Experiment of OCITN: Considering Appropriate Goal Images and Metric for One-Class Image Transformation Network

2021 ◽  
Author(s):  
Toshitaka Hayashi ◽  
Hamido Fujita
Keyword(s):  
Image Data ◽  
Classification Problem ◽  
Model Error ◽  
Input Image ◽  
Training Data ◽  
Distance Metric ◽  
Image Transformation ◽  
Image Entropy ◽  
Image Metrics ◽  
One Class Classification

One-class classification (OCC) is a classification problem where training data includes only one class. In such a problem, two types of classes exist, seen class and unseen class, and classifying these classes is a challenge. Besides, One-class Image Transformation Network (OCITN) is an OCC algorithm for image data. In which, image transformation network (ITN) is trained. ITN aims to transform all input image into one image, namely goal image. Moreover, the model error of ITN is computed as a distance metric between ITN output and a goal image. Besides, OCITN accuracy is related to goal image, and finding an appropriate goal image is challenging. In this paper, 234 goal images are experimented with in OCITN using the CIFAR10 dataset. Experiment results are analyzed with three image metrics: image entropy, similarity with seen images, and image derivatives.

An improved one-class support vector machine classifier for outlier detection

2014 ◽  
Vol 229 (3) ◽  
pp. 580-588 ◽  
Author(s):  
Wenjuan An ◽  
Mangui Liang ◽  
He Liu
Keyword(s):  
Outlier Detection ◽  
Support Vector Machine Classifier ◽  
Dimensional Space ◽  
Classification Problem ◽  
Training Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Higher Dimensional ◽  
Real World Datasets ◽  
One Class Classification

Outlier detection, as a type of one-class classification problem, is one of important research topics in data mining and machine learning. Its task is to identify sample points markedly deviating from the normal data. A reliable outlier detector needs to build a model which encloses the normal data tightly. In this paper, an improved one-class SVM (OC-SVM) classifier is proposed for outlier detection problems. We name this method OC-SVM with minimum within-class scatter (OC-WCSSVM), which exploits the inner-class structure of the training set via minimizing the within-class scatter of the training data. This can construct a more accurate hyperplane for outlier detection, such that the margin between the training data and the origin in a higher dimensional space is as large as possible, while at the same time the decision boundary around the normal data is as tight as possible. Experimental results on a synthetic dataset and 10 real-world datasets demonstrate that our proposed OC-WCSSVM algorithm is effective and superior to the compared algorithms.

scholarly journals Deteksi Penyakit Dengue Hemorrhagic Fever dengan Pendekatan One Class Classification

2017 ◽  
Vol 3 (2) ◽  
pp. 129
Author(s):  
Zida Ziyan Azkiya ◽  
Fatma Indriani ◽  
Heru Kartika Chandra
Keyword(s):  
Support Vector Machine ◽  
Dengue Hemorrhagic Fever ◽  
Hemorrhagic Fever ◽  
Classification Problem ◽  
Training Data ◽  
Classification Model ◽  
Support Vector ◽  
Single Class ◽  
One Class Classification

Abstrak— Pada kasus deteksi penderita penyakit demam berdarah (Dengue Hemorrhagic Fever- DHF), data training yang tersedia umumnya hanya data pasien penderita positif. Sedangkan data orang normal (data negatif) tidak tersedia secara khusus. Pada makalah ini dipaparkan pembangunan model klasifikasi untuk deteksi DHF dengan pendekatan One Class Classification (OCC). Data yang digunakan pada penelitian ini adalah hasil uji darah dari laboratorium dari pasien penderita penyakit demam berdarah. Metode yang diteliti adalah One-class Support Vector Machine dan K-Means. Hasil yang diperoleh pada penelitian ini adalah untuk metode SVM memiliki nilai precision = 1,0, recall = 0,993, f-1 score = 0,997, dan tingkat akurasi sebesar 99,7%  sedangkan dengan metode K-Means diperoleh nilai precision = 0,901, recall = 0,973, f-1 score = 0,936, dan tingkat akurasi sebesar 93,3%. Hal ini  menunjukkan bahwa metode SVM sedikit lebih unggul dibandingkan dengan K-Means untuk kasus ini. Kata Kunci— demam berdarah, Dengue Hemorrhagic Fever, K-Means, One Class Classification, OSVMAbstract— Two class classification problem maps input into two target classes. In certain cases, training data is available only in the form of a single class, as in the case of Dengue Hemorrhagic Fever (DHF) patients, where only data of positive patients is available. In this paper, we report our experiment in building a classification model for detecting DHF infection using One Class Classification (OCC) approach. Data from this study is sourced from laboratory tests of patients with dengue fever. The OCC methods compared are One-Class Support Vector Machine and One-Class K-Means. The result shows SVM method obtained precision value = 1.0, recall = 0.993, f-1 score = 0.997, and accuracy of 99.7% while the K-Means method obtained precision value = 0.901, recall = 0.973, f- 1 score = 0.936, and accuracy of 93.3%. This indicates that the SVM method is slightly superior to K-Means for One-Class Classification of DHF patients. Keywords— Dengue Hemorrhagic Fever, K-Means, One Class Classification, OSVM

