scholarly journals Automatic Classification of Morphologically Similar Fish Species Using Their Head Contours

2020 ◽  
Vol 10 (10) ◽  
pp. 3408
Author(s):  
Pere Marti-Puig ◽  
Amalia Manjabacas ◽  
Antoni Lombarte
Keyword(s):  
Fish Species ◽  
Image Data ◽  
Classification Problem ◽  
Marine Resources ◽  
Data Sets ◽  
Similar Form ◽  
Multi Class Classification ◽  
Demersal Species ◽  
Do So

This work deals with the task of distinguishing between different Mediterranean demersal species of fish that share a remarkably similar form and that are also used for the evaluation of marine resources. The experts who are currently able to classify these types of species do so by considering only a segment of the contour of the fish, specifically its head, instead of using the entire silhouette of the animal. Based on this knowledge, a set of features to classify contour segments is presented to address both a binary and a multi-class classification problem. In addition to the difficulty present in successfully discriminating between very similar forms, we have the limitation of having small, unreliably labeled image data sets. The results obtained were comparable to those obtained by trained experts.

scholarly journals Distributed training and scalability for the particle clustering method UCluster

2021 ◽  
Vol 251 ◽  
pp. 02054
Author(s):  
Olga Sunneborn Gudnadottir ◽  
Daniel Gedon ◽  
Colin Desmarais ◽  
Karl Bengtsson Bernander ◽  
Raazesh Sainudiin ◽  
...  
Keyword(s):  
Particle Physics ◽  
Hadron Collider ◽  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Training Time ◽  
Distributed Training ◽  
Machine Learning Methods ◽  
Multi Class Classification

In recent years, machine-learning methods have become increasingly important for the experiments at the Large Hadron Collider (LHC). They are utilised in everything from trigger systems to reconstruction and data analysis. The recent UCluster method is a general model providing unsupervised clustering of particle physics data, that can be easily modified to provide solutions for a variety of different decision problems. In the current paper, we improve on the UCluster method by adding the option of training the model in a scalable and distributed fashion, and thereby extending its utility to learn from arbitrarily large data sets. UCluster combines a graph-based neural network called ABCnet with a clustering step, using a combined loss function in the training phase. The original code is publicly available in TensorFlow v1.14 and has previously been trained on a single GPU. It shows a clustering accuracy of 81% when applied to the problem of multi-class classification of simulated jet events. Our implementation adds the distributed training functionality by utilising the Horovod distributed training framework, which necessitated a migration of the code to TensorFlow v2. Together with using parquet files for splitting data up between different compute nodes, the distributed training makes the model scalable to any amount of input data, something that will be essential for use with real LHC data sets. We find that the model is well suited for distributed training, with the training time decreasing in direct relation to the number of GPU’s used. However, further improvements by a more exhaustive and possibly distributed hyper-parameter search is required in order to achieve the reported accuracy of the original UCluster method.

Enhanced Fusion of Deep Neural Networks for Classification of Benchmark High-Resolution Image Data Sets

2018 ◽  
Vol 15 (9) ◽  
pp. 1451-1455 ◽  
Author(s):  
Grant J. Scott ◽  
Kyle C. Hagan ◽  
Richard A. Marcum ◽  
James Alex Hurt ◽  
Derek T. Anderson ◽  
...  
Keyword(s):  
Neural Networks ◽  
High Resolution ◽  
Deep Neural Networks ◽  
Image Data ◽  
Data Sets ◽  
Resolution Image ◽  
High Resolution Image

Multi-layer Model Collaboration for Bioimage Temporal Stage Classification

2014 ◽  
Vol 08 (02) ◽  
pp. 123-144
Author(s):  
Tao Meng ◽  
Mei-Ling Shyu
Keyword(s):  
Image Data ◽  
Middle Level ◽  
Data Sets ◽  
Layer Model ◽  
Target Class ◽  
Current State ◽  
Integration Problem ◽  
Bioimage Analysis ◽  
Significant Patterns ◽  
Multi Class Classification

Nowadays, bioimages such as microscopic images and in situ hybridization images increase exponentially. The rapid growth of such images calls for efficient and effective methods for mining significant patterns in them. As a biological process usually consists of several temporal stages, one important task in bioimage analysis is to classify images into different stages. In this paper, a multi-layer model collaboration approach is proposed to capitalize the class correlations in order to enhance the multi-class classification accuracy. First, several middle-level classes, which are relatively easy to annotate are created. A set of subspace-based classifiers are trained. Next, the classification scores output from these models are integrated with the target class classification scores. The score integration problem was formulated as a convex optimization problem, which is solved by the gradient descent approach. Experiments on four biological image data sets demonstrate that the proposed framework outperforms other current state-of-the-art algorithms, which indicates the proposed framework is promising.

