Search

Traffic accident is one of the contributing factors of the death that happened around the world. From various types of drivers that are usually found in the traffic, motorcycle drivers have a relatively higher risk compared with other types of drivers. Therefore, there is a need for a system that is capable to detect dangerous behavior from the driver and gives an alert when abnormal behavior is detected. To develop it, we choose the 2 basic sensors to detect the movement from a driver, which are Accelerometer and Gyroscope. These sensors have been integrated into a smartphone. For the classification process, we proposed an Enhanced Multi-Layer Perceptron (MLP). The complexity of the model is reduced to ensure that our proposed system will be able to work in real-time conditions and in a limited-resources environment. In our model, we use the combination of ReLU and Softmax function, two of the famous Activation function, to enhance the performance of our model. The level of accuracy of our model achieved 97.5% with an average computational time of 45 ms. This proved that our model works better than the previous research with the same dataset.

Nowadays, gender classification using voice has been implemented, for a case in the security sector. The voice of each individual has a unique character, because of the diversity in the sound spectrum, frequency, and amplitude between individual. So, the option of technical features to determine specific characteristics to identifying gender came the major issue in classifying. In this study proposed two parameters to determine gender classification based speaker’s voice. There was a fundamental frequency of the YIN algorithm and the cepstrum coefficient of the Mel Frequency Cepstral Coefficient (MFCC) with the classification of Euclidean Distance and Mahalanobis Distance. Based on the data analyzed, it has classified the data test of females on the YIN algorithm with 100% accuracy. Meanwhile, in the male data test, there were several steps to process data that was still misclassified. The first step with the YIN algorithm got an accuracy of 47.5%, then with a combination of YIN and MFCC-Euclidean Distance, the accuracy had raised to 98%. Then continued the Mahalanobis Distance classification to the combination of YIN and MFCC-Euclidean Distance, the accuracy had come 100%. So it can be concluded the parameters applied to determining gender classification based speaker’s voice affect the process and results of the classification.

Along with technological developments, interaction based on speech does not only occur between humans but also occurs between humans and computers, known as Human-Computer Interaction (HCI). Most HCI system applications focus on contextual information. Whereas in a conversation, emotions are also important information in communication. This study combined the differential MFCC with other features, namely MFCC, chroma, and mel frequency spectrogram. The highest accuracy results in the SER data test were obtained from the test when only using one feature, namely the MFCC of 95.24%. The second-best accuracy is when using delta MFCC with an accuracy of 90.18%. And the use of 4 features (MFCC, Delta MFCC, Chromagram, and Mel Spectrogram) has the lowest accuracy compared to the others, 87.58%. In addition, the use of four features also has a longer computing time.

In the last decade, Indonesia shifted from one of the cleanest countries in the world to one of the countries with high air pollution, especially in big cities like Jakarta, Surabaya, etc. This paper presents a preliminary study of the building of a smart sensor node system to monitor air quality for urban environments. Sampled air parameters were CO, CO2, and CH4. Incoming sensor data were classified using rules from the calculation of the entropy and information gain done before in the Decision Tree Algorithm rule finding steps. The classification is done on a Raspberry Pi device using conditional if-else on the programs. The if-else condition makes the program could achieve air quality results. The decision results in the form of warning alert or data reports packed on a Raspberry Pi device. By then using LoRa transceiver, a medium-range communication system, these results sent to a PC server. Reliability testing has been carried out starting from the sensors, algorithm processing capability, until the transmission process with Time Division Multiplexing technique. Data is sent alternately between one node to another. Based on the testing results, the CO sensor shows good performance at pollutant levels up to 300 ppm, so do the CO2 sensor at values up to 500 ppm, and the CH4 sensor at values up to 250 ppm. Test measurements have been carried out in outdoor environments for feasibility of the transmission system that has designed.

Amateur radio communication used widely for experimental activities or for backup when the main communication access network fail. One of the amateur radio communications is run by using the Weak Signal Propagation Reporter or WSPR system. This system is very reliable to send messages, that composed of callsign, grid locator, and powerTx on very narrow channel widths (6 Hz) and run in the very low signal-to-noise ratio (-28 dB). WSPR systems generally work on the High Frequency band such as the 80 m, 60 m, or 40 m band, and able to reach a very long distance, up to hundreds or even thousands of kilometers. In this paper, we will propose a study of the WSPR system utility on several frequency candidates in the Very High Frequency band (2m band). The system is realized by utilizing a handy talky radio with built-in antenna and raspberry pi device as a WSPR signaling processor. The system performance is analyzed at a low signal- to-noise ratio of -14.92 dB, and still success to transmit the data. In this case we sent a soil moisture data from environmental parameter for agricultural purposes and is inserted at the powerTx.

