Publication Search

Multispectral image is a type of digital image that captures spectral information in several channels or bands. Edge detection is one of the basic techniques in image processing which is used to identify the boundaries of objects in an image. This research aims to analyze the performance of several edge detection algorithms on multispectral images. The algorithms tested include the Sobel, Prewitt, Roberts, Canny, and Laplacian of Gaussian (LoG) algorithms. Tests were carried out on high resolution multispectral images from the Landsat-8 satellite. The evaluation metrics used are accuracy, precision, recall, and F1-score. The research results show that the Canny algorithm has the best performance with the highest F1-score compared to other algorithms. Apart from that, this research also analyzes the effect of the number of channels in multispectral images on the performance of edge detection algorithms.

Universities' development hinges significantly on student admissions, necessitating accurate predictions for effective planning. This study applies the Monte Carlo simulation method to forecast new student arrivals at the Faculty of Mathematics and Natural Sciences (FMIPA) at Universitas Negeri Medan (UNIMED). Utilizing data from 2021 to 2023 sourced from the PDDikti website, the research employs PHP programming for implementation. The Monte Carlo algorithm's numerical prowess ensures precise statistical data simulation, comprising data collection, probabilistic distribution computations, cumulative distribution determinations, random number generation, and simulation analyses. Simulation results for 2022, 2023, and 2024 exhibit consistent trends, projecting an average of 860 to 930 new students per program. This methodology surpasses manual estimations, offering robust insights for university resource allocation and strategic management. Despite its effectiveness, study limitations, such as model assumptions, warrant continuous validation with actual data. This research advances predictive modeling in higher education, providing a foundation for future enhancements and comprehensive prediction integrations.

PT Sayuran Pagi is a company that operates in the agricultural sector and focuses on hydroponic vegetables such as spinach, kale, curly kale and other types of vegetables, and is located in the city of Depok and is a Limited Liability Company (PT). The Morning Vegetable Company has three gardens which are used, one of which is the Cipaku area, Bogor, where all of its production will be sent first to a warehouse in Depok and then distributed to several partners who have collaborated. The increase in consumption of green spinach among the public affects the distribution of this vegetable, which means companies must be able to meet demand with proper distribution. In this research, to determine the shortest route when distributing from the garden to the warehouse using the Dijkstra algorithm. Based on the calculation results, the optimal solution for the shortest route is route A-C-B-F-H-I or from the toll road with a total distance of 10.55km. However, because the focus of this research is on costs, from the results of the research using the Dijkstra algorithm calculation method, it can be concluded that PT. Sayuran Pagi can take the non-toll route because the costs incurred are less than the toll route.

The development of image processing technology today can create systems that are able to effectively recognize digital images, one of which is in the field of agriculture for plant disease identification. Citrus plants experience a decrease in productivity due to pathogen attacks on leaves such as Black Spot, Cancer, and CVDP so that disease identification is needed. The classification method that can be used to classify images is the K-Nearest Neighbor (K-NN) algorithm because it is simple and has high accuracy in image management. This study aims to implement and determine the performance of the K-NN algorithm in identifying citrus plant diseases based on leaf images. This research uses a dataset from the Kaggle website of 1,096 images. There are 12 research scenarios using the comparison between test data and training data as much as 4, namely (90% training data + 10% test data, 80% training data + 20% test data, 70% training data + 30% test data, 60% training data + 40% test data) and testing with 3 random state values (42, 32, 22). The results showed that the K-NN algorithm is very effective in identifying citrus plant diseases with the highest accuracy value in the 90% training data scenario and 10% test data with a value of K = 2 which is 98.5%.

In Indonesia, tuberculosis is ranked third in terms of prevalence among countries with the highest tuberculosis burden. Radiological examination, such as X-rays or X-rays, is a method generally used to detect tuberculosis. Chest X-ray examination is one method used to detect tuberculosis. To achieve these goals, the research will combine two powerful data processing techniques. First, the K-Means algorithm will be used to group x-ray image data based on similar characteristics, making it easier to identify typical patterns from images infected with tuberculosis. The research results show the highest accuracy of 93% using data division with a ratio of 80 : 20 with parameter K = 1. These results show that the combined model of the two algorithms can be applied to identify tuberculosis in the lungs.    

