scholarly journals A NOVEL APPROACH FOR FINDING DIABETIC MELLITUS USING ENSEMBLE MODEL FOR AN OPTIMIZED CLASSIFICATION

2017 ◽  
Vol 10 (9) ◽  
pp. 15 ◽  
Author(s):  
Sekar Kr ◽  
Kamaladevi M ◽  
Sethuraman J ◽  
Ravichandran Ks
Keyword(s):  
Ensemble Classifier ◽  
The Body ◽  
Training Data ◽  
Diabetic Mellitus ◽  
Data Set ◽  
Medical Practitioners ◽  
Novel Approach ◽  
High Care ◽  
Control Disease ◽  
The University

  Diabetic mellitus is a chronic disease caused by hyperglycemia which should be treated with high care and medications. The objective of this work is to identify and classify the severity of the diabetic disease using the training data set. This is caused due to the defect in insulin secretion that may affect several organs in the body. Blood pressure and diabetic mellitus are the common twin diseases occurred in about 69.2 million people living in India around 8.7% of the population as per the data resealed in the year 2015. Correct diet, regular exercise will control disease to a great extent. In this research paper the applied methodology is a concurrent classifier for the diabetic mellitus and the results are analyzed with the supervised learning. From the University of California and Irvine repository related attributes for the diabetic mellitus are carefully measured through the ensemble classifier and the results are categorized in the dataset. This work results that boosting can be made to the dataset for obtaining accurate results and classifications. In the conclusion, ensemble methodology is the well proven methodology from the year 1993. For forecasting in “N” number of domains, so for the ensemble classifier produces 93% of the accurate results are made. An audit can be made on the results and suggestions are given to the patients for taking medications with the help of medical practitioners.

Tailored photometric stereo: Optimization of light source positions for various materials

2020 ◽  
Vol 2020 (6) ◽  
pp. 71-1-71-7
Author(s):  
Christian Kapeller ◽  
Doris Antensteiner ◽  
Svorad Štolc
Keyword(s):  
Surface Defects ◽  
Ground Truth ◽  
Photometric Stereo ◽  
Industrial Applications ◽  
Training Data ◽  
Light Sources ◽  
Data Set ◽  
Novel Approach ◽  
Reconstruction Performance ◽  
Public Data

Industrial machine vision applications frequently employ Photometric Stereo (PS) methods to detect fine surface defects on objects with challenging surface properties. To achieve highly precise results, acquisition setups with a vast amount of strobed illumination angles are required. The time-consuming nature of such an undertaking renders it inapt for most industrial applications. We overcome these limitations by carefully tailoring the required light setup to specific applications. Our novel approach facilitates the design of optimized acquisition setups for inline PS inspection systems. The optimal positions of light sources are derived from only a few representative material samples without the need for extensive amounts of training data. We formulate an energy function that constructs the illumination setup which generates the highest PS accuracy. The setup can be tailored for fast acquisition speed or cost efficiency. A thorough evaluation of the performance of our approach will be given on a public data set, evaluated by the mean angular error (MAE) for surface normals and root mean square (RMS) error for albedos. Our results show, that the obtained optimized PS setups can deliver a reconstruction performance close to the ground truth, while requiring only a few acquisitions.

scholarly journals Robust Wireless Communication for Small Exploration Rovers Equipped with Multiple Antennas by Estimating Attitudes of Rovers in Several Experimental Environments

2017 ◽  
Vol 29 (5) ◽  
pp. 864-876 ◽  
Author(s):  
Masahiko Mikawa ◽  
Keyword(s):  
Estimation Method ◽  
Attitude Estimation ◽  
The Body ◽  
Training Data ◽  
Large Area ◽  
Data Set ◽  
Wireless Mesh ◽  
Surface Exploration ◽  
The Face ◽  
Micro Gravity

We are developing a robotic system for an asteroid surface exploration. The system consists ofmultiplesmall size rovers, that communicate with each other over a wireless network. Since the rovers configure over a wireless mesh sensor network on an asteroid, it is possible to explore a large area on the asteroid effectively. The rovers will be equipped with a hopping mechanism for transportation, which is suitable for exploration in a micro-gravity environment like a small asteroid’s surface. However, it is difficult to control the rover’s attitude during the landing. Therefore, a cube-shaped rover was designed. As every face has two antennas respectively, the rover has a total of twelve antennas. Furthermore, as the body shape and the antenna arrangements are symmetric, irrespective of the face on top, a reliable communication state among the rovers can be established by selecting the proper antennas on the top face. Therefore, it is important to estimate which face of the rover is on top. This paper presents an attitude estimation method based on the received signal strength indicators (RSSIs) obtained when the twelve antennas communicate among each other. Since the RSSI values change depending on an attitude of the rover and the surrounding environment, a significantly large number of RSSIs were collected as a training data set in different kinds of environments similar to an asteroid; consequently, a classifier for estimating the rover attitude was trained from the data set. A few of the experimental results establish the validity and effectiveness of the proposed exploration system and attitude estimation method.

