Garuda - Garba Rujukan Digital

PENERAPAN SISTEM PAKAR DIAGNOSA GANGGUAN MENSTRUASI PALM-COEIN DENGAN METODE DEMPSTER-SHAFER Dewi Amelia; Menur Wahyu Pangestika; Alda Cendekia Siregar
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 10 No. 1 (2026): JATI Vol. 10 No. 1
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v10i1.16661

Gangguan menstruasi merupakan permasalahan kesehatan reproduksi yang sering dialami perempuan, namun kerap tidak terdeteksi sejak dini sehingga menyebabkan keterlambatan penanganan. Penelitian ini bertujuan mengembangkan sistem pakar berbasis web untuk membantu diagnosis awal gangguan menstruasi berdasarkan klasifikasi PALM-COEIN. Sistem dirancang menggunakan metode Dempster-Shafer sebagai pendekatan evidensi untuk mengolah gejala dan menangani ketidakpastian informasi. Data gejala dan pengetahuan diperoleh melalui wawancara dengan pakar serta studi literatur, kemudian diimplementasikan dalam basis pengetahuan sistem. Hasil pengujian BlackBox menunjukkan seluruh fungsi berjalan sesuai kebutuhan, sementara pengujian akurasi terhadap 20 data uji menghasilkan tingkat kecocokan 90% dengan diagnosis pakar. Dengan demikian, sistem ini dapat menjadi alat bantu awal yang cepat, efisien, dan cukup akurat dalam mengenali gangguan menstruasi berdasarkan PALM-COEIN

IDENTIFIKASI IKAN KONSUMSI TIDAK SEGAR DAN SEGAR BERBASIS PENGOLAHAN CITRA DIGITAL BERDASARKAN FITUR WARNA MENGGUNAKAN METODE K-NEAREST NEIGHBORS (K-NN) Siti Putri Anggrayeni; Alda Cendekia Siregar; Barry Ceasar Octariadi
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 10 No. 2 (2026): JATI Vol. 10 No. 2
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v10i2.17438

Kesegaran ikan konsumsi merupakan indikator penting dalam menjamin mutu dan keamanan pangan, namun penilaian secara manual masih bersifat subjektif dan tidak konsisten. Permasalahan tersebut mendorong perlunya sistem identifikasi kesegaran ikan yang objektif dan otomatis. Penelitian ini bertujuan mengembangkan sistem identifikasi kesegaran ikan berbasis pengolahan citra digital menggunakan fitur warna dengan metode K-Nearest Neighbors (K-NN). Dataset yang digunakan berupa citra insang dari empat jenis ikan, yaitu lele, nila, mas, dan kembung, yang diklasifikasikan ke dalam dua kategori kesegaran. Metode penelitian meliputi tahap preprocessing citra berupa resize, Gaussian blur, serta konversi ruang warna RGB ke HSV, dilanjutkan dengan segmentasi insang berbasis warna dan ekstraksi fitur warna menggunakan histogram kanal Hue, Saturation, dan Value. Proses klasifikasi dilakukan menggunakan algoritma K-NN, sedangkan evaluasi kinerja sistem menggunakan metode 5-fold cross-validation. Hasil pengujian menunjukkan bahwa sistem mampu mengklasifikasikan kesegaran ikan dengan akurasi sebesar 98,21%, precision 98,26%, recall 98,21%, dan F1-score 98,18%. Hasil ini membuktikan bahwa kombinasi fitur warna HSV dan metodes K-NN efektif untuk mengidentifikasi kesegaran ikan secara akurat dan efisien.