The rapid advancement of quantum computing has significantly impacted data security, as classical cryptographic algorithms such as RSA and ECC are increasingly vulnerable to quantum attacks. This study aims to evaluate the performance of classical and post-quantum cryptographic algorithms in a quantum simulation environment, focusing on stability, efficiency, and computational time. The research method employed experimental simulations using Qiskit, where cryptographic algorithms were modeled into quantum circuits and tested across varying qubit sizes of 128, 256, 512, and 1024. The simulation results indicate that classical algorithms face substantial limitations, with exponentially increasing computational time and drastically reduced stability beyond 512 qubits. In contrast, post-quantum algorithms demonstrated superior performance, maintaining high stability up to 1024 qubits, achieving greater quantum efficiency, and showing resilience against quantum attacks such as Shor’s and Grover’s algorithms. These findings highlight the urgent need to transition toward post-quantum cryptography as a more adaptive and reliable approach to safeguarding data in the quantum era. Although post-quantum algorithms still face certain challenges, such as larger key sizes and slightly higher computational costs at smaller scales, their overall benefits are far more significant in ensuring sustainable information security. Therefore, adopting post-quantum cryptography represents a strategic step that must be prioritized to address the evolving risks posed by quantum computing technologies.

Sport is an activity that is popular and needed by all levels of society to fulfill a healthy lifestyle. Sports cannot be separated from the equipment or equipment used to complete the activity. One of the sports that is often popular, especially among teenage boys, is Futsal. Futsal shoes are equipment that is really needed to support the continuity of this activity. Various brands of futsal shoes are often found on the Indonesian market today. One of them is the Specs brand of futsal shoes. .In this case, the author analyzes sales of Specs brand futsal shoes to determine the grouping of product sales. The method that will be used to solve the problem that will be examined is one of the data mining methods, namely the data grouping method using the K-Means algorithm. The K-Means algorithm is a grouping algorithm that can group a number of data into certain data groups. In this research, sales data is grouped into 2 clusters, namely best-selling and non-selling data. This clustering test was carried out using MS Excel with several processes which then produced several groups of sales data on Specs brand futsal shoes and implemented using the Weka application to find the effectiveness of grouping data on sales of Specs brand futsal shoe products.

Background: The rapid growth of warehouse automation and autonomous mobile robots has increased the need for adaptive navigation systems capable of operating safely and efficiently in dynamic industrial environments. Classical path planning algorithms such as A* and RRT perform well in structured settings but exhibit limitations when handling moving obstacles and environmental uncertainty. Objective: This study aims to develop and evaluate a reinforcement learning based navigation framework integrated with sensor fusion to improve path efficiency, collision avoidance, and robustness in dynamic warehouse scenarios. Method: An experimental research design was implemented combining high-fidelity simulation and real-world warehouse prototype testing. Deep Q-Network and Proximal Policy Optimization models were developed and trained using multi-sensor inputs from LiDAR, camera, and inertial measurement units. Performance was evaluated using path efficiency, collision rate, computational cost, and robustness metrics, with benchmarking against classical algorithms. Results: The results demonstrate that the Proximal Policy Optimization model achieved the highest path efficiency and lowest collision rate while maintaining stable computational performance under dynamic conditions. Reinforcement learning models significantly outperformed classical planners in adaptability and robustness, confirming their suitability for scalable industrial warehouse automation.

The Binjai District Court is a government agency that has the duty and authority to receive, examine and decide every case registered at the Binjai District Court. The Binjai District Court handles many gambling cases, but data management is still not fast and accurate because it still uses manual methods, so the agency needs to implement an application system. To solve this problem, you can use data mining applications, namely by utilizing existing data to dig up new information. One of the techniques in data mining is clustering. Clustering was chosen because it can group data according to the desired characteristics, in this research it means grouping gambling data in the Binjai City area. The clustering algorithm used is K-Means Clustering integrated into a desktop-based programming application. The conclusion obtained is that the system designed has proven successful in grouping gambling data into 3 clusters (groups). The process using MATLAB R2014a obtained results in group 1 which amounted to 276 data with a data centroid center (6.92; 2.41; 4.33) including the category of low levels of gambling, group 2 which amounted to 337 data with a data centroid center (7.56 ; 2.10; 14.48) is included in the category of moderate level of gambling and group 3 which amounts to 387 data with the centroid data (7.56; 2.10; 28.02) is included in the category of high level of gambling.    

Lampung, a province located at the southern end of Sumatra Island, serves as a gateway for many migrants from different regions in Indonesia. However, some of the locals and tourists still face difficulties in finding the central location for souvenirs due to the  vast number of shops available. The purpose of this research is to assist tourists in finding the shortest distance to the nearest souvenir location using the Floyd Warshall algorithm. The software development method employed in this study is the Prototype, which consists of four stages, namely Communication, Quick Plan, Modeling Quick Design, Construction of Prototype, Deployment Delivery & Feedback. In the Rapid Modeling stage, the Floyd Warshall algorithm is used to determine the shortest distance for users to find the souvenir location. The result of this research is an android-based application that can provide the    nearest souvenir location with the shortest distance around the user.

