Image Data Mining Research Articles

High throughput image labeling on chest computed tomography by deep learning

When mining image data from PACs or clinical trials or processing large volumes of data without curation, the relevant scans must be identified among irrelevant or redundant data. Only images acquired with appropriate technical factors, patient positioning, and physiological conditions may be applicable to a particular image processing or machine learning task. Automatic labeling is important to make big data mining practical by replacing conventional manual review of every single-image series. Digital imaging and communications in medicine headers usually do not provide all the necessary labels and are sometimes incorrect. We propose an image-based high throughput labeling pipeline using deep learning, aimed at identifying scan direction, scan posture, lung coverage, contrast usage, and breath-hold types. They were posed as different classification problems and some of them involved further segmentation and identification of anatomic landmarks. Images of different view planes were used depending on the specific classification problem. All of our models achieved accuracy on test set across different tasks using a research database from multicenter clinical trials.

Estimating the imageability of words by mining visual characteristics from crawled image data

Natural Language Processing and multi-modal analyses are key elements in many applications. However, the semantic gap is an everlasting problem, leading to unnatural results disconnected from the user’s perception. To understand semantics in multimedia applications, human perception needs to be taken into consideration. Imageability is an approach originating from Pyscholinguistics to quantize the human perception of words. Research shows a relationship between language usage and the imageability of words, making it useful for multimodal applications. However, the creation of imageability datasets is often manual and labor-intensive. In this paper, we propose a method using image data mining of a variety of visual features to estimate the imageability of words. The main assumption is a relationship between the imageability of concepts, human perception, and the contents of Web-crawled images. Using a set of low- and high-level visual features from Web-crawled images, a model is trained to predict imageability. The evaluations show that the imageability can be predicted with both a sufficiently low error, and a high correlation to the ground-truth annotations. The proposed method can be used to increase the corpus of imageability dictionaries.

Adaptive Similarity Embedding for Unsupervised Multi-View Feature Selection

Multi-view learning has become a significant research topic in image processing, data mining and machine learning due to the proliferation of multi-view data. Considering the difficulty in obtaining labeled data in many real applications, we focus on the multi-view unsupervised feature selection problem. Most existing multi-view feature selection introduce an identical similarity matrix among different views, which cannot preserve the specific correlation between each single view. Also, some of these methods just consider either global or local structures. In this paper, we propose an embedding method, Adaptive Similarity Embedding for Unsupervised Multi-View Feature Selection (ASE-UMFS). This method reduces the high-dimensional data to the low dimensions and unifies different views to a combination weight matrix. We also use parameters to constraint the similarity matrix for the local structure, where the regularization term is used to add a prior of uniform distribution; taking into account of the independence in projection matrix among different views, optimization of the similarity matrix is further improved. To confirm the effectiveness of ASE-UMFS, comparisons are made with benchmark algorithm on real-world data sets. The experimental results demonstrate that the proposed algorithm outperforms several state-of-the-art methods in multi-view learning.

Research on Screening of Empathy Information Based on Image Recognition and Data Mining

The Internet not only provides help for people to understand the world and facilitate life, but also provides a convenient way for widespread dissemination of bad information. It follows that young people are often harassed by pornographic, violent and other bad images, which affects the development of young people's empathy. In this study, from the perspective of the combination of bad image screening and youth empathy ability, the effect of bad image on youth empathy ability is studied. In this article, a new empathy analysis model is constructed based on traditional empathy theory, combined with image recognition and data mining technology. First, the theoretical principles of bad image recognition technology and their application in the evaluation of empathy ability are expounded. Then, based on image recognition and fusion particle swarm optimization algorithm, the classification of bad images was studied. Finally, on the basis of image classification, a data envelopment model is used to grade the young people's empathy ability. The actual case analysis and performance test results illustrate the superiority of the implemented image classification and empathy evaluation method based on image recognition and data mining. This research has certain theoretical significance for the research of enriching empathy ability and interpersonal relationship. At the same time, it has certain practical significance for improving the youth's interpersonal trust, realizing the harmonious interpersonal relationship and the healthy development of body and mind.

