Garuda - Garba Rujukan Digital

Penerapan Struktur Backpropagation Pada Jaringan Syaraf Tiruan Untuk Mendeteksi Gangguan Penyakit Tropis Novi Yanti
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2018: SNTIKI 10
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (202.182 KB)

Tropical disease is the most common diseases in tropical and subtropical regions. Many factors affected the spread of these diseases, such as poor sanitation and bad environment. Islam establishes the principles in maintaining health through the cleanliness, wudu, and taking bath regularly. Technology through the expert system development tried to transform the expertise knowledge into computers that can mimic the workings of the human brain. One of the methods applied is Artificial Neural Network (ANN) with backpropagation structure. This method detected the tropical diseases of patients, including Dengue Hemorrhagic Fever (DHF) and Typhoid Fever to perform the appropriate treatment as early as possible. ANN diagnosed the type of diseases by identifying the pattern of symptoms in patients. ANN training was presented using 80% of training data and 20% test data. The binary sigmoid activation function [0 1] is used. The learning rate (α) values 0.05, 0.1, 0.2, 0.5, 0.75 and the hidden layers values 10, 50 and 100 are used in testing process. ANN trained the input symptoms, thus the results proposed whether patients affected by any kinds of tropical disease or not. Keywords: DBD, hidden layer, JST, learning rate, Tifoid

Implementasi Metode Learning Vector Quantization (LVQ) Untuk Sentimen Analisis Terhadap Aplikasi Go-Jek Pada Playstore Arif Pratama Budiman; Elvia Budianita; Novi Yanti; Reski Mai Candra
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 3 (2022): Juni 2022
Publisher : Program Studi Teknik Informatika, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i3.4287

Abstrak— Perkembangan teknologi dan informasi pada saat ini sangat pesat, terutama di Indonesia. Salah satu teknologi yang berkembang pesat di Indonesia saat ini adalah teknologi dalam bidang transportasi yaitu, transportasi online. Dengan adanya transportasi online ini sangat membantu segala aktifitas masyarakat. Terdapat beberapa platform tranasportasi yang ada di Indonesia, salah satu yang terkenal adalah transportasi online Gojek. Apliikasi Gojek dapat dengan dengan mudah di download pada google plyastore. Playstore adalah sebuah aplikasi yang berguna untuk mengunduh berbagai aplikasi. Playstore juga menyediakan fitur penilaian terhadap aplikasi yang tersedia di platform tersebut, dengan adanya fitur penilaian ini pengguna dapat memberikan penilaiannya dan juga berkomentar terhadap aplikasi yang digunakannya. Dengan adanya fitur komentar ini maka dapat di lakukannya sentimen analisis untuk mengetahui sentimen publik terhadap suatu aplikasi. Dalam penelitian ini langkah awal yang dilakukan adalah mengumpulkan data dan juga memberikan laber terhadap seluruh data, pada penelitian ini terdapat 3 label yaitu positif, netral, dan Negatif dengan jumlah 900 data. Selanjutnya melakukan proses analisa preprocessing dan juga dilanjutkan dengan proses pembobotan TF, kemudian baru dilakukannya proses klasifikasi menggunakan metode Learning Vector Quantization (LVQ). Hasil pengujiannya sendiri dilakukan dengan menggunakan metode Confussion Matrix. Berdasarkan dari proses dan hasil pengujian yang di lakukan di dapatkan akurasi terbaik pada perbandingan 90 : 10 sebesar 84,44% yang sebagian besar bernilai positif. Kata Kunci: transportasi online, Sentiment analysis , Playstore, Klasifikasi, Learning Vector Quantization Abstract— The development of technology and information is currently very fast, especially in Indonesia. One technology that is developing rapidly in Indonesia today is technology in the field of transportation, namely online transportation. The existence of online transportation is very helpful for all community activities. There are several transportation platforms in Indonesia, which is well-known online transportation called Gojek. The Gojek application can be easily downloaded on the Google Playstore. Playstore is an application that is useful for downloading various applications. Playstore also provides an assessment feature for applications available on the platform, with this assessment feature users can provide an assessment and also comment on the applications they use. With this comment feature, sentiment analysis can be done to find out public sentiment towards an application. In this study, initial step was taken to collect data and also provide a label for all data, in this study there were 3 labels, namely positive, neutral, and negative with a total of 900 data. Next, perform the preprocessing analysis process and also continue with the TF-IDF weighting process, then the classification process is carried out using the Learning Vector Quantization (LVQ) method. The results of the test itself are carried out using the Confusion Matrix method. Based on the process and the results of the tests , the best accuracy obtained is at ratio of 90 : 10 by 84,44%,which is most of it are positiveKeywords:Online Transportation,sentiment analysis , Playstore, Classification, Learning Vector Quantization