A dynamic semisupervised feedforward neural network clustering

2016 ◽  
Vol 31 (1) ◽  
pp. 30-54 ◽  
Author(s):  
Roya Asadi ◽  
Sameem Abdul Kareem ◽  
Shokoofeh Asadi ◽  
Mitra Asadi
Keyword(s):  
Neural Network ◽  
Medical Center ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Network Clustering ◽  
Online Data ◽  
Data Set ◽  
Number Of Clusters ◽  
Cancer Data ◽  
The University

AbstractAn efficient single-layer dynamic semisupervised feedforward neural network clustering method with one epoch training, data dimensionality reduction, and controlling noise data abilities is discussed to overcome the problems of high training time, low accuracy, and high memory complexity of clustering. Dynamically after the entrance of each new online input datum, the code book of nonrandom weights and other important information about online data as essentially important information are updated and stored in the memory. Consequently, the exclusive threshold of the data is calculated based on the essentially important information, and the data is clustered. Then, the network of clusters is updated. After learning, the model assigns a class label to the unlabeled data by considering a linear activation function and the exclusive threshold. Finally, the number of clusters and density of each cluster are updated. The accuracy of the proposed model is measured through the number of clusters, the quantity of correctly classified nodes, and F-measure. Briefly, in order to predict the survival time, the F-measure is 100% of the Iris, Musk2, Arcene, and Yeast data sets and 99.96% of the Spambase data set from the University of California at Irvine Machine Learning Repository; and the superior F-measure results in between 98.14% and 100% accuracies for the breast cancer data set from the University of Malaya Medical Center. We show that the proposed method is applicable in different areas, such as the prediction of the hydrate formation temperature with high accuracy.

EAR BIOMETRICS AND SPARSE REPRESENTATION BASED ON SMOOTHED l0 NORM

2014 ◽  
Vol 28 (08) ◽  
pp. 1456016 ◽  
Author(s):  
RAHMAN KHORSANDI ◽  
MOHAMED ABDEL-MOTTALEB
Keyword(s):  
Sparse Representation ◽  
Majority Voting ◽  
Training Data ◽  
Gabor Wavelet ◽  
Automated System ◽  
Gender Classification ◽  
Classification Rate ◽  
Data Set ◽  
Ear Biometrics ◽  
Novel Approach

Ear biometrics attracted the attention of researchers in computer vision and machine learning for its use in many applications. In this paper, we present a fully automated system for recognition from ear images based upon sparse representation. In sparse representation, extracted features from the training data is used to develop a dictionary. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. In fact, there are many solutions for this problem and the goal is to find the sparsest solution. We use a relatively new algorithm named smoothed l0 norm to find the sparsest solution and Gabor wavelet features are used for building the dictionary. Furthermore, we expand the proposed approach for gender classification from ear images. Several researches have addressed this issue based on facial images. We introduce a novel approach based on majority voting for gender classification. Experimental results conducted on the University of Notre Dame (UND) collection J data set, containing large appearance, pose, and lighting variations, resulted in a gender classification rate of 89.49%. Furthermore, the proposed method is evaluated on the WVU data set and classification rates for different view angles are presented. Results show improvement and great robustness in gender classification over existing methods.

scholarly journals A Novel Approach for Classifying MANETs Attacks with a Neutrosophic Intelligent System based on Genetic Algorithm

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Haitham Elwahsh ◽  
Mona Gamal ◽  
A. A. Salama ◽  
I. M. El-Henawy
Keyword(s):  
Genetic Algorithm ◽  
Ad Hoc ◽  
Intelligent System ◽  
Fitness Function ◽  
Mathematical Formulation ◽  
Training Data ◽  
Data Set ◽  
Novel Approach ◽  
Learning Capabilities ◽  
Hoc Networks

