Claim Missing Document
Check
Articles

Found 18 Documents
Search

Penerapan Metode Fuzzy Logic Dalam Sistem Pemantauan Tanaman Berbasis Internet Of Things (Iot) Dengan Arduino sabil, Muhammad; Sarjon Defit; Gunadi Widi Nurcahyo
Computer Science and Information Technology Vol 5 No 1 (2024): 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.v5i1.6710

Abstract

Hydroponic plants in this increasingly modern era, people are increasingly aware that their vegetable needs must be met so that the body's nutritional balance can be met properly. One of the Urban Farming that is suitable in urban areas with narrow dominant land is the hydroponic system. Hydroponics comes from two Greek syllables combined, namely hydro which means water and ponos which means work, so hydroponics means working using air. One of the advantages of this agricultural system is the minimal use of land, where even small areas of land can be utilized. well. Hydroponics is agricultural cultivation without using soil, so hydroponics is an agricultural activity that is carried out using air as a medium to replace soil. Hydroponic systems are increasingly popular among farmers and agricultural service providers because they are able to produce healthier and more productive plants without using soil as a growing medium. This research aims to test the performance of an Internet of Things (IoT) based Hydroponic Monitoring System using Arduino on plants or vegetables with the method used in this research is Fuzzy logic. This method has 3 stages, namely Fuzzification, Defuzzification, Fuzzy Rule. The data set processed in this research was taken from measurements of pH and temperature on hydroponic vegetable plants in the PKK garden of Kemantan Kebalai Village. The dataset consists of 340 data. The results of this research can identify and calculate the percentage of pH and temperature measurements with an accuracy level of 90%. Therefore, this research can be a reference in measuring acid, normal and alkaline levels in hydroponic plants.
Implementasi Data Mining untuk Pemetaan Persebaran Infeksi Human Imunodeficiency Virus di Provinsi Riau Fadillah, Riszki; Sarjon Defit; Sumijan
Computer Science and Information Technology Vol 5 No 1 (2024): 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.v5i1.6712

Abstract

Based on data released by the Riau Provincial Health Service until October 2022, there were 8034 people living with HIV/AIDS (PLWHA), of which 3,711 were in the AIDS stage. Human Immunodeficiency Virus is a virus that attacks the body's immune system, while Acquired ImmunoDeficiency Syndrome (AIDS) is a collection of diseases caused by the HIV virus due to damage to the immune system in humans, resulting in the body being susceptible to potential diseases. This research aims to map the spread of HIV/AIDS in Riau Province to prevent and control the spread of the HIV/AIDS virus by the relevant agencies. The method used in this research is Fuzzy C-Means to carry out clustering in districts/cities which will then be visualized using a map or with a Geography Informatics System (GIS). The Fuzzy C-Means method is a data grouping technique that uses the existence of each data point in A cluster as determined by the degree of membership. The output from Fuzzy C-Means is a series of cluster centers and several degrees of membership for each data point. The data used in this research is HIV/AIDS data in Riau Province from 1997 to 2023. Based on the results of the tests that have been carried out, the results obtained are 3 clusters, namely the safe zone has 5 districts/cities, the alert zone has 5 districts/cities, and There are 2 districts/cities in the dangerous zone. There needs to be treatment through the Health Service, the AIDS Control Commission, and related Non-Governmental Organizations (NGOs) to prevent and control HIV/AIDS in Riau Province for areas that have a high potential for the spread of HIV/AIDS. The tests that have been carried out obtain a minimum error value of 0.008251 in the 8th iteration with the performance of Fuzzy C-Means being 13.271 in the distance between clusters.
Penerapan Convolutional Neural Network pada Klasifikasi Citra Pola Kain Tenun Melayu Mukhlis Santoso; Sarjon Defit; Yuhandri
Computer Science and Information Technology Vol 5 No 1 (2024): 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.v5i1.6713