Sistem Pakar Diagnosa Gangguan Stress Pasca Trauma Menggunakan Metode Certainty Factor Marliana Safitri; Fitri Insani; Novi Yanti; Lola Oktavia
Jurnal Sistem Komputer dan Informatika (JSON) Vol 4, No 4 (2023): Juni 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i4.6309

Mental health disorder or commonly called Mental Health Disorder is a disturbing psychological behavior and is followed by traumatic events such as shock shell, war fatigue, accidents, victims of sexual violence, and the covid pandemic. Cases of post traumatic stress disorder data from Indonesian Psychiatric Association amounted to 80% of 182 examiners experiencing symptoms of post-traumatic stress due to exposure to covid, 46% experienced severe symptoms, 33% moderate, 2% mild and others did not show symptom. This study aims to diagnose post traumatic stress disorder using the assurance factor method with 35 symptom data and 3 levels of post traumatic stress disorder as a knowledge base. The certainty factor is a circulation management method and a decision-making strategy using the confidence factor in the system. Based on the research results of the expert system for diagnosing post traumatic stress disorder, the test results obtained an accuracy of 80%. The results of the accuracy of this expert system indicate that the expert system can potentially be used to diagnose post traumatic stress disorder.

Analisa Dini Gangguan Disleksia Anak Sekolah dengan Metode Backpropagation Novi Yanti; Adil Setiawan; Sarjon Defit
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 9, No 2 (2023): Volume 9 No 2
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v9i2.64588

Disleksia sering disalah artikan sebagai kebodohan atau kemalasan pada anak. Gejala disleksia dikenal dengan gangguan belajar yang meliputi mengenal huruf, mengeja, membaca, dan menulis. Meskipun gejala disleksia tidak terlihat dengan jelas, kondisi ini dapat berdampak pada perkembangan pola belajar anak. Tujuan penelitian adalah untuk mengidentifikasi gejala disleksia sedini mungkin agar tidak mengganggu perkembangan belajar pada anak. Selain itu, penelitian juga bertujuan untuk mengevaluasi keakuratan teknik yang digunakan. Analisa menggunakan metode jaringan syaraf tiruan dengan teknik backpropagation dengan memberikan nilai bobot, sehingga dapat memberikan nilai input dengan benar. Penelitian menggunakan 150 dataset, 40 variabel input dan 40 lapisan tersembunyi. Keluaran yang diharapkan mencakup disleksia atau non-disleksia. Hasil implementasi dan pengujian untuk data latih dan data uji terbaik adalah 90:10. Dengan nilai epoch maksimum 5000 dan nilai error target 0,001. Metode backpropagation dapat memberikan hasil akurasi terbaik 100% pada learning rate 0,5. Sehingga metode backpropagation dapat dengan baik mendeteksi gangguan disleksia pada anak sejak dini.

Implementasi Metode Learning Vector Quantization (LVQ) Untuk Sentimen Analisis Terhadap Aplikasi Go-Jek Pada Playstore Arif Pratama Budiman; Elvia Budianita; Novi Yanti; Reski Mai Candra
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 3 (2022): Juni 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i3.4287