scholarly journals U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2611
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Intellectual Property ◽  
Object Detection ◽  
Image Data ◽  
Learning Technologies ◽  
Training Data ◽  
Learning Models ◽  
Ecological Data ◽  
Single Class ◽  
Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

scholarly journals Unsupervised content-preserving transformation for optical microscopy

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Xinyang Li ◽  
Guoxun Zhang ◽  
Hui Qiao ◽  
Feng Bao ◽  
Yue Deng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optical Microscopy ◽  
Training Data ◽  
Fluorescence Labeling ◽  
Imaging Data ◽  
Image Transformation ◽  
General Applicability ◽  
Data Annotation ◽  
Biomedical Image ◽  
Wide Range

AbstractThe development of deep learning and open access to a substantial collection of imaging data together provide a potential solution for computational image transformation, which is gradually changing the landscape of optical imaging and biomedical research. However, current implementations of deep learning usually operate in a supervised manner, and their reliance on laborious and error-prone data annotation procedures remains a barrier to more general applicability. Here, we propose an unsupervised image transformation to facilitate the utilization of deep learning for optical microscopy, even in some cases in which supervised models cannot be applied. Through the introduction of a saliency constraint, the unsupervised model, named Unsupervised content-preserving Transformation for Optical Microscopy (UTOM), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. UTOM shows promising performance in a wide range of biomedical image transformation tasks, including in silico histological staining, fluorescence image restoration, and virtual fluorescence labeling. Quantitative evaluations reveal that UTOM achieves stable and high-fidelity image transformations across different imaging conditions and modalities. We anticipate that our framework will encourage a paradigm shift in training neural networks and enable more applications of artificial intelligence in biomedical imaging.

scholarly journals Improved YOLO Network for Free-Angle Remote Sensing Target Detection

2021 ◽  
Vol 13 (11) ◽  
pp. 2171
Author(s):  
Yuhao Qing ◽  
Wenyi Liu ◽  
Liuyan Feng ◽  
Wanjia Gao
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
Target Detection ◽  
Multiple Scales ◽  
Classification Problem ◽  
Input Image ◽  
Detection Accuracy ◽  
Feature Maps ◽  
Regression Problem ◽  
Public Datasets

Despite significant progress in object detection tasks, remote sensing image target detection is still challenging owing to complex backgrounds, large differences in target sizes, and uneven distribution of rotating objects. In this study, we consider model accuracy, inference speed, and detection of objects at any angle. We also propose a RepVGG-YOLO network using an improved RepVGG model as the backbone feature extraction network, which performs the initial feature extraction from the input image and considers network training accuracy and inference speed. We use an improved feature pyramid network (FPN) and path aggregation network (PANet) to reprocess feature output by the backbone network. The FPN and PANet module integrates feature maps of different layers, combines context information on multiple scales, accumulates multiple features, and strengthens feature information extraction. Finally, to maximize the detection accuracy of objects of all sizes, we use four target detection scales at the network output to enhance feature extraction from small remote sensing target pixels. To solve the angle problem of any object, we improved the loss function for classification using circular smooth label technology, turning the angle regression problem into a classification problem, and increasing the detection accuracy of objects at any angle. We conducted experiments on two public datasets, DOTA and HRSC2016. Our results show the proposed method performs better than previous methods.

