Claim Missing Document
Check
Articles

Prediksi Perhitungan Jumlah Produksi Tahu Mahanda dengan Teknik Fuzzy Sugeno Hajar, Siti; Badawi, Masrof; Setiawan, Yudika Dwi; Siregar, Muhammad Noor Hasan; Windarto, Agus Perdana
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 1 (2020): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v4i1.200

Abstract

"Mahanda" tofu industry is a home industry managed by family members located in the city of Pematangsiantar. The purpose of this research is to analyze the amount of "Mahanda" tofu production using fuzzy logic. Sources of data obtained by conducting interviews and direct observation. Fuzzy logic used is the Sugeno method. The variables used are demand variables, inventory variables, and production variables. Each variable has 3 fuzzy sets, the request variable consists of {down, medium, up}. Inventory variables consist of {few, medium, many}. And the production variable consists of {reduced, tolerable and increased}. The test data results there is a difference of error of 0.19% so that this method can be applied to the "Mahanda" tofu factory in the estimated tofu production for the next period.
Prediksi Perhitungan Jumlah Produksi Tahu Mahanda dengan Teknik Fuzzy Sugeno Hajar, Siti; Badawi, Masrof; Setiawan, Yudika Dwi; Siregar, Muhammad Noor Hasan; Windarto, Agus Perdana
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 1 (2020): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (619.631 KB) | DOI: 10.30645/j-sakti.v4i1.200

Abstract

"Mahanda" tofu industry is a home industry managed by family members located in the city of Pematangsiantar. The purpose of this research is to analyze the amount of "Mahanda" tofu production using fuzzy logic. Sources of data obtained by conducting interviews and direct observation. Fuzzy logic used is the Sugeno method. The variables used are demand variables, inventory variables, and production variables. Each variable has 3 fuzzy sets, the request variable consists of {down, medium, up}. Inventory variables consist of {few, medium, many}. And the production variable consists of {reduced, tolerable and increased}. The test data results there is a difference of error of 0.19% so that this method can be applied to the "Mahanda" tofu factory in the estimated tofu production for the next period.
Optimization of the Activation Function for Predicting Inflation Levels to Increase Accuracy Values Windarto, Agus Perdana; Rahadjeng, Indra Riyana; Siregar, Muhammad Noor Hasan; Yuhandri, Muhammad Habib
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7776

Abstract

This study aims to optimize the backpropagation algorithm by evaluating various activation functions to improve the accuracy of inflation rate predictions. Utilizing historical inflation data, neural network models were constructed and trained with Sigmoid, ReLU, and TanH activation functions. Evaluation using the Mean Squared Error (MSE) metric revealed that the ReLU function provided the most significant performance improvement. The findings indicate that the choice of activation function and neural network architecture significantly influences the model's ability to predict inflation rates. In the 5-7-1 architecture, the Logsig and ReLU activation functions demonstrated the best performance, with Logsig achieving the lowest MSE (0.00923089) and the highest accuracy (75%) on the test data. These results underscore the importance of selecting appropriate activation functions to enhance prediction accuracy, with ReLU outperforming the other functions in the context of the dataset used. This research concludes that optimizing activation functions in backpropagation is a crucial step in developing more accurate inflation prediction models, contributing significantly to neural network literature and practical economic applications.
Pelatihan Manajemen Kelas Untuk Meningkatkan Efektivitas Pembelajaran Di MAS YPKS Padangsidimpuan Suleman, Abdul Rahman; Harputra, Yuswin; Lubis, Fitri Romaito; Ramadhani, Yulia Rizki; Siregar, Muhammad Noor Hasan
KALANDRA Jurnal Pengabdian Kepada Masyarakat Vol 3 No 5 (2024): September
Publisher : Yayasan Kajian Riset Dan Pengembangan Radisi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55266/jurnalkalandra.v3i5.488

