Alpha Agape Gopalai

A Wearable Real-Time Intelligent Posture Corrective System Using Vibrotactile Feedback

Biofeedback is known to improve postural control and shorten rehabilitation periods among the young and elderly. A biofeedback system communicates with the human central nervous system through a variety of feedback modalities. Vibrotactile feedback devices are gaining attention due to their desirable characteristics and simplistic manner of presenting biofeedback. In this study, we investigate the potential of incorporating a real-time biofeedback system with artificial intelligence for wobble board training, aimed at improving ankle proprioception. The designed system utilizes vibrotactile actuators to provide forewarning for poor postural control. The biofeedback system depended on Euler angular measurements of trunk and wobble board displacements, from inertial measurement units (IMUs). A fuzzy inference system was used to determine the quality of postural control, based on IMU-acquired measurements of trunk and wobble board. The designed system integrates: 1) two IMUs, 2) a fuzzy knowledge base, and 3) a feedback-generation module. Tests were conducted in eyes-open and eyes-close conditions while standing on the wobble board to assess viability of the system in providing accurate real-time intervention. The results observed an improvement in postural control with biofeedback intervention, demonstrating successfulness of the prototype built for improving postural control in rehabilitative and preventive applications.

A robust real-time gait event detection using wireless gyroscope and its application on normal and altered gaits.

Gait events detection allows clinicians and biomechanics researchers to determine timing of gait events, to estimate duration of stance phase and swing phase and to segment gait data. It also aids biomedical engineers to improve the design of orthoses and FES (functional electrical stimulation) systems. In recent years, researchers have resorted to using gyroscopes to determine heel-strike (HS) and toe-off (TO) events in gait cycles. However, these methods are subjected to significant delays when implemented in real-time gait monitoring devices, orthoses, and FES systems. Therefore, the work presented in this paper proposes a method that addresses these delays, to ensure real-time gait event detection. The proposed algorithm combines the use of heuristics and zero-crossing method to identify HS and TO. Experiments involving: (1) normal walking; (2) walking with knee brace; and (3) walking with ankle brace for overground walking and treadmill walking were designed to verify and validate the identified HS and TO. The performance of the proposed method was compared against the established gait detection algorithms. It was observed that the proposed method produced detection rate that was comparable to earlier reported methods and recorded reduced time delays, at an average of 100 ms.

Malaysia traffic sign recognition with convolutional neural network

Traffic sign recognition system is an important subsystem in advanced driver assistance systems (ADAS) that assisting a driver to detect a critical driving scenario and subsequently making an immediate decision. Recently, deep architecture neural network is popular because it adapts well in various kind of scenarios, even those which were not used during training. Therefore, a deep architecture neural network is implemented to perform traffic sign classification in order to improve the traffic sign recognition rate. A comparative study for a deep and shallow architecture neural network is presented in this paper. Deep and shallow architecture neural network refer to convolutional neural network (CNN) and radial basis function neural network (RBFNN) respectively. In the simulation result, two types of training modes had been compared i.e. incremental training and batch training. Experimental results show that incremental training mode trains faster than batch training mode. The performance of the convolutional neural network is evaluated with the Malaysian traffic sign database and achieves 99% of the recognition rate.

Design and synthesis of reversible arithmetic and Logic Unit (ALU)

In low power circuit design, reversible computing has become one of the most efficient and prominent techniques in recent years. In this paper, reversible Arithmetic and Logic Unit (ALU) is designed to show its major implications on the Central Processing Unit (CPU).In this paper, two types of reversible ALU designs are proposed and verified using Altera Quartus II software. In the proposed designs, eight arithmetic and four logical operations are performed. In the proposed design 1, Peres Full Adder Gate (PFAG) is used in reversible ALU design and HNG gate is used as an adder logic circuit in the proposed ALU design 2. Both proposed designs are analysed and compared in terms of number of gates count, garbage output, quantum cost and propagation delay. The simulation results show that the proposed reversible ALU design 2 outperforms the proposed reversible ALU design 1 and conventional ALU design.

Real-time stability measurement system for postural control

A method for assessing balance, which was sensitive to changes in the postural control system is presented. This paper describes the implementation of a force-sensing platform, with force sensing resistors as the sensing element. The platform is capable of measuring destabilized postural perturbations in dynamic and static postural conditions. Besides providing real-time qualitative assessment, the platform quantifies the postural control of the subjects. This is done by evaluating the weighted center of applied pressure distribution over time. The objective of this research was to establish the feasibility of using the force-sensing platform to test and gauge the postural control of individuals. Tests were conducted in Eye Open and Eye Close states on Flat Ground (static condition) and the balance trainer (dynamic condition). It was observed that the designed platform was able to gauge the sway experienced by the body when subjects states and conditions changed.