scholarly journals Brain Activity-Based Metrics for Assessing Learning States in VR under Stress among Firefighters: An Explorative Machine Learning Approach in Neuroergonomics

2021 ◽  
Vol 11 (7) ◽  
pp. 885
Author(s):  
Maher Abujelala ◽  
Rohith Karthikeyan ◽  
Oshin Tyagi ◽  
Jing Du ◽  
Ranjana K. Mehta
Keyword(s):  
Machine Learning ◽  
Environmental Conditions ◽  
Brain Activity ◽  
Memory Task ◽  
Classification Problem ◽  
Brain Regions ◽  
Training Data ◽  
Information Encoding ◽  
Machine Learning Approach ◽  
Encoding And Retrieval

The nature of firefighters` duties requires them to work for long periods under unfavorable conditions. To perform their jobs effectively, they are required to endure long hours of extensive, stressful training. Creating such training environments is very expensive and it is difficult to guarantee trainees’ safety. In this study, firefighters are trained in a virtual environment that includes virtual perturbations such as fires, alarms, and smoke. The objective of this paper is to use machine learning methods to discern encoding and retrieval states in firefighters during a visuospatial episodic memory task and explore which regions of the brain provide suitable signals to solve this classification problem. Our results show that the Random Forest algorithm could be used to distinguish between information encoding and retrieval using features extracted from fNIRS data. Our algorithm achieved an F-1 score of 0.844 and an accuracy of 79.10% if the training and testing data are obtained at similar environmental conditions. However, the algorithm’s performance dropped to an F-1 score of 0.723 and accuracy of 60.61% when evaluated on data collected under different environmental conditions than the training data. We also found that if the training and evaluation data were recorded under the same environmental conditions, the RPM, LDLPFC, RDLPFC were the most relevant brain regions under non-stressful, stressful, and a mix of stressful and non-stressful conditions, respectively.

scholarly journals A Framework for Leveraging Image Security in Cloud with Simultaneous Compression and Encryption Using Compressive Sensing

2021 ◽  
Vol 35 (1) ◽  
pp. 85-91
Author(s):  
Naga Raju Hari Manikyam ◽  
Munisamy Shyamala Devi
Keyword(s):  
Compressive Sensing ◽  
Image Data ◽  
Input Image ◽  
Security And Privacy ◽  
Cloud Infrastructure ◽  
Security Framework ◽  
Image Security ◽  
Compression Performance ◽  
Security Algorithm ◽  
Simultaneous Sensing

In the contemporary era, technological innovations like cloud computing and Internet of Things (IoT) pave way for diversified applications producing multimedia content. Especially large volumes of image data, in medical and other domains, are produced. Cloud infrastructure is widely used to reap benefits such as scalability and availability. However, security and privacy of imagery is in jeopardy when outsourced it to cloud directly. Many compression and encryption techniques came into existence to improve performance and security. Nevertheless, in the wake of emergence of quantum computing in future, there is need for more secure means with multiple transformations of data. Compressive sensing (CS) used in existing methods to improve security. However, most of the schemes suffer from the problem of inability to perform compression and encryption simultaneously besides ending up with large key size. In this paper, we proposed a framework known as Cloud Image Security Framework (CISF) leveraging outsourced image security. The framework has an underlying algorithm known as Hybrid Image Security Algorithm (HISA). It is based on compressive sensing, simultaneous sensing and encryption besides random pixel exchange to ensure multiple transformations of input image. The empirical study revealed that the CISF is more effective, secure with acceptable compression performance over the state of the art methods.

scholarly journals A Novel Convolutional Neural Network for Classifying Indian Coins by Denomination

2021 ◽  
Author(s):  
Yash Chauhan ◽  
Prateek Singh
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Academic Research ◽  
High Volume ◽  
Classification Problem ◽  
General Purpose ◽  
Training Data ◽  
Slot Machines ◽  
Validation Data ◽  
Starting Point

