Claim Missing Document
Check
Articles

Implementation of Naïve Bayes for Classification of Learning Types Lisnawita, Lisnawita; Guntoro, Guntoro; Musfawati, Musfawati
Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Vol. 13 No. 1 (2022): Digital Zone: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Publisher: Fakultas Ilmu Komputer, Institution: Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/digitalzone.v13i1.9825

Abstract

Learning is a process that is carried out by each individual from not knowing to knowing, or from bad behavior to being good, so that it has a good change for the individual, Each individual has a learning type in receiving the material presented by the teacher, but not all individuals understand what type of learning they need, The purpose of the research is to determine the type of learning of the students of the Faculty of Computer Science. The method used is nave Bayes for the accuracy of its calculations. The results of this study are the classification of visual learning types as many as 50 people, for audio as many as 24 people, while kinesthetic as many as 25 people, for the Informatics Engineering Study Program as many as 61, consists of 37 visual learning types, Auditory 14 people, Kinesthetic 10 people, While the Information Systems Study Program is 37 people, where is Visual 14 people, Auditory 9 people and Kinesthetic 14 people. With this classification, it can help lecturers apply learning methods that are suitable for their students. The best Naïve Bayes accuracy rate is 88.89%
Salicylic Acid Accumulation in Tomato Root Induced by Endopytic Bacteria and Exogenous Salicylic Acid Response to Ralstonia syzygii subsp. indonesiensis Infection Nababan, Triwanto; Lisnawita, Lisnawita; Safni, Irda
Contributions of Central Research Institute for Agriculture Vol. 18 No. 4 (2024): October: Agriculture and related sciences
Publisher : Central Research Institute For Agriculture

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Ralstonia syzygii subsp. indonesiensis causes bacterial wilt disease is a soil-borne pathogen that causes serious damage and major losses in tomato production. To overcome this, the use of Arthrobacter sp. and Bacillus thuringiensis as biological elicitors and salicylic acid as a chemical elicitor were teste their capacity to induce tomato plants to become resistant. Experiments were carried out on the susceptible tomato cultivar "Servo F1" in sterilized soil to test the elicitor's effectiveness in triggering plant defense mechanisms in response to salicylic acid accumulation in afflicted roots. Arthrobacter sp. and salicylic acid treatments significantly reduced the disease severity due to bacterial wilt compared to control treatment within three weeks after inoculation. Tomato with once week application intensity was also better than every two weeks application intensity. The AUDPC value showed by Arthrobacter sp. was 1449.7 with an application intensity every two weeks and 148 with an application intensity once a week compared to control with an AUDPC value of 4962.9. Furthermore, endophytic bacteria and salicylic acid can induce salicylic acid accumulation in pathogen-inoculated tomato roots. The results show that the elicitor is either biological or chemicals play an important role as inducers of plant defenses, thereby reducing bacterial wilt disease.
Implementasi Algoritma Naïve Bayes Classifier Untuk Klasifikasi Penerima Beasiswa BUMN Sekota Dumai Nugraha, Alif; Al-ghifari, Faza; Panigoran, Abdullah; Desmawan, Wahyu; Lisnawita, Lisnawita
Jurnal Karya Ilmiah Multidisiplin (JURKIM) Vol. 4 No. 2 (2024): Jurnal Karya Ilmiah Multidisiplin (Jurkim)
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/jurkim.v4i2.20944

