scholarly journals A Boosted 3-D PCA Algorithm Based on Efficient Analysis Method

2021 ◽  
Vol 11 (16) ◽  
pp. 7609
Author(s):  
Kyung-Min Lee ◽  
Chi-Ho Lin
Keyword(s):  
Cross Validation ◽  
Detection Methods ◽  
Second Step ◽  
Analysis Method ◽  
Image Detection ◽  
Adaboost Algorithm ◽  
Data Imbalance ◽  
Performance Problem ◽  
Pca Algorithm ◽  
Accuracy Performance

In this paper, we propose a boosted 3-D PCA algorithm based on an efficient analysis method. The proposed method involves three steps that improve image detection. In the first step, the proposed method designs a new analysis method to solve the performance problem caused by data imbalance. In the second step, a parallel cross-validation structure is used to enhance the new analysis method further. We also design a modified AdaBoost algorithm to improve the detector accuracy performance of the new analysis method. In order to verify the performance of this system, we experimented with a benchmark dataset. The results show that the new analysis method is more efficient than other image detection methods.

scholarly journals A UNIFIED COMMUNITY DETECTION, VISUALIZATION AND ANALYSIS METHOD

2014 ◽  
Vol 17 (01) ◽  
pp. 1450001 ◽  
Author(s):  
MICHEL CRAMPES ◽  
MICHEL PLANTIÉ
Keyword(s):  
Community Detection ◽  
Directed Graphs ◽  
Real Data ◽  
Semantic Interpretation ◽  
Detection Methods ◽  
Analysis Method ◽  
Overlapping Communities ◽  
Social Graphs ◽  
Tractography Data ◽  
Research Domain

With the widespread social networks on the Internet, community detection in social graphs has recently become an important research domain. Interest was initially limited to unipartite graph inputs and partitioned community outputs. More recently, bipartite graphs, directed graphs and overlapping communities have all been investigated. Few contributions however have encompassed all three types of graphs simultaneously. In this paper, we present a method that unifies community detection for these three types of graphs while at the same time it merges partitioned and overlapping communities. Moreover, the results are visualized in a way that allows for analysis and semantic interpretation. For validation purposes this method is experimented on some well-known simple benchmarks and then applied to real data: photos and tags in Facebook and Human Brain Tractography data. This last application leads to the possibility of applying community detection methods to other fields such as data analysis with original enhanced performances.

scholarly journals Shape Correspondence Analysis for Biomolecules Based on Volumetric Eigenfunctions

2015 ◽  
Vol 3 (1) ◽  
Author(s):  
Tao Liao ◽  
Hao-Chih Lee ◽  
Ge Yang ◽  
Yongjie Jessica Zhang
Keyword(s):  
Correspondence Analysis ◽  
Flexible Structures ◽  
Spectral Shape ◽  
The Other ◽  
Shape Deformation ◽  
Second Step ◽  
Analysis Method ◽  
Shape Correspondence ◽  
Dense Point ◽  
Different Shapes

AbstractThe functionality of biomolecules depends on their flexible structures, which can be characterized by their surface shapes. Tracking the deformation and comparing biomolecular shapes are essential in understanding their mechanisms. In this paper, a new spectral shape correspondence analysis method is introduced for biomolecules based on volumetric eigenfunctions. The eigenfunctions are computed from the joint graph of two given shapes, avoiding the sign flipping and confusion in the order of modes. An initial correspondence is built based on the distribution of a shape diameter, which matches similar surface features in different shapes and guides the eigenfunction computation. A two-step scheme is developed to determine the final correspondence. The first step utilizes volumetric eigenfunctions to correct the assignment of boundary nodes that disobeys the main structures. The second step minimizes the distortion induced by deforming one shape to the other. As a result, a dense point correspondence is constructed between the two given shapes, based on which we approximate and predict the shape deformation, as well as quantitatively measure the detailed shape differences.

scholarly journals A Mass Spectrometric Analysis Method Based on PPCA and SVM for Early Detection of Ovarian Cancer

2016 ◽  
Vol 2016 ◽  
pp. 1-6 ◽  
Author(s):  
Jiang Wu ◽  
Yanju Ji ◽  
Ling Zhao ◽  
Mengying Ji ◽  
Zhuang Ye ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Cancer Detection ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Analysis Method ◽  
Data Set ◽  
Specificity And Sensitivity ◽  
Svm Model ◽  
Tof Ms

