Garuda - Garba Rujukan Digital

OPTICAL PROPERTIES COMPARISON OF CARBON NANODOTS SYNTHESIZED FROM KANGKUNG (IPOMOEA AQUATICA) WITH DEEP FRYING AND ROASTING TECHNIQUES Dwandaru, Wipsar Sunu Brams; Fauzi, Fika; Sari, Dyah Silviana; Sari, Emi Kurnia; Santoso, Iman; Suhendar, Haris
Jurnal Penelitian Fisika dan Aplikasinya (JPFA) Vol 9, No 2 (2019)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jpfa.v9n2.p123-131

Carbon nanodots (Cdots) have many unique properties such as luminescence that can be utilized in various fields. The purposes of this study are to synthesize Cdots from kangkung (Ipomoea aquatica) through frying and roasting techniques and compare the optical properties of the Cdots using UV-Vis, PL, and FTIR. Three stages of synthesizing process of Cdots, i.e.: preparing the kangkung powder (root, stem, leaf) and synthesizing the Cdots through frying and roasting techniques. Each part (root, stem, and leaf) was heated in an oven at 250 oC for 2 hours and mashed into powder. The frying method was done by frying 15 g of the powder in 120 ml oil for 5 minutes at 88 oC, filtered, and dissolved in n-hexane. In addition, the roasting method was done by frying the powder without oil as much as 15 g for 5 minutes, dissolved in 120 ml of distilled water, and then filtered. The UV-Vis characterization showed one absorbance peak for Cdots via frying and roasting techniques at 293 nm to 296 nm and 262 nm to 282 nm, respectively. The Cdots through frying and roasting techniques produce red and green luminescence, respectively. The FTIR characterization showed the presence of C=C and C=O functional groups, which are the core and surface state of the Cdots by frying technique, while the samples via roasting technique showed only the core. It can be concluded that the Cdots samples obtained from frying and roasting methods have different optical properties. The frying method produces Cdots with longer wavelength at the absorbance peak in the UV-Vis test compared to the roasting method. Moreover, the frying and roasting methods produce different color luminescence.

Optical Properties Comparison of Carbon Nanodots Synthesized from Kangkung (Ipomoea aquatica) with Deep Frying and Roasting Techniques Wipsar Sunu Brams Dwandaru; Fika Fauzi; Dyah Silviana Sari; Emi Kurnia Sari; Iman Santoso; Haris Suhendar
Jurnal Penelitian Fisika dan Aplikasinya (JPFA) Vol. 9 No. 2 (2019)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jpfa.v9n2.p123-131

Carbon nanodots (Cdots) have many unique properties such as luminescence that can be utilized in various fields. The purposes of this study are to synthesize Cdots from kangkung (Ipomoea aquatica) through frying and roasting techniques and compare the optical properties of the Cdots using UV-Vis, PL, and FTIR. Three stages of synthesizing process of Cdots, i.e.: preparing the kangkung powder (root, stem, leaf) and synthesizing the Cdots through frying and roasting techniques. Each part (root, stem, and leaf) was heated in an oven at 250 oC for 2 hours and mashed into powder. The frying method was done by frying 15 g of the powder in 120 ml oil for 5 minutes at 88 oC, filtered, and dissolved in n-hexane. In addition, the roasting method was done by frying the powder without oil as much as 15 g for 5 minutes, dissolved in 120 ml of distilled water, and then filtered. The UV-Vis characterization showed one absorbance peak for Cdots via frying and roasting techniques at 293 nm to 296 nm and 262 nm to 282 nm, respectively. The Cdots through frying and roasting techniques produce red and green luminescence, respectively. The FTIR characterization showed the presence of C=C and C=O functional groups, which are the core and surface state of the Cdots by frying technique, while the samples via roasting technique showed only the core. It can be concluded that the Cdots samples obtained from frying and roasting methods have different optical properties. The frying method produces Cdots with longer wavelength at the absorbance peak in the UV-Vis test compared to the roasting method. Moreover, the frying and roasting methods produce different color luminescence.