Abstract

Secara konsisten otoritas publik menawarkan berbagai jenis hibah/bantuan kepada siswanya, salah satu bantuan/hibah dari bumn tidak terkecuali dari unversitas mana saja asal tempat tinggalnya. Secara konsisten jumlah calon penerima hibah ini terus bertambah, namun jumlah yang didapat setiap tahun tetap stabil. Selanjutnya, penting untuk membangun kerangka untuk melengkapi penambangan informasi dari tumpukan informasi ini yang akan dimanfaatkan untuk tujuan tertentu, salah satunya untuk menyelidiki kewajaran penerima hibah agar sempurna. Bayes Classifier merupakan metodologi yang mengacu pada hipotesis Bayes yang menggabungkan informasi masa lalu dengan informasi baru. Jadi perhitungan karakterisasi bersifat mendasar namun memiliki ketelitian yang tinggi. Oleh karena itu, pemeriksaan ini akan menunjukkan kapasitas Bayes Classifire dalam mengelompokkan informasi calon penerima hibah/bantuan yang menjelaskan kemungkinan pemberian hibah/bantuan bumn. Data pelamar beasiswa telah diolah terlebih dahulu agar “bersih” dan siap untuk diproses lebih lanjut. Setelah pra- pemrosesan ini, Naive Bayes Classifier digunakan untuk mengklasifikasikan data, sehingga menghasilkan model probabilitas untuk mengklasifikasikan pelamar beasiswa berikutnya. Dari hasil pengujian ketepatan model kerangka kerja yang dibuat menghasilkan nilai akurasi tertinggi sebesar 75,00%
Hyperparameter Optimization of the Perceptron Algorithm for Determining the Feasibility of Research Proposals and Community Service Lisnawita, Lisnawita; Guntoro, Guntoro; Costaner, Loneli
Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Vol. 15 No. 2 (2024): Digital Zone: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Publisher: Fakultas Ilmu Komputer, Institution: Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/digitalzone.v15i2.17812

Abstract

Higher education in Indonesia includes diploma, bachelor, master, specialist, and doctoral programmes organised by universities. The Institute for Research and Community Service (LPPM) is in charge of assessing lecturers' proposals. This research aims to optimise the Perceptron algorithm to assess proposal eligibility using Turnitin plagiarism scores and reviewer scores. The optimisation results show that Perceptron accuracy reaches 99.44% to 99.63% at various training data ratios. GridSearchCV achieved 100% accuracy, while RandomisedSearchCV recorded accuracy between 98.89% to 99.63%. GridSearchCV also had the lowest MSE , despite higher Loss values, indicating a sacrifice in generalisation ability. Perceptron Default and RandomisedSearchCV had higher MSE and Loss, but remained low. GridSearchCV's AUC reached 100%, while Perceptron Default and RandomisedSearchCV showed very high AUC, ranging from 99.25% to 99.98%. Overall, the Perceptron algorithm is effective in assessing proposal eligibility with high accuracy.
Analysis of The Relationship of Wind Speed and Rainfall on the Development of Coffee Leaf Rust (Hemileia Vastatrix B. & Br.) on Sipirok Arabica Coffee Plants in South Tapanuli District, Indonesia Guntoro, Guntoro; Lisnawita, Lisnawita; Tantawi, A. Rafiqi; Safni, Irda
GMPI Conference Series Vol 3 (2024): The 10th Asian Academic Society International Conference (AASIC)
Publisher : Gemilang Maju Publikasi Ilmiah (GMPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53889/gmpics.v3.424

Abstract

Coffee is one of the agricultural commodities that is a priority for development by the Indonesian government because it has high economic value. Sipirok coffee is a mainstay Arabica coffee from the Highlands, South Tapanuli dictrict, Sumatera Utara - Indonesia. During its cultivation in the field, many problems were discovered, including coffee leaf rust disease caused by the fungus Hemileia vastatrix. This research aims to analysis the relationship between wind speed and rainfall on the development of coffee leaf rust disease (H.vastatrix) on Arabica coffee plants in South Tapanuli Regency, North Sumatere Province. The research was carried out at the community coffee planting center in the Sipirok Highlands, in Sampean Village, Sipirok District, South Tapanuli Regency with coordinates 1.64'N99.26'E with an altitude of 900 meters above sea level. The research was carried out by observing weather elements with a portable weather measuring device, capturing H. vastatrix fungal spores with a modified Kyosawa type spore capture device, and observing the severity of H. vastatrix coffee leaf rust disease. The collected data was analysed using correlation and regression analysis with SPSS Version 25. The results showed that wind speed and rainfall had a very positive effect on conidium capture and disease severity. Accordingly, there is a relationship between the elements of wind speed and rainfall on the development of coffee leaf rust disease (Hemileia broadatrix B. Br.).
Induksi Ketahanan Tanaman Tomat terhadap Ralstonia syzygii subsp. indonesiensis Menggunakan Bakteri Endofit dan Asam Salisilat : Induction of Resistance in Tomato Plants Against Ralstonia syzygii subsp. indonesiensis Using Endophytic Bacteria and Salicylic Acid Nababan, Triwanto; Lisnawita, Lisnawita; Safni, Irda
Jurnal Fitopatologi Indonesia Vol. 20 No. 6 (2024): November 2024 - IN PROGRESS
Publisher : The Indonesian Phytopathological Society (Perhimpunan Fitopatologi Indonesia)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14692/jfi.20.6.263-275