Transportation has become one of the needs of human life. One of the most used transportation in Indonesia is a motorcycle. This transportation is reliable, has a wide variety of uses, is capable of handling traffic jams, and is very economical. But motorbikes have a relatively high risk for the safety of the rider compared to cars. With driver behavior and road congestion conditions, accidents often occur. In this research, we observed the movement of the driver through a smartphone and built an application that was able to provide a warning to motorists. In this system we use 2 types of sensors, Accelerometer and Gyroscope sensors which are generally the basic features of a smartphone. We adopt a Machine Learning-based movement identification process with an Artificial Neural Network (ANN) algorithm. ANN will do what movements it does based on the data obtained from the Accelerometer and Gyroscope sensor values. The application is installed on a smartphone and put it on a vehicle with a fixed position. The device will calculate the activity based on several predetermined categories of the driver status. The status categories are normal, zig-zag, sleepy, turn right, turn left, U-turn, sudden braking, sudden acceleration, and speed bumps. The level of accuracy generated by Machine Learning using the Artificial Neural Network Algorithm in this research was 96,2%.

In the natural disaster areas, a cellular-based telecommunication system is often disrupted. Handy-Talky is a power full as an ad-hoc telecommunication system for this condition. This equipment works in the Very High Frequency (VHF) and Ultra High Frequency (UHF). The VHF band is strongly influenced by the environment where is this system implemented. This system is suitable for short-range terrestrial communication. However, to develop a very long-range communication, it needs an HF type of communication system. In this study, a transverter system was built to convert the frequency signal from VHF to HF and vice versa. The transverter system was implemented on Raspberry Pi and supported by the C programming language. Two identified processes were the transverter process of converting HF signal to VHF/UHF signal and the transverter process of converting VHF/UHF signal to HF signal. The HF gateway device was controlled by VOX mode in order for it to transmit immediately when receiving voice signal from VHF/UHF gateway. The communications between these two devices with different frequency run in half-duplex mode. The voice activity detection technique was employed to replace the user, automatically activated the HT push-to-talk radio power for the threshold value of 60 dB in SNR. The calibration was conducted on EEPIS campus. The HF transceivers were positioned in D3 building and Post-Graduate building, EEPIS. It has shown that the communication process using the transverter was successful.

Throughout 2019 it is predicted as the minimum solar cycle period. It will make conditions less favorable for HF propagation. For this reason, we carried out day by day observations throughout 2019 to examine the existence of HF NVIS channel by WSPR method between Surabaya and Jombang which is separated by approximately 70 Km away. Ionospheric Wave Radio Frequency fading or even the radio-blackout in the band of HF could be caused by an increasing the solar activity, especially C-class level or higher Solar Flare. This occurrence only affects the sunlit region, and it could finish for within several hours. From 1st January 2019 until this report is written, the significant Solar Flare only reach C-class. During ongoing one year sounding activity, we found a measurement result nearly similar with the pattern of impacted ionosphere condition based on occurring solar flare, even though the Solar Flare still in C-class level. In order to verify the Solar-flare impact to the ionosphere, we use a simple qualitative model to verify the results of SNR measurements results to a suspected 3-consecutive-days, based on the nature of Solar-flare impact phenomena. The results show a case of C-class level could impact the ionospheric condition even though another case show that C-class level Solar flare do not affect the ionospheric condition.

In this paper, we evaluated the OFDM performance with Non-uniform Modulation. Then the effect of multipath fading channel analyzed using Additive White Gaussian Noise (AWGN). The types of modulations are Binary phase-shift keying (BPSK), Quadrature phase-shift keying (QPSK) and 16-Quadrature Amplitude Modulation (16-QAM). These modulation techniques were used to develop Nonuniform modulation of OFDM systems. In the simulation results, by maintaining a BER value of 0.001 this system is able to transmit 14443000 bits. Meanwhile, when it is sent by using fixed modulation such as BPSK, QPSK, and 16-QAM respectively i.e. 5252000 bits, 10504000 bits, and 21008000 bits on the same bit error rate (BER) value. The 16-QAM modulation is capable to transmit more bits, but this scheme requires more power. However, Non-uniform Modulation is able to improve bits efficiently with higher data rate compared to fixed modulation techniques.