Background. Surfaced-enhanced laser desorption-ionization-time of flight mass spectrometry (SELDI-TOF-MS) technology plays an important role in the early diagnosis of ovarian cancer. However, the raw MS data is highly dimensional and redundant. Therefore, it is necessary to study rapid and accurate detection methods from the massive MS data.Methods. The clinical data set used in the experiments for early cancer detection consisted of 216 SELDI-TOF-MS samples. An MS analysis method based on probabilistic principal components analysis (PPCA) and support vector machine (SVM) was proposed and applied to the ovarian cancer early classification in the data set. Additionally, by the same data set, we also established a traditional PCA-SVM model. Finally we compared the two models in detection accuracy, specificity, and sensitivity.Results. Using independent training and testing experiments 10 times to evaluate the ovarian cancer detection models, the average prediction accuracy, sensitivity, and specificity of the PCA-SVM model were 83.34%, 82.70%, and 83.88%, respectively. In contrast, those of the PPCA-SVM model were 90.80%, 92.98%, and 88.97%, respectively.Conclusions. The PPCA-SVM model had better detection performance. And the model combined with the SELDI-TOF-MS technology had a prospect in early clinical detection and diagnosis of ovarian cancer.

Prostate and dominant intraprostatic lesion segmentation on PET/CT using cascaded regional-net

2021 ◽  
Author(s):  
Luke A Matkovic ◽  
Tonghe Wang ◽  
Yang Lei ◽  
Oladunni O Akin-Akintayo ◽  
Olayinka A Abiodun Ojo ◽  
...  
Keyword(s):  
Radiation Therapy ◽  
Cross Validation ◽  
Ct Images ◽  
Second Step ◽  
Prostate Segmentation ◽  
Positron Emission ◽  
Pet Ct ◽  
The Mean ◽  
And Training ◽  
Fold Cross Validation

Abstract Focal dose boost to dominant intraprostatic lesions (DILs) has recently been proposed for prostate radiation therapy. Accurate and fast delineation of the prostate and DILs is thus required during treatment planning. We propose a learning-based method using positron emission tomography (PET)/computed tomography (CT) images to automatically segment the prostate and its DILs. To enable end-to-end segmentation, a deep learning-based method, called cascaded regional-Net, is utilized. The first network, referred to as dual attention network (DAN), is used to segment the prostate via extracting comprehensive features from both PET and CT images. A second network, referred to as mask scoring regional convolutional neural network (MSR-CNN), is used to segment the DILs from the PET and CT within the prostate region. Scoring strategy is used to diminish the misclassification of the DILs. For DIL segmentation, the proposed cascaded regional-Net uses two steps to remove normal tissue regions, with the first step cropping images based on prostate segmentation and the second step using MSR-CNN to further locate the DILs. The binary masks of DILs and prostates of testing patients are generated from PET/CT by the trained network. To evaluate the proposed method, we retrospectively investigated 49 PET/CT datasets. On each dataset, the prostate and DILs were delineated by physicians and set as the ground truths and training targets. The proposed method was trained and evaluated using a five-fold cross-validation and a hold-out test. The mean surface distance and DSC values were 0.666±0.696mm and 0.932±0.059 for the prostate and 1.209±1.954mm and 0.757±0.241 for the DILs among all 49 patients. The proposed method has demonstrated great potential for improving the efficiency and reducing the observer variability of prostate and DIL contouring for DIL focal boost prostate radiation therapy.

scholarly journals Traffic marking recognition based on generating antagonistic neural network

2019 ◽  
Vol 136 ◽  
pp. 04076 ◽  
Author(s):  
Shuwei Xu ◽  
Shan Zhang ◽  
Shuwei Xu
Keyword(s):  
Neural Network ◽  
Markov Chain ◽  
High Accuracy ◽  
Experimental Results ◽  
Detection Methods ◽  
Image Detection ◽  
Fast Recognition ◽  
Repeated Sampling ◽  
Backward Propagation ◽  
Traditional Image

This paper presents a method of extracting traffic lines from image images by GAN. Compared with the traditional image detection methods, the counter neural network does not need repeated sampling of Markov chain and adopts the method of backward propagation. Therefore, when detecting the image, GAN do not need to be updated with samples; it can produce better quality samples, express more clearly. Experimental results show that the method has strong generalization ability, fast recognition speed and high accuracy.

scholarly journals The Proposition and Evaluation of the RoEduNet-SIMARGL2021 Network Intrusion Detection Dataset

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4319
Author(s):  
Maria-Elena Mihailescu ◽  
Darius Mihai ◽  
Mihai Carabas ◽  
Mikołaj Komisarek ◽  
Marek Pawlicki ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Cross Validation ◽  
Real Life ◽  
Arms Race ◽  
Detection Methods ◽  
Network Intrusion Detection ◽  
Network Intrusion ◽  
Academic Network ◽  
The Stability

Cybersecurity is an arms race, with both the security and the adversaries attempting to outsmart one another, coming up with new attacks, new ways to defend against those attacks, and again with new ways to circumvent those defences. This situation creates a constant need for novel, realistic cybersecurity datasets. This paper introduces the effects of using machine-learning-based intrusion detection methods in network traffic coming from a real-life architecture. The main contribution of this work is a dataset coming from a real-world, academic network. Real-life traffic was collected and, after performing a series of attacks, a dataset was assembled. The dataset contains 44 network features and an unbalanced distribution of classes. In this work, the capability of the dataset for formulating machine-learning-based models was experimentally evaluated. To investigate the stability of the obtained models, cross-validation was performed, and an array of detection metrics were reported. The gathered dataset is part of an effort to bring security against novel cyberthreats and was completed in the SIMARGL project.

