Jurnal Infotel (Sekolah Tinggi Teknologi Telematika Telkom Purwokerto)
Not a member yet
392 research outputs found
Sort by
Chattering reduction effect on power efficiency of ifoc based induction motor
Full text linkNowadays, the strategies to control Induction Motor (IM) is growing fast. The vector control strategies give better performance than the scalar control to control IM. IFOC is one of the vector control strategies which more realistic to apply in industry, military, and transportation. However, IFOC requires Sliding Mode Control (SMC) with the Lyapunov function to ensure robustness and stability. The first-order SMC or ordinary SMC uses boundary layers technique such as the saturation function and the tangent-hyperbolic function to overcome the chattering phenomenon. The performance of boundary layer is analyzed in rotor speed response, stator current response in dq0 frame and power performance. In rotor speed response, the SMC with and without boundary layer has error steady-state less than 2%. In stator current response with dq0 frame, the boundary layer with tangent-hyperbolic function has the best performance. The power analysis shows that the boundary layer with saturation function has an active power loss of 39.16%, reactive power loss of 23.37% and apparent power loss of 30.30%. The boundary layer with tangent-hyperbolic functions has the best performance in reducing power consumption with active power loss of 41.24%, reactive power loss of 24.78% and apparent power loss of 31.96%
Vegetation classification algorithm using convolutional neural network ResNet50 for vegetation mapping in Bandung district area
Full text linkBandung District is one of crop provider for West Java Province. About 31.158,22 ha is used for crop. However, some of them are not maintained well due to lack of vegetation map information. Local authority has tried to map the vegetation in their area by using free license satellite images, and aerial images from Unmanned Aerial Vehicle (UAV). Despite both images being able to provide large plantation area images, both are unable to classify the vegetation type in those images. Telkom University with Bandung Agriculture Regional Office (Dinas Pertanian Kabupaten Bandung) has conducted joint research to develop algorithm based on 50-layer residual neural network (ResNet50) to classify the vegetation type. The input is of this algorithm is primarily aerial images are captured from different type, height, and position of crops. Seven different ResNet50 configurations have been set and simulated to classify the crop images. The result is the configuration with resized images, employing triangular policy of cyclic learning rate with rate 1.10−7 – 1.10−4 comes out as the best setup with more than 95% accuracy and relatively low loss.Bandung District is one of crop provider for West Java Province. About 31.158,22 ha is used for crop. However, some of them are not maintained well due to lack of vegetation map information. Local authority has tried to map the vegetation in their area by using free license satellite images, and aerial images from Unmanned Aerial Vehicle (UAV). Despite both images being able to provide large plantation area images, both are unable to classify the vegetation type in those images. Telkom University with Bandung Agriculture Regional Office (Dinas Pertanian Kabupaten Bandung) has conducted joint research to develop algorithm based on 50-layer residual neural network (ResNet50) to classify the vegetation type. The input is of this algorithm is primarily aerial images are captured from different type, height, and position of crops. Seven different ResNet50 configurations have been set and simulated to classify the crop images. The result is the configuration with resized images, employing triangular policy of cyclic learning rate with rate 1.10−7 – 1.10−4 comes out as the best setup with more than 95% accuracy and relatively low loss
Software-based simulation to analyze the variation of digital modulation and atmospheric condition on the free space optic (FSO) link performance