Abstract

Pengelolaan kelas merupakan keterampilan fundamental yang harus dikuasai guru untuk menciptakan pembelajaran yang efektif. Program pengabdian masyarakat ini bertujuan untuk meningkatkan kompetensi guru MAS YPKS Padangsidimpuan dalam mengelola kelas melalui pelatihan dan pendampingan intensif. Program dilaksanakan dalam empat tahap: analisis kebutuhan, pelatihan intensif, pendampingan implementasi, serta monitoring dan evaluasi. Metode yang digunakan meliputi workshop interaktif, simulasi, praktik, dan pendampingan berkelanjutan. Hasil program menunjukkan peningkatan signifikan dalam empat aspek utama: pengetahuan manajemen kelas meningkat hingga 82% (target 75%), keterampilan pengelolaan kelas mencapai 73% (target 70%), keterlibatan siswa dalam pembelajaran meningkat hingga 85% (target 80%), dan penurunan masalah perilaku di kelas sebesar 65% (target 50%). Program ini berhasil memberikan dampak positif dalam meningkatkan kualitas pembelajaran di MAS YPKS Padangsidimpuan dan dapat dijadikan model untuk pengembangan program serupa di sekolah lain.
Optimasi Fungsi Aktivasi pada Artificial Neural Network untuk Prediksi Gagal Jantung Secara Akurat Raharjo, Mokhamad Ramdhani; Indra Riyana Rahadjeng; Siregar, Muhammad Noor Hasan; Alkhairi, Putrama
Explorer Vol 5 No 1 (2025): January 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/explorer.v5i1.1840

Abstract

Heart failure is one of the major health problems that can be fatal if not diagnosed properly and quickly. Therefore, early prediction using artificial intelligence models, especially Artificial Neural Network (ANN), is needed to improve the accuracy in detecting heart failure. This study aims to optimize the activation function in ANN to predict heart failure accurately. Several optimization algorithms tested, namely Adam, RMSprop, SGD, Adagrad, and Adadelta, were used to evaluate model performance in terms of accuracy, precision, recall, and F1-score. The results showed that the Adam optimization algorithm provided the best performance with an accuracy of 86.74%, precision of 75.12%, recall of 66.67%, and F1-score of 70.64%. Meanwhile, other algorithms such as RMSprop, SGD, Adagrad, and Adadelta showed lower performance, with some metrics reaching 0%. This study shows that proper activation function optimization in ANN is very important to improve the model's ability to predict heart failure with a high level of accuracy.
Analisis Kombinasi itemset pada Bisnis Online dengan Teknik Asosiasi Data mining Siregar, Muhammad Noor Hasan
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 6, No 1 (2021): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v6i1.268

Abstract

Online business is one of the industries that thrives on social media. With business competition starting to grow a lot these days, businesses are setting up online businesses to boost sales. One suggestion is to reduce the price on combination of items that are commonly purchased at the same time. Using the transaction data obtained through purchase, an association rule may be used to discover the rules for combinations of items. The association process uses an a priori algorithm to access sales transaction data. The positive results of this study can be used to produce the strategies in the development of online businesses.
Optimalisasi Penggunaan Komputer Sebagai Alat Edukasi di Komunitas Lokal Rizki, Cindy Atika; Iqbal, Muhammad; Putra, Eka; Siregar, Muhammad Noor Hasan; Mardiah; Hendry
JURIBMAS : Jurnal Hasil Pengabdian Masyarakat Vol 4 No 1 (2025): Juli 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juribmas.v4i1.319

Abstract

Kemajuan dalam teknologi informasi dan komunikasi telah membuka peluang besar di dunia pendidikan, termasuk di tingkat masyarakat setempat. Tujuan dari penelitian ini adalah untuk mempertimbangkan strategi untuk mengoptimalkan penggunaan komputer sebagai peralatan pendidikan di masyarakat, terutama untuk mendukung pembelajaran non-formal, pengembangan keterampilan digital dasar, dan meningkatkan kemampuan informasi publik. Metode yang digunakan dalam penelitian ini adalah pendekatan kualitatif deskriptif dengan metode perekaman data dalam bentuk pengamatan lapangan, wawancara dengan manajer pusat pembelajaran masyarakat, dan dokumentasi kegiatan pendidikan berbasis komputer. Hasil penelitian menunjukkan bahwa penggunaan komputer secara tepat meningkatkan akses publik ke sumber belajar, memperkuat kemampuan teknologi informasi, dan mempromosikan kemandirian pembelajaran. Namun, ada banyak hambatan, termasuk perangkat terbatas, kurangnya pelatihan, dan kemampuan digital awal yang buruk di masyarakat. Oleh karena itu, strategi optimasi diperlukan dalam bentuk pelatihan langkah demi langkah, pengadaan fasilitas komputer yang berkelanjutan, dan pembentukan tim sukarelawan pendidikan berbasis teknologi. Studi ini merekomendasikan bahwa sinergi dengan pemerintah, lembaga pendidikan dan komunitas membantu mendigitalkan pendidikan berdasarkan standar. Mengoptimalkan penggunaan komputer tidak hanya akses ke pendidikan, tetapi juga memperkuat kemampuan masyarakat dalam era digital yang terintegrasi dan kompetitif.
Sosialisasi Pendidikan Tinggi sebagai Strategi Peningkatan Minat Studi Lanjut Siswa Sekolah Menengah Atas Ramadhani, Yulia Rizki; Harputra, Yuswin; Siregar, Muhammad Noor Hasan; Suleman, Abdul Rahman
KALANDRA Jurnal Pengabdian Kepada Masyarakat Vol 4 No 4 (2025): Juli
Publisher : Yayasan Kajian Riset Dan Pengembangan Radisi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55266/jurnalkalandra.v4i4.578