The Ionosphere layer is used as a reflective mirror of the HF radio communications system. They have dynamic characteristics that are constantly changing at any time and place. It is need a reliable prediction system to be able to estimate the condition of the ionosphere. The term "forecast" is adopted for the practical schemes which are based on solar-terrestrial relations. In the case of zero lead-time, the forecast becomes a real-time probing of ionosphere, or well known as Real Time Channel Evaluation (RTCE) for HF communication. The term "now-casting" also used to describe an observation-intensive approach at very short term (up to one hour) ionopheric forecasting. Since the era of the 2000s the HF radio has advanced to be an intelligent HF radio system that is able to adapt to the condition of propagation at any time in order to maintain the quality of communication performance. The main component of the intelligent HF radio implementation is a low-power sounding/beacon system to probe the propagation conditions of each available HF channel. Implementation of sounding /beacon technology with small signal was of course still very secret, since then a group of scientists Amateur Radio member introduce/unlock this beacon/ sounding technology, which then called WSPR. With this openness of WSPR technology, we will replicate and integrate this small signal beacon/sounding technology in an intelligent HF communications system that is expected to be of immediate benefit to open communications in mountain-covered areas, in NVIS mode, or directly build HF radio networks throughout Indonesia in the sky wave mode, to respond to disaster mitigation. In this study we tried to carry out a simple probing/sounding technique by using WSPR. We concluded that the SNR of observations values are comparable with those of VOACAP simulation software Furthermore, we found that there is no difference observations results between two receivers located more than 100 Km away. We also concluded that both receivers only received sky wave signals.

Adaptive modulation is a powerful technique to improve the power efficiency and to increase the data rate of communication system in the underwater acoustic channel, which has a time varying characteristics. In this paper we propose an OFDM transmission system with adaptive modulation schemes, i.e. BPSK, QPSK, and 16-QAM. The system has ability to change the modulation scheme adaptively based on the signal-to-noise ratio (SNR), while maintaining the bit error rate (BER) under 0.01. The evaluation is conducted with simulation for the flat fading channel condition, and the system showed a good performance. It show that the system has ability to change the modulation scheme adaptively, and improve the channel capacity for certain value.

Nowadays, acoustic technology Is used In many sectors of human life. One of acoustic benefit is to know mechanical property of material, such kind of liquid and solid. One of mechanical property is acoustic impedance. Several methods are used to estimate acoustic impedance of material. Most of them use high focused ultrasound transducer, and utilize pure water as a common coupling material. However, this type of transducer is still expensive. Another type of ultrasound so called range finder ultrasound (RFU) is very cheap transducer. It is usually use to measure distance and place localization for its applications. Since RFU utilizing air as a coupling material, RFU became to a very sensitive sensor. Small displacement and small difference of distance from the sensor will produce a massive different of measurement. Hence, an accurate and precision method should be built for best result of measurement. In this paper, we utilized range finder ultrasound (RFU) sensor to estimate acoustic impedance of several saline solutions. Based on theoretical, the denser the solution the higher the acoustic impedance. From the experiment, it can be obtained that the higher the acoustic impedance of saline solutions the higher the echo signal that is received by receiver transducer. A characterization conversion curve was successfully developed from the experiment. However, assuming one plane wave for this type of transducer produced significant error. Detail discussion related to this research is presented in this paper.

The underwater acoustic communication is characterized with multipath channel affected by the reflection signal from the surface and the bottom, and the ambient noise of the underwater environment which depend on the condition where the measurement has been conducted. This paper presents a performance analysis of BPSK system in the underwater acoustic channel environment with the additive Laplacian noise model. Performance has been evaluated with the measurement data of ambient noise from two diferent location, ie. Mangrove river and Kenjeran beach. The bit error rate (BER) performance is very close to the probability of error (Pe) of multipath channel with additive Laplacian noise model. When compared to the Gaussian noise model, this system need more 2–4 dB to achieved the same value of BER.

Transmission process of underwater information signal becomes useful technology in shallow water area by using an acoustic signal as a transmission medium. One of the acoustic signal propagation parameter which has been observed is an ambient noise. Ambient noise affects the channel condition become non ideal and thus require further research. This paper presents ambient noise measurement in Mangrove estuary as representation of shallow water of Surabaya. Ambient noise has statistical characterization which can be analysed into time-frequency domain. Probability density function (pdf) and cumulative distribution function (cdf) curve estimation is performed as observations in time domain analysis with each fitting process of the resulting pdf and cdf with Gaussian and Laplace distribution functions for the validation. The ambient noise distribution is close to Laplace distribution which validated by some methods. The methods give values in Mean Square Error are 1.3720×10−4 for pdf and 0.0127 for cdf, Bhattacharyya distance is 0.0305 for pdf, Kolmogorov-Smirnov test is 0.2308 for cdf, and Kullback-Leibler divergence is 0.0851 for pdf. Observation in frequency domain analysis is done through the Power Spectral Density (PSD) estimation. It is showed that the spectral is flat white spectral within frequency range of 16–18.5 kHz with average level power is about −38 dB.