Determining Level of Postural Control in Young Adults Using Force-Sensing Resistors

A force-sensing platform (FSP), sensitive to changes of the postural control system was designed. The platform measured effects of postural perturbations in static and dynamic conditions. This paper describes the implementation of an FSP using force-sensing resistors as sensing elements. Real-time qualitative assessment utilized a rainbow color scale to identify areas with high force concentration. Postprocessing of the logged data provided end-users with quantitative measures of postural control. The objective of this research was to establish the feasibility of using an FSP to test and gauge human postural control. Tests were conducted in eye open and eye close states. Readings obtained were tested for repeatability using a one-way analysis of variance test. The platform gauged postural sway by measuring the area of distribution for the weighted center of applied pressure at the foot. A fuzzy clustering algorithm was applied to identify regions of the foot with repetitive pressure concentration. Potential application of the platform in a clinical setting includes monitoring rehabilitation progress of stability dysfunction. The platform functions as a qualitative tool for initial, on-the-spot assessment, and quantitative measure for postacquisition assessment on balance abilities.

Design of reversible multiplexer/de-multiplexer

Reversible logic is an emerging technique of upcoming future technologies. Low heat dissipation and energy recycle principle are encouraging its demand for low power daily usage portable devices. In this paper, two reversible gates have been proposed, named as R-I gate and R-II gate, for realizing reversible combinational logic circuits. The proposed two gates can be used for realisation of basic logical functions such as AND, XOR, MUX etc. Besides these functions, other advantage of the proposed R-I gate is that it can be used as a 1:2 de-multiplexer without requiring any extra logic circuits and the proposed R-II gate can be used as a half adder circuit. The proposed reversible gates are implemented and verified using Xilinx ISE 10.1 software. The simulation results show that the proposed designs are more efficient in terms of gate count, garbage outputs and constant inputs than the existing reversible logic gate.

Reversible logic gate implementation as switch controlled reversible full adder/subtractor

Reversible computation plays an important role in low power circuit design and efficient energy recycling. In this paper, a switch controlled efficient Reversible Full Adder/Subtractor (RFAS) is presented. RFAS block is further used in the construction of n-bit adder/subtractor. The proposed design is analyzed and compared against the existing reversible techniques. Features such as, hardware cost, logic calculation and gate count etc. are investigated to show the efficiency of the design. Simulation results are verified using Altera Quartus II and ModelSim software. Observations suggest that the circuit offers lesser hardware complexity compared to the existing reversible full adder.

Multilayer perceptron neural network classification for human vertical ground reaction forces

In this paper, human motion classification using multilayered neural network is proposed to classify motion signal based on vertical ground resultant force (VGRF). VRGF readings were acquired using an instrumented treadmill. The work presented in this paper seeks to classify six activities i.e. standing to walking, walking, walking to jogging, jogging, jogging to running and running, based on the measured VGRF. The data set involved 229 healthy Asians aged between 20 and 24, yielding a total of 740 activity classes. All activities varied as a result of subjects desired speed. However, it was observed that the VGRF of the last five strides reaction forces was sufficient to achieve 83% classification rate for the training set and 73% for testing set. The influence of number of hidden neurons was also analyzed to obtain optimal classification performance.

Blood Pressure measurement from Photo-Plethysmography to Pulse Transit Time

Blood Pressure (BP) is one of the vital signs in the clinical assessment of patients in both acute and chronic care settings. However, existing BP measurement devices are less portable or invasive and do not allow continuous ambulatory monitoring. In this study, we propose a non-invasive BP-monitoring system using an efficient mathematical model and algorithm to measure the BP by relating Pulse Wave Velocity (PWV) and Pulse Transit Time (PTT) obtained from the Photo-Plethysmography (PPG). An optical system including two sets of PPG sensor probes are used to detect two light reflected signals via finger and wrist. From these PPGs, Pulse Wave Velocity (PWV) and PTT can be estimated to understand the blood flow in the blood vessel. This portable BP monitoring system measures the BP continuously without the need for a cuff and ECG signals. The device does not require a pneumatic cuff and so it facilitates rapid assessment of patients in an acute setting and allows ambulatory self-monitoring of the BP. It also reduces patients stress and discomfort due to cuff inflations.