Ary Setijadi Prihatmanto

A computer cursor controlled by eye movements and voluntary eye winks using a single channel EOG

This paper proposes a computer mouse-like device that is controlled by eye movements and voluntary eye winks using a single channel of EOG. The position of a pair electrode, and time-domain signal analysis are also presented.

Cloud computing reference model: The modelling of service availability based on application profile and resource allocation

Under unconsolidated resources, cloud computing providers have to allocate some resources to fullfil client request based on the on-demand mode. Using the applications profile, Infrastructure-as-a-Service model can be developed. Basically, Infrastructure-as-a-Service model provides resources in the form of computation power (CPU-hours unit), storage (gigabytes unit), network bandwidth (Internet data transfer, GB per day unit), and electrical power (kWh). From service availability point of view, reference model is previously developed as a backup framework. In this research, the development of cloud computing reference model for on-demand services is based on both application characteristics and resources availability. The objective of development model in this research is to decrease idle resources.

Design and implementation of adaptive neural networks algorithm for DC motor speed control system using simple microcontroller

This paper shows the design and implementation of adaptive neural networks controller for DC motor speed control system. The DC motor is actuated by a pulse width modulation (PWM)-based H-bridge actuator. By using certain learning methods to the networks, changing a plants parameter can be estimated and used to produce an appropriate control action. The experiment shows that the controller conforms to the adaptive control scheme, although there are flaws which relate to feedback resolution. The most interesting result is that the implementation circuit is based on a very simple 8-bit microcontroller system.

Gamification design of traffic data collection through social reporting

Congestion is a common problem faced by large cities. The ineffective implementation of control functions by road operator may contribute to produce this problem. To overcome it, road operators must be able to produce appropriate policies. But to make policy or the right traffic decisions, it require as much data as possible that can be obtained continuously. Where the quality or validity of these data will affect the quality of the decision obtained. This research proposed a concept of the form of digital activities for collecting traffic data through a kind of social networking that is focused on the transportation system. Where through this system the public can be involved in the collection and validation of data. Thereby collecting traffic data can take place faster with better results in quality and quantity. With the availability of good data, then the great concept of the Intelligent Transportation System will be achieved. Gamification is used in the design and implementation process to increase interest and public confidence towards the system.

Brain signal reference concept using cross correlation based for brain computer interface

The sub system for EEG based brain computer interface system are feature extraction and classification. Translation from brain signal that contain a human intention into computers command or message should be accomplished with good feature extraction nor classification. One of the methods for analyzing brain signal in feature extraction process is using band power measurement from few or many EEG channels. Recalibration or daily calibration was needed in using brain computer interface instrument. In order to make the feature extraction more reliable, the proposed method is using brain signal reference. To develop brain signal reference, sampling method taken from brain signal when human intention occur. The next feature extraction will analyze whether the signal is similar with signal reference or not. Feature extraction will uses cross correlation method to measure the similarity. Based on the hypothesis that brain will produce the similar signal in the same intention, the brain signal reference concept is the method can be used for feature extraction process. It is also should be considered the level of similarity which it will transfer to classification process in estimating the intention. It is feasible using brain signal reference concept based on cross correlation method.

Time-Frequency Features Combination to Improve Single-Trial EEG Classification

In this paper, we propose a combination of two simple feature extraction methods from time and frequency domain to improve singe-trial EEG classification in self-paced BCI. ‘Bereitschaftspotential’ (BP) features from time domain and event-related desynchronization (ERD) features from frequency domain are merged and feed into four different classifiers which are probabilistic neural network (PNN), support-vector machine (SVM), K-nearest neighbor (KNN), and Parzen classifier (PC). Results using BCI competition 2003 [1] dataset IV are showing that the combined features are quite discriminative as we reached an accuracy on the test set ranging from 82% to 85% whereas the winner of the competition on this data set reached 84% using three types of features [2,3].

Designing gamification for taxi booking system (Case study: Bandung smart transportation system)

Traffic congestion is one of the main problems in the transportation system. This continues to happen because road capacity is no longer able to accommodate the number of vehicles, while the number of vehicles continues to increase every year. Based on statistical data sourced from the Indonesian National Police, the number of private vehicles increased significantly each year. People prefer to use private vehicles to travel. Security issues, comfort, and travel expenses flexibility are the reason they prefer to use private vehicles. Taxi should be a solution for them, because taxi is more flexible, convenient, and safe compared to other public transportation. But the problems of security and ease of access that back into obstacles. Bandung Smart Transportation System (BSTS) is present as one of technology Intelligent Transportation System (ITS) use Bandung City as a case study. BSTS is a system developed with the aim to collect all traffic information integrated with the transport system infrastructure and manage information centrally. This research discusses the designing of gamification system in a taxi booking service. Aims to increase the interest, motivation, loyalty and further the public to continue using BSTS and use public transportation. If peoples more interested in public transportation, expected to reduce the use of private vehicles. So the number of vehicles can be reduced and traffic arrangements can be run better as it can be ascertained that the drivers on the road is a professional driver.

Bicep brachii's force estimation using MAV method on assistive technology application

This paper presents signal processing of single channel surface electromyography (sEMG) on bicep brachii and its alternative application on assistive technology. Mean Absolute Value (MAV) method is used to estimate the average of muscles force which correlates with its sEMG voltage amplitude. As a result, this estimating value controls box in virtual world as biofeedback in three classes; rest condition, lifted arm without load, and lifted arm with load. From this point, bicep brachiis force value can be estimated by using its sEMG voltage amplitude in particular range.

Shesop Healthcare: Android application to monitor heart rate variance, display influenza and stress condition using Polar H7.

Shesop is an integrated system to make human lives more easily and to help people in terms of healthcare. Stress and influenza classification is a part of Shesops application for a healthcare devices such as smartwatch, polar and fitbit. The main objective of this paper is to create a proper application to implement the stress and influenza classification. The application use Android studio, XML and Java. Also, while creating this application, all design and program is considered to be available for future updates. The application needs an android smartphone with Bluetooth Low Energy technology (bluetooth v4.0 or above). SheSop application will accommodate data entry, device picker, data gathering process, result and saving the result. In the end, we could use the polar H7 and this application to get a real-time heart rate, Heart rate variability and diagnose our stress and influenza condition.

Shesop Healthcare: Stress and influenza classification using support vector machine kernel

Shesop is an integrated system to make human lives more easily and to help people in terms of healthcare. Stress and influenza classification is a part of Shesops application for a healthcare devices such as smartwatch, polar and fitbit. The main objective of this paper is to classify a new data and inform whether you are stress, depressed, caught by influenza or not. We will use the heart rate data taken for months in Bandung, analyze the data and find the Heart rate variance that constantly related with the stress and flu level. After we found the variable, we will use the variable as an input to the support vector machine learning. We will use the lagrangian and kernel technique to transform 2D data into 3D data so we can use the linear classification in 3D space. In the end, we could use the machine learnings result to classify new data and get the final result immediately: stress or not, influenza or not.