IMPLEMENTASI METODE DEPTH FIRST SEARCH PADA SISTEM PAKAR KONSULTASI BANTUAN HUKUM CERAI GUGAT Rabbil Budiman; Rachmat Wahid Saleh Insani; Alda Cendekia Siregar
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 12 No. 1 (2026): Volume 12 Nomor 1 Tahun 2026
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/mtk.v12i1.5065

The problem of divorce, especially in Pontianak city, has increased significantly, but community access to legal information and services is often hampered by a lack of legal understanding, creating a gap in justice that can lead to other social problems. Therefore, this research focuses on the development of an expert system that utilizes the depth first search (DFS) method to provide consultation results on legal issues of contested divorce based on the compilation of Islamic law. The research methods include problem identification, data collection through interviews with legal experts followed by design using the waterfall method to ensure the system runs well. The test results show that the depth first search method is able to provide fast and accurate consultation results regarding the problems faced by wives who want to divorce based on the results of testing the accuracy of the system by comparing the results of system diagnosis and experts obtained 80% results so it is concluded that the accuracy of the system made is considered successful.

Implementasi Fuzzy Mamdani untuk Rekomendasi Total Kalori Harian Bagi Penderita Diabetes Tipe 2 : Implementasi Fuzzy Mamdani untuk Rekomendasi Total Kalori Harian Bagi Penderita Diabetes Tipe 2 Widiasari, Putu Puja Diva; Siregar, Alda Cendekia; Octariadi, Barry Ceasar
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.v7i1.11027

Type 2 Diabetes Mellitus is a metabolic disease that requires precise regulation of daily calorie intake to maintain stable blood sugar levels. Determining calorie requirements is not simple because it must take into account factors such as age, gender, body mass index (BMI), and physical activity level. This study aims to develop a Mamdani fuzzy logic-based expert system to provide recommendations for daily calorie requirements for people with type 2 diabetes. The system process is carried out through the stages of fuzzification, inference, aggregation, and defuzzification using the centroid method. Testing was conducted using 20 type 2 diabetes patient data with input variables of age, height, weight, gender, and physical activity. The testing methods used were accuracy and black-box. Accuracy testing was performed by comparing the system's results with manual calculations based on medical standards, while black-box testing ensured that the system functioned as designed. The results showed that the system had an accuracy rate of 80%, making it sufficiently valid and usable as a tool for recommending daily calorie intake to support diet management for type 2 diabetes patients.

Classification Of Stunting In Toddlers Using The Random Forest Method Sutarti Dwi Yanti; Menur Wahyu Pangestika; Alda Cendekia Siregar
International Journal of Health Engineering and Technology Vol. 5 No. 1 (2026): IJHET MAY 2026
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55227/ijhet.v5i1.786

Monitoring and data collection related to stunting at several community health centers (Puskesmas) in Ketapang Regency play a crucial role in assessing optimal growth and development of fetuses and newborns. One of the recurring issues in Ketapang Regency is the inaccuracy and inconsistency in monthly stunting data collection. This study aims to design a stunting classification model for children under five using the random forest method and to evaluate its classification accuracy. The research follows several stages problem identification, literature review, data collection, data processing, testing, and drawing conclusions. The performance of the random forest method is assessed to determine the impact of each stage on the model’s classification ability. Evaluation metrics are derived from the confusion matrix. The confusion matrix results show a recall of 97%, precision of 96%, F1-score of 96%, and an accuracy of 91%, indicating that the random forest method performs excellently in classifying nutritional status.

BIMBINGAN TEKNIS STRATEGI MENGANALISA USAHA EKONOMI DESA DALAM RANGKA PENDAMPINGAN BUMDES SEKALIMANTAN BARAT Istikoma Istikoma; Alda Cendekia Siregar
JMM (Jurnal Masyarakat Mandiri) Vol 8, No 2 (2024): April
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v8i2.21518

