Wahju Sediono

Hybrid Technique Using Singular Value Decomposition (SVD) and Support Vector Machine (SVM) Approach for Earthquake Prediction

Most of the existing earthquake (EQ) prediction techniques involve a combination of signal processing and geophysics techniques which are relatively complex in computation for analysis of the Earths electric field data. This paper proposes a relatively simpler and faster method that involves only signal processing procedures. The prediction of the EQ occurrence estimation using a combination of singular value decomposition (SVD)-based technique for feature extraction and support vector machine (SVM) classifier is presented in this paper. Using the proposed method, the Earths electric field signal is transformed into a new domain using SVD-based approach. In this approach, the time domain signal is projected on the left eigenvectors of impulse response matrix of the linear prediction coefficient (LPC) filter. Several features have been extracted from the transformed signal. These features are used as input for the SVM classifier in order to predict the location of the forthcoming EQ. Once the location is determined, a similar approach is used to estimate its magnitude. Finally, the time estimation of the forthcoming EQ is estimated based on the statistical observation. The occurred EQs during 2008 in Greece are used to train the classifiers, whereas those occurred from 2003 to 2010 in the same region are used to evaluate the performance of the proposed system. In predicting the location of the future EQs, the proposed system could achieve 77% accuracy. As for the magnitude prediction, the proposed system provides an accuracy of 66.67%. Moreover, the predicted time for the EQ with magnitude greater than Ms = 5 is 2 days ahead, whereas for magnitude greater than Ms = 6 is up to 7 days ahead.

2D Image reconstruction of radar INDERA

INDERA is the first Indonesian maritime radar that works using the frequency modulated continuous wave (FMCW) technology. In the surveillance mode INDERA continuously transmits modulated electromagnetic waves to detect targets in the surrounding area. Since the transmitted signal is a continuous wave, INDERA needs only a very small power to transmit its signal. Consequently, the level of signals arrived on the Rx-antenna part is also very low. The frequency of the transmitted signal is varied with time. As a result, the signal reflected by a target will generate a beat signal with a frequency proportional to the target distance. Thus basically we can compose a two-dimensional image from such signals. In this paper we present a method to reconstruct a 2D radar image from the signals received by radar INDERA.

Systematic review of computational modeling of mood and emotion

In the recent years, more studies that aim to make computers understand, experience and respond to affects accordingly through computational models have been widely researched. Although many studies have defined and distinguished the words affect, mood and emotion, such terms are still used interchangeably. Thus, in this study, a systematic literature review was implemented to summarize and evaluate the current states of the arts on computational modeling of mood. From three online databases including IEEE Xplore, ScienceDirect and Springer Link, 825 scientific articles were extracted. Furthermore, through the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta Analyses) Statement, 9 articles were selected for the review. These resulting articles were reviewed based on several categories including the aim of the study, the study population, the measurement of mood, the basic emotion dimension, and proposed computational model, as well as evaluation. As a result, the systematic literature review has provided a good starting point in the study of the computational modeling of mood and emotion.

Anomaly Detection in Vessel Tracking Using Support Vector Machines (SVMs)

The paper is devoted to supervise method approach to identify the vessel anomaly behaviour in waterways using the Automated Identification System (AIS) vessel reporting data. In this work, we describe the use of SVMs to detect the vessel anomaly behaviour. The SVMs is a supervised method that needs some pre knowledge to extract the maritime movement patterns of AIS raw data into information. This is the basis to remodel information into a meaningful and valuable form. The result of this work shows that the SVMs technique is applicable to be used for the identification of vessel anomaly behaviour. It is proved that the best accuracy result is obtained from dividing raw data into 70% for training and 30% for testing stages.

Adaptive Short Time Fourier Transform (STFT) Analysis of seismic electric signal (SES): A comparison of Hamming and rectangular window

Seismic electric signal (SES) is one of features for predicting earthquakes (EQs) because of its significant changes in the amplitude of the signal prior to the earthquake. This paper presents detailed analysis of SES recorded prior to earthquake that occurred in Greece in the period from January 1, 2008 to June 30, 2008. During this period of time 5 earthquakes were recorded with magnitudes greater than 6R. In this analysis STFT involving adaptively sliding window technique is used, in which Hamming and rectangular window functions are applied and compared. The comparison shows that Hamming window gives better results in analyzing the first significantly changes of SES prior to the EQ. The application of Hamming window resulted in less rippled spectrum shape which is more suitable to be used in characterizing the SES.

