Muhammad Naufal Mansor

New newborn jaundice monitoring scheme based on combination of pre-processing and color detection method

Newborn jaundice is an apparent yellowing of the sclera or yellowish skin in newborn infants. This symptom is caused by a yellow pigment known as bilirubin. A high level of bilirubin in the infant is referred to as hyperbilirubinemia. Significant complications can occur if significantly increased bilirubin levels are not treated promptly. Severe hyperbilirubinemia can be caused by dehydration, lack of adequate nutritional intake, extravasation of blood, cephalohematoma, contusions and asphyxia, and may potentially cause kernicterus. Because many of these problems affect newborns, they may require critical care from specialty medical disciplines. Thus, in this paper we proudly proposed a Combination of pre-processing and the skin color detection method to detect jaundiced infants. Few statistical features are derived from the texture images and used as features to quantify infant image textures. Finally, a k-NN is employed as classifier for discriminating infant image textures. The experimental results reveal that the proposed method can act as a supplement to support earlier detection and more effective treatment due to improved jaundice recognition.

Patient monitoring in ICU under unstructured lighting condition

In this paper, fuzzy classifier is explained and reviewed for detecting facial changes of patient in a hospital in Intensive Care Unit (ICU). The facial changes are most widely represented by eyes and mouth movements. The proposed system uses color images and it consists of three modules. The first module implements skin detection to detect the face. The second module constructs eye and mouth maps that are responsible for changes in eye and mouth regions. The third module extracts the features of eyes and mouth by processing the image and measuring certain dimensions of eyes and mouth regions. Finally a fuzzy classifier used to classify the movements at different illumination levels. From 300 samples of face images, it is found that the identification rate of awakness reaches 97%.

Detection of facial changes for ICU patients using KNN classifier

This paper presents an integrated system for detecting facial changes of patient in a hospital in Intensive Care Unit(ICU).In this research we have considered the facial changes most widely represented by eyes and mouth movements. The proposed system uses color images and it consists of three modules. The first module implements skin detection to detect the face. The second module constructs eye and mouth maps that are responsible for changes in eye and mouth regions. The third module extracts the features of eyes and mouth by processing the image and measuring certain demensions of eyes and mouth regions. Finally the result of this work shows that the (k-NN) can be used for used to classify the awake ness with the average accuracy of 94%.

Detection of facial changes for hospital ICU patients using neural network

This paper presents an integrated system for detecting facial changes of patient in a hospital in Intensive Care Unit (ICU). The facial changes are most widely represented by eyes movements. The proposed system uses color images and it consists of three modules. The first module implements skin detection to detect the face. The second module constructs eye maps that are responsible for changes in eye regions. The third module extracts the features of eyes by processing the image and measuring certain demensions of eyes regions. Finally a neural network classifier used to classify the motion of eyes either it open, half open or close. From 300 samples of face images, it is found that the maximum classification accuracy of 93.33% was obtained for the proposed features and classification technique.

Fast infant pain detection method

within this paper, pain detection is exposed and reviewed for detecting facial changes of patient in a hospital in Neonatal Intensive Care Unit (NICU). The system propesed three stage. The first stage implements Haar Cascade detection to detect the infant face. Secondly, PCA was employed for feature extraction. The third module extracts the PCA features of faces by measuring certain dimensions of pain and no pain regions with Support Vector Machine classifier. From 300 samples of face images, it is found that the identification rate of reaches 93.18%.

Automatically infant pain recognition based on LDA classifier

This paper discusses the challenges and possibilities of infant pain automatic detection and analysis of infant faces in the scene. The first module implements Haar Cascade Classifier to detect the face. Secondly, extracts the features of faces based on Principal Component Analysis. Finally a LDA classifier used to classify the pain score. From the trial, it is found that the identification rate of reaches 93.12%.

A computational model of the infant pain impressions with Gaussian and Nearest Mean Classifier

In the last recent years, non-invasive methods through image analysis of facial have been proved to be excellent and reliable tool to diagnose of pain recognition. This paper proposes a new feature vector based Local Binary Pattern (LBP) for the pain detection. Different sampling point and radius weighted are proposed to distinguishing performance of the proposed features. In this work, Infant COPE database is used with illumination added. Multi Scale Retinex (MSR) is applied to remove the shadow. Two different supervised classifiers such as Gaussian and Nearest Mean Classifier are employed for testing the proposed features. The experimental results uncover that the proposed features give very promising classification accuracy of 90% for Infant COPE database.

Crime Detection with DCT and Artificial Intelligent Approach

Crime rate in Malaysia is almost in awareness stage. The centre for Public Policy Studies Malaysia reports that the ratio of police to population is 3.6 officers to 1,000 citizens in Malaysia. This lack of manpower sources ratios alone are not a comprehensive afford of crime fighting capabilities. Thus, dealing with these circumstances, we present a comprehensive study to determine bandit behavior with Discrete Cosine Transform (DCT), Support vector machine (SVM) and k Nearest Neighbor (k-NN) Classifier. This system provided a good justification as a monitoring supplementary tool for the Malaysian police arm forced.

AR Model for infant pain anxiety recognition using Fuzzy k-NN

Pain Assessment in Neonatal has been discussed recently nowadays. A rapid research, equipment and pain course has yet been improved. However, the robustness, accurate and fast pain scheme is yet far beyond the schedule comparing to the pain assessment for the adult patient. Thus, an infant pain detection scheme is been proposed based on Autoregressive Model (AR Model) and Fuzzy k-NN. The accuracy result is quite promising around 90.77%.

Safety system based on Linear Discriminant Analysis

A Linear Discriminant Analysis Classifier for home security system we describe in this paper. Images were taken in uncontrolled indoor environment using video cameras of various qualities. Database contains 4,005 static images (in visible and infrared spectrum) of 267 subjects. Images from different quality cameras should mimic real-world conditions and enable robust face recognition algorithms testing, emphasizing different law enforcement and surveillance use case scenarios. In addition to database description, this paper also elaborates on possible uses of the database and proposes a testing protocol. A baseline Haar Cascade Method for face recognition algorithm was tested following the proposed protocol based on LDA Classifier. Other researchers can use these test results as a control algorithm performance score when testing their own algorithms on this dataset. Database is available to research community through the procedure described at http://www.lrv.fri.uni-lj.si/facedb.html.