Digital Video Broadcasting-Terrestrial second generation (DVB-T2) is developed from Digital Video Broadcasting — Terrestrial first generation (DVB-T) standard. DVB broadcasting development based is still open. In this research, the development or evaluation of MIMO-OFDM system which is a transmission technique used in the DVB-T2 standard. Multiple Input Multiple Output (MIMO) techniques using multiple antennas at the transmitter side and receiver side for increase communications capabilities. Modulation technique for wireless communication that is chosen is Orthogonal Frequency Division Multiplexing (OFDM), with the purpose of reliable large data supplying in radio channel. Increased the model of channel estimation at the receiver side to determine system performance DVB-T2. Channel estimation used Minimum Mean Square Error (MMSE) algorithm, while the detector configuration using Zero Forcing (ZF). From the analysis results, the channel attenuation of subcarrier curve and the Bit Error Rate (BER) as a function of Signal to Noise Ratio (SNR) curve stating the results of the comparison value of channel estimation and ideal channel with the results obtained from the simulation is similar approach. The performance of system is described by BER over SNR curve.

Understanding of environmental characteristic is a key factor in design of communication system. This paper describes an ambient noise characterization of measurement in the shallow water of Surabaya bay. The result showed that probability density function (pdf) of ambient noise is close to a Gaussian distribution with the mean of −2.85×10−5 V, and deviation standard of 9.87×10−4V. Validation has been done by using mean square error (MSE) and Bhattacharya distance. In the frequency domain analysis, it is showed that in the range of 0 ∲ 9 kHz has a deceasing level from −100 until −140 dB. In the frequency of 9 ∲ 13.5 kHz, the spectral is flat as like a white. It can be used as a reference in decision of range frequency of underwater acoustic communication systems that will be applied.

Acoustic propagation in the underwater channel influenced by three factors: signal attenuation, multipath propagation, and low speed of sound propagation. Understanding of underwater acoustic channel is the basis in the design of a reliable communication system, and until now there is no standard fading model for underwater acoustic channel. Experimental method supported with measurement data is a commonly method used as a first step in modeling of channel properties for underwater sensor network applications. In this study, we will begin a discussion about research development of underwater acoustic communications. In the next section will be presented about experimental planning for underwater propagation characteristics. The characterization results are used to evaluate the performance of communication system through software simulation. At the end of this paper, a PC-based soft acoustic modem test bed will be presented.

Development of an underwater acoustic communication system is a necessity for the majority of the nation as a sea area of Indonesia. Most area s of the ocean in Indonesia is shallow, the environment has unique characteristics compared to other countries. It is a challenge in the research underwater acoustic communication system. This paper presented a preliminary study of the developing of soft acoustic modem testbed for underwater acoustic communication system with OFDM technique. Modem has been implemented on a PC with Matlab, with the objective to evaluate the algorithm development. Image file in JPEG format is encoded with a discrete cosine transform (DCT). To improve performance, information is encoded with a forward error correction, FEC-Hamming. The system uses BPSK modulation, OFDM transmission techniques, and using acoustic signal as carrier wave. In this system, the occupation bandwidth is 5.3 kHz, transmission rate of 3.7 k sps, and center frequency at 13.3 kHz. As an initial stage, the model presented in the form of simulator tesbed passband, and is treated with the propagation parameters that was obtained from measurements in a Towing Tank in previous experiment. The next stage is tesbed evaluation through experimental in a laboratory, such the effect of conversion process from electrical to audio signal at PC sound card and the capability of the receiver to recover the information.

Research developments and applications in the underwater acoustic communication fields have been a challenge for researchers. In this paper we present a study about image transmission over underwater acoustic channels. We present the 256 OFDM transmission technique with BPSK modulation, forward error correction (FEC)-Hamming (7,4), least square (LS) and minimum mean square error (MMSE) equalizations. The simulation results show that FEC-Hamming gives a good performance, e.g. 5 dB SNR results in 0.0017 BER and 20.84 dB SNR. The performance of LS equalization and MMSE equalization at the receiver are compared. MMSE equalization need approximately 12 dB SNR for the BER of 0.001, or 2 dB lower than the LS case.