Resmana Lim

Facial landmarks localization based on fuzzy and Gabor wavelet graph matching

Proposes a method that automatically finds human faces as well as its landmark points in color images based on a fuzzy analysis. The proposed approach first uses color information to detect face candidate regions and then uses a fuzzy analysis of the color, shape, symmetry and interior facial features. A deformable Gabor wavelet graph matching is used to locate the facial landmark points describing the face. The latter allows for size and orientation variation since the search for landmark points allows for affine transformations as well as local deformations of the Gabor wavelet graph. The search is performed using a genetic algorithm that is essential because it effectively searches the solution space. Results based on the proposed method are included to verify the effectiveness of the proposed approach.

Voice conversion application (VOCAL)

Recently, a lot of works has been done in speech technology. Text-to-Speech and Automatic Speech Recognition have been the priorities in research efforts to improve the human-machine interaction. The ways to improve naturalness in human-machine interaction is becoming an inportant matter of concern. Voice conversion can be served as a useful tools to provide new insights related to personification of speech enabled systems. In this research, there are two main parameters are considered vocal tract structure and pitch. For conversion process speech is resolved in two components, excitation component and filtered component using Linear Predictive Coding (LPC). Ptich is determined by autocorrelation. After obtained the acoustic components from source speaker and target speaker, then the acoustic components will be mapped one-to-one to replaced the the acoustic feature from source speaker to target speaker. At least, signal is modified by resynthesis so the resulted speech would perceive as if spoken by target speaker.

Proceedings of Second International Conference on Electrical Systems, Technology and Information 2015 (ICESTI 2015)

This book includes the original, peer-reviewed research papers from the 2nd International Conference on Electrical Systems, Technology and Information (ICESTI 2015), held in September 2015 at Patra Jasa Resort & Villas Bali, Indonesia. Topics covered include: Mechatronics and Robotics, Circuits and Systems, Power and Energy Systems, Control and Industrial Automation, and Information Theory. It explores emerging technologies and their application in a broad range of engineering disciplines, including communication technologies and smart grids. It examines hybrid intelligent and knowledge-based control, embedded systems, and machine learning. It also presents emerging research and recent application in green energy system and storage. It discusses the role of electrical engineering in biomedical, industrial and mechanical systems, as well as multimedia systems and applications, computer vision and image and signal processing. The primary objective of this series is to provide references for dissemination and discussion of the above topics. This volume is unique in that it includes work related to hybrid intelligent control and its applications. Engineers and researchers as well as teachers from academia and professionals in industry and government will gain valuable insights into interdisciplinary solutions in the field of emerging electrical technologies and its applications.

Adaptive Cars Headlamps System with Image Processing and Lighting Angle Control

The project proposed a prototype of an adaptive car headlamps control using image processing. The adaptive headlamps system focuses on the lighting angle control of low beam in the headlamps which its light tracks moved horizontally. The controller in headlamps is based on image processing from a camera mounted on the car. Adaptive headlamps system consists of portable tiny computer of Raspberry Pi, Arduino microcontroller, and two stepper motors for the left and the right headlamps. The system was implemented on the headlamps of a Toyota Avanza car. The adaptive headlamps system could detect most types of cars ahead. It could decrease a ‘glare’ effect and increase the driver sight based on survey taken from the driver and the driver of opposite car. The system still couldn’t detect the opposite car with high intensity of light from braking lamps, as well as the light from the opposite front lamps.

SISTEM PENGEMBANGAN KENDALI FUZZY LOGIC BERBASIS MIKROKONTROLER KELUARGA MCS51 (PetraFuz)

This paper presents a project of Web-based Distance Learning support system. The system has been built based on the Internet and World Wide Web facility. The system could be accessed with a web browser which is directed to a certain web server address so that students can do learning process just like in the real situation, such as student admissions, taking course materials, syllabus, assignments, students grades, class discussions through web, and doing online quizzes. Students could also join collaboration works by giving opinions, feedback and student produced paper/web which can be shared to the entire learning community. Therefore, it will build a collaborative learning environment where lectures together with students make constructive knowledge databases for entire learning community. This system has been developed based on Active Server Pages (ASP) technology from Microsoft which is embedded in a web server. Web pages reside in a web server which is connected to an SQL Database Server. Database server is used to store structured data such as lectures/students personal information, course lists, syllabus and its descriptions, announcement texts from lecturers, commentaries for discussion forum, student’s study evaluations, scores for each assignment, quizzes for each course, assignments text from lectures, assignments which are collected by students and students contribution/materials. This system has been maintained by an administrator for maintaining and developing web pages using HTML. The administrator also does ASP scripts programming to convert web pages into active server pages. Lectures and students could contribute some course materials and share their ideas through their web browser. This web-based collaborative learning system gives the students more active role in the information gathering and learning process, making the distance students feel part of a learning community, therefore increasing motivation, comprehension and interaction with other students.Nowadays, most of the information is still in printed format. To reproduce it in the electronic form, we need an efficient way to save the scanned document. For this purpose, AT & T Labs has been developing a new technology called DjVu. In this paper, we try to compare DjVu and JPG format. The goal is to decide whether DjVu is better or not. To achieve the goal, we try to scan the document and save it in DjVu and JPG format, make comparison between these two based on file size and image quality. Comparison is done for three types of document, such as b/w photo, document with text, and document in colour. The conclusion is, DjVu format is better than JPG in file size and quite good in image quality. So, DjVu have a chance to become a new standart.

