In recent years, hyperspectral remote sensing has become popular in various applications. This technology can capture hyperspectral images with a large terrestrial data. In this paper, the feasibility of applying various machine learning and deep learning techniques to perform classification on hyperspectral images are investigated and compared. Particularly, a total of three popular machine learning classifiers namely supports vector machine (SVM), K-nearest neighbors (KNN) and artificial neural networks (ANN) are used for hyperspectral imagine classification, followed by another two deep architectures in convolutional neural networks (CNN). Three benchmarking datasets of hyperspectral images are used to evaluate the classification performances of suggested machine learning and deep learning techniques, namely: Indian Pines (IP) dataset, Salinas dataset, and Pavia University (PU) dataset. Extensive simulation studies reveal the excellent performance of 3D CNN deep learning in solving larger datasets with better classification accuracy despite the longer training time is required. However, it is not really the case when the dataset is not large enough. This is because deep learning is data-hungry architecture. Furthermore, the 3D CNN deep learning models employed in this study have shown more advantageous as compared to other machine learning models for having simplified pre-processing stages such as feature extraction in solving the classification problems of hyperspectral images.

Quadrotor is a type of unmanned aerial vehicle that has been widely used in many applications, such as, policing, surveillance, aerial photography and agriculture. Conventionally, the control of quadrotor flight direction is accomplished by varying speeds of motors or manipulating torques. In this paper, a novel mechanism is proposed. The mechanism uses stepper motors to control the arm length for changing flight directions, while maintaining motors' speed at constant. A mathematical model has been created. The analysis results have shown that varying arm length can effectively control the moment of bending of quadrotors. Increasing the length of arms can result in the increase of the moment of bending without changing speed of motors, thus saving energies. Experimental results have shown that the new mechanism is able to carry more payloads which the motor speed can be utilized fully at 100% while the flight direction is been controlled by changing of the arm length compared to conventional flight control mechanisms

Classifying human face based on race and gender is a vital process in face recognition. It contributes to an index database and eases 3D synthesis of the human face. Identifying race and gender based on intrinsic factor is problematic, which is more fitting to utilizing nonlinear model for estimating process. In this paper, we aim to estimate race and gender in varied head pose. For this purpose, we collect dataset from PICS and CAS-PEAL databases, detect the landmarks and rotate them to the frontal pose. After geometric distances are calculated, all of distance values will be normalized. Implementation is carried out by using Neural Network Model and Fuzzy Logic Model. These models are combined by using Adaptive Neuro-Fuzzy Model. The experimental results showed that the optimization of address fuzzy membership. Model gives a better assessment rate and found that estimating race contributing to a more accurate gender assessment.

Agricultural wastes are renewable resources that are potentially useful as microwave absorbing materials. This paper presents the investigation on the carbon composition, surface porosity of the raw coconut shell powder particles and the dielectric properties of coconut shell powder with epoxy resin matrix composites. From CHNS elemental analysis, it was found that the carbon composition of coconut shell powder is 46.700%. Presences of macropores (≈ 2μm) were detected in the SEM analysis of the coconut shell powder particles. Measurement on dielectric properties of the coconut shell powder composites was performed by using open-ended coaxial probe method over microwave frequency range of 1-8 GHz. The overall dielectric constant (εr’) and dielectric loss factor (εr”) of the composite with ratio 50:50 were 3.56 and 0.26, ranging from 3.35-3.76 and 0.21-0.30 respectively; whereas for composite ratio 40:60, the overall dielectric constant (εr’) and dielectric loss factor (εr”) were 2.97 and 0.21, ranging from 2.74-3.17 and 0.16-0.27 respectively. The electrical conductivity calculated based on measured εr” was 0.067 and 0.054 for composite ratio 50:50 and 40:60 respectively. The dielectric properties and electrical conductivity of the coconut shell powder composites were influenced by the greater presence of high dielectric material (coconut shell powder). This experimental investigation on the potential of the coconut shell powder with epoxy resin composites indicates that the ability of the composite to absorb and convert microwave signals is dependent on the carbonaceous materials of the composite. This result offers a great opportunity to diversify the use of coconut shell powder as microwave absorbing material.