scholarly journals DISCRIMINATION OF URBAN SETTLEMENT TYPES BASED ON SPACE-BORNE SAR DATASETS AND A CONDITIONAL RANDOM FIELDS MODEL

2015 ◽  
Vol II-3/W4 ◽  
pp. 143-148 ◽  
Author(s):  
T. Novack ◽  
U. Stilla
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Residential Buildings ◽  
Classification Algorithms ◽  
Data Sets ◽  
Single Family ◽  
Urban Settlement ◽  
Membership Value ◽  
Multi Class Classification

In this work we focused on the classification of Urban Settlement Types (USTs) based on two datasets from the TerraSAR-X satellite acquired at ascending and descending look directions. These data sets comprise the intensity, amplitude and coherence images from the ascending and descending datasets. In accordance to most official UST maps, the urban blocks of our study site were considered as the elements to be classified. The considered USTs classes in this paper are: Vegetated Areas, Single-Family Houses and Commercial and Residential Buildings. Three different groups of image attributes were utilized, namely: Relative Areas, Histogram of Oriented Gradients and geometrical and contextual attributes extracted from the nodes of a Max-Tree Morphological Profile. These image attributes were submitted to three powerful soft multi-class classification algorithms. In this way, each classifier output a membership value to each of the classes. This membership values were then treated as the potentials of the unary factors of a Conditional Random Fields (CRFs) model. The pairwise factors of the CRFs model were parameterised with a Potts function. The reclassification performed with the CRFs model enabled a slight increase of the classification’s accuracy from 76% to 79% out of 1926 urban blocks.

scholarly journals Centrifuge: rapid and sensitive classification of metagenomic sequences

2016 ◽  
Author(s):  
Daehwan Kim ◽  
Li Song ◽  
Florian P. Breitwieser ◽  
Steven L. Salzberg
Keyword(s):  
High Speed ◽  
Classification Problem ◽  
Data Sets ◽  
Accurate Analysis ◽  
Desktop Computers ◽  
Metagenomics Data ◽  
High Throughput Dna Sequencing ◽  
Small Index ◽  
Burrows Wheeler Transform

AbstractCentrifuge is a novel microbial classification engine that enables rapid, accurate and sensitive labeling of reads and quantification of species on desktop computers. The system uses an indexing scheme based on the Burrows-Wheeler transform (BWT) and the Ferragina-Manzini (FM) index, optimized specifically for the metagenomic classification problem. Centrifuge requires a relatively small index (4.2 GB for 4,078 bacterial and 200 archaeal genomes) and classifies sequences at very high speed, allowing it to process the millions of reads from a typical high-throughput DNA sequencing run within a few minutes. Together these advances enable timely and accurate analysis of large metagenomics data sets on conventional desktop computers. Because of its space-optimized indexing schemes, Centrifuge also makes it possible to index the entire NCBI non-redundant nucleotide sequence database (a total of 109 billion bases) with an index size of 69 GB, in contrast to k-mer based indexing schemes, which require far more extensive space. Centrifuge is available as free, open-source software from www.ccb.jhu.edu/software/centrifuge

scholarly journals Classification of Fish Species with Image Data Using K-Nearest Neighbor

2021 ◽  
Vol 2 (2) ◽  
pp. 54-58
Author(s):  
Kaharuddin Kaharuddin ◽  
Eka Wahyu Sholeha
Keyword(s):  
Computer Science ◽  
Everyday Life ◽  
Fish Species ◽  
Nearest Neighbor ◽  
Image Data ◽  
Test Results ◽  
Shape Features ◽  
K Nearest Neighbor ◽  
The World

Abstract— Classification is a technique that many of us encounter in everyday life, classification science is also growing and being applied to various types of data and cases in everyday life, in computer science classification has been developed to facilitate human work, one example of its application is to classify fish species in the world, the number of fish species in the world is very much so that there are still many people who are sometimes confused to distinguish them, therefore in this study a study will be conducted to classify fish species using the K-Nearest Neighbor Method. 4 types of fish, all data totaling 160 data. The purpose of this study was to test the K-Nearest Neighbor method for classifying fish species based on color, texture, and shape features. Based on the test results, the accuracy value of the truth is obtained using the value of K = 7 with a percentage of the truth of 77.50%, the second-highest accuracy value is the value of K = 10, namely 76.88%. Based on the results of this study, it can be concluded that the K-Nearest Neighbor method has a good enough ability to classify, but it can be done by adding variables or adding more amount of data, and using other types of fish.