Coins recognition systems have humungous applications from vending and slot machines to banking and management firms which directly translate to a high volume of research regarding the development of methods for such classification. In recent years, academic research has shifted towards a computer vision approach for sorting coins due to the advancement in the field of deep learning. However, most of the documented work utilizes what is known as ‘Transfer Learning’ in which we reuse a pre-trained model of a fixed architecture as a starting point for our training. While such an approach saves us a lot of time and effort, the generic nature of the pre-trained model can often become a bottleneck for performance on a specialized problem such as coin classification. This study develops a convolutional neural network (CNN) model from scratch and tests it against a widely-used general-purpose architecture known as Googlenet. We have shown in this study by comparing the performance of our model with that of Googlenet (documented in various previous studies) that a more straightforward and specialized architecture is more optimal than a more complex general architecture for the coin classification problem. The model developed in this study is trained and tested on 720 and 180 images of Indian coins of different denominations, respectively. The final accuracy gained by the model is 91.62% on the training data, while the accuracy is 90.55% on the validation data.

scholarly journals Lightweight Convolutional Neural Network Based Intrusion Detection System

2020 ◽  
pp. 808-817
Author(s):  
Vinh Pham ◽  
◽  
Eunil Seo ◽  
Tai-Myoung Chung
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Intrusion Detection ◽  
Convolutional Neural Network ◽  
Network Traffic ◽  
Detection System ◽  
Image Data ◽  
Training Data ◽  
Deep Packet Inspection ◽  
Detection Model

Identifying threats contained within encrypted network traffic poses a great challenge to Intrusion Detection Systems (IDS). Because traditional approaches like deep packet inspection could not operate on encrypted network traffic, machine learning-based IDS is a promising solution. However, machine learning-based IDS requires enormous amounts of statistical data based on network traffic flow as input data and also demands high computing power for processing, but is slow in detecting intrusions. We propose a lightweight IDS that transforms raw network traffic into representation images. We begin by inspecting the characteristics of malicious network traffic of the CSE-CIC-IDS2018 dataset. We then adapt methods for effectively representing those characteristics into image data. A Convolutional Neural Network (CNN) based detection model is used to identify malicious traffic underlying within image data. To demonstrate the feasibility of the proposed lightweight IDS, we conduct three simulations on two datasets that contain encrypted traffic with current network attack scenarios. The experiment results show that our proposed IDS is capable of achieving 95% accuracy with a reasonable detection time while requiring relatively small size training data.

scholarly journals Identifikasi Kesegaran Ikan Nila menggunakan Teknik Citra Digital

2020 ◽  
Vol 2 (1) ◽  
pp. 6-10
Author(s):  
Juli Elprida Hutagalung ◽  
Mhd Ihsan Pohan ◽  
Yuli Happy Marpaung
Keyword(s):  
Least Squares ◽  
Least Squares Method ◽  
Image Data ◽  
The Body ◽  
Training Data ◽  
Application System ◽  
Fresh Fish ◽  
Average Value ◽  
Color Changes ◽  
Image Format

Fish contain many nutrients that are very beneficial for the body, but often fish are traded in a state of death as well as being alive. To observe the freshness of tilapia is done by the introduction of color changes that appear on digital images using the least squares method. The purpose of this research is to build an image management application system to detect the freshness of tilapia. The data used are 10 samples of tilapia images which are photographed every 1 hour for 15 hours and obtained 150 image data and then processed and analyzed using the least squares method. The first process begins with image processing by cropping at the edge of the eye of the original image and then proceed with resizing to 1000 x 1000 pixels and changing the image format to *. Png. After the image has been processed then the average value is calculated rata grayscale uses the 'rata_rata Gambar' application system and an equation is stored which is stored as training data on the application system. After the image has been processed then the image is input into the system, the image will be converted into grayscale form and displayed at a predetermined place together with the rgb and grayscale histograms and then calculated using the least squares method. The last process we do is matching the test image with the image stored as training data and we conclude whether the image is (very fresh, fresh, fresh enough, not fresh, or very not fresh), the percentage of freshness of the anchor fish, and the length of time the anchor fish dies. This study used 150 samples of fish images from fresh fish that were still very fresh until the fish were not very fresh (rotten).

Sign in / Sign up

Export Citation Format

Share Document