181 research outputs found
Classification of Corn Quality Using Faster Region Convolutional Neural Network
No full textMaize is the second food commodity after rice. Corn also has various qualities. Determining the quality of corn kernels plays an important role in determining the selling price of corn kernels, in determining the quality of corn kernels still uses manual labor which causes subjectivity in the assessment, so that the assessment of the quality of corn kernels is not fully based on the object of the corn kernels and will cause differences in opinion between observers and other observers. The quality of corn kernels can be seen physically based on the texture of the corn kernels, which is seen from the crunchiness of the germ and the color of the corn kernels. This research produces a system that can classify the quality of corn kernels by looking at the color, texture and shape of the germ of corn kernels to minimize subjectivity in determining the quality of corn kernels. The quality of corn is then divided into five levels, namely Quality A, Quality B, Quality C, Quality D and Quality E. This research uses the Faster Region Convolutional Neural Network algorithm and uses ResNet50 as feature extraction. The data used in this study amounted to 2500 data which were then divided into 2000 training data, 250 validation data and 250 testing data. After testing, this research resulted in an accuracy of 95.2%.84 PagesSkripsi Sarjan
Forecasting Ethereum Cryptocurrency Prices Using Random Forest With Random Search Hyperparameter Tuning
No full textThe cryptocurrency market, particularly Ethereum, is known for its high volatility and the complex factors that influence its price. This makes Ethereum price prediction a significant challenge, especially for investment decision-making. This study aims to evaluate the capability of the Random Forest algorithm in predicting Ethereum prices and assess the impact of Random Search optimization on the model's performance. The research uses five years of historical Ethereum data with features including open, high, low, close, volume, and percentage change. The results show that the non-optimized Random Forest model achieved a Mean Absolute Percentage Error (MAPE) of 2.82% and a Root Mean Square Error (RMSE) of 101 USD for one-day-ahead predictions. After applying Random Search optimization, the model performance improved, with MAPE arround 2.60% and 96.5 USD of RMSE. However, the prediction accuracy tends to decrease over longer prediction horizons, reaching a MAPE of up to 10.2% by the tenth day, indicating that the model is only good for short-term forecasting. In conclusion, Random Search optimization enhances the accuracy of the Random Forest algorithm, although the model still struggles with long-term predictions. Another limitation lies in the use of limited features, relying solely on historical price values without considering external factors such as multi-week trends or macroeconomic conditions that may affect Ethereum's price. Future studies are recommended to incorporate additional features to improve model performance.63 PagesSkripsi Sarjan
Prediction of Solar Radiation Using Deep Autoregressive Method
No full textSolar energy is one of the renewable energy sources that is growing very rapidly in its utilization. Through solar power plants (PLTS), solar radiation can be converted into electrical energy using solar cells that utilize photovoltaic (PV) technology. However, the performance of PV systems can be affected by various environmental factors, such as temperature, humidity, wind speed, and light intensity. In addition, the operation of solar power systems with high penetration can lead to voltage fluctuations and unstable solar electricity production, causing an imbalance between energy demand and supply. In this case, accurate prediction of solar radiation is essential to make good planning in managing and operating solar power systems so that it can produce energy optimally and maintain the balance of energy supply and demand. In this study, the Deep Autoregressive (DeepAR) method is applied to train a model to predict solar radiation. The results of this study show that the model trained with the DeepAR method has good performance in predicting solar radiation with the best evaluation metric value achieved in the prediction time span of 7 days with an R² value of 0.956675, MAE of 7.835733, MSE of 97.33104, and RMSE of 9.86565.91 PagesSkripsi Sarjan
An Analysis of the Brand Positioning of Cleo Bottled Drinking Water in Medan City
