Papers by FERGYANTO GUNAWAN
ICIC Express Letters, 2019
Heart disease is known to be one of the primary causes of death worldwide. In the United States, ... more Heart disease is known to be one of the primary causes of death worldwide. In the United States, the disease is the leading cause of death for people of most ethnic-ities. In Indonesia, the disease contributes 17% of the total mortality. It is also well-known that a regular or continuous monitoring the heart rate is necessary to minimize the fatality. At the current technological state, the monitoring method is expensive and often requires a wearable sensor, which is inconvenient. This study intends to establish a relationship between the heart rate and speech signals empirically by using regression and correlation analysis. The speech signals are analyzed through a frequency analysis using fast Fourier transform. The results suggest that vowel 'e' speech signal has a strong correlation to the heart rate.
Bookmarks Related papers MentionsView impact
ICIC Express Letters, 2018
We address the issue of reliability of F-statistic method for predicting the structural integrity... more We address the issue of reliability of F-statistic method for predicting the structural integrity on the basis of the vibration data. The method is traditional but to the best of the author's knowledge, its weaknesses and reliability have not been explored. As this work demonstrates, the use of the method often leads to false-positive predictions, where intact structures are predicted to be damaged, and false-negative predictions, where damaged structures are predicted to be intact. We claim the use of the statistic in conjunction with a linear classification model should improve the prediction accuracy. To demonstrate the claim, 17494 examples of data are established from a numerical simulation of a seven-degree-of-freedom model, which is widely studied in the field of structural health monitoring. Then, the data are divided into two groups with the ratio of 70:30 for model development and testing. A linear classification model is established by minimizing a combination of a hinge loss function and a regularization loss function. An optimal regularization parameter is also determined. The present approach is able to increase the classification accuracy by about 10%.
Bookmarks Related papers MentionsView impact
ICIC Express Letters, 2018
Nowadays, there is a growing interest in e-learning, online learning that can be performed anywhe... more Nowadays, there is a growing interest in e-learning, online learning that can be performed anywhere at any time. The gamification is integrated in some e-learning management systems, and it is expected to increase the students' satisfaction, motivation, and engagement. This study aims to evaluate the effectiveness of gamification in e-learning. For this purpose, an educational website, www.bangsacerdas.com, is established, where the survey is conducted for registered students. There are two parts of participants: the students who are directed to a learning system with gamification and the students who are enrolled in a learning system without gamification. During the process, the level of user engagement and the quality of learning are being evaluated in each group. The t-test results for these two populations suggest that there are significant improvements in the learning experience of the participants in the classes that implement the gamification in their system.
Bookmarks Related papers MentionsView impact
TELKMONIKA, 2018
Most face recognition algorithms are generally capable to achieve a high level of accuracy when t... more Most face recognition algorithms are generally capable to achieve a high level of accuracy when the image is acquired under wellcontrolled conditions. The face should b e still during the acquisition process; otherwise, the resulted image would b e b lur and hard for recognition. Enforcing persons to stand still during the process is impractical; extremely likely that recognition should b e performed on a b lurred image. It is important to understand the relation b etween the image b lur and the recognition accuracy. The ORL Datab ase was used in the study. All images were in PGM format of 92 × 112 pixels from forty different persons, ten images per person. Those images were randomly divided into training and testing datasets with 50-50 ratio. Singular value decomposition was used to extract the features. The images in the testing datasets were artificially b lurred to represent a linear motion, and recognition was performed. The b lurred images were also filtered using various methods. The accuracy levels of the recognition on the b asis of the b lurred faces and filtered faces were compared. The performed numerical study suggests that at its b est, the image improvement processes are capab le to improve the recognition accuracy level b y less than five percent.
Bookmarks Related papers MentionsView impact
International Journal of Mechanical Engineering and Technology , 2018
Natural fibers are considered as the most ecological material, but their mechanical properties wi... more Natural fibers are considered as the most ecological material, but their mechanical properties widely vary from one fiber to another. To use natural fibers for component of a structural material, the wide scatter in tensile strength must be reduced to a certain level. This research aims to develop a method that can reduce the wide scatter in tensile strength of natural fibers. Pre-screening test was proposed here for one of the methods and the effectiveness was examined using experimental results on tensile strength of virgin and surviving fibers after the pre-screening test. It was indicated that three-parameter lognormal distribution could well characterize the experimental results, and the threshold tensile strength in three-parameter lognormal distribution could be related to allowable stress for strength design.