Abstrak : Dinas Pemberdayaan Masyarakat dan Desa (DPMD) mempunyai tugas untuk memantau dan memonitor perkembangan ekonomi Desa khususnya Badan Usaha Milik Desa (BUMDes). Terdapat 549 BUMDes yang aktif di seluruh Kalimantan Barat, namun setelah tahun 2019 perkembangan BUMDes semakin lama semakin menurun bahkan terdapat BUMDes yang mangkrak atau mati suri. Tujuan Bimtek ini diharapkan kepada seluruh pengurus BUMDes di Kalimantan Barat memperoleh pengetahuan yang memadai untuk memahami teknik dan strategi dalam bidang pengembangan sumber daya manusia, tatakelola ekonomi desa, pemetaan bentang dan studi kelayakan usaha, membangun sistem data dan informasi desa sehingga bermanfaat bagi para pengelola BUMDes untuk lebih mudah dalam memanfaatkan sumberdaya desa menjadi peluang penggerak ekonomi masyarakat Desa pada setiap BUMDes. Terdapat 35 peserta dari 35 perwakilan setiap BUMDes yang dihadirkan oleh pihak mitra dari dinas DPMD Kalimantan Barat. Materi yang disampaikan dibuat dengan menarik dan mudah dipahami yang meliputi materi pemetaan bentang dan analisis kelayakan usaha. Evaluasi dilakukan dengan melihat peningkatan jawaban benar dan berkurangnya jawaban salah saat pretest dan posttest. Persentase jawaban benar lebih besar daripada jawaban salah, mengindikasikan terjadinya peningkatan pemahaman peserta dalam bidang soft skill dan hard skill mengenai pemetaan bentang dan analisis kelayakan usaha, dimana peningkatan pengetahuan terlihat meningkat dari 38% saat pretest menjadi 77% saat posttes, sedangkan jawaban salah berbanding terbalik dengan jawaban benar yaitu 62% saat pretest dan 23% saat posttest sehingga dapat disimpulkan kegiatan ini sangat bermanfaat dan ditargetkan akan mampu meningkatkan daya saing BUMDes guna mengembangkan ekonomi Desa di masa akan dating.Abstract: The Community and Village Empowerment Service (DPMD) has the task of monitoring and monitoring Village economic development, especially Village-Owned Enterprises (BUMDes). There are 549 active BUMDes throughout West Kalimantan, but after 2019 the development of BUMDes has decreased over time and there are even BUMDes that have stalled or are in suspended animation. The aim of this Bimtek is that it is hoped that all BUMDes administrators in West Kalimantan will gain sufficient knowledge to understand techniques and strategies in the fields of human resource development, village economic management, landscape mapping and business feasibility studies, building village data and information systems so that they are useful for BUMDes managers. to make it easier to utilize village resources to become opportunities to drive the village community's economy in each BUMDes. There were 35 participants from 35 representatives for each BUMDes presented by partners from the West Kalimantan DPMD service. The material presented is made interesting and easy to understand, including material on landscape mapping and business feasibility analysis. Evaluation is carried out by looking at the increase in correct answers and the decrease in incorrect answers during the pretest and posttest. The percentage of correct answers is greater than wrong answers, indicating an increase in participants' understanding in the areas of soft skills and hard skills regarding landscape mapping and business feasibility analysis, where the increase in knowledge appears to have increased from 38% during the pretest to 77% during the posttest, while the wrong answers are inversely proportional. With correct answers, namely 62% in the pretest and 23% in the posttest, so it can be concluded that this activity is very useful and is targeted to be able to increase the competitiveness of BUMDes in order to develop the village economy in the future.

Diagnosa Penyakit Jagung Menggunakan Dempster Shafer Tanaman Pangan Dan Hortikultural Kalimantan Barat Putri Nabila Aprilia; Menur Wahyu Pangestika; Alda Cendekia Siregar
Progresif: Jurnal Ilmiah Komputer Vol 22, No 3 (2026): Juli
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i3.3833