Recently designing an effective intrusion detection systems (IDS) within Mobile Ad Hoc Networks Security (MANETs) becomes a requirement because of the amount of indeterminacy and doubt exist in that environment. Neutrosophic system is a discipline that makes a mathematical formulation for the indeterminacy found in such complex situations. Neutrosophic rules compute with symbols instead of numeric values making a good base for symbolic reasoning. These symbols should be carefully designed as they form the propositions base for the neutrosophic rules (NR) in the IDS. Each attack is determined by membership, nonmembership, and indeterminacy degrees in neutrosophic system. This research proposes a MANETs attack inference by a hybrid framework of Self-Organized Features Maps (SOFM) and the genetic algorithms (GA). The hybrid utilizes the unsupervised learning capabilities of the SOFM to define the MANETs neutrosophic conditional variables. The neutrosophic variables along with the training data set are fed into the genetic algorithm to find the most fit neutrosophic rule set from a number of initial subattacks according to the fitness function. This method is designed to detect unknown attacks in MANETs. The simulation and experimental results are conducted on the KDD-99 network attacks data available in the UCI machine-learning repository for further processing in knowledge discovery. The experiments cleared the feasibility of the proposed hybrid by an average accuracy of 99.3608 % which is more accurate than other IDS found in literature.

scholarly journals A Machine Learning Approach for the Segmentation of Driving Maneuvers and its Application in Autonomous Parking

2017 ◽  
Vol 7 (4) ◽  
pp. 243-255 ◽  
Author(s):  
Gennaro Notomista ◽  
Michael Botsch
Keyword(s):  
Classification System ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Ensemble Classifier ◽  
Classification Performance ◽  
Open Loop ◽  
Training Data ◽  
Small Scale ◽  
Data Set ◽  
Loop Control

AbstractA classification system for the segmentation of driving maneuvers and its validation in autonomous parking using a small-scale vehicle are presented in this work. The classifiers are designed to detect points that are crucial for the path-planning task, thus enabling the implementation of efficient autonomous parking maneuvers. The training data set is generated by simulations using appropriate vehicle-dynamics models and the resulting classifiers are validated with the small-scale autonomous vehicle. To achieve both a high classification performance and a classification system that can be implemented on a microcontroller with limited computational resources, a two-stage design process is applied. In a first step an ensemble classifier, the Random Forest (RF) algorithm, is constructed and based on the RF-kernel a General Radial Basis Function (GRBF) classifier is generated. The GRBF-classifier is integrated into the small-scale autonomous vehicle leading to excellent performance in parallel-, cross- and oblique-parking maneuvers. The work shows that segmentation using classifies and open-loop control are an efficient approach in autonomous driving for the implementation of driving maneuvers.

Corporate Default Prediction with AdaBoost and Bagging Classifiers

2015 ◽  
Vol 73 (2) ◽  
Author(s):  
Suresh Ramakrishnan ◽  
Maryam Mirzaei ◽  
Mahmoud Bekri
Keyword(s):  
Ensemble Classifier ◽  
Training Data ◽  
Generalization Error ◽  
Classifier Systems ◽  
Data Set ◽  
Corporate Default ◽  
Noisy Information ◽  
Linear Relationships ◽  
Default Prediction ◽  
Prediction Problems

This study aims to show a substitute technique to corporate default prediction. Data mining techniques have been extensively applied for this task, due to its ability to notice non-linear relationships and show a good performance in presence of noisy information, as it usually happens in corporate default prediction problems. In spite of several progressive methods that have widely been proposed, this area of research is not out dated and still needs further examination. In this paper, the performance of ensemble classifier systems is assessed in terms of their capability to appropriately classify default and non-default Malaysian firms listed in Bursa Malaysia. AdaBoost and Bagging are novel ensemble learning algorithms that construct the base classifiers in sequence using different versions of the training data set. In this paper, we compare the prediction accuracy of both techniques and single classifiers on a set of Malaysian firms, considering the usual predicting variables such as financial ratios. We show that our approach decreases the generalization error by about thirty percent with respect to the error produced with a single classifier. 