Bookmarks Related papers MentionsView impact
ICIC Express Letters, 2018
This study focuses on developing a simple three-layer Artificial Neural Network (ANN) model for a... more This study focuses on developing a simple three-layer Artificial Neural Network (ANN) model for automatic classification of road anomalies. The model is particularly important to facilitate the development of the road condition monitoring system. We limit the discussion to the system that utilizes vehicle vibration data to predict the associated road condition. The vibration data are obtained from a probe vehicle running over four road types: a road in a good condition, a road containing a pothole, a road containing a speed bump, and a road containing an expansion joint. The data are then used to extract the vehicle maximum rates of rotations in three directions: pitch, roll, and yaw. This study reports the aspects of the optimum size of the training data, the effects of the number of the neurons in the hidden layer, and the level of the achievable classification accuracy. The results show the optimized model with three neurons on the hidden layer is able to correctly classify damages at 85% accuracy.
Bookmarks Related papers MentionsView impact
TELKOMNIKA, 2018
The massive proliferation of social media has opened possib ilities for the perpetrator conductin... more The massive proliferation of social media has opened possib ilities for the perpetrator conducting the crime of online child grooming. Because the pervasiveness of the prob lem scale, it may on ly b e tamed effectively and efficiently b y using an automatic grooming conversation detection system. The current study intends to address the issue b y using Support Vector Machine and k-nearest neighb ors' classifiers. Besides, the study also proposes a low-computational cost classification method, which classifies a conversation using the numb er of the existing grooming conversation characteristics. All proposed methods are evaluated using 150 textual conversations of which 105 are grooming, and 45 are non-grooming. We identify that grooming conversations possess 17 features of grooming characteristics. The results suggest that the SVM and k-NN can identify grooming conversations at 98.6% and 97.8% of the level of accuracy. Meanwhile, the proposed simple method has 96.8% accuracy. The empirical study also suggests that two among the seventeen characteristics are insignificant for the classification.
Bookmarks Related papers MentionsView impact
ICIC Express Letters, 2019
Heart disease is known to be one of the primary causes of death worldwide. In the United States, ... more Heart disease is known to be one of the primary causes of death worldwide. In the United States, the disease is the leading cause of death for people of most ethnic-ities. In Indonesia, the disease contributes 17% of the total mortality. It is also well-known that a regular or continuous monitoring the heart rate is necessary to minimize the fatality. At the current technological state, the monitoring method is expensive and often requires a wearable sensor, which is inconvenient. This study intends to establish a relationship between the heart rate and speech signals empirically by using regression and correlation analysis. The speech signals are analyzed through a frequency analysis using fast Fourier transform. The results suggest that vowel 'e' speech signal has a strong correlation to the heart rate.
Bookmarks Related papers MentionsView impact
International journal of innovative computing, information and control, 2019
Car-following model is a mathematical model that regulates the movement of a vehicle in the longi... more Car-following model is a mathematical model that regulates the movement of a vehicle in the longitudinal direction in microscopic level. Commonly, the model describes the vehicle movement as a function of the vehicle relative position and velocity with respect to the leading vehicle. One of the widely used models is the Gazis-Herman-Rothery model, which is characterized by coefficients m and l. The values of the coefficients vary depending on many aspects such as vehicle type and road condition. The coefficients are usually determined from a calibration test where the vehicle position, velocity, and acceleration are measured accurately. So far, a few calibration methods have been proposed; some modern methods are by using remote sensing and RTK G-PS. In the current work, the vehicle movement is recorded in a perspective view from an elevation. The recorded vehicle movement is analyzed for the vehicle position using computer vision methods. Then, the position is transformed to the actual vehicle position. Two computer vision methods are evaluated: multilayer-and Eigen-background-subtraction methods. The proposed method is evaluated to track the movement of a vehicle traveling in a short-straight distance. The results show that the tracking accuracy of the multilayer-background-subtraction method is better than the Eigen-background-subtraction method. The multilayer-background-subtraction method has 96.6% for position accuracy and 88.9% for velocity accuracy, while the Eigen-background-subtraction method has 92.9% for position accuracy and 84.3% for velocity accuracy. The most reliable car following parameters are estimated with 3.2% of error. The obtained parameter m is 0.4 and l is 1.2. Various values of m and l have been proposed by many researchers where the reliable values are in the range of 0-2.7 for m and 0-2.8 for l. Our findings are within the range.