A wired glove system is developed by designing a low cost dataglove 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 rectangular object 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 rectangular object 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.

In this paper, using a set of irregular and regular ellipse fitting equations using Genetic algorithm (GA) are applied to the lip and eye features to classify the human emotions. Two South East Asian (SEA) faces are considered in this work for the emotion classification. There are six emotions and one neutral are considered as the output. Each subject shows unique characteristic of the lip and eye features for various emotions. GA is adopted to optimize irregular ellipse characteristics of the lip and eye features in each emotion. That is, the top portion of lip configuration is a part of one ellipse and the bottom of different ellipse. Two ellipse based fitness equations are proposed for the lip configuration and relevant parameters that define the emotions are listed. The GA method has achieved reasonably successful classification of emotion. In some emotions classification, optimized data values of one emotion are messed or overlapped to other emotion ranges. In order to overcome the overlapping problem between the emotion optimized values and at the same time to improve the classification, a fuzzy clustering method (FCM) of approach has been implemented to offer better classification. The GA-FCM approach offers a reasonably good classification within the ranges of clusters and it had been proven by applying to two SEA subjects and has seen improvement compared to the earlier work. 

A full ground plane dual band microstrip antenna (FGP-DBMA) over ISM and HiperLAN/2 applications is presented. The structural design of the FGP-DBMA is based on suspended plate antenna. The FGP-DBMA antenna features a 56 × 55 mm2 rectangular radiating element suspended over 90 × 90 mm2 ground plane. ShieldIt Super conductive textile features are used as the radiating element and ground plane while felt textile features are used as the dielectric substrate. The rectangular radiator patch is designed using slits for dual-band resonance over ISM band (2.4 GHz to 2.48 GHz) and HiperLAN/2 band (5.725 GHz to 5.875 GHz). The FGP-DBMA radiates unidirectional with a fully grounded plane to avoid coupling onto user's body. The FGP-DBMA shows efficiency over the range of 69.6 % to 75.6 % and gain over the range of 6.052 dB to 6.323 dB in the free space scenario. The evaluation of FGP-DBMA with bending effects shows no significant changes to the performance of the FGP-DBMA. This indicates that the curvature effect on the proposed FGP-DBMA for on-body performance, i.e. on human arm, does not affect the performance of the antenna.

In this paper, an industrial machine vision system incorporating Optical Character Recognition (OCR) is employed to inspect the marking on the Integrated Circuit (/C) Chips. This inspection is carried out while the /Cs are coming out from the manufacturing line. A TSSOP-DGG type of /C package from Texas Instrument is used in this investigation. The /C chips markings are laser printed. This inspection system tests are laser printed marking on IC chips and are according to the specifications. Artificial intelligence (AI) techniques are used in this inspection. AI techniques utilized are neural network and fuzzy logic. The inspection is carried out to find the print errors; such as illegible character, upside down print and missing characters. The vision inspection of the printed markings on the /C chip is carried out in three phases, namely, image preprocessing, feature extraction and classification. MATLAB platform and its toolboxes are used for designing the inspection processing technique. The percentage of accuracy of the classification is found to be between 97%100%. INTRODUCTION In 1954, Rainbow developed a prototype machine that was able to read upper case written output atthe speed of one character per minutes [1]. From the late 1960's, the OCR technology has undergone many dramatic developments. Multiple recognition system used in the postal department has the capability to read and recognize the characters one by one [2]. Now, reading several hundred characters per minutes is a reality [3]. The document analysis has reached an important position in certain market. The application of OCR in the postal automation followed into the banks and industrial inspection [4, 5]. Further more, a successful recognition rate of 99.9% of multifont of any size has been reported [6]. IC chips play a vital role in the electronic industry. Mass production of IC chips have brought down the price of the electronic products. Texas Instrument is one of