Tracing Related Scientific Papers by a Given Seed Paper Using Parscit

The project developed a web site learning support for tracing scientific articles relating to a given input seed paper/article. The system will finds related articles that are listed on the references of the seed article. First, the reference list of an input seed article is extracted by utilizing Parscit citation extraction. Furthermore, the system searches the reference articles using Google Scholar and Mendeley API. Thus articles which are related to the seed article can be found. The system was built using PHP programming, it is utilizing Parscit modules, Google Scholar search and https://www.mendeley.com/ API. Testing has been done by giving an input seed article. User will obtain the results of several articles related to the seed article.

Games and Multimedia Implementation on Heroic Battle of Surabaya: An Android Based Mobile Device Application

Number of users of who use mobile devices and other handheld devices is rapidly increased (such as smartphones and tablet computers). This phenomena has changed the lifestyle of many people, especially in the ease of access to information. For example, access to any business information, political information, tourism information, as well as educational information. Education has also entered a new era, where books and other teaching materials, are not only presented using paper media but also in electronic form. Student can easily access that electronic information using computer/laptop or smartphone/tablet PC. So now, learning can be delivered in a more interesting and interactive media and model. It becomes new challenges for education, especially in teaching nation history, where education in paper material is no longer quite interesting. Therefore, new teaching media is required, that more interesting and interactive to the student. At this time, there are not many applications on mobile devices that explore education especially on heroic history of Indonesia. On the other hand, the education of heroic history become more necessary today, especially for young people. To answer this challenge, in this research we like to build an application software based on android mobile devices that contain education the history of the heroic battles 10 November 1945 in Surabaya. The application will provide the information of battle history, and also games and multimedia interactive such as sound, video streaming that built on android based mobile device. With this educational applications we expected that everyone especially young people can learning the knowledge about the history of the heroic battle 10 November 1945 Surabaya in the mobile device based on Android in interactive educational applications that provide a thorough understanding and fascinating history of the events surrounding the battle, and also exploring the historic sites in Surabaya and found fascinating city of Surabaya.

Odometry Algorithm with Obstacle Avoidance on Mobile Robot Navigation

Many algorithms have been devised on mobile robot navigation system. Some of them use algorithm based on newer concept like fuzzy logic or genetic algorithm. Some are stick on older algorithm like odometry. A simple, less intensive calculation algorithm for a lightweight telepresence robot is required. To accommodate the requirement, odometry algorithm is chosen specifically. Obstacle avoidance feature is proposed to enhance the algorithm. A mobile robot prototype is implemented using Arduino UNO, two DC geared motors, single caster wheel, and an ultrasonic sensor. Two kind of experiments are performed. The first experiment is to verify that odometry algorithm is working. The second one is used to verify obstacle avoidance mechanism. The results are satisfying. Mobile robot can avoid the obstacle and reach the destination correctly. Further experiment is needed to decide about ultrasonic sensor placement in a real telepresence robot.

Room Access Control System Using Facial Image Recognition

The aim of the project is to implement a facial recognition system for access control to enter a room. The facial image captured by a webcam and then be detected/tracked using Haar face tracking algorithm. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) algorithm have been used for face recognition. The system was tested with 10 users from the member of a laboratory room. Each user registered 100 images for training of the PCA and LDA. The recognition rate achieved using PCA was 70% and 97% for LDA.

GALILEE: AN INTERNET WEB BASED DISTANCE LEARNING SUPPORT SYSTEM

This paper presents a project of Web-based Distance Learning support system. The system has been built based on the Internet and World Wide Web facility. The system could be accessed with a web browser which is directed to a certain web server address so that students can do learning process just like in the real situation, such as student admissions, taking course materials, syllabus, assignments, students grades, class discussions through web, and doing online quizzes. Students could also join collaboration works by giving opinions, feedback and student produced paper/web which can be shared to the entire learning community. Therefore, it will build a collaborative learning environment where lectures together with students make constructive knowledge databases for entire learning community. This system has been developed based on Active Server Pages (ASP) technology from Microsoft which is embedded in a web server. Web pages reside in a web server which is connected to an SQL Database Server. Database server is used to store structured data such as lectures/students personal information, course lists, syllabus and its descriptions, announcement texts from lecturers, commentaries for discussion forum, student’s study evaluations, scores for each assignment, quizzes for each course, assignments text from lectures, assignments which are collected by students and students contribution/materials. This system has been maintained by an administrator for maintaining and developing web pages using HTML. The administrator also does ASP scripts programming to convert web pages into active server pages. Lectures and students could contribute some course materials and share their ideas through their web browser. This web-based collaborative learning system gives the students more active role in the information gathering and learning process, making the distance students feel part of a learning community, therefore increasing motivation, comprehension and interaction with other students.Nowadays, most of the information is still in printed format. To reproduce it in the electronic form, we need an efficient way to save the scanned document. For this purpose, AT & T Labs has been developing a new technology called DjVu. In this paper, we try to compare DjVu and JPG format. The goal is to decide whether DjVu is better or not. To achieve the goal, we try to scan the document and save it in DjVu and JPG format, make comparison between these two based on file size and image quality. Comparison is done for three types of document, such as b/w photo, document with text, and document in colour. The conclusion is, DjVu format is better than JPG in file size and quite good in image quality. So, DjVu have a chance to become a new standart.