Full text linkFree Space Optic (FSO) is the solution for telecommunications technology that offers high data rates, wide bandwidth, and low power consumption. However, to maximize the performance of the FSO system, the modulation used should be considered in environmental conditions. This study aims to compare the performance of the FSO communication link based on digital modulation variations used in various weather conditions, including sunny, rainy, and foggy weather. This study uses two attenuation models, namely the Kim and Kruse models, with variations in transmission distance from 500 meters to 10 kilometers. Modulation variations used include QPSK, 8-PSK, 16-PSK, and 16-QAM at 10 Gbps bitrate. The simulation is accomplished using OptiSystem 17.0 software. The study results show that sunny weather (very clear) has the best visibility compared to rain and fog conditions with an attenuation value of 0.46 dB/km on the Kim and Kruse models. QPSK modulation has the best performance with a BER value of less than 1x10-12 up to a transmission distance of 8 km in sunny weather, 3 km in rainy weather (medium rain), and 800 m in foggy (moderate fog) weather. The 8-PSK modulation has a BER value of less than 1x10-12 with a range of 2000 m in sunny weather and 1500 m in rainy weather but does not meet the standards in foggy weather conditions. 16-PSK and 16-QAM modulation have above baseline BER values during rainy and foggy conditions, but 16-QAM modulation still has a BER value of less than 1x10-3 during foggy conditions at a distance of 500 m.Free Space Optic (FSO) merupakan solusi untuk teknologi telekomunikasi yang menyediakan kecepatan data yang tinggi, bandwidth yang lebar dan konsumsi daya yang rendah, Namun untuk memaksimalkan kinerja dari sistem FSO tersebut, modulasi yang digunakan harus diperhatikan dan sesuai dengan kondisi lingkungan. Penelitian ini bertujuan membandingkan kinerja dari link komunikasi FSO berdasarkan variasi modulasi digital yang digunakan dengan berbagai kondisi cuaca meliputi cuaca cerah, hujan dan berkabut. Penelitian ini menggunakan dua model attenuasi yaitu model Kim dan model Kruse dengan variasi jarak transmisi mulai 500 meter hingga 10 kilometer. Variasi modulasi yang digunakan meliputi QPSK, 8-PSK, 16-PSK dan 16-QAM dengan bit rate 10 Gbps.Simulasi dilakukan dengan menggunakan software Optisystem 17.0. Berdasarkan hasil penelitian menunjukkan bahwa cuaca cerah memiliki visibilitas yang paling baik dibandingkan dengan kondisi hujan dan kabut dengan nilai atenuasi sebesar 0,46 dB/km pada model Kim dan model Kruse. Modulasi QPSK memiliki kinerja paling baik dengan nilai BER kurang dari 1x10-12 hingga jarak transmisi 8 km pada cuaca cerah, 3 km pada cuaca hujan dan 800 m pada kondisi cuaca kabut. Modulasi 8-PSK memiliki nilai BER kurang dari 1x10-12 dengan jangkauan jarak 2000 m pada cuaca cerah dan 1500 m pada cuaca hujan namun tidak memenuhi standar pada kondisi cuaca kabut. Modulasi 16-PSK dan 16-QAM memiliki nilai BER yang sangat besar saat kondisi hujan dan berkabut, namun modulasi 16-QAM masih memiliki nilai BER kurang dari 1x10-3 saat kondisi berkabut pada jarak 500 m
The reduction of polynomial degrees using moving average filter and derivative approach to decrease the computational load in polynomial classifiers
Full text linkCarbon monoxide is a type of pollutant that is harmful to human health and the environment. On the other hand, carbon monoxide also has benefits for industrial matter. Since the benefits and disadvantages of carbon monoxide, the measurement of carbon monoxide concentration is required. The measurement of carbon monoxide level is not easy moreover with low-cost sensors. The usage of 4 sensors namely TGS2611, TGS2612, TGS2610 and TGS2602 has been used along with feature extractor. The polynomial classifier is required to interpret the feature vector into the amount of substance concentration. The common classifier methods suffer fatal limitations. The polynomial classifiers method offers lower complexity in solution and lower computational effort. Since the involvement of a huge number of data points in the modelling process leads to high degree in the polynomial model. The occurrence of Runge's phenomenon is highly possible in this condition. This phenomenon affects the accuracy level of the generated model. The degree reduction algorithm is required to prevent the occurrence of Runge’s phenomenon. The combination of MAF (Mean Average Filter) and derivative approach as degree reductor algorithm has succeeded in reducing the polynomial model degree. The greater the number degree in the model means the greater the computational load. The model degree reductor algorithm has been succeeded to reduce computational load by 96.6%.Karbon monoksida merupakan salah satu jenis polutan yang berbahaya bagi kesehatan manusia dan lingkungan. Di sisi lain, karbon monoksida