Wan Khairunizam

Infant cry classification to identify asphyxia using time-frequency analysis and radial basis neural networks

Highlights? Time-frequency analysis based classification of normal and asphyxia infant cries is proposed. ?Proposed features are tested using 4 different classifiers (MLP, TDNN, PNN and GRNN). ?The accuracy of 99% (normal and asphyxia cries) ensures the efficacy of the proposed method. A cry is the first verbal communication of infants and it is described as a loud, high-pitched sound made by infants in response to certain situations. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. Two types of radial basis neural networks such as Probabilistic Neural Network (PNN) and General Regression Neural Network are employed as classifiers for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals of infants with asphyxia. For comparison, the proposed features are also tested using two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm. The experimental results show that the PNN and GRNN give very promising classification accuracy compared to MLP and TDNN and the proposed methods can effectively classify normal and pathological infant cries of infants with asphyxia.

Performance comparison of Daubechies wavelet family in infant cry classification

Infant cry is a non-stationary, loud, high-pitched signal made by infants in response to certain situations. This acoustic signal can be used to identify physical or psychology status of infant. The aim of this work is to compare the performance of Daubechies wavelet family in infant cry classification. The orders of db1, db3, db4, db6 and db10 are chosen randomly for this investigation. Infant cry signals are decomposed into five levels using wavelet packet transform. Energy and entropy features are computed at different sub bands. Two different case studies such as, normal versus asphyxia and normal versus hypoacoustic are performed. Two different types of radial basis artificial neural networks namely, Probabilistic Neural Network (PNN) and General Regression Neural Network (GRNN) are used to classify the infant cry signals. The results emphasized that the proposed features and classification algorithms can be used to aid the medical professionals for diagnosing pathological status of infant cry.

Optimal selection of mother wavelet for accurate infant cry classification

Wavelet theory is emerging as one of the prevalent tool in signal and image processing applications. However, the most suitable mother wavelet for these applications is still a relative question mark amongst researchers. Selection of best mother wavelet through parameterization leads to better findings for the analysis in comparison to random selection. The objective of this article is to compare the performance of the existing members of mother wavelets and to select the most suitable mother wavelet for accurate infant cry classification. Optimal waveletxa0is found using three different criteria namely the degree of similarity of mother wavelets, regularity of mother wavelets and accuracy of correct recognition during classification processes. Recorded normal and pathological infant cry signals are decomposed into five levels using wavelet packet transform. Energy and entropy features are extracted at different sub bands of cry signals and their effectiveness are tested with four supervised neural network architectures. Findings of this study expound that, the Finite impulse response based approximation of Meyer is the best wavelet candidate for accurate infant cry classification analysis.

Infant cry classification: Time frequency analysis

Acoustic analysis of infant cry has been the subject of a number of researchers since half decades ago. This paper addresses a simple time-frequency analysis based signal processing technique using short-time Fourier transform (STFT) for the investigation and classification of infant cry signals. A cluster of statistical features are derived from the time-frequency plots of infant cry signals. The extracted feature vectors are used to model and train two types of radial basis neural network namely Probabilistic Neural Network (PNN) and General Regression Neural Network (GRNN) in classification phases. Three classes of infant cry signals are considered such as normal cry signals cry signals from deaf infants and infants with asphyxia. Promising classification results above 99% reveals that the proposed features and classification technique can effectively classify different infant cries.

Investigation of Steering Wheel Control of an Electric Buggy Car for Designing Fuzzy Controller

Steering control for path tracking and navigation are important for the autonomous vehicle. A good steering control system can determine the success of autonomous navigation through designed paths. Comfort and safety for the passenger are the main concerns in developing a controller for an autonomous electric vehicle (AEV). Comfort and the safe autonomous system can be achieving by imitating human intelligence and decision-making ability into the controller. A GPS module couple with a fuzzy controller to follow the designed path. Steering is control by using brushless DC motor with certain gear configuration. In order to achieve better drive performance for the autonomous vehicle, the behaviors of human subjects are studied and investigated. Investigation of steering angle on 3 different paths is designed to study the driving patterns by the human subjects, which are straight, turn right and turn left. The results show satisfactory outcomes as the subject navigates through the designed path with the similar patterns. The average value of steering wheel angle for the straight, right and left path are 13°, −151°, and 237°, respectively. The maximum angle to turning to the left and right are 286° (subject #1) and −226° (subject #1). This paper consists of the construction of a Fuzzy logic controller to control steering wheel and experiments set-up to develop the Fuzzy controller for an autonomous vehicle.

Analysis of Human Behavior During Braking for Autonomous Electric Vehicles

Nowadays, the development of modern technologies in the transportation area has increased rapidly. The latest technology is focused on autonomous vehicles. The most important aspect in autonomous vehicle control systems is safety, smooth operation and comfort. It can be provided by the natural element which is from human behavior as a reference to the autonomous control system. This paper is briefly describing the human behavior during braking for autonomous electric vehicle (AEV) control system development. To obtain the human behaviour during accelerating and braking, two units of angle sensors were installed to the accelerator and brake pedal of an electric car to measure the angle of both pedals. Real-time speed is recorded by using a GPS unit. The experiment is focused on braking characteristic of the electric vehicle. It was carried out based on four different distances with fixed initial speed before braking action was recorded. A software interface was designed to display and control real-time speed and pedal angle value during operation.

Ontological Framework of Arm Gesture Information for the Human Upper Body

In the research of the human motion analysis, the characteristic movements of the human upper body are intensively investigated for many applications such as sign language recognition, robot control and gait analysis. The human upper body consists of many body parts such as both arms including fingers, facials and head movements. Previously, many researches proposed various sensors to record arm movements and the acquired data are used to train the computer understand the behavioral motion of arms movements by using various algorithmic approaches. However, the current challenge is to increase the knowledge level of the computational systems to recognize gestural information containing in arm movements. The objective of this paper is to construct and derive the arm movement’s model based on the conceptual of ontology. The gestural information is investigated from characteristic features of arm movements. The knowledge of the computational systems about gestural information is developed by describing the characteristic features of arm movements in the form of the ontological framework. The ontological framework is defined as a structure containing characteristic features placed in mathematical order and has the relationship among them. Based on the mathematical model as proposed in this paper, the ontology framework could be used to describe knowledge of the arm gesture and could recognize it with a higher accuracy.

Experimental studies of touching sensation of human fingertip force based on weights

A wired glove system is developed by designing a low cost glove which has the similar function with the conventional dataglove and has been named as GloveMAP. The system involves the finger movements with some of grasping activities to investigate the force exerted on the fingertips during grasping a cylinder with different weight. Force sensing resistors (FSR) are attached to the thumb, index and middle fingers to obtain the voltage changes from the activities of fingers grasping. The output data from different weight of cylinder (bottle) during grasping are analyzed based on statistical approaches. The correlation between weight and force has been determined by comparing the gradient slope between both graphs.