Showing papers in "Indonesian Journal of Electronics and Instrumentation Systems in 2019"
TL;DR: In this article, an android based system using Local Binary Pattern (LBP) and Regression Analysis to measure soil nutrients and provide fertilizer dosage recommendations based on the LPT Bogor's formula.
Abstract: Nitrogen, Phosphorus and Potassium (NPK) are macro elements that important for the paddy development. NPK is a parameter that used for calculating fertilizer dosage. Current NPK measurement through laboratory requires a relatively long time, so we design a new system that can speed up the process and provide correct fertilizer dosage recommendations. This paper proposes an android based system using Local Binary Pattern (LBP) and Regression Analysis to measure soil nutrients and provide fertilizer dosage recommendations based on the LPT Bogor's formula. Samples of soil image taken from rice fields in Special Region of Yogyakarta. The measurement is processed by extracting LBP features from the soil image that has through the pre-processing stage. The extraction results were then analyzed using Multiple Linear Regression (MLR). The equation results from MLR is used to calculate NPK. The results show that the proposed system can detect NPK levels in paddy fields in Yogyakarta and provide fertilization dosage with an average detection accuracy of 70.65% (N 94.98%, P 50.84 %, and K 66.14%). The accuracy was obtained from the image taking at an optimal height of 70 cm and optimal angle of 0 o to the ground surface. The average processing time is 0.61 seconds.
4 citations
TL;DR: The LEACH algorithm with 70 data snippets is an optimal state that results in a network lifetime of 7,387 seconds, whereas with the same number of data snippets when using a non-LEACH algorithm the network lifetime can only reach 5,565 seconds.
Abstract: Wireless Sensor Network (WSN) is a wireless network consisting of a group of nodes scattered in a certain area. Each node has the ability to gather data around it and communicate with other nodes. In WSN, energy efficiency is important to maintain the lifetime of a network. A WSN consisting of several clusters and having a Cluster Head (CH) in each cluster requires a CH change mechanism in each cluster so that the network lifetime is longer. The LEACH algorithm is implemented on a system consisting of 9 sensor nodes and 1 sink node. Each sensor node monitors the temperature and humidity of the surrounding air. System testing is done by varying the number of data snippets per CH selection process in each LEACH cycle. Based on the results of testing, the application of the LEACH algorithm can increase network lifetime. The LEACH algorithm with 70 data snippets is an optimal state that results in a network lifetime of 7,387 seconds, whereas with the same number of data snippets when using a non-LEACH algorithm the network lifetime can only reach 5,565 seconds.
3 citations
TL;DR: This research used thresholding method as segmentation and multilayer method of back propagation perceptron with variations in the extraction of textural features, geometry, and colors to classify white blood cells.
Abstract: Leukemia is a type of cancer that is on white blood cell. This disease are characterized by abundance of abnormal white blood cell called lymphoblast in the bone marrow. Classification of blood cell types, calculation of the ratio of cell types and comparison with normal blood cells can be the subject of diagnosing this disease. The diagnostic process is carried out manually by hematologists through microscopic image. This method is likely to provide a subjective result and time-consuming. The application of digital image processing techniques and machine learning in the process of classifying white blood cells can provide more objective results. This research used thresholding method as segmentation and multilayer method of back propagation perceptron with variations in the extraction of textural features, geometry, and colors. The results of segmentation testing in this study amounted to 68.70%. Whereas the classification test shows that the combination of feature extraction of GLCM features, geometry features, and color features gives the best results. This test produces an accuration value 91.43%, precision value of 50.63%, sensitivity 56.67%, F1Score 51.95%, and specitifity 94.16%.
2 citations
TL;DR: In this article, the authors used fuzzy logic and Zigbee pro communication for telematics control of plant hydroponics to control ph, volume and nutrients solution using fuzzy logic.
Abstract: The utilization of bare areas like narrow tract, building roof, or unused warehouse can be maximized as agricultural land using hydroponics system. Hydroponics is a cultivation technique by using nutrient solution. The plant nutrient is an alternative soil which relate with water acidity (pH), that has reaction with nutrient solubility to plant fertility. In fact, pH of the nutrients can change because of many factors like media of plant. The temperature of nutrient solution affect an ion nutrient absorption by plant root. The higher temperature reduces plant root ability to absorb water and ion nutrients. The more advanced technological developments, the agriculture can be controlled automatically and monitored remotely. The aim of this research is to make design control ph, volume and nutrients solution using fuzzy logic and zigbee pro communication for telematics control of plant hydroponics. The result of this experiment shown that fuzzy logic has effectiveness to control pH of hydroponics. It needs 429 seconds to setting point of range pH 5 ppm to 7 ppm and 459 seconds to setting point of range pH 9 ppm to 7 ppm.
