Syed Saad Azhar Ali

An adaptive learning rate for RBFNN using time-domain feedback analysis.

Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control and time series prediction. In this paper, the learning algorithm of radial basis function neural networks is analyzed in a feedback structure. The robustness of the learning algorithm is discussed in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. An intelligent adaptation rule is developed for the learning rate of RBFNN which gives faster convergence via an estimate of error energy while giving guarantee to the l 2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development.

U-Model based online identification of Air Flow Plant

A key and critical challenge in Industrial processes is real-time system identification. This has prompted a lot of research efforts towards the development of model based adaptive identification methods. Their key advantage is that system parameters are tuned adaptively and online. This paper proposes online identification of Air Flow Plant using adaptive U-Model. The recently developed model is based on a polynomial structure. It adaptively corresponds to uncertain system parameters to adjust them online. U-Model method has shown promising results in terms of system identification. The proposed method is verified by simulation. Being control oriented in nature, an effective control strategy based upon U-Model can easily be developed.

Cloud task scheduling using nature inspired meta-heuristic algorithm

In this paper we investigate the application of Meta-Heuristic for cloud task scheduling on Hadoop. Hadoop is an open source implementation of MapReduce framework which extensively used for processing computational intensive jobs on huge amount of data over multi-node cluster. In order to achieve an efficient execution schedule, the scheduling algorithm requires to determining the order and the node on which tasks will be executed. A scheduling algorithm uses execution time, order of task arrival and location of data (i.e., assign task to the node which contains the required data) to determine the best execution schedule. We use Particle Swarm Optimization (PSO) to determine the tasks execution schedule and compare with tasks schedules obtained from other techniques like Genetic Algorithm (GA), Brute Force (BF) algorithm, First In First Out (FIFO) algorithm and Delay Scheduling Policy (DSP) algorithm. The results of this study prove the significance of PSO algorithm for cloud task scheduling over other algorithms.

Study on Wing Aspect Ratio on the Performance of a Gliding Robotic Fish

In this paper, the performance of a gliding robotic fish with different wing aspect ratio is investigated. The gliding robotic fish, developed by Michigan State University, has the energy efficient locomotion of an underwater glider and high maneuverability of a robotic fish. ANSYS Computational Fluid Dynamics turbulence model was used to determine lift and drag coefficients for various wing aspect ratios at different angle of attack. Subsequently, the corresponding glide angle and velocity were determined analytically based on its dynamic model. The simulation results compare well with published experimental data and shows that the drag and lift coefficients are inversely proportional to the wing aspect ratio. As such, a gliding robotic fish with a low wing aspect ratio is suitable for shallow waters only, due to the high lift forces generated for a given angle of attack, requiring greater energy to sustain the glide velocity and vice versa.

Underwater 3-D Scene Reconstruction Using Kinect v2 Based on Physical Models for Refraction and Time of Flight Correction

Commercial RGB-D cameras provide the possibility of fast, accurate, and cost-effective 3-D scanning solution in a single package. These economical depth cameras provide several advantages over conventional depth sensors, such as sonars and lidars, in specific usage scenarios. In this paper, we analyze the performance of Kinect v2 time-of-flight camera while operating fully submerged underwater in a customized waterproof housing. Camera calibration has been performed for Kinect’s RGB and NIR cameras, and the effect of calibration on the generated 3-D mesh is discussed in detail. To overcome the effect of refraction of light due to the sensor housing and water, we propose a time-of-flight correction method and a fast, accurate and intuitive refraction correction method that can be applied to the acquired depth images, during 3-D mesh generation. Experimental results show that the Kinect v2 can acquire point cloud data up to 650 mm. The reconstruction results have been analyzed qualitatively and quantitatively, and confirm that the 3-D reconstruction of submerged objects at small distances is possible without the requirement of any external NIR light source. The proposed algorithms successfully generated 3-D mesh with a mean error of ±6 mm at a frame rate of nearly 10 fps. We acquired a large data set of RGB, IR and depth data from a submerged Kinect v2. The data set covers a large variety of objects scanned underwater and is publicly available for further use, along with the Kinect waterproof housing design and correction filter codes. The research is aimed toward small-scale research activities and economical solution for 3-D scanning underwater. Applications such as coral reef mapping and underwater SLAM in shallow waters for ROV’s can be a viable application area that can benefit from results achieved.

Stock market prediction using machine learning techniques

The main objective of this research is to predict the market performance of Karachi Stock Exchange (KSE) on day closing using different machine learning techniques. The prediction model uses different attributes as an input and predicts market as Positive & Negative. The attributes used in the model includes Oil rates, Gold & Silver rates, Interest rate, Foreign Exchange (FEX) rate, NEWS and social media feed. The old statistical techniques including Simple Moving Average (SMA) and Autoregressive Integrated Moving Average (ARIMA) are also used as input. The machine learning techniques including Single Layer Perceptron (SLP), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and Support Vector Machine (SVM) are compared. All these attributes are studied separately also. The algorithm MLP performed best as compared to other techniques. The oil rate attribute was found to be most relevant to market performance. The results suggest that performance of KSE-100 index can be predicted with machine learning techniques.