Transient stability analysis plays an important role for planning, designing and upgrading an existing electrical power system network. In this paper, transient stability analysis is carried out by considering a three-phase fault at the busbars 7 and 4 with the effect of various fault-clearing times. The simulation is carried out using CYME 5.02 power system software with fast decoupled method. It is found that at fault clearing times of 0.05s, 0.1s, and 0.15s, the generators (G2, G3) under test are stable with respect to the simulation time. Whereas, at fault clearing times of 0.2s and 0.3s, these generators are found to be unstable for both faulted busbars 7 and 4. These simulation results are then compared with the proposed model results and are found to be in good agreement. In addition, it has been demonstrated that the transient stability of a system can be improved using control devices.

The aim of this study is to investigate the effect of energy drinks consumption on cardiac function of human being by analyzing the spectral components of pulse and ECG of several healthy people. Using pulse transducer connected with MP36 (Biopac, USA) data acquisition unit, pulse recordings were performed. With electrode lead set connected to the same MP36 data acquisition unit, ECG recordings were also performed. At before and after the consumption of energy drinks available in Bangladesh, pulse and ECG recordings as well as analysis were performed with Biopac software. After having energy drinks, the spectral components such as power of spectral density and amplitude of fast Fourier transform of pulse signal decreased about 47.5 and 37%, respectively. In case of ECG signal, the spectral components such as power of spectral density and amplitude of fast Fourier transform increased about 17 and 7.5% within a short interval about 0-20 min, then effective decrements about 10 and 18.5%, respectively started for long duration. Analyzing spectral parameters, the findings highlight the adverse impacts on cardiac function which may cause cardiac abnormality as well as severe cardiac disease due to the regular consumption of energy drinks.

This study proposes a statistical features-based classification system for human emotions by using Electroencephalogram (EEG) bio-sensors. A total of six statistical features are computed from the EEG data and Artificial Neural Network is applied for the classification of emotions. The system is trained and tested with the statistical features extracted from the psychological signals acquired under emotions stimulation experiments. The effectiveness of each statistical feature and combinations of statistical features in classifying different types of emotions has been studied and evaluated. In the experiment of classifying four main types of emotions: Anger, Sad, Happy and Neutral, the overall classification rate as high as 90% is achieved.

Diabetic retinopathy is an eye problem that face by the diabetic's patient. Diabetic Retinopathy (DR) is caused by the changes of the blood vessel in the retina. In the early stage of DR, the blood vessels may swell and leak fluid. However, in the advance stage of DR a new blood vessel that fragile and abnormal may formed and leaks blood to the retina. This can caused vision loss or even blindness. Therefore, this paper proposed to extract the blood vessel based on the peak and valley detection. The proposed methods utilized a green channel image and the inversion image. Next, the resulting images from both methods are combined. Three (3) databases are utilized namely from STructured Analysis of the Retina (STARE), Digital Retina Images for Vessel Extraction (DRIVE) and a database that is acquired from the local hospital.

This paper discuss about the method or techniques on how to detect the mango from a mango tree. The techniques using are such as colour processing which are use as primary filtering to eliminate the unrelated colour or object in the image. Besides that, shape detection are been used where it will use the edge detection, Circular Hough Transform (CHT). This technique will determine the candidates of mango and find the circular pattern with the given radius within an image by collecting the maximum voting. The program should automatically detect the desire object and count the total number of it.

In this paper, lip and eye features are applied to classify the human emotion through a set of irregular and regular ellipse fitting equations using Genetic algorithm (GA). South East Asian face is considered in this study. All six universally accepted emotions and one neutral are considered for classifications. The method which is fastest in extracting lip features is adopted in this study. Observation of various emotions of the subject lead to an unique characteristic of lips and eye. GA is adopted to optimize irregular ellipse and regular ellipse characteristics of the lip and eye features in each emotion respectively. That is, the top portion of lip configuration is a part of one ellipse and the bottom of different ellipse. Two ellipse based fitness equations are proposed for the lip configuration and relevant parameters that define the emotion are listed. One ellipse based fitness function is proposed for eye. The GA method approach has achieved reasonably successful classification of emotion. While performing classification, optimized values can mess or overlap with other emotions range. In order to overcome the overlapping problem between the emotions and at the same time to improve the classification, a neural network (NN) approach is implemented. The GA-NN based process exhibits a range of 83% - 90% classification of the emotion from the optimized feature of top lip, bottom lip and eye.