juga memiliki manfaat untuk keperluan industri. Karena kelebihan dan kekurangan karbon monoksida, maka diperlukan pengukuran konsentrasi karbon monoksida. Pengukuran kadar karbon monoksida tidak mudah apalagi dengan sensor yang murah. Penggunaan 4 sensor yaitu TGS2611, TGS2612, TGS2610 dan TGS2602 telah digunakan bersama dengan feature extractor. Pengklasifikasi polinomial diperlukan untuk menginterpretasikan vektor fitur ke dalam jumlah konsentrasi zat. Metode pengklasifikasi umum mengalami keterbatasan fatal. Metode pengklasifikasi polinomial menawarkan kompleksitas yang lebih rendah dalam solusi dan upaya komputasi yang lebih rendah. Karena keterlibatan sejumlah besar titik data dalam proses pemodelan mengarah ke derajat yang tinggi dalam model polinomial. Fenomena Runge sangat mungkin terjadi pada kondisi ini. Fenomena ini mempengaruhi tingkat akurasi model yang dihasilkan. Algoritma reduksi derajat diperlukan untuk mencegah terjadinya fenomena Runge. Kombinasi MAF (Mean Average Filter) dan pendekatan turunan sebagai algoritma pereduksi derajat telah berhasil mereduksi derajat model polinomial. Semakin besar angka derajat dalam model berarti semakin besar beban komputasinya. Algoritma pereduksi derajat model telah berhasil mengurangi beban komputasi sebesar 96,6%
A deep learning model to detect the brain tumor based on magnetic resonance images
Full text linkDeep learning techniques have been widely used in everything from analyzing medical information to tools for making medical diagnoses. One of the most feared diseases in modern medicine is a brain tumor. MRI is a radiological method that can be used to identify brain tumors. However, manual segmentation and analysis of MRI images is time-consuming and can only be performed by a professional neuroradiologist. Therefore automatic recognition is required. This study propose a deep learning method based on a hybrid multi-layer perceptron model with Inception-v3 to predict brain tumors using MRI images. The research was conducted by building the Inception-v3 and multilayer perceptron model, and comparing it with the proposed model. The results showed that the hybrid multilayer perceptron model with inception-v3 achieved accuracy, recall, precision, and fi-score of 92%. While the inception-v3 and multilayer perceptron models only obtained 66% and 56% accuracy, respectively. This research shows that the proposed model successfully predicts brain tumors and improves performanc
Evaluations of the Predistortion Technique by Neural Network Algorithm in MIMO-OFDM System Using USRP
Full text linkMIMO OFDM is the key technology of 4G network system. MIMO-OFDM system enhances the spectrum efficiency and increases the capacity of the system. The implementation of USRP hardware to MIMO OFDM system has been attracted some researchers to conduct the experiments. So we conduct the experiments in a MIMO OFDM system that applies the predistortion technique. In this experiment, we evaluate performances of the predistortion technique by using the artificial neural network. USRP 2920 hardware which is supported by LabVIEW and Phyton software are used in this experiment. OFDM system uses 128 subcarriers to produce an OFDM symbol, and MIMO system uses 2 antennas at transmitter and receiver side. And no obstacles between Tx and Rx, or line of sight transmission scenarios. The performances of the predistortion technique using the artificial neural network algorithm are shown in symbol constellations or Error Vector Magnitude (EVM) at the receiver. And the texts or characters are used as the input of the system. From the experiment results can be seen that the distance between Tx and Rx affects the Error Vector Magnitude (EVM) and predistortion technique produces the Error vector magnitude (EVM) improvement. More shorter the distance between Tx and Rx can decrease distortions of the received signal, At the transmitter side, the performance of predistortion technique is shown as the linearization improvement of the non-linearity power amplifier. Therefore more wider the linear region of power amplifier results the decreasing in band distortion of transmitted signal, and can be seen as the Error Vector Magnitude (EVM) improvement.MIMO OFDM is the key technology of 4G network system. MIMO-OFDM system enhances the spectrum efficiency and increases the capacity of the system. The implementation of USRP hardware to MIMO OFDM system has been attracted some researchers to conduct the experiments. So