SINTESIS GRAPHENE OXIDE DAN REDUCED GRAPHENE OXIDE Yeti Rafitasari; Haris Suhendar; Nurul Imani; Fitri Luciana; Hesti Radean; Iman Santoso
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol 5 (2016): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2016
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Graphene oxide (GO) and reduced graphene oxide (rGO) have been synthesized chemically from graphite powder. Graphite powder was oxidized with strong oxidator agent molekul to get graphite oxide, this process was called by Hummerâ€™s methode. Graphite oxide was dispersed in water with ultasonic vibrator to exfoliated graphite oxide layers, and become graphene oxide. Epoxy group in GO structure was reduced by hydrazine 80 wt% to get rGO. Comparation was done between self synthetic rGO and Sigma Aldrich synthetic rGO using UV-Vis and FTIR spectroscopy, which showed that optical properties of self synthetic rGO have same UV-Vis and FTIR spectroscopy with Sigma Aldrich synthetic rGO. Keywords: Graphene Oxide, Reduced Graphene Oxide, Sigma Aldrich, Optical Properties.

Development of a Real-Time Gas Concentration Measurement System Using Internet of Things-Based Monitoring Suhendar, Haris; Indrasari, Widyaningrum; Ghina Muqita, Saffanah; Isnaini, I Gusti Ayu
Spektra: Jurnal Fisika dan Aplikasinya Vol. 9 No. 1 (2024): SPEKTRA: Jurnal Fisika dan Aplikasinya, Volume 9 Issue 1, April 2024
Publisher : Program Studi Fisika Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/SPEKTRA.091.03

Transportation and industrial activities have contributed to an increase in the concentration of pollutant gases such as CO, NO2, and SO2 in the air. High concentrations of these gases can adversely affect human health. One approach to addressing this issue is by measuring and monitoring gas concentrations in the air. The advancement of technology, specifically the Internet of Things (IoT), facilitates the monitoring process. Therefore, this research focuses on the development of a gas concentration measurement system, utilizing the MQ-7 sensor for CO, the MiCS-6814 sensor for NO2, and the MQ-136 sensor for SO2. Additionally, the system is integrated with a website as a platform for monitoring the sensor measurements. The research results indicate that the system has been successfully developed with relative errors of 0.286% for the MQ-7 sensor, 0.325% for the MiCS-6814 sensor, and 0.280% for the MQ-136 sensor. The system underwent testing at three different locations, conducting gas concentration measurements in the environment for 24 hours. The environmental testing revealed measured gas concentration ranges of 2.52-7.67 PPM for CO, 0.00450-0.103 PPM for NO2, and 0.0100-0.0652 PPM for SO2. The measurement data is accessible and observed in real-time through the website, presented in graphical form, indicating average concentration values of CO, NO2, and SO2 over a 3-hour period. Moreover, the website is equipped with indicator lights that serve as alarms if the environmental gas concentration exceeds predefined thresholds.

KARAKTERISTIK FITUR SUARA KETUKAN BUAH KELAPA BERDASARKAN DOMAIN WAKTU DAN DOMAIN FREKUENSI Oktaviani, Paulina Riska; Iswanto, Bambang Heru; Suhendar, Haris
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol. 12 (2024): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2023
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/03.1201.FA02

Abstrak Pada penelitian ini dilakukan untuk menganalisis karakteristik suara akustik hasil ketukan buah kelapa dengan tingkat kematangan pada buah kelapa yang berbeda yaitu muda, setengah tua, dan tua. Analisis suara ketukan buah kelapa dilakukan untuk menentukan apakah perbedaan respons akustik dapat membantu meningkatkan diferensiasi buah pada tingkat kematangan yang berbeda. Dalam pendekatan ini analisis suara akan dilakukan dengan mengekstraksi beberapa fitur seperti Mel Frequency Cepstral Coefficients (MFCC), Mel spectrogram, centroid, zero crossing rate (ZCR), spectral rolloff, dan contrast. Fitur yang diekstraksi kemudian direduksi dimensinya dengan teknik Principal Componen Analysis (PCA). Efektivitas pendekatan ini dievaluasi dengan menganalisis representasi fitur yang dihasilkan. Hasil percobaan menunjukkan kemampuan metode yang diusulkan dalam menangkap informasi penting yang berkaitan dengan tingkat kematangan kelapa. Kata-kata kunci: analisis suara, kematangan buah kelapa, ekstraksi fitur Abstract This research was conducted to analyze the characteristics of the acoustic sound produced by tapping coconuts with different levels of maturity on coconuts, namely young, fairly mature, and mature. The Analysis of coconut sound-tapping was conducted to determine whether differences in acoustic responses can aid in improving fruit differentiation at various maturity levels. In this approach, sound analysis is performed by extracting several features, including Mel Frequency Cepstral Coefficients (MFCC), Mel spectrogram, centroid, zero crossing rate (ZCR), spectral rolloff, and contrast. The extracted features are then subjected to dimensionality reduction using Principal Component Analysis (PCA). The effectiveness of this approach needs to be evaluated by analyzing the resulting feature representation. The experimental results demonstrate the capability of the proposed method in capturing essential information related to coconut maturity levels. Keywords: suara analysis, coconut maturity, feature extraction