Abstract

Patogen Ralstonia syzygii subsp. indonesiensis adalah penyebab penyakit layu bakteri pada tanaman tomat. Patogen ini sulit dikendalikan karena kemampuannya bertahan dalam sisa bahan inang, tanah, dan dapat menyebar dengan mudah melalui aliran air, serta menginfeksi jaringan tanaman secara sistemik. Belum ada pestisida kimia yang efektif untuk mengendalikan patogen layu bakteri. Oleh karena itu, alternatif pengendalian yang dipilih ialah dengan menggunakan bakteri endofit dan asam salisilat. Dua jenis bakteri endofit, yaitu Arthrobacter sp. dan Bacillus thuringiensis, serta asam salisilat digunakan dalam penelitian secara tunggal ataupun kombinasi untuk mengevaluasi potensinya dalam menginduksi ketahanan tanaman tomat dalam menekan penyakit layu bakteri R. syzygii subsp. indonesiensis. Penelitian dilakukan dengan rancangan acak lengkap non faktorial dengan 14 perlakuan terdiri atas perlakuan tunggal dan kombinasi. Setiap perlakuan terdiri atas tiga unit tanaman dan tiga ulangan. Hasil penelitian menunjukkan bahwa kombinasi Arthrobacter sp. dan asam salisilat yang diaplikasikan satu kali seminggu (ABAS1) merupakan perlakuan yang paling efektif untuk menginduksi ketahanan tomat. Hal ini tampak pada periode inkubasi yang paling lama, rendahnya insidensi dan keparahan penyakit, meningkatnya aktivitas enzim peroksidase, polifenoloksidase, dan jaringan xilem tidak dominan terkolonisasi patogen pada pengamatan histopatologi.
Naïve Bayes Alpha Parameter Optimization with Ant Colony for Clinical Text Classification Taslim, Taslim; Fajrizal, Fajrizal; Handayani, Susi; Toresa, Dafwen; Lisnawita, Lisnawita
Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Vol. 16 No. 1 (2025): Digital Zone: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Publisher: Fakultas Ilmu Komputer, Institution: Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/digitalzone.v16i1.24118

Abstract

This study addresses the challenges of text classification in domain-specific Natural Language Processing (NLP) within the medical field, which differs significantly from general NLP due to the presence of complex medical jargon and informal language in clinical documents. The primary objective of this research is to develop and evaluate a cancer-related text classification model by integrating the Naïve Bayes algorithm with Laplacian smoothing and optimizing its alpha parameter using Ant Colony Optimization (ACO). Specifically, the study aims to determine whether ACO can effectively identify the optimal alpha value that enhances the classification performance of the Naïve Bayes model. Experimental results demonstrate that with an alpha value of 0.27, the proposed model achieves an accuracy of 81.05%. This indicates that the combination of ACO and Naïve Bayes significantly improves classification efficiency and accuracy. The findings contribute to more accurate interpretation of clinical cancer-related texts, supporting better-informed decision-making in medical contexts
Optimization of LBP Texture Feature Extraction using Correlation And Mi For SVM-Based Diabetic Retinopathy Classification costaner, loneli; lisnawita, lisnawita; Guntoro, Guntoro
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/4vrj4930