we conduct the experiments in a MIMO OFDM system that applies the predistortion technique. In this experiment, we evaluate performances of the predistortion technique by using the artificial neural network. USRP 2920 hardware which is supported by LabVIEW and Phyton software are used in this experiment. OFDM system uses 128 subcarriers to produce an OFDM symbol, and MIMO system uses 2 antennas at transmitter and receiver side. And no obstacles between Tx and Rx, or line of sight transmission scenarios. The performances of the predistortion technique using the artificial neural network algorithm are shown in symbol constellations or Error Vector Magnitude (EVM) at the receiver. And the texts or characters are used as the input of the system. From the experiment results can be seen that the distance between Tx and Rx affects the Error Vector Magnitude (EVM) and predistortion technique produces the Error vector magnitude (EVM) improvement. More shorter the distance between Tx and Rx can decrease distortions of the received signal, At the transmitter side, the performance of predistortion technique is shown as the linearization improvement of the non-linearity power amplifier. Therefore more wider the linear region of power amplifier results the decreasing in band distortion of transmitted signal, and can be seen as the Error Vector Magnitude (EVM) improvemen
Evaluation of cellular network performance involving the LTE 1800 band and LTE 2100 band using the drive test method
Full text linkIn the 4G Network on the cellular system, the possibility of high traffic increase is a big problem for users, the proposed solution is to reduce the possibility of full traffic and decrease the quality of the cellular system by dividing the frequency channel into several parts. The purpose of this paper is to study the effect of network optimization on the value of Key Performance Indicator (KPI) in the LTE 1800 and LTE 2100 bands. KPI values, In the LTE 1800 and LTE 2100 bands tested using the drive test method using the Telkomsel sim card provider, the results show that the LTE 2100 band on the TML 013 site has a very high CSSR number compared to the band LTE 1800 which is 99.73% after optimization. The results showed that the LTE band 2100 is better than the LTE band 1800 in terms of KPI Summary
English An implementation of smart agriculture for optimizing growth using sonic bloom and IoT integrated
No full textThis paper proposes the implementation of IoT-based agriculture monitoring with audio growth (sonic bloom) to optimize the growth of plants and harvest. Sonic bloom is a technology that combines high-frequency sound waves from living things, nature or music, and organic nutrients, which aims to make plants grow more optimally so that they can increase productivity. The method’s main advantage is implementing an innovative IoT monitoring hybrid with audio growth systems to boost the plantation growth and maximize the yield. Our experiment in 10 planters using chilies, has proven the proposed procedure. This work is backed up with literature studies of the audio growth (sonic bloom) in IoT technologies. To validate our findings, four parameters were measured through different sensors such as light sensors, temperature, humidity, and soil moisture. It was found that the proposed method can achieve significant results against the comparison in terms of plant heights and new sprouts for the harvest.Paper ini mengusulkan implementasi monitoring pertanian berbasis IoT dengan audio growth (sonic bloom) untuk mengoptimalkan pertumbuhan tanaman dan panen. Sonic bloom adalah teknologi yang menggabungkan gelombang suara frekuensi tinggi dari makhluk hidup, alam atau musik, dan nutrisi organik, yang bertujuan agar tanaman tumbuh lebih optimal, sehingga dapat meningkatkan produktivitas. Keuntungan utama metode ini adalah menerapkan pemantauan IoT yang inovatif dengan sistem pertumbuhan audio untuk mendorong pertumbuhan pertanian cerdas dan hasil maksimal. Percobaan kami di 10 titik menggunakan tanaman cabai telah membuktikan prosedur yang diusulkan. Paper ini didukung dengan studi literatur tentang pertumbuhan audio (sonic bloom) dalam teknologi IoT. Untuk memvalidasi temuan kami, empat parameter diukur melalui sensor yang berbeda seperti sensor cahaya, suhu, kelembaban, dan kelembaban tanah. Ditemukan bahwa metode yang diusulkan dapat mencapai hasil yang signifikan terhadap perbandingan dalam hal tinggi tanaman dan kecambah baru untuk panen