KLASIFIKASI KERUSAKAN JALAN RAYA BERBASIS CITRA UDARA MENGGUNAKAN OBJECT-BASED IMAGE-ANALYSIS (OBIA) Sukmaningsih, Rania Virda; Iswanto, Bambang Heru; Suhendar, Haris
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol. 12 (2024): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2023
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/03.1201.FA05

Abstrak Kerusakan jalan merupakan masalah serius yang dapat menyebabkan kemacetan, kecelakaan, dan risiko keselamatan. Pada makalah ini, diusulkan penggunaan citra drone untuk mengidentifikasi kerusakan jalan raya. Pendekatan pixel-to-pixel pada citra drone yang beresolusi spasial tinggi sulit dilakukan karena kerusakan jalan menyebar ke beberapa piksel. Oleh karena itu, pendekatan OBIA digunakan untuk mengklasifikasikan kerusakan jalan raya dengan memfokuskan objek sebagai kesatuan. Klasifikasi citra dilakukan menggunakan pendekatan Object-Based Image-Analysis (OBIA) dengan mengimplementasikan algoritma Simple Linear Iterative Clustering (SLIC). SLIC akan dieksplorasi dengan memvariasikan jumlah cluster untuk mendapatkan metode ekstraksi ciri yang tepat sebelum dilakukan klasifikasi menggunakan CNN. Terdapat dua objek yang dipilih untuk memvalidasi hasil klasifikasi, yaitu jalan rusak dan jalan tidak rusak. Hasil eksperimen menunjukkan bahwa pendekatan OBIA mampu mengidentifikasi objek kerusakan jalan dengan optimal. Bahkan, pemilihan jumlah cluster juga mempengaruhi nilai akurasi klasifikasi. Penggunaan jumlah maksimal 300 cluster memberikan hasil akurasi klasifikasi terbaik dengan peningkatan 13,87% dibandingkan dengan 500 cluster. Kata-kata kunci: Kerusakan Jalan, OBIA, SLIC, Klasifikasi, Unmanned Aerial Vehicles (UAV) Abstract Road damage is a serious problem that can lead to congestion, accidents, and safety risks. This paper proposes the use of drone imagery for identifying road damage. The pixel-to-pixel approach on high-resolution drone imagery is challenging as road damage can span across multiple pixels. Therefore, an Object-Based Image Analysis (OBIA) approach is employed to classify road damage by focusing on objects as a whole. The classification of images is conducted using the Object-Based Image Analysis (OBIA) approach, implementing the Simple Linear Iterative Clustering (SLIC) algorithm. SLIC will be explored by varying the number of clusters to obtain appropriate feature extraction methods before performing classification using a Convolutional Neural Network (CNN). Two objects, namely damaged road and undamaged road, are selected to validate the classification results. The experimental results demonstrate that the OBIA approach can effectively identify road damage objects. Moreover, the selection of the number of clusters also influences the classification accuracy. The use of a maximum of 300 clusters yields the highest classification accuracy with a 13.87% improvement compared to 500 clusters. Keywords: Road Damage, OBIA, SLIC, Classification, Unmanned Aerial Vehicles (UAV)

EKSTRAKSI FITUR BUNYI KETUKAN BUAH KELAPA BERBASIS POWER-NORMALIZED CEPSTRAL COEFFICIENTS (PNCC) Abdillah, Muhlis Ahmad; Iswanto, Bambang Heru; Suhendar, Haris
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol. 12 (2024): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2023
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/03.1201.FA06