Abstract

Pendidikan tinggi memiliki peran penting dalam meningkatkan kualitas sumber daya manusia dan mempersiapkan generasi muda menghadapi persaingan global. Namun, masih banyak siswa Sekolah Menengah Atas (SMA) yang kurang berminat melanjutkan pendidikan ke jenjang perguruan tinggi karena keterbatasan informasi, ekonomi, dan motivasi. Kegiatan pengabdian ini bertujuan untuk meningkatkan minat dan pemahaman siswa terhadap pentingnya melanjutkan pendidikan tinggi melalui sosialisasi yang dilaksanakan di SMAN 1 Padang Bolak Julu. Metode yang digunakan meliputi observasi awal, penyusunan materi, pelaksanaan ceramah interaktif, sharing session, dan evaluasi dengan kuisioner. Hasil kegiatan menunjukkan bahwa minat siswa untuk melanjutkan ke perguruan tinggi meningkat dari 38,6% menjadi 71,4%. Pengetahuan siswa tentang jalur masuk perguruan tinggi dan program beasiswa juga mengalami peningkatan signifikan. Kegiatan ini membuktikan bahwa sosialisasi pendidikan tinggi merupakan strategi yang efektif untuk membangun kesadaran dan motivasi siswa SMA dalam merencanakan masa depan pendidikan mereka.
Implementation of Natural Language Processing for Chatbots in Customer Service Iqbal, Muhammad; Siregar, Muhammad Noor Hasan; Rismayanti, Rismayanti
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 1 (2024): May 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i1.4

Abstract

The development of artificial intelligence technology has driven significant transformations in various sectors, including customer service. One of its increasingly developed applications is the use of chatbots based on Natural Language Processing (NLP). This research aims to explore the implementation of NLP in chatbots to enhance efficiency, accuracy, and customer satisfaction in digital customer service systems. By using descriptive analysis methods and case studies on several customer service platforms, this research examines how NLP components such as natural language processing, sentiment analysis, and context understanding are used to automatically and relevantly respond to customer inquiries. The analysis results show that chatbots equipped with NLP are capable of understanding human language more naturally, answering questions with appropriate context, and significantly reducing the workload of human agents. Additionally, the integration of NLP allows for personalized responses and continuous learning from previous interactions. However, there are also challenges such as limitations in understanding language ambiguity and the need for large training data. This research concludes that the implementation of NLP in chatbots is a strategic step to improve customer service quality, but it must be supported by the design of adaptive and user experience-oriented systems.
Utilization of Sales Data Analysis for Product Recommendation Systems in E-Commerce Using the Apriori Algorithm Muhammad Noor Hasan Siregar; Furqan Khalidy; Rismayanti; Khairunnisa
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.17

Abstract

The rapid development of e-commerce has significantly increased the volume of sales transactions and customer interaction data. This presents an opportunity for businesses to leverage data mining techniques to extract valuable insights that support decision-making processes. One such application is the development of product recommendation systems, which play a crucial role in enhancing customer satisfaction and driving sales. This research focuses on utilizing sales transaction data to build a product recommendation system using the Apriori algorithm, a well-known method for association rule mining. The study begins with the collection and preprocessing of transaction data from an e-commerce platform. Through the application of the Apriori algorithm, frequent itemsets are identified, and association rules are generated based on specified support and confidence thresholds. These rules reveal purchasing patterns and relationships between products that are frequently bought together. The system then uses these patterns to recommend relevant products to users, aiming to improve cross-selling opportunities and personalize the shopping experience. The results demonstrate that the Apriori-based recommendation model is effective in identifying meaningful product combinations and can be implemented as a lightweight, interpretable alternative to more complex machine learning methods. Furthermore, the system helps e-commerce businesses optimize inventory management and marketing strategies by understanding customer buying behavior. This research concludes that the integration of the Apriori algorithm into recommendation systems provides tangible benefits for e-commerce platforms seeking data-driven personalization solutions.