Abstract

The use of electronic computerized media is growing along with advances in hardware and software as an analytical tool with various algorithms and methods for classifying and measuring objects in various contexts. This progress aims to overcome the weaknesses that exist in conventional methods used in the identification process. The identification process can be applied to various objects, one of which is an image object. An image is a visual representation of an object formed through a combination of RGB (red, green, blue) colors. RGB color components or features have a range of values from 0 to 255 in an image. Weaving is a type of fabric that is specially made with distinctive motifs. Malay weaving motifs have a lot of diversity, this diversity makes it difficult to distinguish the motifs of these fabrics.This study aims to recognize and distinguish the pattern of Malay woven fabric. The method used in this research is Convolutional Neural Network (CNN). The CNN method has several stages, namely Convolution Layer, Pooling Layer, Rectifed Linear Unit (ReLU) Function, Fully-Connected Layer, Transfer Learning, Optimizer and Accuracy. The dataset used in this research is sourced from Tenun Putri Mas Bengkalis. The dataset used consists of 1000 images of weaving motifs which are divided into 80% training data and 20% testing data, from the existing dataset divided into three categories of weaving motifs namely pucuk rebung, elbow clouds and elbow keluang. The results in this study are considered good because they produce accuracy with a result of 95% with an epoch value of 15. From the results of good enough accuracy, it is hoped that it can help the community in recognizing Malay weaving motifs.
Penerapan jst perceptron untuk mengenali huruf hijaiyah sebagai media pembelajaran anak usia dini Dwiprihatmo, Mohammad Reza; Sarjon Defit; Sumijan
Computer Science and Information Technology Vol 5 No 1 (2024): 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.v5i1.6718

Abstract

Computer vision is the transformation of data obtained or taken from a webcam into another form to determine the decisions to be taken. All forms of transformation are carried out to achieve certain goals. One of the techniques that supports the application of computer vision to a system is digital image processing, because the aim of digital image processing techniques is to transform images into digital format so that they can be processed by a computer. Computer vision and digital image processing can be implemented into a hijaiyah letter pattern recognition system on cards that have been prepared and placed on a white board which is supported by the perceptron algorithm artificial neural network method which is used as a learning technique for the system to be able to learn and recognize hijaiyah letter patterns. This research aims to enable computers to read hijaiyah letters using a camera. The methods used in this research are image processing and the perceptron algorithm. The data set processed in this research comes from 783 hijaiyah letters consisting of 29 hijaiyah letters and 30 samples per each hijaiyah letter. How it works is that each hijaiyah letter is captured using a webcam and produces a continuous image which is transformed into a digital image and processed using several techniques including grayscale images, binary images and cropping images. The results of this research are that the system is able to identify and classify hijaiyah letters with a testing rate of 99,746%. Therefore, this research can be a reference in the modern teaching and learning process and is expected to help children's interest in learning hijaiyah letters.
Multi-Process Data Mining with Clustering and Support Vector Machine for Corporate Recruitment Zain, Ruri Hartika; Randy Permana; Sarjon Defit
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 2 (2025): April 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i2.6197

Abstract

Having an efficient and accurate recruitment process is very important for a company to attract candidates with professionalism, a high level of loyalty, and motivation. However, the current selection method often faces problems due to the subjectivity of assessing prospective employees and the long process of deciding on the best candidate. Therefore, this research aims to optimize the recruitment process by applying data mining techniques to improve efficiency and accuracy in candidate selection. The method used in this research utilizes a multi-process Data Mining approach, which is a combination of clustering and classification algorithms sequentially. In the initial stage, the K-Means algorithm is applied to cluster candidates based on administrative selection data, such as document completeness and reference support. Next, a classification model was built using a Support Vector Machine (SVM) to categorize the best candidates based on the results of psychological tests, medical tests, and interviews. The experimental results show that the SVM model produces high evaluation scores, with an AUC of 87%, Classification Accuracy (CA) of 90%, F1-score of 89%, Precision of 91%, and Recall of 90%. With these results, it can be concluded that this model is able to improve accuracy in the employee selection process and help companies make more measurable and data-based recruitment decisions.
Utilization of Convolutional Neural Network Method in Customer Identification Based on Facial Images Ade, Ade Puspita Sari; Sarjon Defit; Sumijan
Jurnal KomtekInfo Vol. 12 No. 3 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i3.664