Abstrak— Perkembangan teknologi dan informasi pada saat ini sangat pesat, terutama di Indonesia. Salah satu teknologi yang berkembang pesat di Indonesia saat ini adalah teknologi dalam bidang transportasi yaitu, transportasi online. Dengan adanya transportasi online ini sangat membantu segala aktifitas masyarakat. Terdapat beberapa platform tranasportasi yang ada di Indonesia, salah satu yang terkenal adalah transportasi online Gojek. Apliikasi Gojek dapat dengan dengan mudah di download pada google plyastore. Playstore adalah sebuah aplikasi yang berguna untuk mengunduh berbagai aplikasi. Playstore juga menyediakan fitur penilaian terhadap aplikasi yang tersedia di platform tersebut, dengan adanya fitur penilaian ini pengguna dapat memberikan penilaiannya dan juga berkomentar terhadap aplikasi yang digunakannya. Dengan adanya fitur komentar ini maka dapat di lakukannya sentimen analisis untuk mengetahui sentimen publik terhadap suatu aplikasi. Dalam penelitian ini langkah awal yang dilakukan adalah mengumpulkan data dan juga memberikan laber terhadap seluruh data, pada penelitian ini terdapat 3 label yaitu positif, netral, dan Negatif dengan jumlah 900 data. Selanjutnya melakukan proses analisa preprocessing dan juga dilanjutkan dengan proses pembobotan TF, kemudian baru dilakukannya proses klasifikasi menggunakan metode Learning Vector Quantization (LVQ). Hasil pengujiannya sendiri dilakukan dengan menggunakan metode Confussion Matrix. Berdasarkan dari proses dan hasil pengujian yang di lakukan di dapatkan akurasi terbaik pada perbandingan 90 : 10 sebesar 84,44% yang sebagian besar bernilai positif. Kata Kunci: transportasi online, Sentiment analysis , Playstore, Klasifikasi, Learning Vector Quantization Abstract— The development of technology and information is currently very fast, especially in Indonesia. One technology that is developing rapidly in Indonesia today is technology in the field of transportation, namely online transportation. The existence of online transportation is very helpful for all community activities. There are several transportation platforms in Indonesia, which is well-known online transportation called Gojek. The Gojek application can be easily downloaded on the Google Playstore. Playstore is an application that is useful for downloading various applications. Playstore also provides an assessment feature for applications available on the platform, with this assessment feature users can provide an assessment and also comment on the applications they use. With this comment feature, sentiment analysis can be done to find out public sentiment towards an application. In this study, initial step was taken to collect data and also provide a label for all data, in this study there were 3 labels, namely positive, neutral, and negative with a total of 900 data. Next, perform the preprocessing analysis process and also continue with the TF-IDF weighting process, then the classification process is carried out using the Learning Vector Quantization (LVQ) method. The results of the test itself are carried out using the Confusion Matrix method. Based on the process and the results of the tests , the best accuracy obtained is at ratio of 90 : 10 by 84,44%,which is most of it are positiveKeywords:Online Transportation,sentiment analysis , Playstore, Classification, Learning Vector Quantization

Bioinformatic Analysis in Designing Mega-primer in Overlap Extension PCR Cloning (OEPC) Technique Mardalisa, -; Suhandono, Sony; Yanti, Novi; Rozi, Fazrol; Nova, Fitri; Primawati, -
JOIV : International Journal on Informatics Visualization Vol 5, No 2 (2021)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.5.2.459

Bioinformatics has developed into an application tool for basic and applied research in the biomedical and biotechnology field. Polymerase Chain Reaction (PCR) is a common technique in the molecular area that has always involved bioinformatics science. PCR cloning techniques such as TA cloning and PCR-mediated cloning exhibit complex processes with low success rates. One easy, effective, and practical solution is to use a mega-primer with the Overlap Extension PCR Cloning (OEPC) technique. The success of PCR cloning using the mega-primer design in the OEPC technique is strongly influenced by the characteristics of the mega-primer used. Knowledge of mega-primer characteristics is one of the important factors in the success of PCR cloning. The design process for the mega-primer str promoter was characterized based on the principle of a genetic algorithm using the web-based bioinformatics tools such as ClustalW, NetPrimer, and BLAST. The success of the mega-primer construction in producing recombinant pSB1C3 vector has been confirmed by the sequencing method and the function of the reporting protein (AmilCP). DNA analysis shows a 100 % homologous sequence on the str promoter, whileÂ E. coli colonies successfully express the purplish-blue color. Mega-primer characters can save costs and time of the research by maintaining the primer parameters that provide optimal values and increase the success value of PCR cloning via bioinformatics software. Hence, implications on biological problems, especially using DNA and amino acid sequences, could solve rapidly.

Sistem Pakar Diagnosa Gangguan Stress Pasca Trauma Menggunakan Metode Certainty Factor Marliana Safitri; Fitri Insani; Novi Yanti; Lola Oktavia
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 4 (2023): Juni 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i4.6309

Mental health disorder or commonly called Mental Health Disorder is a disturbing psychological behavior and is followed by traumatic events such as shock shell, war fatigue, accidents, victims of sexual violence, and the covid pandemic. Cases of post traumatic stress disorder data from Indonesian Psychiatric Association amounted to 80% of 182 examiners experiencing symptoms of post-traumatic stress due to exposure to covid, 46% experienced severe symptoms, 33% moderate, 2% mild and others did not show symptom. This study aims to diagnose post traumatic stress disorder using the assurance factor method with 35 symptom data and 3 levels of post traumatic stress disorder as a knowledge base. The certainty factor is a circulation management method and a decision-making strategy using the confidence factor in the system. Based on the research results of the expert system for diagnosing post traumatic stress disorder, the test results obtained an accuracy of 80%. The results of the accuracy of this expert system indicate that the expert system can potentially be used to diagnose post traumatic stress disorder.