Wind farm layout design using modified particle swarm optimization algorithm

Wind energy has shown tremendous potential for power generation. The energy is generated by wind turbines placed in a wind farm. To extract maximum energy from these wind farms, one of the most important issues is an efficient layout of the farms. This layout governs the location of each turbine in the wind farm. Due to its complexity, the wind farm layout design problem is classified as a complex optimization problem. Several attempts have been made previously to come up with better approaches and algorithms for optimization of wind farm. This paper proposes yet another optimization algorithm which is based on the particle swarm optimization (PSO) algorithm, which is a popular optimization algorithm. The proposed algorithm, termed as the modified particle swarm optimization algorithm (MPSO), is compared with previous results generated by another optimization algorithm, namely, genetic algorithm. Results indicate that MPSO generated better results.

Underwater 3D scanning using Kinect v2 time of flight camera

This paper presents preliminary results of using commercial time of flight depth camera for 3D scanning of underwater objects. Generating accurate and detailed 3D models of objects in underwater environment is a challenging task. This work presents experimental results of using Microsoft Kinect v2 depth camera for dense depth data acquisition underwater that gives reasonable 3D scanned data but with smaller scanning range. Motivations for this research are the user friendliness and low-cost of the device as compared to multi view stereo cameras or marine-hardened laser scanning solutions and equipment. Preliminary results of underwater point cloud generation and volumetric reconstruction are also presented. The novelty of this work is the utilization of the Kinect depth camera for real-time 3D mesh reconstruction and the main objective is to develop an economical and compact solution for underwater 3D scanning.

An EEG-based functional connectivity measure for automatic detection of alcohol use disorder

BACKGROUND The abnormal alcohol consumption could cause toxicity and could alter the human brains structure and function, termed as alcohol used disorder (AUD). Unfortunately, the conventional screening methods for AUD patients are subjective and manual. Hence, to perform automatic screening of AUD patients, objective methods are needed. The electroencephalographic (EEG) data have been utilized to study the differences of brain signals between alcoholics and healthy controls that could further developed as an automatic screening tool for alcoholics. METHOD In this work, resting-state EEG-derived features were utilized as input data to the proposed feature selection and classification method. The aim was to perform automatic classification of AUD patients and healthy controls. The validation of the proposed method involved real-EEG data acquired from 30 AUD patients and 30 age-matched healthy controls. The resting-state EEG-derived features such as synchronization likelihood (SL) were computed involving 19 scalp locations resulted into 513 features. Furthermore, the features were rank-ordered to select the most discriminant features involving a rank-based feature selection method according to a criterion, i.e., receiver operating characteristics (ROC). Consequently, a reduced set of most discriminant features was identified and utilized further during classification of AUD patients and healthy controls. In this study, three different classification models such as Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were used. RESULTS The study resulted into SVM classification accuracy=98%, sensitivity=99.9%, specificity=95%, and f-measure=0.97; LR classification accuracy=91.7%, sensitivity=86.66%, specificity=96.6%, and f-measure=0.90; NB classification accuracy=93.6%, sensitivity=100%, specificity=87.9%, and f-measure=0.95. CONCLUSION The SL features could be utilized as objective markers to screen the AUD patients and healthy controls.

Forearm pressure distribution during ambulation with elbow crutches

This paper studies the pressure distribution on the forearm and the hand palm during ambulation with forearm crutches. It also presents the design, modelling and development of a forearm crutch that is capable of eliminating the high pressure induced on patients palm and forearm areas while gating; preventing other injuries to the nerves and muscles of the mentioned extremities. Eventually, one of the main objective of conducting this project is to make the patients feel less tired and more comfortable during crutch-aided ambulation. The design of the crutch is drawn using CATIA software, a CAD modelling package. The study on the developed design is to prove that it is of high quality and is more comfortable compared to available regular forearm crutches. It is developed using two experimental methods, namely: Energy Expenditure Index (EEI) and Electromyography (EMG). The experiments related to the mentioned methods have been conducted with the help of 10 healthy/normal volunteers. Also the crutch parts have been simulated using COMSOL Multiphysics Software. Lastly, a survey was prepared and its results are also provided in accordance with the way the patients feel about the developed design. The results of all four methods mentioned, show that the focal pressure on the patients hand and forearm has been significantly reduced; also, the energy expenditure level has been dropped. It can be concluded that the developed crutch is of high quality and is more comfortable compared to regular forearm crutches.