Claim Missing Document
Check
Articles

Found 38 Documents
Search

Deteksi Tepi untuk Mendeteksi Kondisi Otak Menggunakan Metode Prewitt Irzal Arief Wisky; Sumijan
Jurnal Teknologi Vol. 12 No. 2 (2022): Jurnal Teknologi
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (258.739 KB) | DOI: 10.35134/jitekin.v12i2.68

Abstract

The brain is an organ that is in the head as a controller of all functions of the human body, thus enabling humans to think and solve problems. Brain health conditions are very important in keeping the body's functions running properly. Several diseases can adversely affect brain health, such as cancer, tumors, meningitis, encephalitis and other brain diseases. Brain conditions can be identified through Magnetic resonance imaging (MRI). This study aims to identify brain conditions based on Brain Edge Detection on MRI images. The technique used is Prewitt method. The stages of the process carried out in edge detection begun with the pre-processing process in reducing the noise contained in the MRI image. The number of MRI images tested was 25. The results of this study can localize the edges of the image very well. The accuracy of this study is 85%, so this research can be recommended in identifying brain organs.
Mengidentifikasi Kanker Ginjal Menggunakan Metode Robert, Canny, dan Sobel Dhio Saputra; Sumijan
Jurnal Teknologi Vol. 12 No. 2 (2022): Jurnal Teknologi
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (299.332 KB) | DOI: 10.35134/jitekin.v12i2.69

Abstract

Kidneys are organs that function to filter metabolic waste in the blood and dispose of them in the form of urine. One of kidney disease is kidney cancer. Kidney cancer occurs due to gene mutations in kidney cells that cause kidney cells to grow abnormally and uncontrollably. To take an image of kidney cancer using a Magnetic Resonance Imaging (MRI) tool. The purpose of this research is to identify and recognize the pattern object of kidney cancer in the MRI image. To identify kidney cancer images, it begins with collecting image data, image processing, image edge detection, image thinning, and identification processes. Edge detection is used to detect the boundaries of objects in the image. The method used in this research is the Canny and Sobel method. The number of images taken were 23 images of kidney cancer samples. The results of this research show that the Canny method gives better image results than the Sobel image results
Medical Product Sales Forecasting for Business Optimization Using Double Exponential Smoothing Salsa Fitiansyah; Sumijan; Devia Kartika
Methods in Science and Technology Studies Vol. 1 No. 1 (2025): June
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/msts.v1i1.2025.24

Abstract

Accurate sales forecasting plays a critical role in inventory management, particularly for medical equipment companies where stock availability directly affects operational efficiency and customer service. However, many small and medium-scale distributors still lack reliable forecasting systems, resulting in overstocking, high storage costs, or stockouts that lead to missed sales opportunities. Addressing this gap, this study aims to develop a web-based sales prediction system for PT Etiqa Prima Utama—a medical equipment distributor in Padang, West Sumatra—by applying the Double Exponential Smoothing method. The system was designed using PHP and MySQL to generate monthly sales forecasts for various medical products based on historical data. Key findings show diverse forecast accuracy across 20 product categories. The Glucose HK product achieved the lowest MAPE value at 10%, indicating excellent predictive performance, while the Clean Chem product showed the highest MAPE at 54%. Several other products, such as Total Bilirubin (12%), Urea (10%), and Diluent 20L (14%), demonstrated favorable accuracy with MAPE values below 60%. These results imply that Double Exponential Smoothing can support inventory optimization by providing reasonably accurate forecasts for most products, enabling better stock planning and more informed decision-making within the company.
Public Sentiment Analysis of Train Services Based on Twitter Opinions Using K-Menas and SVM Methods Dina Selvia; Sumijan; Musli Yanto
Jurnal KomtekInfo Vol. 13 No. 1 (2026): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v13i1.677

Abstract

The development of social media, particularly Twitter, has become a primary means for the public to express opinions, criticisms, and complaints regarding train services, ranging from delays, facility comfort, to ticket policies. The large number of opinions appearing in short, non-standard characters, and containing slang and emoticons makes manual analysis ineffective, resulting in service providers not optimally utilizing valuable information from the public. This study aims to analyze public opinion sentiment on Twitter regarding train services to systematically and structuredly determine public perceptions. The methods used in this study are K-Means Clustering and Support Vector Machine (SVM). K-Means is used to group public opinion based on similarities in language patterns and sentiments to obtain initial labels, while SVM is used to classify opinions into positive and negative sentiments more accurately. The research data comes from the Twitter platform and is obtained through a crawling technique. The maximum limit of tweets retrieved is set at 2005 tweets. The results show that the K-Means method is able to assist the initial labeling process of sentiment data, while the SVM algorithm can classify public opinion with an accuracy level of 99.02%. The combination of clustering and classification methods has proven effective in processing large-scale, unstructured opinion data. Based on the research results, it can be concluded that the sentiment analysis approach using K-Means and Support Vector Machines can provide an objective picture of public perception of train service quality. The results of this analysis are expected to be used by service providers as evaluation material and a basis for decision-making to improve service quality to the public
Utilization of IT Business Management for Marketing Development with the Analytical Hierarchy Process Method Andreas Malau; Sumijan; Muhammad Hafizh
Journal of Computer Scine and Information Technology Volume 9 Issue 3 (2023): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v9i3.75