Disease attacks on corn plants can reduce productivity, requiring a system capable of rapid and accurate diagnosis. This study aims to develop a web-based expert system for diagnosing corn plant diseases using the Dempster-Shafer method. The system was built using a knowledge base obtained from experts at the Food Crops and Horticulture Service of West Kalimantan Province. The variables processed included symptom data, disease type, belief value, and control solutions. The diagnosis process was carried out by combining the belief value for each symptom using the Dempster-Shafer combination rule to generate a confidence level for the disease. Testing was conducted by comparing the system's diagnosis results with expert diagnoses on 20 test data sets. The test results showed the system achieved 90% accuracy, indicating that the Dempster-Shafer method is effective in handling symptom uncertainty and is capable of producing accurate corn plant disease diagnoses.Keyword: Corn Plants; Expert System; Dempster Shafer AbstrakSerangan penyakit pada tanaman jagung dapat menurunkan produktivitas sehingga diperlukan sistem yang mampu membantu diagnosis secara cepat dan akurat. Penelitian ini bertujuan mengembangkan sistem pakar berbasis web untuk mendiagnosis penyakit tanaman jagung menggunakan metode Dempster-Shafer. Sistem dibangun menggunakan basis pengetahuan yang diperoleh dari pakar di Dinas Tanaman Pangan dan Hortikultura Provinsi Kalimantan Barat. Variabel yang diproses meliputi data gejala, jenis penyakit, nilai belief, dan solusi pengendalian. Proses diagnosis dilakukan dengan menggabungkan nilai belief setiap gejala menggunakan aturan kombinasi Dempster-Shafer untuk menghasilkan tingkat keyakinan terhadap penyakit. Pengujian dilakukan dengan membandingkan hasil diagnosis sistem terhadap diagnosis pakar pada 20 data uji. Hasil pengujian menunjukkan sistem memperoleh akurasi sebesar 90%, sehingga metode Dempster-Shafer efektif dalam menangani ketidakpastian gejala dan mampu menghasilkan diagnosis penyakit tanaman jagung secara akurat.Kata kunci: Desmpster Shafer; Diagnosis; Penyakit Jagung; Sistem Pakar

Diagnosa Penyakit Jagung Menggunakan Dempster Shafer Tanaman Pangan Dan Hortikultural Kalimantan Barat Putri Nabila Aprilia; Menur Wahyu Pangestika; Alda Cendekia Siregar
Progresif: Jurnal Ilmiah Komputer Vol. 22 No. 3 (2026): Juli
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i3.3833

Disease attacks on corn plants can reduce productivity, requiring a system capable of rapid and accurate diagnosis. This study aims to develop a web-based expert system for diagnosing corn plant diseases using the Dempster-Shafer method. The system was built using a knowledge base obtained from experts at the Food Crops and Horticulture Service of West Kalimantan Province. The variables processed included symptom data, disease type, belief value, and control solutions. The diagnosis process was carried out by combining the belief value for each symptom using the Dempster-Shafer combination rule to generate a confidence level for the disease. Testing was conducted by comparing the system's diagnosis results with expert diagnoses on 20 test data sets. The test results showed the system achieved 90% accuracy, indicating that the Dempster-Shafer method is effective in handling symptom uncertainty and is capable of producing accurate corn plant disease diagnoses.Keyword: Corn Plants; Expert System; Dempster Shafer AbstrakSerangan penyakit pada tanaman jagung dapat menurunkan produktivitas sehingga diperlukan sistem yang mampu membantu diagnosis secara cepat dan akurat. Penelitian ini bertujuan mengembangkan sistem pakar berbasis web untuk mendiagnosis penyakit tanaman jagung menggunakan metode Dempster-Shafer. Sistem dibangun menggunakan basis pengetahuan yang diperoleh dari pakar di Dinas Tanaman Pangan dan Hortikultura Provinsi Kalimantan Barat. Variabel yang diproses meliputi data gejala, jenis penyakit, nilai belief, dan solusi pengendalian. Proses diagnosis dilakukan dengan menggabungkan nilai belief setiap gejala menggunakan aturan kombinasi Dempster-Shafer untuk menghasilkan tingkat keyakinan terhadap penyakit. Pengujian dilakukan dengan membandingkan hasil diagnosis sistem terhadap diagnosis pakar pada 20 data uji. Hasil pengujian menunjukkan sistem memperoleh akurasi sebesar 90%, sehingga metode Dempster-Shafer efektif dalam menangani ketidakpastian gejala dan mampu menghasilkan diagnosis penyakit tanaman jagung secara akurat.Kata kunci: Desmpster Shafer; Diagnosis; Penyakit Jagung; Sistem Pakar