No full textThe rapid growth of the bottled drinking water industry and increasingly selective consumer preferences for high-quality yet affordable products demand that producers thoroughly examine consumer perceptions in choosing bottled drinking water. This study aims to analyze the brand positioning of bottled drinking water products—Cleo, Le Minerale, Ades, and Club—using Aqua as the benchmark, based on consumer perceptions in Medan City. A quantitative method was employed with a survey approach, utilizing both closed questionnaires and open- ended questions to explore consumer perceptions in greater depth, and analyzed using the Multidimensional Scaling method. The findings show that Le Minerale occupies the top position in the attributes of product, place, and promotion; Cleo excels in product and promotion; Ades is stronger in the price aspect; while Club remains weak in nearly all attributes. Aqua, as the benchmark, is still dominant in terms of distribution and brand awareness. The study concludes that price is the primary differentiating factor, while product, promotion, and place are interrelated in shaping consumer perceptions. The strategic implications recommended include improving distribution and pricing strategies for Cleo, maintaining competitive pricing for Le Minerale, product differentiation for Ades, and overall improvement for Club.143 PagesSkripsi Sarjan
Prediction of Solar Radiation Using Deep Autoregressive Method
No full textSolar energy is one of the renewable energy sources that is growing very rapidly in its utilization. Through solar power plants (PLTS), solar radiation can be converted into electrical energy using solar cells that utilize photovoltaic (PV) technology. However, the performance of PV systems can be affected by various environmental factors, such as temperature, humidity, wind speed, and light intensity. In addition, the operation of solar power systems with high penetration can lead to voltage fluctuations and unstable solar electricity production, causing an imbalance between energy demand and supply. In this case, accurate prediction of solar radiation is essential to make good planning in managing and operating solar power systems so that it can produce energy optimally and maintain the balance of energy supply and demand. In this study, the Deep Autoregressive (DeepAR) method is applied to train a model to predict solar radiation. The results of this study show that the model trained with the DeepAR method has good performance in predicting solar radiation with the best evaluation metric value achieved in the prediction time span of 7 days with an R² value of 0.956675, MAE of 7.835733, MSE of 97.33104, and RMSE of 9.86565.91 PagesSkripsi Sarjan
TRANSFORMASI DAKWAH TRADISIONAL KE DIGITAL PADA MAJELIS NURUL AMIN DI SAMARINDA
Full text linkDakwah Islam mengalami pergeseran besar dari metode konvensional ke penggunaan media digital selama pandemi COVID-19. Studi ini melihat bagaimana dakwah di Majelis Nurul Amin berubah sebelum, selama, dan setelah pandemi. Tulisan ini bertujuan untuk memberikan gambaran langsung tentang bagaimana strategi dakwah berubah, serta masalah dan perubahan yang dihadapi komunitas dakwah tradisional. Meskipun media digital seperti YouTube telah digunakan untuk menyebarkan dakwah, hasil wawancara mendalam menunjukkan bahwa fokus dakwah tetap pada hubungan emosional dan nilai-nilai spiritual, terutama cinta kepada Nabi Muhammad SAW
MONITORING SUPLAI TEGANGAN PADA MOTOR INDUKSI TIGA FASA MENGGUNAKAN MIKROKONTROLER ARDUINO DAN SENSOR TEGANGAN ZMPT101B
Full text linkABSTRAK
PUTRI RAMADHANI ADAM, MONITORING SUPLAI TEGANGAN PADA MOTOR INDUKSI TIGA FASA MENGGUNAKAN MIKROKONTROLER ARDUINO DAN SENSOR TEGANGAN ZMPT101B, Skripsi. Jakarta: Fakultas Teknik Universitas Negeri Jakarta 2020. Dosen Pembimbing: Drs. Purwanto Gendroyono, MT., Nur Hanifah Yuninda, ST.MT.
Penelitian ini bertujuan untuk membuat sistem monitoring suplai tegangan motor induksi tiga fasa berbasis mikrokontroler Arduino Uno menggunakan sensor tegangan ZMPT101B. Selain itu, dalam penelitian ini bertujuan untuk mengetahui persentase ketidakseimbangan tegangan sumber yang masuk pada motor induksi 3 fasa berdasarkan standar The National Standard for Electric Power System and Equipment ANSI Std C84.1-1995, NEMA Std MGI.2009 dari hasil monitoring alat yang telah dibuat.
Metode penelitian yang digunakan penulis yaitu metode eksperimen laboratorium yang meliputi manipulasi, pengendalian, dan pengamatan. Adapun penelitian yang dilakukan yaitu membuat sistem monitoring tegangan menggunakan tiga Arduino Uno dan tiga sensor tegangan ZMPT101B yang dihubungkan pada laptop. Kemudian dibuat pemrograman untuk pembacaan masing-masing sensor tegangan ZMPT101B yang telah dihubungkan pada sumber tegangan yang masuk ke motor induksi tiga fasa. Setelah itu, hasil monitoring pembacaan sensor dapat ditampilkan pada serial monitor yang ada di aplikasi Arduino IDE pada laptop.