An Improved Motion Compensation Algorithm Based on Discriminant Analysis

2013 ◽  
Vol 850-851 ◽  
pp. 918-921
Author(s):  
Da Lei Song ◽  
Zhao Long Su ◽  
Yong Fang Wang ◽  
Li Ping Chen
Keyword(s):  
Discriminant Analysis ◽  
Motion Compensation ◽  
Cross Validation ◽  
Analysis Method ◽  
Experiment Data ◽  
Ocean Turbulence ◽  
Vibration Signals ◽  
Filter Order ◽  
Compensation Algorithm ◽  
Acceleration Signals

Considering the problem that vibration signals which are generated by three-axis accelerations will impact turbulence signal, an improved motion compensation algorithm based on discriminant analysis is proposed. The characteristics of three axis acceleration signals are got by using cross validation discriminant analysis method to test the performance of de-noising among different filtering orders which are got by three-axis accelerations vibration signals. Finally the discriminant function is found to get the optimal filter order. The results of simulation and real sea experiment data statistical analysis shows that the algorithm improves the de-noising performance and can be better applied to ocean turbulence signal de-noising processing.

Detection of Traffic and Road Condition Based on Adaboost

2013 ◽  
Vol 433-435 ◽  
pp. 1357-1360
Author(s):  
Shi Jie Jia ◽  
Yu Ting Zhai ◽  
Xiao Wei Jia
Keyword(s):  
Experimental Results ◽  
Image Feature ◽  
Detection Methods ◽  
Weather Factors ◽  
Edge Orientation ◽  
Adaboost Algorithm ◽  
The Road ◽  
Road Condition

In order to avoid the drawbacks of physical detection methods, such as spoiling the road, having complex algorithms and affected by weather factors, the detection methods of traffic and road condition are explored using the Adaboost algorithm and its three variants based on PHOG (pyramid histogram of edge orientation gradients) image feature. Experimental results show that this method can effectively classify 4 types of traffic and road condition images, and Gentle Adaboost algorithm has the best performance for the noisy samples.

scholarly journals Automated Attendance Monitoring System using Face Detection and RFID Cards

2020 ◽  
Vol 9 (8) ◽  
pp. 539-544
Keyword(s):  
Monitoring System ◽  
Face Detection ◽  
Radio Frequency Identification ◽  
Traditional Approach ◽  
Second Step ◽  
Automatic Process ◽  
Adaboost Algorithm ◽  
Cascade Classifiers ◽  
The Face ◽  
Frequency Identification

The attendance serves the most important role in the academic life of any student. Most of the colleges follow the traditional approach of attendance in which the professor speaks out student’s name and record attendance. For each lecture, this repetition of attendance calling is actually wastage of time and a time-taken procedure for calculating attendance of each student. Here an automatic process is proposed which is based on image processing with radio-frequency identification to avoid the losses. In this project approach, there is a use of face detection & RFID cards. Firstly, use the pre-processing step for the face detection and RFID receiver for the RFID cards counting and the second step is to detect, recognize and then the face is matched with stored images in the database. In this paper, viola-Jones algorithm is used for face detection, in which first step of integral image is used for feature computation and Adaboost algorithm is used for feature selection in second step. Then for discarding the non-faces, cascade classifiers is used in the third step of algorithm. The working of this project is to detect and recognize the face and RFID cards then mark the attendance for the corresponding face in the database on matching the face and unique number to the stored dataset. Face detection and RFID cards will be used as input and the attendance will be marked as output. This project is being conferred as a clarification for the “Automated attendance monitoring system.” Here a system of automatic face detection and recognition is proposed to mark the attendance automatically in database. This will save the time of person who is using traditional pen & paper based approach for attendance and hence is a solution for the automated attendance monitoring system. RFID cards are very helpful here for tracking or monitoring the student/teacher/employees within the campus. This system can be used in schools, colleges for students as well as for teachers also and it can be also used in companies, hospitals and malls for maintain records of accurate attendance of their employees.

Sign in / Sign up

Export Citation Format

Share Document