Implementasi Algoritma Random Forest pada Web-App Sebagai Instrumen Deteksi Dini Penyakit Diabetes Fauzan, Habibul; Haerani, Elin; Kurnia, Fitra; Yanti, Novi
Computer Science and Information Technology Vol 7 No 1 (2026): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v7i1.11261

Diabetes is a chronic metabolic disease and one of the leading causes of death worldwide, with the number of sufferers projected to reach 1.3 billion by 2050. Delayed diagnosis remains a primary challenge, as nearly half of those affected are unaware of their condition in the early stages, thereby increasing the risk of fatal complications. Data mining approaches using classification algorithms have been widely utilized for early screening. However, the development of medical record models is often hindered by imbalanced data, which causes models to be biased toward the majority class and reduces detection sensitivity for the minority class (patients with diabetes). Furthermore, there is a lack of research integrating these predictive models into responsive application interfaces for end-users. Consequently, this study implements Random Forest optimized with the SMOTE (Synthetic Minority Over-sampling Technique) into a web-based application to serve as a practical early detection tool. Random Forest was selected for its ability to handle complex data and reduce the risk of overfitting. The research stages include data preprocessing, balancing training data using SMOTE, model parameter adjustment through hyperparameter tuning with Grid Search, and the development of a client-server architecture using AstroJS and Flask. The evaluation results demonstrate that the use of SMOTE significantly improves the model's ability to identify the minority class. The model achieved a Recall of 75.0% and an overall accuracy of 95.8%, effectively minimizing False Negative errors. The developed application was verified through Black Box Testing and was declared successful as a responsive and accessible early detection tool for both healthcare professionals and the general public.

Analysis of the vo2max physical condition of tarung derajat athletes through yoyo test: Preparation for pre-PON XX Yanti, Novi; Gustian, Uray; Gani, Ruslan Abdul; Setiawan, Edi
Journal Sport Area Vol 7 No 1 (2022): April
Publisher : UIR Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/sportarea.2022.vol7(1).6717

During the current Covid-19 pandemic crisis, it found that Vo2max possessed by Tarung Derajat athletes has decreased significantly during training, therefore the purpose of this study was to analyze the level of Vo2max physical condition of Tarung Derajat athletes. This study used a quantitative approach through the survey method. The sample in this study were all Tarung Derajat martial arts athletes who took part in the XX Pre-PON championship, with a total of 24 athletes. This study used total sampling technique and obtained 24 athletes as samples. The instrument applied in this study was Yoyo Test and data were analyzed by using Microsoft Excel 2010. The results showed that most of the female athletes had a poor physical condition, while the physical condition of some male athletes was in the good category, some were in the very good category. Thus, it was still need an improvement, especially studies in the preparation of training programs, in improving physical condition, particularly for female athletes. The contribution of the results of this research will be able to increase understanding and information for trainers in order to achieve maximum performance.

Yo-Yo Intermitten Recovery Test: A study of football players’ VO2max physical condition Suryadi, Didi; Yanti, Novi; Tjahyanto, Teddy; Ramli; Rianto, Louis
Journal Sport Area Vol 8 No 2 (2023): August
Publisher : UIR Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/sportarea.2023.vol8(2).12392

The Yo-Yo Intermittent Recovery Test is frequently used to evaluate VO2max and is crucial for determining an athlete's physical condition. However, its effectiveness in accurately assessing the physical condition of football players remains limited. This study aims to analyze the level of the physical condition of football players' VO2max which will be used as evaluation material for designing training programs so that the pattern of coaching becomes focused and produces achievements. This research used a quantitative approach to the survey method. The subjects of this study were Pusaka FC football club athletes, the sampling technique used total sampling so that all athletes were a sample of 23 players. The test instrument used the Yo-Yo Intermitten Recovery Test level 2. Data analysis used descriptive percentages, with the assistanceof the Microsoft Excel 2019 software application. The results of the study show that the VO2max level value in soccer athletes is 13.04% of athletes in the poor category and 34.78% in the good category. Below average, 47.82% shows the average category, and there is only 4.35%, which shows the value of the good category. Based on the results of the VO2max ability test, the average classification of Club Pusaka FC players is still relatively low. However, it is necessary to know that the limitations of this study lie in the condition of the players' nutritional intake which has not been controlled and their age which must also be taken into consideration by researchers. Furthermore, it can find information on the effect of athlete nutrition on endurance ability.

Title

Found 21 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 21 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 21 Documents
Search