Hasil penelitian menunjukkan bahwa nilai persentase ketidakseimbangan tegangan rata rata untuk di waktu pagi nilainya masih di bawah 1 %. Sedangkan untuk nilai persentase ketidakseimbangan tegangan di waktu siang dan sore hari nilainya sudah di atas 1 %. Jika sesuai dengan standar, persentase ketidakseimbangan tegangan yang diijinkan tanpa melakukan derating (penurunan daya) berdasarkan NEMA adalah 1 %. Sedangkan, maksimum persentase ketidakseimbangan tegangan yang diijinkan adalah 5 %. Maka, hasil dari data penelitian ketiga waktu tersebut yang paling aman kondisinya adalah di waktu pagi hari. Sedangkan, data penelitian yang diambil saat siang dan sore hari kondisinya masih aman tetapi akan ada penurunan daya. Selain itu, Perbandingan sensor tegangan ZMPT101B dengan alat ukur AVO meter digital saat mendeteksi tegangan memiliki error rata-rata yaitu 0,07 % untuk sensor tegangan ZMPT101B yang pertama, 0,28 % untuk sensor tegangan ZMPT101B yang kedua dan 0,15 % untuk sensor tegangan ZMPT101B yang ketiga. Sehingga dapat dikatakan bahwa sistem monitoring tegangan yang dibuat sesuai dengan ketentuan dan bisa diaplikasikan sebagai pembelajaran mahasiswa Pendidikan Teknik Elektro.
Kata Kunci: Ketidakseimbangan Tegangan, Monitoring, Motor Induksi 3 Fasa, Arduino Uno, Sensor Tegangan ZMPT101B
PUTRI RAMADHANI ADAM, VOLTAGE SUPPLY MONITORING ON THREE PHASE INDUCTION MOTOR USING ARDUINO MICROCONTROLLER AND ZMPT101B VOLTAGE SENSOR, Skripsi. Jakarta: Faculty of Engineering, Jakarta State University 2020. Supervisor: Drs. Purwanto Gendroyono, MT., Nur Hanifah Yuninda, ST.MT.
The purpose of this study is to create a three-phase induction motor voltage monitoring system based on Arduino Uno microcontroller using a ZMPT101B voltage sensor. In addition, this study aims to determine the percentage of voltage unbalance on a 3 phase induction motor based on the National Standard for Electric Power System and Equipment ANSI Std C84.1-1995, NEMA Std MGI.2009 from the results monitoring tools that have been made.
The research method used by the author in completing this research is the laboratory experimental method which includes manipulation, control, and observation. The research conducted is to create a voltage monitoring system using three Arduino Uno and three ZMPT101B voltage sensors that are connected to a laptop. Then programming is made for the reading of each ZMPT101B voltage sensor which has been connected to the voltage source that enters the three-phase induction motor. After that, the results of monitoring the sensor readings can be displayed on the serial monitor in the Arduino IDE application on the laptop.
The results showed that the value of the percentage of voltage unbalance, the average for the morning the value is still below 1%. As for the value of the percentage of voltage unbalance in the afternoon and evening, the value is already above 1%. If according to the standard, the percentage of voltage unbalance permitted without derating (based on power reduction) based on NEMA is 1%. Meanwhile, the maximum percentage of allowable voltage unbalance is 5%. So, the results of the research data of the three times the safest condition is in the morning. Meanwhile, research data taken during the afternoon and evening conditions are still safe but there will be a decrease in power. In addition, the comparison of the ZMPT101B voltage sensor with a digital AVO meter when detecting the voltage has an average error of 0.07% for the first ZMPT101B voltage sensor, 0.28% for the second ZMPT101B voltage sensor and 0.15% for the sensor the third voltage ZMPT101B. So that it can be said that the voltage monitoring system that is made in accordance with the provisions and can be applied as learning by students of Electrical Engineering Education.