2 citations
TL;DR: In this study, hand image taken using a camera will be processed using a single board computer to be recognized and the results are passed on to arduino leonardo and DC motor to control twelve wheeled robot movement.
Abstract: Currently, Human and computer interaction is generally done using a remote control. This approach tends to be impractical for wheeled robot operation because it must always carry an intermediary tool during the operation. The application of hand gesture recognition using digital image processing techniques and machine learning in the control process of wheeled robots will facilitate the control of wheeled robots because control no longer requires an intermediary tool. In this study, hand image taken using a camera then will be processed using a single board computer to be recognized. The results of recognized are passed on to arduino leonardo and DC motor to control twelve wheeled robot movement . The method used in this study is contrast stretching for preprocessing and Convolutional Neural Network (CNN) for hand recognition . This method is tested with a variation of bright 26 - 1 40 lux, the distance from the face to the camera is 12 0 -200 cm. Hand recognition systems using this method resulting accuracy 97,5 %, precision 9 7 ,57 %, sensitivity 97. 5 % , spesificity 99,77 and f 1 score 9 7 . 45 %.
2 citations
TL;DR: A portable mini weather station system was built named Amicagama with the concept of high scalability which means the system is designed to be used publicly, with each user able to manage the nodes which are their respective weather stations.
Abstract: Indonesia is a country that has unique weather that provides not only abundant natural resources but also can causes disasters at any time. To reduce the threat of losses, observing weather elements using a weather station is a solution that can be used. The development of systems related to environmental monitoring and weather stations is not new. However, most research focuses on various innovations in utilization, low cost and power savings. These studies have not touched on the aspect of ease of system development, especially in the concept of adding nodes. Indonesia, as a country with diverse regional topography, needs an integrated weather monitoring system with the concept of centralized data collection to get a complete picture. In this study, a portable mini weather station system was built named Amicagama. This system is built with the concept of high scalability which means the system is designed to be used publicly, with each user able to manage the nodes which are their respective weather stations. Management by each user here means that each user can manage weather data to be submitted, add nodes at a new location, and can delete nodes at a certain location if something unexpected happens.
2 citations
TL;DR: The design and implementation of CRC generator on FPGA that capable to minimaze computational time is proposed and the method is to reduce calculation latency by separating the coefficients of certain digits and calculating directly the result of polinomial key modulo.
Abstract: Data integrity in high speed data transmission process is a major requerment that can not be ignored. High speed data transmission is prone to data errors. CRC (Cyclic Redundancy Check) is a mechanism that is often used as a detector errors in data transmission and storage process. When CRC is implemented using embedded software or processor, CRC requires many clock cycles. If CRC Generator implemented in special dedicated hardware, computational time reduced so that it can be met the high speed system communication requirement. This paper propose the design and implementation of CRC generator on FPGA that capable to minimaze computational time. The method is to reduce calculation latency by separating the coefficients of certain digits and calculating directly the result of polinomial key modulo. CRC Generator in this paper was implemented on Xilinx Spartan®-6 Series (XC6LX16-CS324). The modeling results have succeeded to finish computation on 1 clock cycle. Hardware eficiency is achieved 0.38 Gbps/Slice, while the throughput is 3,758 Gbps.
2 citations
TL;DR: This research recognizes handwritten character pattern of numbers and alphabet using K-Nearest Neighbour (KNN) algorithm using data from training and testing data to improve handwritten character recognition accuracy.
Abstract: Handwritten characters are difficult to be recognized by machine because people had various own writing style. This research recognizes handwritten character pattern of numbers and alphabet using K-Nearest Neighbour (KNN) algorithm. Handwritten recognition process is worked by preprocessing handwritten image, segmentation to obtain separate single characters, feature extraction, and classification. Features extraction is done by utilizing Zone method that will be used for classification by splitting this features data to training data and testing data. Training data from extracted features reduced by K-Support Vector Nearest Neighbor (K-SVNN) and for recognizing handwritten pattern from testing data, we used K-Nearest Neighbor (KNN). Testing result shows that reducing training data using K-SVNN able to improve handwritten character recognition accuracy.