Preface

The First International Conference on Emerging Electrical Energy, Electronics and Computing Technologies 2019 (ICE4CT 2019) was held in Melaka, Malaysia during 29 – 31, October 2019. The conference was organized by the School of Electrical Systems Engineering, Universiti Malaysia Perlis. This was the first edition of the ICE4CT series. ICE4CT 2019 received technical papers from variety of topics, which includes High Voltage Engineering & Insulation Technology, Power Electronics and Energy Efficient Drives, Computer Vision and Image Analysis, Data Mining and Cloud Computing, Wireless Communications, Medical Informatics, Internet of Things (IoT) Applications and many more. There are 97 research articles included in this proceedings.ICE4CT 2019 would not be possible without the dedicated work and efforts of the organizing committee and its cadre of volunteers who worked tirelessly to develop and strengthen every aspect of the conference. I wish to express my gratitude for their hard work and commitment towards making ICE4CT 2019 a success one.Dr. Haziah Abdul Hamid General Chair, ICE4CT 2019DeanSchool of Electrical Systems Engineering (SoESE)Universiti Malaysia Perlis (UniMAP)Malaysia

2735 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: B6605129219/2019©BEIESP DOI: 10.35940/ijitee.B6605.129219 Journal Website: www.ijitee.org Image Substance Extraction using Data Mining Clustering Method

Dater retrieval is one of the key challenging factor for today. Because of increasing the volume of data sets every year due to various factors. Information extraction in image data sets are too multifaceted compare with normal text data recovery. Image data set consist of different attributes those attribute sets are normalized before it extract from the stored data base. This required additional burden to the user who wish to extract any information from this data sets. This key challenges invite more researchers in the field of image data mining. Today many of the data sets in the form of image it gives more accurate result and more outputs. For extracting any image data image attributes are properly trained for better result. The proposed work based on grouping the data sets using image attributes. The entire process of this work divided into two major separate operations. Experiments dons against various data sets, and outputs verified proposed work gives more accurate results than the existing techniques.

Discriminant analysis and feature selection in mass spectrometry imaging using constrained repeated random sampling - Cross validation (CORRS-CV)

The identification of biomarkers through Mass spectrometry imaging (MSI) is gaining popularity in the clinical field. However, considering the complexity of spectral and spatial variables faced, data mining of the hyperspectral images can be troublesome. The discovery of markers generally depends on the creation of classification models which should be validated to ensure the statistical significance of the discriminants m/z detected. Internal validation using resampling methods such as cross validation (CV) are widely used for model selection, the estimation of its generalization performance and biomarker discovery when sample sizes are limited and an independent test set is not available. Here, we introduce for first time the use of Constrained Repeated Random Subsampling CV (CORRS-CV) on multi-images for the validation of classification models on MSI. Although several aspects must be taken into account (e.g. image size, CORRS-CV∂value, the similarity across spatially close pixels, the total computation time), CORRS-CV provides more accurate estimates of the model performance than k-fold CV using of biological replicates to define the data split when the number of biological replicates is scarce and holding images back for testing is a waste of valuable information. Besides, the combined use of CORRS-CV and rank products increases the robustness of the selection of discriminant features as candidate biomarkers which is an important issue due to the increased biological, environmental and technical variabilities when analysing multiple images, especially from human tissues collected in clinical studies.

Double Line Clustering based Colour Image Segmentation Technique for Plant Disease Detection.

Agriculture is one of the most essential industry that fullfills people's need and also plays an important role in economic evolution of the nation. However, there is a gap between the agriculture sector and the technological industry and the agriculture plants are mostly affected by diseases, such as the bacterial, fungus and viral diseases that lead to loss in crop yield. The affected parts of the plants need to be identified at the beginning stage to eliminate the huge loss in productivity. In the present scenario, crop cultivation system depend on the farmers experience and the man power, but it consumes more time and increases error rate. To overcome this issue, the proposed system introduces the Double Line Clustering technique based disease identification system using the image processing and data mining methods. The introduced method analyze the Anthracnose, blight disease in grapes, tomato and cucumber. The leaf images are captured and the noise has been removed by non-local median filter and the segmentation is done by double line clustering method. The segmented part compared with diseased leaf using pattern matching algorithm. The efficiency of the system is implemented in tomato, grape, cucumber plants leaf images and the results are analyzed in terms of the error rate, sensitivity, specificity, accuracy and time. The result of the clustering algorithm achieved high accuracy, sensitivity, and specificity. The feature extraction is applied after the clustering process which produces minimum error rate.