Keywords: Voltage Unbalance, Monitoring, 3 Phase Induction Motor, Arduino Uno, ZMPT101B Voltage Senso
Determination of Covid-19 Pneumonia Lesion Area Using SegNet Architecture on X-Ray Images
No full textLung disease is a highly serious public health issue and a leading cause of death worldwide. One of the diseases affecting the lungs is pneumonia. On December 1, 2019, a new variant of pneumonia caused by a novel virus emerged. This virus is a variant of the coronavirus known as Covid-19. The virus has a higher mortality rate compared to general pneumonia. Common symptoms of viral pneumonia include fever, cough, shortness of breath, chest pain, and fatigue, while Covid-19 pneumonia often presents symptoms such as high fever, persistent dry cough, severe shortness of breath, loss of the sense of smell, fatigue, and body aches . Machine learning has recently been frequently employed for disease diagnosis due to the limited number of radiologist experts available to interpret X-ray results. Additionally, reading test results takes time and introduces the possibility of human error. In this study, the author proposes research that will result in a website to assist healthcare professionals in areas with a shortage of experts in identifying the extent of Covid-19 lesion based on X-ray results using the SegNet architecture. A total of 2,912 Covid pneumonia data and 2,912 normal lung data were used, with 2,331 training data, 290 validation data, and 290 testing data, respectively. The application of the SegNet architecture for lung segmentation and lesion segmentation from X-ray images resulted in a mean IoU of 93.96%, an AUC of 99.24%, and a precision of 97.93%.70 PagesSkripsi Sarjan
EVALUASI PENGGUNAAN OBAT ANTIMALARIA DI RAWAT INAP DEWASA RSUD RATU AJI PUTRI BOTUNG PENAJAM PASER UTARA PERIODE TAHUN 2018
Full text linkObat antimalaria merupakan terapi dalam pengobatan malaria yang tidak hanya mempersingkat lamanya penyakit malaria tetapi juga menurunkan insiden dari komplikasi dan kematian.Evaluasi perlu dilakukan dalam pemilihan obat antimalaria untuk mengatasi masalah yang telah terjadi (ketidaktepatan dalam pemilihan jenis obat, dosis, durasi, frekuensi, rute pemberian) dan mencegah timbulnya masalah baru terkait penggunaan obat (resitensi).Penelitian ini bertujuan untuk mengevaluasi penggunaan obat antimalaria di ruang rawat inap dewasa RSUD Ratu Aji Putri Botung selama periode tahun 2018.Penelitian ini merupakan penelitian deskriptif dengan pengambilan data secara restropektif.Data yang digunakan merupakan data sekunder yang diambil dari data rekam medis pasien rawat inap dewasa selama periode tahun 2018. Hasil dari penelitian ini menunjukkan hasil bahwa penderita malaria tertinggi adalah laki – laki (94,52%) dan terendah pada perempuan (5,48%) dengan rentang usia 15-25 tahun (28,77%), 26 – 35 tahun (42,26%), 36 – 45 tahun (28,77%). Obat antimalaria yang digunakan pada pasien malaria di rawat inap dewasa RSUD Ratu Aji Putri Botung periode tahun 2018 yaitu DHP (Dihydroartemisin-Piperakuini), primakuin dan kina dengan ketepatan obat, ketepatan dosis dan ketepatan lama pemberian obat yang belum mencapai 100%
Konsep dan praktek bimbingan rohani Islam di Rumah Sakit Jiwa Prof. Dr. Muhammad Ildrem Provinsi Sumatera Utara
Full text linkThis study aims first to find out about the concept of islamic spiritual
guidance, such as lectures and questions and answers conducted by clerics to
patients. Second, to find out the practices of Islamic Spiritual guidance, such as
the practice of reading istigfar, zikir, pray, and prayer. The theory in this Islamic
Spiritual Guidance. The research approach used is qualitative research. There
were 4 informants in this ustadz , two nurse and patient. Data collection
techniques are interviews and documentation. The data analysis technique uses
data reduction, data presentation and conclusion drawing. The data validity
basically done to prove whether this research is really scientific research as well
as to test the data obtained.
The results of the study show that the concept of Islamic spiritual guidance by the
cleric in lectures and questions and answers and practice of Islamic spiritual guidance by
the cleric in this activity has been proven to work like patients can do how to read istigfar,
zikir, prayer and read the short well. As for the achievement in question is includes
spiritual attiudes, social, and skills. Bottlenecks in this proces is when a patient is having
uncontrollable emotions then he cannot follow the islamic spiritual guidance activities
- …