The rapid advancements in Artificial Intelligence (AI) have raised significant ethical concerns across various sectors, necessitating the need for robust ethical frameworks to guide their development and implementation. This study explores the intersection of AI ethics and Islamic law, focusing on how Maqāṣid al-Sharīʿah, the higher objectives of Islamic law, can be applied to AI governance. By examining key Islamic principles such as justice, transparency, privacy, and human dignity, the study investigates how these values can provide a moral compass for addressing AI-related ethical challenges, such as algorithmic bias, privacy violations, and the erosion of human autonomy. The Maqāṣid al-Sharīʿah framework offers a proactive and vision-oriented approach, prioritizing societal well-being while ensuring the alignment of AI technologies with Islamic moral standards. Unlike traditional Islamic legal responses, which are often reactive and case-specific, the Maqāṣid approach promotes the anticipatory evaluation of technologies, emphasizing the need for a balance between technological innovation and ethical responsibility. The paper also discusses potential solutions to bridge the gaps between global AI ethics frameworks and Islamic ethical standards, including interdisciplinary collaboration and the development of hybrid regulatory models. Additionally, it highlights the need for continuous updates to Islamic legal frameworks to address emerging technological issues, ensuring that AI systems are ethically sound, Shariah-compliant, and beneficial to society. This study aims to contribute to the growing discourse on the ethical implications of AI from an Islamic perspective, offering insights into how Islamic law can play a crucial role in shaping the future of AI governance.

The Family Hope Program (PKH) is a program that provides attention to the community, especially the health category, education category and social welfare category for poor families. The Family Hope Program (PKH) aims to reduce poverty and improve the welfare of the Indonesian population. Due to the large number of residents who want to register themselves as PKH recipients, there are residents who manipulate data or claim to be poor people in order to get PKH. If this continues to happen, and there is no preventive action, it is not impossible that many residents are not right in receiving PKH provided by the Government. One of the efforts that can be made is to test the classification of prospective PKH recipients in Bah Sorma Village. This study aims to classify prospective recipients of the Family Hope Program in Bah Sorma Village. The dataset used is data on prospective PKH recipients in Bah Sorma Village, Pematang Siantar City. This research is a comparative study of previous research using the Naïve Bayes method. The method used in this research is Data Mining with the C4.5 method which is used to see the accuracy of the best method than previous research. The accuracy result obtained by this research is 98.18%. Based on the results obtained, research with the case of classification of prospective PKH recipients in Bah Sorma Village using the C4.5 Algorithm gets better accuracy than previous research using Naïve Bayes obtaining an accuracy of 80%.

Alzheimer's and Parkinson's diseases are neurodegenerative conditions that affect the brain, with Alzheimer's causing cognitive and behavioral decline, while Parkinson's leads to motor and non-motor impairments. Both diseases have significant impacts on the health and quality of life of patients, with prevalence increasing in recent years. Although the exact causes of these diseases are still unknown, MRI (Magnetic Resonance Imaging) is widely used to detect brain activity and serves as one of the diagnostic methods. With technological advancements, intelligent systems in image processing for image classification have been extensively used and have become a popular field due to their ability to replicate human visual capabilities. Image classification is performed using various supervised learning machine learning algorithms based on the shape, texture, and color of the images. This study employs two Convolutional Neural Network (CNN) architectures, ResNet50 and GoogLeNet, to compare the performance of these models in classifying MRI scans of patients with Alzheimer's and Parkinson's diseases. The results show that the ResNet50 model outperforms the GoogLeNet model, with parameters set to 100 epochs, a batch size of 128, a learning rate of 0.0001, and the Adam optimizer, achieving an accuracy rate of 90%.

This research aims to develop and apply a Convolutional Neural Network (CNN) algorithm to detect handwritten Roman numerals. Handwriting recognition is a classic challenge in the fields of image processing and machine learning, especially for less common characters such as Roman numerals. In this research, we use data augmentation techniques to increase the diversity and number of datasets used in model training, which is expected to increase model accuracy and generalization. The dataset used consists of 1,120 images for testing and 280 images for validation, each of which is divided into 14 classes of Roman numerals I, II, III, IV, V, VI, VII, VIII, IX, X, L, C, D , and M. Image data was created directly using simple software, namely Paint version 6.3. This research uses the Python programming language and Google Colab as a computing platform. Model training was carried out for 300 epochs and showed significant accuracy in the 150th to 300th iteration. The results at the 300th epoch show an accuracy of 0.9607 and a loss of 0.1162. The implementation of this algorithm shows significant potential in practical applications, such as in the fields of education and historical documentation. The conclusion of this research is that data augmentation is an effective technique to improve the performance of CNN models in detecting handwritten Roman numerals.

