Jurnal Komtika (Komputasi dan Informatika)

Pengembangan Layanan dan Pengenalan Akademik di Lingkungan Kampus berbasis Aplikasi Chatbot bagi Calon Mahasiswa Baru

Damar Wicaksono — 2024-05-31

Technology has a crucial role in information dissemination, creating a need for interactive and user-friendly communication tools. One of tools that can be used in this research is chatbot. Chatbots serve as effective intermediaries in the information exchange process, providing a simple and interactive interface. This research aims to develop a Button-Based Chatbot using the Smojo AI platform, with an easy-to-use interface for delivering college preparation information to prospective students. The development of the chatbot employs the SDLC Waterfall method. The chatbot is named "KaKa: Campus Companion" and it provides information on interest tests recommendations, effective study methods, admission pathways to public universities, and scholarship recommendations. The results of this research demonstrate the successful development of a chatbot that delivers simple and interactive information. The implementation of the SDLC Waterfall method in chatbot development ensures a well-structured and coordinated approach, focusing on each menu within the chatbot. Based on the test results, which have been carried out both white-box and black-box testing, the application can run correctly 100% and UAT testing with an accuracy level of 91%.

Studi Komparasi Software berbasis GUI dan CLI Terhadap Pengukuran Kualitas Throughput Jaringan Nirkabel IEEE 802.11ac

Vian Ardiyansyah Saputro — 2024-05-31

One indicator of wireless network performance is throughput quality where the measurement of throughput quality itself has the aim of knowing the quality of service of a network and a picture of the behavior of the network. In measuring the quality of service of a network, supporting software is needed that can be used to measure the value of the quality of throughput. One of the software that can be used is graphical user interface-based software, namely JPERF, and command-line-based software, namely IPERF version 3. This study aims to compare and analyze two Command Line (CLI) based software using iperf version 3 and Graphical User Interface (GUI) based software using jperf which can produce the highest quality of TCP and UDP network throughput. The test results show that the use of JPERF software produces a higher throughput value when measuring throughput quality using the TCP protocol where the largest difference produced is 5 Mbps when sending 384 KB data packets while the throughput quality measurement using the UDP protocol iperf software version 3 produces a higher throughput value where there is the largest difference generated by 22 Mbps when sending 128 KB packets.

Implementasi Algoritma K-Means Clustering Dalam Menentukan Blok Tanaman Sawit Produktif Pada PT Arta Prigel

Yesi Pitaloka Anggriani — 2024-05-31

The purpose of this study is to implement the K-Means Clustering method to determine the patterns of productive oil palm production based on their blocks at Pt Arta Prigel. The research is motivated by issues within the oil palm blocks, such as the absence of productive block summaries, insufficient plantation land analysis, and erroneous decision-making. The development method utilizes CRISP-DM, with data spanning 2 years from October 2021 to October 2023. From the 1275 production records, after cleaning, 1015 records remain. Filtering the initial 51 blocks results in 37 blocks for the years 2021 and 2022, and 46 blocks for the year 2023. After clustering, the production outcomes for the year 2021 are as follows: cluster_0 has 34 blocks, cluster_1 has 2 blocks, and cluster_2 has 10 blocks. For the year 2022, cluster_0 has 36 blocks, cluster_1 has 8 blocks, and cluster_2 has 28 blocks. In the year 2023, cluster_0 has 39 blocks, cluster_1 has 8 blocks, and cluster_2 has 33 blocks. The testing method employs the silhouette coefficient, and the silhouette score testing results indicate the formation of 3 clusters (K=3) with a value of 0.61. The findings of this study include patterns, graphs, and production tables generated using the K-Means Clustering method at Pt Arta Prigel.