Abstrak Bunyi ketukan buah kelapa bervariasi bergantung pada tingkat kematangan buah kelapa. Penentuan tingkat kematangan buah kelapa secara manual memiliki beberapa kendala yang perlu diatasi. Proses ini cenderung subjektif dan rentan terhadap ketidakkonsistenan, karena tergantung pada pengalaman dan penilaian individu. Oleh karena itu, penelitian ini bertujuan untuk memaparkan hasil eksperimen ekstraksi ciri bunyi kelapa menggunakan Power-Normalized Cepstral Coefficients (PNCC). Melalui pendekatan ini diperoleh gambaran yang lebih objektif dan komprehensif tentang perbedaan karakteristik bunyi ketukan pada tingkat kematangan yang berbeda. PNCC digunakan untuk mengekstraksi fitur bunyi ketukan buah kelapa yang muda, matang, dan tua. Data yang digunakan dalam penelitian ini diakuisisi menggunakan mikrofon dua arah yang ditempatkan pada kotak tertutup. Fitur diekstrak dengan membagi rekaman bunyi ketukan berdurasi satu detik. Fitur PNCC diekstrak dari bunyi ketukan buah kelapa dan dilakukan reduksi dimensi menggunakan Principal Component Analysis (PCA) dengan tiga jenis kernel, yaitu Linear, RBF, dan Sigmoid. Evaluasi perbedaan karakteristik bunyi dilakukan dengan menghitung Silhouette Score pada setiap kernel PCA. Hasil penelitian menunjukkan bahwa pada kernel Linear, RBF, dan Sigmoid, diperoleh Silhouette Score berturut-turut sebesar 0.205446, 0.179289, dan 0.194963. Temuan ini memberikan pemahaman lebih dalam tentang perbedaan karakteristik bunyi ketukan pada tingkat kematangan buah kelapa yang berbeda dan dapat menjadi dasar untuk pengembangan metode non-invasif yang efisien dalam menentukan tingkat kematangan buah kelapa secara akurat. Kata-kata kunci: analisis bunyi, sinyal akustik, buah kelapa, PNCC, ekstraksi fitur Abstract The tapping sound of a coconut varies depending on the ripeness level of the coconut. Manually determining the ripeness level of a coconut has several obstacles that need to be overcome. This process tends to be subjective and prone to inconsistency, as it depends on individual experience and judgment. Therefore, this study aims to present the experimental results of coconut sound feature extraction using Power-Normalized Cepstral Coefficients (PNCC). Through this approach, a more objective and comprehensive picture of the differences in beat characteristics at different maturity levels is obtained. PNCC was used to extract the beat sound features of young, mature and old coconuts. The data used in this study was acquired using a two-way microphone placed in a closed box. Features were extracted by splitting a one-second recording of the tapping sound. PNCC features were extracted from the coconut tapping sound and dimension reduction was performed using Principal Component Analysis (PCA) with three types of kernels, namely Linear, RBF, and Sigmoid. Evaluation of differences in sound characteristics was carried out by calculating the Silhouette Score on each PCA kernel. The results showed that for Linear, RBF, and Sigmoid kernels, the Silhouette Score was 0.205446, 0.179289, and 0.194963, respectively. These findings provide a deeper understanding of the differences in the characteristics of tapping sounds at different maturity levels of coconut fruits and can be the basis for the development of efficient non-invasive methods to accurately determine the maturity level of coconut fruits. Keywords: sound analysis, acoustic signal, coconut fruit, PNCC, feature extraction

KARAKTERISASI DAN PENGUJIAN SENSOR MQ-4 DAN MG-811 UNTUK PENGEMBANGAN SISTEM MONITORING KONSENTRASI GAS METANA DAN KARBON DIOKSIDA DI UDARA Ramadhani, I Gusti Ayu Isnaini Fatha; Indrasari, Widyaningrum; Suhendar, Haris; Marpaung, Mangasi Alion
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol. 12 (2024): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2023
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/03.1201.FA12