2 citations
TL;DR: Electronic tongue sensors consisting of 16 sensor array made of TOMA and OA lipids that have been used to classify samples of pure cannabis, Cannabis mixed with tea and cannabis mixed with tobacco does not involve the feature selection technique so that a lot of duplicated data is generated from data sampling.
Abstract: Electronic tongue sensors consisting of 16 sensor array made of TOMA and OA lipids that have been used to classify samples of pure cannabis, cannabis mixed with tea and cannabis mixed with tobacco does not involve the feature selection technique so that a lot of duplicated data is generated from data sampling. Feature selection is performed using PCA. Data analysis resulted in loading values shows the contribution of each sensor, and the similarity in sensor performance in characterizing samples, then analyzed using the correlation test so that the sensors that produce redundant information are known. Validation is performed using the SVM method and the classification performance is compared to the original sensor. The sensor optimization produces a subset of features with 6 sensors (Sensor 7, Sensor 10, Sensor 12, Sensors 13, Sensor 14 and Sensor 15) in the cannabis-tea sample test and a feature subset with 3 sensors (Sensor 3, Sensor 7 and Sensor 14) in the cannabis-tobacco sample test. Sensor optimization that has been done produced classification accuracy by 100% and shorten the running time by a difference of 0.578 microseconds in the test of cannabis-tea samples and a difference of 1.696 microseconds in the test of cannabis-tobacco samples.
2 citations
TL;DR: The requisite of intelligent classroom's saving the information from speakers inside the class using ubiquitous computing concept requires a system that can tracking the speaker in real time, ignore the other speaker, and recording speaker’s activity.
Abstract: The requisite of intelligent classroom’s saving the information from speakers inside the class using ubiquitous computing concept. It said the most profound technologies are those that disappear, and they weave themselves into fabric of everday life until they are indistinguishable from it. It requires a few capability such as tracking the speaker and record it. Therefore it will be require the system that can tracking the speaker in real time, ignore the other speaker, and recording speaker’s activity. The system consumes 168.02 ms in one move, like detection using statis camera, send the centroid to microcontroller, second detection using dinamis camera, and record it. The system had an accuracy of 93.37 % to fits the speaker at the middle of frame record. The system is also had an accuracy of 98% to detecting the correct speaker.
1 citations
TL;DR: The results showed that the MFCC and Backpropagation ANN methods were able to identify speech words with 60% accuracy, 40% precision and 40% sensitivity.
Abstract: Speech impaired is the inability of someone to speak, even though speaking ability is important in order to communicate with other people. Dealing with this as someone who has speech impairments has their own way of communicating, namely by using sign language, but not everyone understands the sign language. The MFCC and Backpropagation ANN methods are implemented on a Single Board Computer (SBC) designed to overcome speech impaired communication problems. The MFCC method is used to retrieve the features of speech impairment and the Backpropagation ANN is used for sound pattern recognition. The system was trained using 750 sound samples consisting of 5 speakers, each uttering as many as 30 repetitions of the pronunciation of words (makan, kamar, kerja, harga and lapar), then tested using 125 sound samples consisting of 5 speakers, each saying 5 repetitions of words. Training and testing of Backpropagation ANN using input coefficients generated from MFCC. The results showed that the MFCC and Backpropagation ANN methods were able to identify speech words with 60% accuracy, 40% precision and 40% sensitivity.
TL;DR: In this paper, a system designed to stabilize quadrotor during flight condition by maintaining at angle of roll, pitch, yaw, and x, y, and z axis position using LQR full state feedback with artificial neural network (ANN).
Abstract: Quadrotor is one type of unmanned aerial vehicle that has the ability to vertical takeoff and landing. In this research, a system designed to stabilize quadrotor during flight condition by maintaining at angle of roll, pitch, yaw, and x, y, and z axis position using LQR full state feedback with artificial neural network (ANN). The LQR full state feedback method uses 12 states with each K constant being tuned with ANN. This research implements ANN method to change feedback constant at angle of roll, pitch, and yaw and x, y, and z axis. The artificial neural network method uses 12 input layers, 12 hidden layers, and 1 output layer. Testing with ANN improved the rise time to ± 2.18 seconds at the roll angle, ± 1.23 seconds at the pitch angle, and ± 0.31 seconds at the yaw angle. Improved settling time value up to ± 2.41 seconds at roll angle, ± 1.23 seconds at pitch angle, and ± 1.07 seconds at yaw angle. Improved steady state eror value of ± 0.61% at roll angle, ± 4.88% at pitch angle, and ± 0.82% at the yaw angle.