Abstract

Artificial intelligence-based facial recognition technology, especially using the Convolutional Neural Network (CNN) method, is increasingly widespread in various business applications, such as customer data management. This technology allows the system to recognize and identify individuals automatically through facial images, so it is very potential to be applied in customer management. This study aims to implement CNN technology in automatically identifying old customers in a case study in JAVApace Studio. CNN method for facial recognition, optimizing the accuracy of old customer identification, designing CNN system integration in computer vision-based applications, and measuring CNN performance in real-time facial identification. The research method was carried out using a quantitative approach through data collection stages in the form of 875 customer facial images taken in JAVapace Studio, data preprocessing (cropping, resizing, and data augmentation), dataset division for training, validation, and testing. The CNN model used is the ResNet-50 architecture with fine-tuning techniques and freezing layers to improve training efficiency. Model performance evaluation uses a confusion matrix with accuracy, recall, and precision metrics. The results show that the CNN-based facial recognition system achieved 95.7% accuracy in distinguishing existing customers from the test data used. The recall rate was 94.5%, while the precision rate reached 96.2%. The discussion of the results also indicates that the fine-tuning approach is effective in optimizing model performance with an inference time suitable for real-time implementation needs. This study confirms that the implementation of CNN with ResNet-50 architecture is effectively able to recognize the faces of old customers with high levels of accuracy, recall, and precision, making it the right solution in managing customer data automatically and efficiently.
Analyzing the use of Social Media by Fashion Designers with K-Means and C45 Abulwafa Muhammad; Sarjon Defit
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 21 No. 2 (2022)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v21i2.1432

Abstract

Social media is one part of digital marketing that is used for the development of marketing business products known as social-marketing. The use of social media as social marketing is still managed conventionally and has not implemented business social media. This study was conducted to analyze the clusters and classifications of the use of social media by fashion designers in West Sumatra in marketing their products. This analysis uses the k-Means algorithm and c45 uses the Rapidminer application for the fashion designer industry in West Sumatra. Data is collected from Instagram and Facebook of fashion designers. The data analyzed by K-Means resulted in 3 clusters of social media use, namely 3 less active clusters, 12 active clusters and 1 very active, then classification using the C45 method resulted in a decision tree that described the most and the least in using social media. This study resulted in grouping and classifying variables from whether or not the use of social media in social marketing for the fashion designer industry players in West Sumatra was good or not. The results of this study can be used as a reference for developing integrated marketing for West Sumatra fashion designers.
ANALISIS BIG DATA BEASISWA KIP-K MENGGUNAKAN K-MEANS CLUSTERING Defi Pebriyanti; Sarjon Defit; Gunadi Widi Nurcahyo
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v8i2.3959

Abstract

The Kartu Indonesia Pintar Kuliah (KIP-K) Scholarship Program is a government initiative to provide higher education access to underprivileged students. It aims to reduce educational disparities and improve access for eligible students. However, the selection process faces challenges, particularly in identifying applicants who truly need financial aid. With the increasing number of applicants each year, a Big Data-based approach is essential to enhance selection efficiency and accuracy. This study analyzes KIP-K scholarship recipients’ profiles using the K-Means Clustering method. This technique groups data based on attribute similarities, allowing an objective and data-driven selection process. The dataset, obtained from Universitas Prima Nusantara Bukittinggi (2024), consists of 479 applicants. It includes attributes such as academic performance, parental income, number of dependents, KIP-K card ownership, and achievements. Results indicate that recipients can be categorized based on document completeness, academic scores above 85, and more than three family dependents. Implementing K-Means Clustering improves the selection process by making it more objective, transparent, and efficient.