-RPN). Second, in order to solve the problem that the Faster R-CNN cannot effectively detect small targets, a method that combines the features of the third, fourth, and fifth layers of VGG16 to enrich the features of small targets is proposed. Third, the secondary region of interest method to enhance the feature of detection objects and improve the classification capability of the Faster R-CNN is proposed. Finally, a method of merging the German traffic sign detection benchmark (GTSDB) and Chinese traffic sign dataset (CTSD) databases into one larger database to increase the number of database samples is proposed. Experimental results show that our method improves the detection performance, especially for small targets.

Sign in / Sign up

Export Citation Format

Share Document