Abstract

Diabetic retinopathy (DR) is a leading cause of blindness, making early detection based on retinal fundus images crucial. This study proposes a DR classification method with a primary contribution in feature optimization: integrating the LBP Contrast feature with a Local Binary Pattern (LBP) histogram and performing hybrid feature selection based on Mutual Information (MI) to assess relevance and correlation analysis to reduce redundancy. This method was tested using 168 images from the public Messidor dataset, with 100 images for training and 68 for testing to evaluate performance. Classification was performed using a Support Vector Machine (SVM) with a linear kernel, where model performance was evaluated before and after optimization to measure the significance of the improvement. The results showed a significant improvement after optimization, with accuracy increasing from 88% to 94%, recall increasing from 88% to 100%, and F1-score increasing from 0.92 to 0.96. Although precision decreased slightly from 96% to 93%, increasing recall to 100% is considered more crucial in a medical context as it minimizes the risk of missed positive cases. These findings confirm that the proposed feature optimization approach can significantly improve the accuracy and reliability of the DR detection system, offering potential clinical relevance for supporting early intervention.
Peningkatan Kemampuan Tentang Penyakit Kelapa Sawit Akibat Serangn Patogen Ganoderma boninense Melalui Kegiatan Penyuluhan Lapangan Lisnawita, Lisnawita; Saragih, Wismaroh Sanniwati; Tantawi, Ahmad Rafiqi; Hanum, Hamidah; Sitepu, Suzanna Fitriani; Safni, Irda; Lubis, Khairunnisa
Journal Of Human And Education (JAHE) Vol. 4 No. 1 (2024): Journal Of Human And Education (JAHE)
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jh.v4i1.680

Abstract

Penyakit yang sangat penting di perkebunan kelapa sawit adalah busuk pangkal batang yang disebabkan Ganoderma boninense dan merugikan secara ekonomi hampir 43%. Kejadian penyakit akibat G. boninense di perkebunan rakyat telah berdampak terhadap penurunan produksi dan tingkat pendapatan petani juga menurun. Pelaksanaan pengabdian kepada masyarakat dilakukan di desa Tebing Syahbandar Kabupaten Serdang Bedagai Provinsi Sumatera Utara. Tujuan pengabdian untuk meningkatkan pengetahuan kemampuan masyarakat tentang penyakit kelapa sawit yang disebabkan G. boninense. Target yang diharapkan adalah masyarakat mampu mengidentifikasi serangan sejak dini sehingga metode pengendalian dengan cara membumbun atau menggunakan bibit unggultahan G. boninense. Metode pengabdian kepada masyarakat dilakukan melalui ceramah, diskusi, dan kunjungan langsung di perkebunan rakyat. Pelaksanaan pengabdian melalui koordinasi dengan Dinas Pertanian Kabupaten Serdang Bedagai, penyuluh lapangan, serta masyarakat pemilik perkebunan kelapa sawit. Pelaksanaan ceramah dan diskusi bersama tim dosen dan mahasiswa dengan sasaran petani kebun kelapa sawit rakyat.
Content Creator Training for MSMEs in Air Terbit Village, Kampar Regency: Pelatihan Kreator Konten Untuk UMKM di Desa Air Terbit, Kabupaten Kampar Guntoro, Guntoro; Lisnawita, Lisnawita; Monika, Winda Monika; Costaner, Loneli Costaner
CONSEN: Indonesian Journal of Community Services and Engagement Vol. 4 No. 2 (2024): Consen: Indonesian Journal of Community Services and Engagement
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/consen.v4i2.1567

Abstract

Pelatihan kreator konten untuk UMKM di Desa Air Terbit, Kabupaten Kampar, bertujuan untuk meningkatkan kemandirian ekonomi dan finansial desa melalui pemanfaatan media sosial. Dengan fokus pada urgensi content creator, personal branding, dan optimalisasi content creator dalam era industri 5.0, kegiatan ini mencakup ceramah, diskusi, dan praktik langsung pembuatan konten digital menggunakan aplikasi Canva. Hasil pre-test menunjukkan bahwa 100% peserta termotivasi menjadi content creator untuk mendapatkan penghasilan, 50% aktif membuat konten selama 6 bulan hingga 1 tahun, dan 35% merasa sangat percaya diri dalam kemampuan mereka. Post-test menunjukkan bahwa 85% peserta merasa kualitas konten mereka meningkat, 60% merasa lebih percaya diri, dan 100% berencana menggunakan strategi yang diajarkan dalam pelatihan. Hasil menunjukkan peningkatan signifikan dalam kualitas dan kepercayaan diri peserta dalam membuat konten setelah mengikuti pelatihan. Peserta juga menyatakan niat untuk menerapkan strategi yang diajarkan dalam aktivitas mereka sebagai kreator konten.