TL;DR: In this article, the optimization of the heating temperature of black tea samples for the measurement of aroma with electronic nose (e-nose) has been successfully performed, and the method used to obtain the optimum heating temperature by analyzing the sensor response of the aroma transformation that is captured by e-Nose.
Abstract: The optimization of heating temperature of black tea samples for the measurement of aroma with electronic nose (e-nose) has been successfully performed. Sample heating is done because black tea has a low aroma intensity and easily lost. However, the selection of such temperature should be selective because it can result in damage to the aroma of the sample. Therefore, temperature optimization needs to be done so that the resulting sensor response comes from the transformation of the undamaged aroma. The method used to obtain the optimum heating temperature by analyzing the sensor response of the aroma transformation that is captured by e-nose. Consistency and pattern changes formed from the sensor response are used as a comparison of optimal heating temperature selection. The measured sample varied in temperature (30 - 60 °C) so that the resulting sensor response was observed. Change in patterns indicate the aroma has been burning. After optimal temperature is obtained then black tea (50 gr) Broken Orange Pokoe, Broken Pokoe II and Bohea with a total sample of 300 bags were measured with e-nose. For further analysis, the result of classification by method of Principal Component Analysis (PCA) as proof of sample heating temperature optimization successfully done. The experimental results show optimal sample heating for black tea 3 quality 40 - 45 °C. After then with the third PCA the sample can be classified up to 92.5% of the total data variant. This indicates the aroma of tea is relatively constant and there is no pattern change.
TL;DR: In this article, the Raspberry Pi 2-based APRS packets for UGM earth stations have been designed, which is much cheaper than commercial devices on the market, and the test was carried out by receiving the APRS package emitted by the International Space Station (ISS) satellite and the LAPAN-A2 satellite.
Abstract: The design of Raspberry Pi 2-based APRS packets for UGM earth stations has been designed, which is much cheaper than commercial devices on the market. A TV tuner is used as a signal receiver, the receiver is accessed via a laptop wirelessly. A directed antenna with a controller is used to automatically point to the satellite. The test was carried out by receiving the APRS package emitted by the International Space Station (ISS) satellite and the LAPAN-A2 satellite. The results showed that the tool was able to get the ISS satellite APRS package with a total of 6 packages out of 10 packets emitted. The package received has an average amplitude of 1,200 Hz and 2,200 Hz which is much smaller than the overall audio amplitude. This indicates that there is high noise in the signal. While the APRS package from the LAPAN-A2 satellite has not been successfully obtained.
TL;DR: The results of the test concluded that the ontology design can be realized as a prototype of the smart home system.
Abstract: Smart home system is a computer-aided system that will provide all comfort, safety, security and energy savings, which works automatically and programmed through a computer in a building or home . One of the method that can be used to design smart home is context aware method. Context aware can work with the help of several other methods such as ontology method. Ontology has a variety of definition and always changes time by time. Ontology method is one of method that can process complex data. The ontology method allows complex reasoning and representation with better results . Constraints that are often encountered when designing a system that looks complex will face many problems such as many ambiguous domains. The existence of an ontology design before carrying out the prototype design of the smart home system will facilitate the smart home design process especially if the system will be made more complex so it would allows ambiguity from multiple domains. Testing with this ontology method is effective enough to minimize ambiguity from each domain , because each domain is designed with different characteristics . The results of the test concluded that the ontology design can be realized as a prototype of the smart home system .
TL;DR: This research presented system with ROI segmentation for any static objects, stitching for each objects and combine them become a panoramic image then shown in citra panoroscopic.
Abstract: Stitching citra with different object’s depth and disposed close to the camera willing caused panoramic citra with distortion perspective (caused double or disappear object) because the camera see in two dimension with large horizontal disparity by each camera. For solve that problem, stereoscopic method purpose to give depth perception of three dimension from two images with same background so information of depth by the object be able to get with intuitive way. This research presented system with ROI segmentation for any static objects, stitching for each objects and combine them become a panoramic image then shown in citra panoramic. SIFT descriptor used for detect and extract feature from the images. The result of this system successful presented combination for stitching by the static objects.