Bookmarks Related papers MentionsView impact
ICIC Express Letters, 2019
Technology Enhanced Learning (TEL) is one of the most dynamic areas of inquiry in education. One ... more Technology Enhanced Learning (TEL) is one of the most dynamic areas of inquiry in education. One form of TELs, on-screen learning, has become the topic of interest to many works. It is popular mainly with young people despite all findings, which undoubtedly suggest that it is detrimental to learning. The method hinders learning experience due to the reading spatial instability, difficulties in establishing mental map, and reduced visual ergonomics. Currently, many textbooks are available in electronic form and a majority of the students in Bina Nusantara University in Indonesia, for example, consider the way to be more convenient and preferable. In the electronic form, the textbooks are much more affordable. They are more accessible than the printed books. This work intends to explore a method of improving the learning quality of the electronic textbooks. The improvement is expected to be achieved by enriching the electronic textbook with cues in the form of margin notes, highlights, markers, lines and arrows, and navigation tools provided by the subject matter expert. The method is evaluated on a small class of 18 students at the university, and its effects are assessed. The participants are divided into two groups having the same distribution of the past academic performance where one group is assigned to learn using the recommendation system, and the other is without the system. After the learning, their mentalities are assessed systematically by qualitative and quantitative methods. The participants with the recommendation system outperform those without it significantly, marked by the values of the Cohen's effect size d larger than 1.20 with the standard deviation about 0.563.
Bookmarks Related papers MentionsView impact
TELKOMNIKA, 2018
It is necessary to develop an automated method to detect damaged road because manually monitoring... more It is necessary to develop an automated method to detect damaged road because manually monitoring the road condition is not practical. Many previous studies had demonstrated that the vibration-based technique has potential to detect damages on roads. This research explores the potential use of Artificial Neural Network (ANN) for detecting road anomalies based on vehicle accelerometer data. The vehicle is equipped with a smart-phone that has a 3D accelerometer and geo-location sensors. Then, the vehicle is used to scan road network having several road anomalies, such as, potholes, speedbump, and expansion joints. An ANN model consisting of three layers is developed to classify the road anomalies. The first layer is the input layer containing six neurons. The numbers of neurons in the hidden layer is varied between one and ten neurons, and its optimal number is sought numerically. The prediction accuracy of 84.9% is obtained by using three neurons in conjunction with the maximum acceleration data in x, y, and z-axis. The accuracy increases slightly to 86.5%, 85.2%, and 85.9% when the dominant frequencies in x, y, and z-axis, respectively, are taken into account beside the previous data.
Bookmarks Related papers MentionsView impact
ARCHIVE OF MECHANICAL ENGINEERING, 2018
Experimental design and computational model for predicting debonding initiation and propagation a... more Experimental design and computational model for predicting debonding initiation and propagation are of interest of scientists and engineers. The design and model are expected to explain the phenomenon for a wide range of loading rates. In this work, a method to measure and quantify debonding strength at various loading rates is proposed. The method is experimentally verified using data obtained from a static test and a pulse-type dynamic test. The proposed method involves the cohesive zone model, which can uniquely be characterized with a few parameters. Since those parameters are difficult to be measured directly, indirect inference is deployed where the parameters are inferred by minimizing discrepancy of mechanical response of a numerical model and that of the experiments. The main finding suggests that the design is easy to be used for the debonding characterization and the numerical model can accurately predict the debonding for the both loading cases. The cohesive strength of the stress-wave case is significantly higher than that of the static case; meanwhile, the cohesive energy is twice larger.
Bookmarks Related papers MentionsView impact
ICIC Express Letters, 2018
In Indonesia, especially Jakarta, many public facilities such as airports, train stations, bus st... more In Indonesia, especially Jakarta, many public facilities such as airports, train stations, bus stations are equipped with the Automatic External Defibrillators (AE-Ds). The effective use of these AEDs in public places by lay bystanders is important to improve the survival rate. Unfortunately, many people still have limited knowledge about AED and its critical function and lack of willingness to use the device. This research intends to measure the proportion of people in public places who have the knowledge concerning AED device and its use. The relevant data are collected by a survey on a random sample of 400 participants performed at the busiest railway station in Jakarta, Indonesia. The results suggest that almost 65% of them are unaware of the existence of the device in the public places. As many as 35% respondents do not recognize the device, and less than 35% respondents are willing to use the equipment.
Bookmarks Related papers MentionsView impact
Inverse Problems in Science and Engineering, 2015
Bookmarks Related papers MentionsView impact
Industrial and Systems Engineering Assessment Journal, Oct 27, 2012
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2016
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Procedia Computer Science, 2015
Bookmarks Related papers MentionsView impact
2015 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2015
Bookmarks Related papers MentionsView impact
Uploads
Papers by FERGYANTO GUNAWAN