Abstrak Seiring dengan perkembangan zaman, berbagai kegiatan indrustrialisasi dan urbanisasi dapat memicu peningkatan gas CH4 dan CO2 yang dapat memperburuk kualitas udara di lingkungan. Salah satu upaya untuk mengetahui kualitas udara adalah dengan melakukan monitoring konsentrasi gas di udara. Konsentrasi gas CH4 di udara dapat diukur menggunakan sensor MQ-4 sedangkan gas CO2 diukur menggunakan sensor MG-811. Dalam penggunaannya, perlu dilakukan karakterisasi sensor dan pengujian sensor dengan tujuan untuk mendapatkan persamaan kalibrasi, kesalahan relatif pengukuran, dan rentang kerja dari masing-masing sensor. Maka pada penelitian ini dilakukan proses karakterisasi sensor dengan membandingkan hasil keluaran sensor MQ-4 dengan CH4 Analyzer G2203 dan sensor MG-811 dengan CO2 Analyzer G2301 Picarro. Adapun hasil karakterisasi menunjukkan bahwa sensor MQ-4 memiliki kesalahan relatif rata-rata sebesar 0,066%. Sedangkan sensor MG-811 memiliki kesalahan relatif rata-rata sebesar 0,047%. Sedangkan pengujian sensor dilakukan dengan melakukan pengukuran sampel berupa asap kendaraan bermotor menggunakan variasi waktu. Adapun hasil pengujian menunjukkan bahwa sensor MQ-4 dapat bekerja dengan baik dalam rentang 1,885-1,914 PPM, sedangkan sensor MG-811 dapat bekerja dengan baik dalam rentang 406,311-409,169 PPM. Hasil tersebut selanjutnya akan digunakan dalam pengembangan sistem monitoring konsentrasi gas CH4 dan CO2 di udara. Kata-kata kunci: metana, karbon dioksida, MQ-4, MG-811, konsentrasi gas. Abstract Along with times, various industrialization and urbanization activities can trigger an increase in CH4 and CO2 gases which can improve air quality in environment. One effort to determine air quality is to monitor gas concentrations in air. Concentration of CH4 gas in air can be measured using MQ-4 sensor and CO2 gas is measured using MG-811 sensor. In use, it is necessary to characterize sensors and test sensors with aim of obtaining measured equations, relative measurement errors, and working distance of each sensor. So, in this research sensor characterization process was carried out by comparing output results of MQ-4 sensor with CH4 Analyzer G2203 and MG-811 sensor with CO2 Analyzer G2301 Picarro. Characterization results show that MQ-4 sensor has an average relative error of 0,066% and MG-811 sensor has an average relative error of 0,047%. While sensor testing is done by measuring samples in form of motorized vehicle smoke using time variations. The sensor testing results show that The MQ-4 sensor can work well in range of 1,885-1,914 PPM, while MG-811 sensor can work well in range of 406,311-409,169 PPM. These results will then be used in development of a monitoring system for CH4 and CO2 gases concentrations in air. Keywords: methane, carbon dioxide, MQ-4, MG-811, gas concentration.

KARAKTERISASI DAN PENGUJIAN SENSOR MQ-7 DAN MQ-136 UNTUK PENGEMBANGAN SISTEM MONITORING KONSENTRASI GAS KARBON MONOKSIDA (CO) DAN SULFUR DIOKSIDA (SO2) Muqita, Saffanah Ghina; Indrasari, Widyaningrum; Suhendar, Haris; Marpaung, Mangasi Alion
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol. 12 (2024): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2023
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/03.1201.FA13

Abstrak Jenis gas polutan yang banyak dihasilkan dari kegiatan transportasi dan industri adalah CO dan SO2. Apabila gas tersebut berada dalam konsentrasi tinggi, maka akan memicu terjadinya pencemaran udara. Oleh sebab itu, dibutuhkan sistem monitoring konsentrasi gas dengan memanfaatkan sensor MQ-7 untuk mengukur konsentrasi gas CO dan sensor MQ-136 untuk mengukur konsentrasi gas SO2. Untuk menghasilkan pengukuran yang akurat, sensor tersebut perlu dilakukan karakterisasi dan pengujian dengan tujuan untuk mendapatkan persamaan kalibrasi, kesalahan relatif pengukuran dan rentang kerja dari masing-masing sensor. Maka dari itu pada penelitian ini dilakukan proses karakterisasi sensor dengan membandingkan hasil keluaran sensor MQ-7 dengan CO Analyzer CO-30r Los Gatoss dan sensor MQ-136 dengan SO2 Analyzer Model 43i-TLE Thermo. Hasil karakterisasi menunjukkan bahwa sensor MQ-7 memiliki kesalahan relatif pengukuran sebesar 0,286%, sedangkan sensor MQ-136 memiliki kesalahan relatif rata-rata sebesar 0,280%. Adapun pengujian sensor dilakukan dengan mengukur sampel berupa asap kendaraan bermotor menggunakan variasi waktu. Hasil pengujian menunjukkan bahwa sensor MQ-7 dapat bekerja dengan baik dalam rentang 4,36 – 4,68 PPM, sedangkan sensor MQ-136 dapat bekerja dengan baik dalam rentang 0,00387 – 0,00419 PPM. Hasil tersebut selanjutnya akan digunakan dalam pengembangan sistem monitoring konsentrasi gas CO dan SO2 di udara. Kata-kata kunci: karbon monoksida, sulfur dioksida, MQ-7, MQ-136, konsentrasi gas. Abstract Types of pollutant gases that are mostly produced from transportation and industrial activities are CO and SO2. If these gases are in high concentrations, it will trigger air pollution. Therefore, a gas concentration monitoring system is needed by utilizing MQ-7 sensor to measure CO gas concentration and MQ-136 sensor to measure SO2 gas concentration. To produce accurate measurements, these sensors need to be characterized and tested with the aim of obtaining calibration equations, relative measurement errors and working ranges of each sensor. Therefore, in this study, the sensor characterization process was carried out by comparing output of MQ-7 sensor with CO Analyzer CO-30r Los Gatoss and MQ-136 sensor with SO2 Analyzer Model 43i-TLE Thermo. The characterization results show that MQ-7 sensor has a relative measurement error of 0,286%, while MQ-136 sensor has has a relative measurement error of 0,280%. The sensor testing was carried out by measuring samples in the form of motor vehicle smoke using time variations. The test results show that MQ-7 sensor can work well in range of 4,36 – 4,68 PPM, while MQ-136 sensor can work well in range of 0,00387 – 0,00419 PPM. These results will then be used in the development of a monitoring system for CO and SO2 gas concentrations in the air. Keywords: carbon monoxide, sulfur dioxide, MQ-7, MQ-136, gas concentration.