Sistem Pakar Diagnosa Hama Penyakit Tanaman Kentang Dengan Metode Forward Chaining

Muhammad Arif Rahman — 2024-05-31

Potatoes (Solanum tuberosum L.) are a priority vegetable crop due to their high domestic trade value and export potential. Potatoes are used for various purposes, both as a vegetable and as a carbohydrate substitute. In addition to being used as a vegetable, potatoes are also utilized as raw materials in the food industry, such as chips, potato flour, and potato starch. Due to the relatively low temperature requirement (20-22°C) for tuber formation, potato cultivation areas in Indonesia are generally located in mountainous regions. One of the potato commodity centers is in the city of Batu, particularly in the Bumiaji District. According to vegetable crop potential data from the Batu City extension program in 2022, the area planted with potatoes is 485.2 hectares with a production potential of 968 tons. Since potato plants are more susceptible to pests and diseases, substandard maintenance can lead to low harvest yields, poor sales, and even crop failure. This issue has led to the development of an application for diagnosing potato pests. The expert system uses forward chaining methods and is web-based. The expert system processes facts answered by users of the potato application, diagnoses the symptoms present, and generates diagnostic results in the form of solutions for the diagnosed potato plant diseases or pests. With the availability of an expert system application for diagnosing potato plant diseases and pests, the limitation of expert manpower is no longer a hindrance for potato farmers. Recommendations and information regarding potato diseases and pests can be obtained online without the need to consult a specialist.

Implementasi Metode Klasifikasi LightGBM dan Analisis Survival dalam Memprediksi Pelanggan Churn

Ibnu Zahy' Atha Illah — 2024-06-05

Increasingly tight competition in the business world causes every business sector to try to utilize relevant technology to maintain its market share. The success of a company is often measured by how strong the customer network they have. Loss of customers (customer churn) can cause a significant decrease in revenue and can even threaten the existence of the company itself. Therefore, predictive modeling and projection of customer churn is needed as a customer retention effort. This research involves the LightGBM classification algorithm for customer churn prediction and utilizes survival analysis for future projections. The results of the research can be used to prevent customer churn at companies, especially PT Kasir Pintar Internasional. LightGBM classification performance as measured by model evaluation reaches Accuracy, Precision, Recall, and F1-score values of 0.964, 0.971, 0.990, and 0.980 respectively. The LightGBM classification model also provides information on five important features that influence customer churn. Companies can use these five important features as material for designing customer retention strategies. Apart from that, the Cox Proportional Hazard survival model has a C-index evaluation value of 0.83, which means it is quite capable of projecting customer survival. The survival model also shows that currently non-churn customers have an average survival expectation of 15 months.

Identifikasi Tutupan Lahan Menggunakan Support Vector Machine di Kawasan Perkotaan Cekungan Bandung

Alvian Aji Purboyo — 2024-05-31

The current mapping challenge is to obtain land cover information with a very high level of accuracy. This information can be useful for regional development, especially in the Bandung Basin Urban Area (KPCB). One of the problems in KPCB is spatial planning issues regarding land cover development. One approach to obtaining land cover information is by utilizing remote sensing technology using the Support Vector Machine (SVM) method. The research method employed in this study is remote sensing, with a unit of analysis based on Regency/City administrative boundaries. The data used in this research consists of Landsat imagery recorded in 2023. The aim of this research is to classify land cover and assess accuracy using the SVM method in KPCB. The SVM results provide information on six land covers: water bodies, secondary forests and mixed gardens, wet agricultural land, dry agricultural land, plantations, built-up land, and primary forests. The accuracy test yielded an overall accuracy of 90% and a kappa value of 0.88. The obtained accuracy in land cover classification is very high, indicating that the data used can be employed for further analysis. For instance, spatial analysis reveals that built-up land development in KPCB tends towards the south, highlighting the phenomenon of urban sprawl. Thus, the utilization of remote sensing technology for land cover information can offer valuable policy insights for addressing spatial planning and development in KPCB.

Analysis of Acceptance Factors of Job Portal Applications for Job Seekers in Indonesia Using TAM

Graha Prakarsa — 2024-06-11

This research is based on the problem of the high number of job portal application users which is supported by the large number of job seekers in Indonesia. This research aims to determine the acceptance of job portal applications for job seekers in Indonesia with external factors, information quality and system quality. This research uses quantitative methods with the data analysis technique used is PLS-SEM using smartPLS 3.2.9 software. Data collection was carried out by distributing online questionnaires to job portal application users in Indonesia and involving 610 respondents. Based on the results of the data analysis that has been carried out, it can be seen that information quality and system quality have a positive and significant influence on perceived usefulness and the magnitude of the influence is 58.8%, information quality and system quality have a positive and significant influence on perceived ease of use and magnitude. The influence is 56.4%, perceived usefulness and perceived ease of use have a positive and significant influence on continuance intention to use and the magnitude of the influence is 63.8% and continuance intention to use has a significant positive influence on actual system use. Overall, information quality and system quality play a role in influencing actual system use indirectly.