Machine learning applications in epilepsy.

Machine learning leverages statistical and computer science principles to develop algorithms capable of improving performance through interpretation of data rather than through explicit instructions. Alongside widespread use in image recognition, language processing, and data mining, machine learning techniques have received increasing attention in medical applications, ranging from automated imaging analysis to disease forecasting. This review examines the parallel progress made in epilepsy, highlighting applications in automated seizure detection from electroencephalography (EEG), video, and kinetic data, automated imaging analysis and pre-surgical planning, prediction of medication response, and prediction of medical and surgical outcomes using a wide variety of data sources. A brief overview of commonly used machine learning approaches, as well as challenges in further application of machine learning techniques in epilepsy, is also presented. With increasing computational capabilities, availability of effective machine learning algorithms, and accumulation of larger datasets, clinicians and researchers will increasingly benefit from familiarity with these techniques and the significant progress already made in their application in epilepsy.

Power–Delay-Error-Efficient Approximate Adder for Error-Resilient Applications

Power dissipation has been the prime concern for CMOS circuits. Approximate computing is a potential solution for addressing this concern as it reduces power consumption resulting in improved performance in terms of power–delay product (PDP). Decrease of power consumption in approximate computing is achieved by approximating the demand of accuracy as per the error tolerance of the system. This paper presents a new approach for designing approximate adder by introducing inexactness in the existing logic gate(s). Approximated logic gates provide flexibility in designing low power error-resilient systems depending on the error tolerance of the applications such as image processing and data mining. The proposed approximate adder (PAA) has higher accuracy than existing approximate adders with normalized mean error distance of 0.123 and 0.1256 for 16-bit and 32-bit adder, respectively, and lower PDP of 1.924E[Formula: see text]18[Formula: see text]J for 16-bit adder and 5.808E[Formula: see text]18[Formula: see text]J for 32-bit adder. The PAA also performs better than some of the recent approximate adders reported in literature in terms of layout area and delay. Performance of PAA has also been evaluated with an image processing application.

Detection of acute lymphoblastic leukemia using image segmentation and data mining algorithms.

Blood is composed of white blood cells, red blood cells, and platelets. Segmentation of the blood smear cells and extraction of features of the cells is essential in the field of medicine. Acute lymphoblastic leukemia is a form of blood cancer caused due to the abnormal increase in the production of immature white blood cells in the bone marrow. It mostly affects the children below 5years and adults above 50years of age. Due to the late diagnosis and cost of the devices used for the determination, the mortality rate has increased drastically. Flow cytometry technique that performs automated counting fails to identify the abnormal cells. Manual recount performed using hemocytometer are prone to errors and are imprecise. The proposed work aims to survey different computer-aided system techniques used to segment the blood smear image. The primary objective here is to derive knowledge from the different methodologies used for extracting features from white blood cells and develop a system that would accurately segment the blood smear image by overcoming the drawbacks of the previous works. The objective mentioned above is achieved in two ways. Firstly, a novel algorithm is developed to segment the nucleus and cytoplasm of white blood cell. Secondly, a model is built to extract the features and train the model. The different supervised classifiers are compared, and the one with the highest accuracy is used for the classification. Six hundred images are used in the experimentation. InfoGainAttributeEval and the Ranker Search method are used to achieve the feature selection which in turn helps in improvising the classifier performance. The result shows the classification of the acute lymphoblastic leukemia into its three respective categories namely: ALL-L1, ALL-L2, ALL-L3. The model can differentiate between a normal peripheral blood smear and an abnormal blood smear. The extracted feature values of a cancerous cell and a normal cell are also shown. The performance of the model is evaluated using the test images stained with various stains. The proposed algorithm achieved an overall accuracy of 98.6%. The promising results show that it can be used as a diagnostic tool by the pathologists. Graphical abstract.

Aesthetics-Guided Graph Clustering With Absent Modalities Imputation.