ANALISIS MODEL PREDIKSI CUACA MENGGUNAKAN SUPPORT VECTOR MACHINE, GRADIENT BOOSTING, RANDOM FOREST, DAN DECISION TREE Risanti, Risanti; Indrasari, Widyaningrum; Suhendar, Haris
PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) Vol. 12 (2024): PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL) SNF2023
Publisher : Program Studi Pendidikan Fisika dan Program Studi Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/03.1201.FA18

Abstrak Machine learning dapat diaplikasikan untuk melakukan prediksi terhadap suatu data. Salah satu data yang berkaitan dengan fenomena alam yang terdokumentasi dengan baik dan dapat diakses dengan mudah adalah data kondisi cuaca. Dalam penelitian ini digunakan data kondisi cuaca untuk melakukan pengembangan model machine learning dan prediksi keadaan cuaca. Data yang digunakan terdiri dari pengukuran suhu udara, kelembaban udara, dan kecepatan angin menggunakan data BMKG Provinsi Jawa yang bersifat open source dengan selang waktu 3 jam tahun 2020 dari bulan Januari - Desember. Tujuan penelitian ini adalah untuk mendapatkan nilai akurasi, presisi, F1 score, dan recall serta membandingkan fitur yang memberikan pengaruh paling besar terhadap hasil prediksi cuaca. Model yang digunakan dalam penelitian ini adalah support vector machine, gradient boosting, random forest, dan decision tree. Perbandingan antara data training dan data test adalah 70:30. Hasil penelitian menunjukan bahwa hasil akurasi model support vector machine, gradient boosting, random forest, decision tree masing-masing sebesar 0.1697; 0.6696; 0.7918; 0.8416; 0.8280. Pada hasil terlihat bahwa random forest memiliki pengaruh paling besar terhadap hasil prediksi cuaca dengan dengan hasil akurasi 0.8416. Kata-kata kunci: Prediksi, Cuaca, SVM, Gradient Boosting, Random Forest, Decision Tree. Abstract Machine learning can be applied to make predictions on a given dataset. One well-documented and easily accessible dataset related to natural phenomena is weather condition data. In this study, weather condition data is used to develop machine learning models and predict weather conditions. The data used consists of air temperature, air humidity, and wind speed measurements obtained from the BMKG (Meteorology, Climatology, and Geophysics Agency) of the Jawa Province, which are open source and collected at 3-hour intervals throughout the year 2020 from January to December. The aim of this research is to obtain accuracy, precision, F1 score, and recall values and compare the features that have the most significant influence on weather prediction outcomes. The models used in this study are support vector machine, gradient boosting, random forest, and decision tree. The data is divided into a 70% training set and a 30% test set. The research results show that the accuracy values for, support vector machine, gradient boosting, random forest, and decision tree models are 0.1697, 0.6696, 0.7918, 0.8416, and 0.8280, respectively. It can be observed that random forest has the greatest influence on weather prediction outcomes, with an accuracy value of 0.8416. Keywords: Prediction, Weather, SVM, Gradient Boosting, Random Forest, Decision Tree.

Title

Found 16 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 16 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 16 Documents
Search