Automated identification of distinct events in an assembly process using tracking of body postures

2017 ◽  
Vol 26 (2) ◽  
pp. 198-207 ◽  
Author(s):  
Santhi Balaraman ◽  
Amaresh Chakrabarti ◽  
Balan Gurumoorthy ◽  
Dibakar Sen
Keyword(s):  
Traditional Method ◽  
The Body ◽  
Assembly Process ◽  
Automated Identification ◽  
Data Set ◽  
Body Postures ◽  
Novel Approach ◽  
Key Frames ◽  
Torso Angle ◽  
Assembly Performance

An ergonomic assembly process is safer for operators and is more efficient in quality, time, cost and productivity. An assembly process is carried out in a series of distinct events. Ergonomic assessment of an assembly process therefore involves identification of the distinct events within the process and assessment of difficulty in carrying out each event, so that the process can be improved in an event-specific manner. So far, such assessment of assembly is carried out using video by identifying key frames manually. Manual identification of key frames consumes more time. To resolve this drawback, a novel approach has been proposed for tracking the body segments using electromagnetic trackers. It is done automatically in real time. Then, a data smoothening method is used for analysing automatically the tracked data to identify distinct events in an assembly process. An experiment in a laboratory setting is used in this study to test the following hypothesis: ‘An event is characterized by gross movements at its beginning and its end’. This hypothesis encapsulates the essence of the signature in postural data, which is used by the proposed method for identifying distinct events within an assembly; the tracked data were used to identify this signature automatically from the trackers and the tracked data set with a threshold of movement for each body segment; using this threshold, gross motions and thereby starts and ends of distinct events can be identified. The method of identifying events was based on a reach experiment; thus, the variation of torso angle was studied in this work. The result of the study indicates that this method can be applied easily in detecting events in an assembly. Performance of the proposed method is compared with the traditional method and it is observed that the proposed approach outperforms traditional method in terms of time and accuracy.

Diagnostics of professional competence of IT students based on digital footprint data

2020 ◽  
pp. 4-11
Author(s):  
I. G. Zakharova ◽  
Yu. V. Boganyuk ◽  
M. S. Vorobyova ◽  
E. A. Pavlova
Keyword(s):  
Information Technology ◽  
Educational Program ◽  
Professional Competence ◽  
Objective Data ◽  
Text Data ◽  
Data Set ◽  
Job Requirements ◽  
Digital Footprint ◽  
Graduate Employment ◽  
The University

The article goal is to demonstrate the possibilities of the approach to diagnosing the level of IT graduates’ professional competence, based on the analysis of the student’s digital footprint and the content of the corresponding educational program. We describe methods for extracting student professional level indicators from digital footprint text data — courses’ descriptions and graduation qualification works. We show methods of comparing these indicators with the formalized requirements of employers, reflected in the texts of vacancies in the field of information technology. The proposed approach was applied at the Institute of Mathematics and Computer Science of the University of Tyumen. We performed diagnostics using a data set that included texts of courses’ descriptions for IT areas of undergraduate studies, 542 graduation qualification works in these areas, 879 descriptions of job requirements and information on graduate employment. The presented approach allows us to evaluate the relevance of the educational program as a whole and the level of professional competence of each student based on objective data. The results were used to update the content of some major courses and to include new elective courses in the curriculum.

Dziedinošās darbības un to veicēji folkloras un valodas liecībās

2020 ◽  
pp. 372-389
Author(s):  
Ieva Ančevska
Keyword(s):  
General Term ◽  
Spoken Word ◽  
The Body ◽  
Folk Healing ◽  
Medical Practitioners ◽  
Medical Terms ◽  
Healing Tradition

This article summarizes the various healing-related activities used in the Latvian healing tradition. To explain these activities and describe their performers and specialization, folklore sources and linguistic materials were used. The aim of this article is to demonstrate the diversity of folk healing activities and their names, while also clarifying their nature and use as much as possible. The linguistic and etymological analysis was used to investigate the healing activities and the names of their performers, but folklore examples were used for clarifying the meanings. By studying the healing tradition, the names of medical practitioners were collected from various sources, adding up to over 60 labels. When compiling the report, the representatives of the healing activities were divided into conditional groups according to the type of their main medical activities. Thus, the following groups of healing activities were formed: healing activities using the body, actions with spoken word and blowing, ritual and magic activities, defense techniques and liberating rituals. In addition to the medicinal practitioners who were active in healing, there were also counselors who sought out the causes of diseases through various means and searched for their best remedies. The survey in the article shows that the healing tradition uses diverse and specialized medical terms. However, as the examples show, most of them have used a combination of different practices. The name of the healer in question usually described the skills that were particularly developed and had been used most frequently. During tradition bans, names of healers became more general, and tabooed names were used instead. The general term “healer” has only been naturalized into society after the restoration of national independence.

Sign in / Sign up

Export Citation Format

Share Document