Abstract

Marketing development is an important factor in a business that must be considered to increase market share. Choosing the right marketing strategy greatly influences the smooth running of sales. This study aims to determine a decision on the right marketing method so that it can be applied by Rozi Bike Shop in expanding its market share. Determination of the marketing strategy at the Rozi bicycle shop is determined based on four criteria, namely organization, product, place and distribution channel. The four criteria are analyzed and processed using the Analytical Hierarchy Process (AHP) method in order to obtain an appropriate marketing decision to implement. method The Analytical Hierarchy Process (AHP) is a multicriteria decision method for solving complex or complex problems, in unstructured situations into parts (variables) which are then formed into functional hierarchies or network structures. The results of calculations using the AHP method show that Strategy A (Technological Innovation) gets the highest value, namely 0.46984 . The results obtained from this study are a decision-making system designed using the AHP method and the application of IT business management in developing the store's marketing.
Poor Family Classification Decision Support System using the Simple Additive Weighting (SAW) Method Lili Amareza Patriani; Sumijan; Sofika Enggari
Journal of Computer Scine and Information Technology Volume 9 Issue 3 (2023): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v9i3.83

Abstract

Poverty is a problem that continues to be the focus of attention for the government. Poverty has also caused people to be willing to sacrifice anything for their survival. To anticipate this problem, various policies have been adopted by the government to break the chain of poverty. One of them is providing assistance funds to poor families (PKH). This is felt directly by all levels of underprivileged society. One of the efforts of the Koto Ranah Tapan government to eradicate poverty that occurs in Koto Ranah Tapan is to follow the central government program, namely the launch of government financial assistance (PKH). These funds will be distributed to poor residents in Koto Ranah Tapan through the nagari guardian office in Koto Ranah Tapan. However, the distribution of aid funds to poor families is often not on target due to a large level of manual calculation error which makes the aid not on target and also the office of the nagari village of high cliff village has not been able to objectively determine the families who receive the aid. To help determine which families are worthy of receiving poor family assistance funds, a decision support system is needed. With this Decision Support System (DSS), it is hoped that the decision-making process can minimize the occurrence of wrong targets that often arise in the process of selecting poor families who wish to receive aid funds . In this calculation the author uses the Simple Additive Weighting (SAW) method, because this method is suitable for accurate calculations and is very helpful in calculating any data obtained. The results obtained were that Ade Irma Suryani got the highest score with a score of 10.8 and was ranked at the top (Best 1), so she could be considered the best recipient of aid funds.
Expert System for Diagnosing Malnutrition Using the Certainty Factor Method Wijaya Hakim; Sumijan; Dinul Akhiyar
Journal of Computer Scine and Information Technology Volume 10 Issue 1 (2024): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v10i1.95

Abstract

Malnutrition in toddlers causes a negative impact on motor nerve development, inhibits behavioral and cognitive development causing a decrease in academic performance and social skills . In addition, malnutrition during infancy can cause long-term risks that focus on later in life, increasing the risk of disease or disability or even death. With advances in information technology today, it is very helpful in predicting or identifying an event, one of which is an expert system that can help an expert in identifying a disease in the world of medicine. Therefore, an expert system is needed that can help doctors and the public find out the type of malnutrition they are suffering from based on the symptoms they are experiencing. The expert system uses the Certainty Factor method in reasoning to obtain diagnostic results from the symptoms shown. This method uses the value of an expert's belief in the symptoms of a disease. The aim of this research is to apply the certainty factor method in identifying malnutrition and providing definitions and suggestions for the disease suffered. The expert system was built using PHP and MySQL database. The results of applying the Certainty Factor method based on the tested data showed that the disease suffered by the patient was Kwarshiorkor with a Certainty Factor level of 0.958528 or 95%. The results of this test show that the certainty factor method expert system is able to identify a disease based on the symptoms experienced
Implementation of the Topsis and AHP Methods in the Decision Support System for Determining the Best Employees Yolan Ananda Putri; Sumijan; Sofika Enggari
Journal of Computer Scine and Information Technology Volume 10 Issue 2 (2024): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v10i2.103

Abstract

Every company or agency needs Human Resources (HR) in the form of employees who have competence and good performance. Employees are one of the most important assets owned by a company. The West Sumatra Province Transportation Service is the organizer of government affairs in the field of transportation or transportation policy for the West Sumatra Province region where the selection of the best employees is still not optimal using Microsoft Excel. The aim of designing a new system at the Provincial Transportation Service is to create optimization in the assessment of each employee to facilitate the recapitulation of employee data. The data is analyzed and processed according to the research framework, namely using a Decision Support System, especially the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Analytic Hierarchy Process (AHP) methods. In this research, 10 alternative employees were taken to be assessed. Based on formula calculations using the AHP method, it is used to determine the weighted value of each existing criterion, then the resulting values from the weighting are used to carry out rankings using the TOPSIS method. After carrying out calculations using these 2 methods, the result was that the best employee was alternative 9 in the name of Rusdi with a value of 0.9995. So with this calculation the results can show which employees have the right to be the best employees in that agency