The spread of hoaxes on social media has become a serious problem in society. This research aims to analyze the factors that cause the spread of hoaxes, the characteristics of hoax content, a well as their impact on society. The research method used is the study of literature and content analysis from various online news sources. The results showed that the main factors of the spread of hoaxes were lack of digital literacy., economic motivation, and political polarization. Hoax content generally spreads quickly, has sensational titles, and contains inaccurate information. The impact of hoaxes on society includes confusion, social conflict, and a decline in public trust. This research concludes that comprehensive efforts from the government, media, and the public are needed to overcome the hoax problem. This research aims to analyze the causes, patterns of spread, and the impact of hoaxes on social media on the community. The research methods used are literature studies and content analysis from various trusted sources. Patterns of spreading hoaxes generally utilize sicial media algorithms to achieve a wide reach quickly. The negative impact of  hoaxes on society is very diverse, ranging from triggering social confilcts, affecting public opinion, to threatening political stability and national security. This shows the urgency of handing hoaxes comprehensively, involving the role of government, social media platforms, and the public.

In this research, data was taken from the distribution route which was recorded by the cashier at the Cahaya Kristal Tube Ice Ice Factory which is located on Jl, Damai, Prujakan Tambakan Village, Sinduharjo, Ngaglik, Sleman Yogyakarta. Then the data is processed using the Clarke and Wright Savings Algorithm and Sequential Insertion with the aim of providing the best or most effective route suggestions and then comparing the two methods to produce the Travel Route Distance and Distribution Costs. By using the Clarke and Wright Saving Algorithm, we get 2 vehicle routes which produce a combined route of 72 km with a daily distribution cost of IDR 147,000, and for the sequential insertion algorithm method we also get 2 vehicle routes which produce a combined route of 107 km with a daily distribution cost of IDR 182,000. Thus it can be concluded that routes formed using the Clarke and Wright Savings Algorithm are more effective and economical compared to routes formed using the Sequential Insertion

In the rapidly developing digital era, social media such as Twitter has become part of everyday life and facilitates the rapid dissemination of information, including information about criminals. This research aims to analyze public sentiment towards information about criminals spread on Twitter using the Naive Bayes algorithm. This algorithm was chosen because of its simplicity and effectiveness in text classification. Data was collected through a crawling process from Twitter, followed by a preprocessing stage to remove noise. The research results show that public sentiment towards information about criminals on Twitter is divided into three categories: positive, neutral and negative. After classification, it was found that neutral sentiment increased significantly to 63.4%, while positive and negative sentiment decreased to 10.5% and 26.1%. These findings indicate that people tend to be more careful in reacting to sensitive information. This research provides important insights for related parties in managing information about criminals on social media and can be a reference for developing further policies and strategies.

This study examines the impact of artificial intelligence (AI) on the dynamics and ethics of the workplace environment at PT COLAB PROSPERITY JAYA, a company engaged in the coconut product export industry. Using a qualitative approach, this research involved in-depth interviews with employees at various levels to explore how AI affects work efficiency, decision-making, ethical issues, and employee interactions. The results indicate that AI improves efficiency and supports decision-making with accurate data. However, there are serious ethical concerns, especially regarding data privacy and algorithmic bias. Furthermore, although AI facilitates task management, it also has the potential to reduce social interactions that are crucial for creativity and teamwork. This study suggests the need for stronger policies and ethical training to ensure that AI is integrated in a responsible and fair manner, emphasizing the importance of balancing the benefits of technology with human values in the development and application of AI in the workplace.

During the period of compulsory education in Indonesia, which is 12 years, the government requires mathematics as the main learning subject for extracts which will continue to have an impact on people’s lives. The level of ability in a field of science must be measured to obtain valid data for the development of education in Indonesia. The use of Geogebra Mathematics Software in schools in Indonesia is not surprising at this time, technological developments have made the use of Geogebra mathematics software commonplace. This research is a Systematic Literature Review, in this research the author analyzes and compares several articles obtained from the internet or digital databases, for example Semantic Scholar or Sprinter Link. The articles that have been found are then selected according to the title researched, so that several reference articles are obtained. The research results show that the use of Geogebra mathematics software in learning has a great influence on students’ computing abilities. Geogebra is a media with a visual, analytical and numerical approach that can be solved using algorithms that require computational capabilities to operate. There is empathy in computational thinking, namely algorithmic thinking problem solving, pattern recognition, and abstraction and generalization.

The use of social media is already powerful and difficult to avoid. Social media users are not only limited to the general public, but also public figures and even economic actors who use social media as a means of marketing. In every post from the account owner, there will always be followers who can give likes and comments. Unfortunately, not all comments are related to the uploaded post. One of the most annoying comments is spam comments. Spam comments are comments that are not clear and contain about business (promos / selling), links or various other things that are promoting something. Using the Naive Bayes algorithm, this study wants to identify spam comments, especially on Instagram social media. Where the data is retrieved using the tools provided by Google. Which is then processed with the Rapidminer application to get the Naive Bayes calculation results.