Multi-stereo Camera System to Enhance the Position Accuracy of Image-Guided Surgery Markers

The development of Image-guided Surgery (IGS) system as an assistant tool in medical navigation has led to new challenges for researchers to enhance the accuracy of the medical surgery. In IGS, a stereo camera is used to find the position of medical markers and visualize it on the screen of the surgeon. However, the line of sight (LOS) between the camera and the markers causes the stoppage of the tracking system if it cut during the operation. This paper presents a multi-stereo camera system to overcome the LOS problem, and to improve the accuracy of the IGS system. A pair of stereo cameras has been used to recognize and detect the reference markers and visualize a patients body part and a surgical needle. A multi-stereo camera has generated a very good accuracy of 3D visualization with 2.88 mm of root mean square error (RMSE). Image filtering techniques have been used to process the captured images. Thus, IGS system based on multi-stereo camera, contributes promising results of medical navigation and enhances the capabilities of IGS system.

Method of measuring Doppler shift of moving targets using FMCW maritime radar

During the operation of an FMCW (frequency modulated continuous wave) maritime radar, the system transmits a continuous radio energy with a frequency modulated by a triangular or sawtooth-shaped signal. As a result, the frequency of the transmitted signal varies gradually with time. When the signal is reflected by an object, the received waveform will build up a delayed replica of the transmitted waveform, with the time delay as a measure of the target range. If the target is moving, the radar system will register a Doppler shift within the received signal. Compared to the frequency of the emitted signal, the received signal will show a higher frequency when the target is approaching and a lower frequency when the target is moving away from the radar location. Thus, the total Doppler shift may result from the superposition of both source and observer motions. Specifically, the amount of Doppler shift is directly proportional to the radial speed of the target. The Doppler shift can be determined after performing the range Fourier transform (range FFT) first. For a target of interest, we can repeat the range FFT until we have enough data to perform the second level of FFT. The result of this second FFT is a two dimensional complex valued matrix, whose spectral peak corresponds to the Doppler shift of the moving target. This method is known as Doppler FFT. Some results of the measurement of target speed using this method are presented in this paper.

Design and development of the FMCW Radar Scene Generator

Like other radar systems, Frequency Modulated Continuous Wave (FMCW) maritime radar can measure simultaneously the range, velocity, reflectivity and azimuth of targets on the sea. However, compared with conventional pulse radar, FMCW radar has many advantages. It is relatively small and simple, offers high resolution, provides data over wide bandwidths, and is relative inexpensive. On the other hand, the fast development in technologies of radar, electronic charts and further navigational aids requires permanent training. Such training can be conducted with the aid of a radar simulator. The benefit of using a radar simulator is that the radar environment is electronically synthesized, and therefore exactly repeatable. Furthermore, a good physics-based FMCW radar simulator requires a radar scene generator. This scene generator will provide a real-world test and training environment for the operation of the simulated radar system. The aim of this work is to develop a two-dimensional FMCW radar scene generator that can be used as an aid in the ship navigation training. In this work a suitable graphical user interface (GUI) is also designed and developed. Using this GUI the user can easily generate static and dynamic components of the radar scene generator.

Altitude Tracking Using Colour Marker Based Navigation System for Image Guided Surgery

Optical tracking method has been largely usedfor medical navigation system in Robotic Image GuidedSurgery (IGS). One of the methods proposed by recentresearcher is to use colour feature as the marker for medicalinstruments detection and tracking. Since IGS system isusing preoperative imaging data set for reference, unintended patient movement can result in major errors. Inthis work, the position for the medical instruments markeris being investigated to prove that the method can be usedfor tracking in navigation system. Moving target marker willrepresent the unintended patient movement. The toolmarker will be navigated autonomously using robotics armto adjust the changes. Multithreading programmingapproach is being implemented in the system to increase theposition update rate for real-time application. The system isable to track the markers and navigate the tool marker tothe target marker with certain error tolerance. The accuracyand performance of the system are still in the need of someimprovements.

Classifications of clinical depression detection using acoustic measures in Malay speakers

Objective screening mechanism using paralinguistic cues to enhance current diagnostic on detecting depression is desirable, which resulted in the rise of research on this area. However, to date, there has been no research done using dataset of Malay speakers. This paper presented an acoustic depression detection classification using Linear and Quadratic Discriminant analysis with transition parameters and power spectral density as the acoustic features. Among the two features, power spectral density performed better, especially with the combination of band 1, 2 and 3 for both male and female data. As for the Transition parameters, we found that unvoiced feature performed best overall for both male and female.