Sistem Pakar Menentukan Jenis Produk Kecantikan Berdasarkan Ph Pada Kulit Wajah Perempuan

Januardi Nasir — 2024-06-21

This research aims to providing alternative solutions to consumers in determining which products are right and suitable for the Ph of their facial skin. Shows that the expert system really helps users in solving problems, in terms of determining the type of cosmetics. Applying a web-based forward chaining method in program creation. Design/methodology/approach: The method used in creating the system to determine which products are suitable for the PH type of facial skin is the Forward Chaining method. Forward chaining is a search technique that starts with known facts, then matches these facts with the IF part of the IF-THEN rules. If there is a fact that matches the IF part, then the rule is executed. Findings/result: To determine the type of cosmetic product that is suitable, it will be analysed using a web-based forward changing method. Using the PHP programming language and MySQL database. Dreamweaver is a software application that is used as an editor. System analysis and design using starUMLOriginality/value/state of the art: From the research results, this expert system has an accuracy of 80% and functions quite well in determining the type of cosmetic product using a web-based forward changing method to make it easier for consumers to find the right cosmetics.

Pengembangan Sistem Pendeteksi Gangguan Spektrum Autisme dengan Menggunakan Metode Certainty Factor

Ika Arthalia Wulandari — 2024-06-23

Autism Syndrome Disorder is a multifaceted developmental disorder of mental function with symptoms of impaired communication, social interaction, and distinctive behavioural patterns. A person with Autism Syndrome Disorder cannot form normal social relationships or communication. They have their world. This condition causes them to be isolated from the surrounding environment. Because the main problem faced in Indonesia is the misdiagnosis of autistic children as mentally retarded, so they cannot get the necessary treatment that allows these children to live like normal children. The diagnosis of autism is considered a big problem because the symptoms are easily confused with those of mental retardation. Diagnosis is one of the most challenging and complex problems due to the lack of specialist doctors who can diagnose it scientifically, resulting in misdiagnosis or neglect of autism in the early stages of a child's life, which leads to difficulties in intervention later in life. Successful intervention requires a correct diagnosis. Diagnosing autism disorders manually requires a specialist doctor, making this system have many shortcomings and weaknesses. Therefore, applying an expert system can help diagnose autistic disorders in patients. This expert system will be able to diagnose and obtain accurate results. Based on the results of system testing that has been carried out, it was found that of the 12 cases tested using the expert system, there was 1 case that should have had autism. However, the system diagnosed it as harmful, and 1 case should not have had autism, but the system diagnosed autism. So, it can be concluded that the system's accuracy rate for diagnosing autism is 83%

Klasifikasi Sentimen Presepsi Masyarakat di Instagram Terhadap Paslon Pilpres 2024 Menggunakan Naïve Bayes Classifier (NBC)

Lionita Asa Akbar — 2024-06-24

The 2024 presidential election has attracted considerable attention as it has become a controversial issue among the public. Various positive and negative opinions generated can potentially turn into rumors. One of the means used by the public to express their opinions is the social media platform Instagram. Data on public opinions on Instagram can be processed into valuable information through sentiment classification. This research conducted sentiment classification on public perceptions towards the 2024 presidential candidates using a naïve Bayes classifier. The study utilized a dataset consisting of 1000 comments. These comments were collected from several posts on the social media platform Instagram discussing the presidential and vice-presidential candidates. The comments were manually labeled by an expert who is a lecturer in the Indonesian language. Classification was carried out after preprocessing and weighting TF-IDF stages. Based on the research findings, the naïve Bayes classifier method showed an accuracy of 82% and an F1-Score of 83.93% obtained from a 90%:10% split of training and testing data. These results indicate that the naïve Bayes classifier method is effective in classifying the sentiments of the public on Instagram towards the 2024 presidential candidates.