scholarly journals Dental Anomaly Detection Using Intraoral Photos Via Deep Learning

2021 ◽  
Author(s):  
Ronilo Ragodos ◽  
Tong Wang ◽  
Carmencita Padilla ◽  
Jacqueline Hecht ◽  
Fernando Poletta ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Dental Anomalies ◽  
Orofacial Clefting ◽  
Saliency Maps ◽  
Phenotypic Spectrum ◽  
Wide Range ◽  
Multi Class Classification ◽  
Post Hoc ◽  
Do So

Abstract Children with orofacial clefting (OFC) present with a wide range of dental anomalies. Identifying these anomalies is vital to understand their etiology and to discern the complex phenotypic spectrum of OFC. Such anomalies are currently identified using intra-oral exams by dentists, a costly and time-consuming process. We claim that automating the process of anomaly detection using deep neural networks (DNNs) could increase efficiency and provide reliable anomaly detection while potentially increasing the speed of research discovery. This study characterizes the use of` DNNs to identify dental anomalies by training a DNN model using intraoral photographs from the largest international cohort to date of children with nonsyndromic OFC and controls (OFC1). In this project, the intraoral images were submitted to a Convolutional Neural Network (CNN) model to perform multi-label multi-class classification of 10 dental anomalies. The network predicts whether an individual exhibits any of the 10 anomalies and is able to do so significantly faster than a human rater. For every anomaly except mammalons, F1 scores suggest that our model performs competitively at anomaly detection when compared to a dentist with 8 years of clinical experience. In addition, we use saliency maps to provide a post-hoc interpretation for our model’s predictions. This enables dentists to examine and verify our model’s predictions.

scholarly journals Multi-Class Classification of Lung Diseases Using CNN Models

2021 ◽  
Vol 11 (19) ◽  
pp. 9289
Author(s):  
Min Hong ◽  
Beanbonyka Rim ◽  
Hongchang Lee ◽  
Hyeonung Jang ◽  
Joonho Oh ◽  
...  
Keyword(s):  
Lung Diseases ◽  
Image Data ◽  
National Institutes Of Health ◽  
Fine Tuning ◽  
University Hospital ◽  
Improve Performance ◽  
Average Sensitivity ◽  
Average Accuracy ◽  
Multi Class Classification

In this study, we propose a multi-class classification method by learning lung disease images with Convolutional Neural Network (CNN). As the image data for learning, the U.S. National Institutes of Health (NIH) dataset divided into Normal, Pneumonia, and Pneumothorax and the Cheonan Soonchunhyang University Hospital dataset including Tuberculosis were used. To improve performance, preprocessing was performed with Center Crop while maintaining the aspect ratio of 1:1. As a Noisy Student of EfficientNet B7, fine-tuning learning was performed using the weights learned from ImageNet, and the features of each layer were maximally utilized using the Multi GAP structure. As a result of the experiment, Benchmarks measured with the NIH dataset showed the highest performance among the tested models with an accuracy of 85.32%, and the four-class predictions measured with data from Soonchunhyang University Hospital in Cheonan had an average accuracy of 96.1%, an average sensitivity of 92.2%, an average specificity of 97.4%, and an average inference time of 0.2 s.

scholarly journals Selective Feature Generation Method for Classification of Low-Dimensional Data

2018 ◽  
Vol 13 (1) ◽  
pp. 24
Author(s):  
Sang-Il Choi ◽  
Sang Tae Choi ◽  
Haanju Yoo
Keyword(s):  
Feature Vector ◽  
Image Data ◽  
Classification Performance ◽  
Data Sets ◽  
Facial Image ◽  
Discrimination Power ◽  
Input Feature ◽  
Low Dimensional ◽  
Candidate Feature

We propose a method that generates input features to effectively classify low-dimensional data. To do this, we first generate high-order terms for the input features of the original low-dimensional data to form a candidate set of new input features. Then, the discrimination power of the candidate input features is quantitatively evaluated by calculating the ‘discrimination distance’ for each candidate feature. As a result, only candidates with a large amount of discriminative information are selected to create a new input feature vector, and the discriminant features that are to be used as input to the classifier are extracted from the new input feature vectors by using a subspace discriminant analysis. Experiments on low-dimensional data sets in the UCI machine learning repository and several kinds of low-resolution facial image data show that the proposed method improves the classification performance of low-dimensional data by generating features.

Sign in / Sign up

Export Citation Format

Share Document