Accurately clustering Internet-scale Internet users into multiple communities according to their aesthetic styles is a useful technique in image modeling and data mining. In this paper, we present a novel partially supervised model which seeks a sparse representation to capture photo aesthetics. It optimally fuzes multi-channel features, i.e., human gaze behavior, quality scores, and semantic tags, each of which could be absent. Afterward, by leveraging the KL-divergence to distinguish the aesthetic distributions between photo sets, a large-scale graph is constructed to describe the aesthetic correlations between users. Finally, a dense subgraph mining algorithm which intrinsically supports outliers (i.e., unique users not belong to any community) is adopted to detect aesthetic communities. The comprehensive experimental results on a million-scale image set grabbed from Flickr have demonstrated the superiority of our method. As a byproduct, the discovered aesthetic communities can enhance photo retargeting and video summarization substantially.

Computer Aided Detection of Clustered Microcalcification: A Survey

This paper attempts to pinpoint different techniques for Pectoral Muscle (PM) segmentation, Microcalcification (MC) detection and classification in digital mammograms. The segmentation of PM and detection of MC and its classification are mostly based on image processing and data mining techniques. The review centered on major techniques in image processing and data mining that is employed for PM segmentation, MC detection and classification in digital mammograms. Breast cancer is one of the significant causes of death among women aged above 40. Mammography is considered the most successful means for prompt and timely detection of breast cancers. One notable visual indication of the malignant growth is the appearance of Masses, Architectural Distortions, and Microcalcification Clusters (MCCs). There are some disadvantages and hurdles for mankind viewers, and it is hard for radiologists to supply both precise and steady assessment for a large number of mammograms created in extensive screening. Computer Aided Detection has been employed to help radiologists in detecting MC and MCCs. The automatic recognition of malignant MCCs could be very helpful for diagnostic purpose. In this paper, we summarize the methods of automatic detection and classification of MCs in digitized mammograms. Pectoral muscle segmentation techniques are also summarized. The techniques used for segmentation of PM, MC detection and classification in a digitized mammogram are reviewed.

An improvement method of DBSCAN algorithm on cloud computing

DBSCAN is a density-based data clustering algorithm, in image processing, data mining, machine learning and other fields are widely used. With the increasing of the size of clusters, the parallel DBSCAN algorithm is widely used. in image processing, data mining, machine learning and other fields are widely used. However, we consider current partitioning method of DBSCAN is too simple and steps of GETNEIGHBORS query repeatedly access the data set on spark. So we proposed DBSCAN-PSM which applies new data partitioning and merging method. In the first stage of our method we import the KD-Tree, combine the partitioning and GETNEIGHBORS query, reduce the number of access to the data set and decrease the influence of I/O in the algorithm. In the second stage of our method we use the feature of points in merging so as to avoid the time costing of the global label. Experimental results showed that our new method can improve the parallel efficiency and the clustering algorithm performance.

Web Data Extraction Approach for Deep Web using WEIDJ

Data extraction is one of the most prominent areas in data mining analysis that is been extensively studied especially in the field of data requirements and reservoir. The main aim of data extraction with regards to semi-structured data is to retrieve beneficial information from the World Wide Web. The data from large web data also known as deep web is retrievable but it requires request through form submission because it cannot be performed by any search engines. Data mining applications and automatic data extraction are very cumbersome due to the diverse structure of web pages. Most of the previous data extraction techniques were dealing with various data types such as text, audio, video and etc. but research works that are focusing on image as data are still lacking. Document Object Model (DOM) is an example of the state of the art of data extraction technique that is related to research work in mining image data. DOM was the method used to solve semi-structured data extraction from web. However, as the HTML documents start to grow larger, it has been found that the process of data extraction has been plagued with lengthy processing time and noisy information. In this research work, we propose an improved model namely Wrapper Extraction of Image using DOM and JSON (WEIDJ) in response to the promising results of mining in a higher volume of web data from a various types of image format and taking the consideration of web data extraction from deep web. To observe the efficiency of the proposed model, we compare the performance of data extraction by different level of page extraction with existing methods such as VIBS, MDR, DEPTA and VIDE. It has yielded the best results in Precision with 100, Recall with 97.93103 and F-measure with 98.9547.