Recently, little attention has been paid to EEG signal for emotion recognition when compared to other physiological signals. This paper proposes an emotion recognition system from EEG (Electroencephalogram) signals. We designed an efficient acquisition protocol for acquiring the EEG signals under audio-visual induction environment for participants. Totally, 6 healthy subjects with an age group of 21-27 using 63 biosensors are used for registering the EEG signal for various emotions. After preprocessing the signals, discrete wavelet transform is employed to extract the EEG parameters. These extracted features are classified into discrete emotions using Fuzzy C-Means (FCM) clustering. Results confirm the possibility of using dif- ferent wavelet transform based feature extraction for assessing the human emotions from EEG signal.

Problem statement: Template matching had been a conventional method for object detection especially facial features detection at t he early stage of face recognition research. The appearance of moustache and beard had affected the performance of features detection and face recognition system since ages ago. Approach: The proposed algorithm aimed to reduce the effect of beard and moustache for facial features detection a nd introduce facial features based template matching as the classification method. An automated algorithm for face recognition system based on detected facial features, iris and mouth had been d eveloped. First, the face region was located using skin color information. Next, the algorithm compute d the costs for each pair of iris candidates from intensity valleys as references for iris selection. As for mouth detection, color space method was use d to allocate lips region, image processing methods t o eliminate unwanted noises and corner detection technique to refine the exact location of mouth. Fi nally, template matching was used to classify faces based on the extracted features. Results: The proposed method had shown a better features detection rate (iris = 93.06%, mouth = 95.83%) than conventio nal method. Template matching had achieved a recognition rate of 86.11% with acceptable processi ng time (0.36 sec). Conclusion: The results indicate that the elimination of moustache and bear d has not affected the performance of facial featur es detection. The proposed features based template mat ching has significantly improved the processing time of this method in face recognition research.

One of the few challenges facing face recognition systems is real time processing. In order for a face recognition system to be viable for real world implementations, it needs to be fast enough to track and identify facial images and do on-the-fly one-to-many identification from a multitude of database images. This is time consuming since face recognition requires a complex process of pre-processing and post-processing to be done along with the actual processing itself In order to save precious processing time and increase the processing speed, specific compiler optimizations could be applied to the algorithms to help in reducing system processing time and increase total system performance.In this paper, we explore different levels of compiler optimization techniques when applied to face recognition systems to help improve the algorithm's performance and in turn improve the entire system performance when implemented in real time and real life situations. A multitude of different compiler optimization techniques are tested and implemented during the stages of development and the effects of such optimizations are logged and compared.

An algorithm to automatically detect facial features from color images has been developed. First, face region is located using skin-color information. Then, the iris candidates are extracted from the intensity valleys created from the detected face. Next, the costs for each pair of iris candidates are computed to determine the real pair of irises. Mouth region and corners are detected using color space method, image processing and corners detection techniques. This algorithm has been tested to specifically reduce the effects of beard, moustache, hairstyle and facial expression in automated facial features detection.

Universiti Malaysia Perks (UniMAP) is one of the public higher learning institutions in Malaysia to offer Biomedical Engineering at the undergraduate level. Biomedical engineering is a new branch of engineering which apply the engineering principle and techniques to the health sector. The needs for such specialization are due to the advancement of medical technology, risk of shoddy medical products which flooded the country's market and also current public awareness on health issues. Thus, Universiti Malaysia Perlis has taken the challenge to develop her own course of Biomedical Engineering to cater the needs of producing capable biomedical engineer in this field to serve the job market locally and abroad. This article will give an update to the recent development of the curricular structure and physical facilities through out these sessions of running the program.