Classification of Hypertension Disease Using the Fuzzy K-Nearest Neighbors Method Mustafa Mustafa; Alda Cendekia Siregar; Syarifah Putri Agustini Alkadri
International Journal of Health and Information System Vol. 4 No. 2 (2026): September
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/ijhis.v4i2.101

Hypertension is one of the most prevalent non-communicable diseases and a major public health problem because it increases the risk of cardiovascular disease and other serious complications if not detected early. Therefore, a system capable of classifying blood pressure accurately and consistently may support preliminary assessment. This study aims to develop and evaluate a hypertension classification system based on the Fuzzy K-Nearest Neighbor (FKNN) method using systolic and diastolic blood pressure parameters. The system was developed using 814 training data and 202 testing data, classified into three categories: Hypertension, Prehypertension, and Normal. The classification process consists of data normalization, Euclidean distance calculation between testing and training data, determination of the K nearest neighbors, calculation of fuzzy membership degrees for each class, and assignment of the class with the highest membership value. The system was evaluated using K values ranging from 3 to 30 with a fuzziness parameter (m) of 2 to analyze the effect of the number of neighbors on classification performance and identify the optimal K value. System performance was assessed using accuracy, precision, recall, and F1-score metrics. The experimental results showed that the FKNN method achieved high classification performance, with the highest accuracy of 98.02% at K = 3, followed by 97.03% at K = 5 and 96.53% at both K = 9 and K = 15. The precision, recall, and F1-score values across the three classes also indicated good classification performance. These findings suggest that the FKNN method has potential for classifying blood pressure based on systolic and diastolic measurements, with K = 3 yielding the highest accuracy among the tested parameter settings. However, the evaluation was limited to the available dataset and did not include external validation, assessment by clinical professionals, or prospective evaluation within clinical workflows. Therefore, the developed system should be regarded as a preliminary classification prototype, and its clinical applicability and operational suitability as a decision-support tool require further investigation.

Performance Comparison of CNN and ResNet50 for Skin Cancer Classification Using U-Net Segmented Images Aris Wahyu Murdiyanto; Dian Hafidh Zulfikar; Bagus Satrio Waluyo Poetro; Alda Cendekia Siregar
Indonesian Journal of Data and Science Vol. 5 No. 3 (2024): Indonesian Journal of Data and Science
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v5i3.200

Skin cancer is a significant global health issue, with melanoma, basal cell carcinoma, and actinic keratosis being the most common types. Early and accurate detection is critical to improve survival rates and treatment outcomes. This study evaluates the performance of Convolutional Neural Networks (CNN) and ResNet50 in classifying segmented images of skin lesions. The dataset, sourced from Kaggle, was pre-processed using U-Net for lesion segmentation to enhance the quality of input data. Both models were trained and evaluated using accuracy, precision, recall, and F1-score metrics. The CNN model demonstrated a balanced performance across classes, with a weighted F1-score of 47%, but suffered from overfitting, as indicated by the divergence between training and validation losses. ResNet50 achieved better recall for basal cell carcinoma (100%) but failed to classify actinic keratosis and melanoma, resulting in a macro F1-score of 23%. The findings reveal that U-Net segmentation improved classification focus but was insufficient to address dataset imbalance and model-specific limitations. This study highlights the challenges of skin cancer classification using deep learning and underscores the importance of addressing data imbalance and overfitting. Future research should explore advanced techniques, such as ensemble methods, data augmentation, and transfer learning, to improve the generalization and clinical applicability of these models. The proposed framework serves as a foundation for further investigation into automated skin cancer detection systems.

Title

Found 50 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 50 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 50 Documents
Search