DBSCAN-PSM: an improvement method of DBSCAN algorithm on Spark

DBSCAN is a density-based data clustering algorithm; in image processing, data mining, machine learning and other fields are widely used. With the increasing of the size of clusters, the parallel DBSCAN algorithm is widely used. However, we consider current partitioning method of DBSCAN is too simple and steps of GETNEIGHBORS query repeatedly access the dataset on Spark. So we proposed DBSCAN-PSM which applies new data partitioning and merging method. In the first stage of our method, we import the KD-tree, combine the partitioning and GETNEIGHBORS query, reduce the number of access to the dataset and decrease the influence of I/O in the algorithm. In the second stage of our method, we use the feature of points in merging so as to avoid the time costing of the global label. Experimental results showed that our new method can improve the parallel efficiency and the clustering algorithm performance.

DBSCAN-PSM: an improvement method of DBSCAN algorithm on Spark

DBSCAN is a density-based data clustering algorithm; in image processing, data mining, machine learning and other fields are widely used. With the increasing of the size of clusters, the parallel DBSCAN algorithm is widely used. However, we consider current partitioning method of DBSCAN is too simple and steps of GETNEIGHBORS query repeatedly access the dataset on Spark. So we proposed DBSCAN-PSM which applies new data partitioning and merging method. In the first stage of our method, we import the KD-tree, combine the partitioning and GETNEIGHBORS query, reduce the number of access to the dataset and decrease the influence of I/O in the algorithm. In the second stage of our method, we use the feature of points in merging so as to avoid the time costing of the global label. Experimental results showed that our new method can improve the parallel efficiency and the clustering algorithm performance.

Piecewise Linear Regression Based on Plane Clustering

Piecewise linear regressions have shown many successful applications in image denoising, signal process, and data mining fields. In essence, they attempt to seek multiple linear functions (piecewise/stepwise function) to fit the given scatter data points by various methodologies, typically point-centered clustering methods, such as ${k}$ -means or fuzzy c means. Obviously, it is reasonable that plane-centered clustering is more suitable for capturing the linearities in data. In this paper, we propose an efficient piecewise linear regression method based on ${k}$ -plane clustering, termed as PlrPC. The proposed method first partitions the data into multiple plane-centered clusters and then analytically compute corresponding piecewise linear functions. Compared with the state-to-the-art linear regressors, the advantages of the PlrPC lie in fourfold: 1) it is generated from plane clustering, which is truly coincident with geometrical intuition; 2) to fuse the linear characteristics into plane clustering, a new implicit regression method is proposed; 3) a new plane jump method is proposed to detect the number of clusters, and; 4) the leading problem can be solved by ordinary eigenvalue problems. The experimental results will show the aforesaid characters on some artificial and some benchmark datasets.

Artificial Neural Networks for Satellite Image Classification of Shoreline Extraction for Land and Water Classes of the North West Coast of Peninsular Malaysia

Monitoring and measuring the shoreline of coastal zones helps establish the boundary of a country. Such an activity entails ground survey, topographic survey, aerial photo, or remote sensing techniques to extract the shoreline. For example, the remote sensing technique to determine shorelines involves the extraction of relevant data from satellite images. Specifically, the satellite image classification enables shorelines to be extracted from land and water classes with a high degree of precision. However, extracting information from satellite images is challenging as it relies on a strong understanding of image processing, machine learning, and data mining techniques. Thus, the researchers discuss the study of the pixel-based classification of machine learning techniques to classify land and water classes in terms of accuracy, training time, and testing time. The research findings showed that the Multilayer Perceptron Artificial Neural Network (MLP ANN) was the most effective technique, compared with other techniques, hence reinforcing its importance in classifying land and water classes.

Direct Search Methods on Reductive Homogeneous Spaces

Direct search methods are mainly designed for use in problems with no equality constraints. However, there are many instances where the feasible set is of measure zero in the ambient space and no mesh point lies within it. There are methods for working with feasible sets that are (Riemannian) manifolds, but not all manifolds are created equal. In particular, reductive homogeneous spaces seem to be the most general space that can be conveniently optimized over. The reason is that a ‘law of motion’ over the feasible region is also given. Examples include $$\mathbb {R}^{n}$$ and its linear subspaces, Lie groups, and coset manifolds such as Grassmannians and Stiefel manifolds. These are important arenas for optimization, for example, in the areas of image processing and data mining. We demonstrate optimization procedures over general reductive homogeneous spaces utilizing maps from the tangent space to the manifold. A concrete implementation of the probabilistic descent direct search method is shown. This is then extended to a procedure that works solely with the manifold elements, eliminating the need for the use of the tangent space.