KLIK: Kajian Ilmiah Informatika dan Komputer

Perancangan dan Implementasi UI/UX Website Edukasi Kesehatan Balita Menggunakan Metode Design Thinking

Mufadhal Faraz Addhifa — 2024-08-14

This research examines the design and implementation of user interface (UI) and user experience (UX) on a toddler health education website using a design thinking approach. The main problem studied is the low accessibility and interactivity of toddler health information available online, which leads to a lack of parental understanding of the nutritional needs of toddlers. This research aims to design an intuitive UI and satisfying UX to increase parents' participation and understanding of toddler health information. The research method consists of three main stages: problem identification, design, and implementation, which include data collection through literature review, online survey, and in-depth interviews. The design process followed the design thinking methodology with empirical steps: empathize, define, ideate, prototype, and test. Data obtained from surveys and interviews were used to inform the creation of an initial prototype, which was then tested to obtain user feedback. Evaluation was conducted using usability testing and System Usability Scale (SUS) methods, resulting in an average score of 83.5, indicating an excellent level of user acceptability of the developed design. The findings of this research indicate that the simplified, easy-to-use, and interactive UI/UX design successfully addresses the challenges of accessing under-five health information. The resulting website, known as "Pelita", provides valid and reliable health information content, as well as additional features such as nutrition guidance, health service locations, and consultation services. This research not only resulted in an innovative and relevant design, but also increased parents' understanding and active participation in maintaining the health of their toddlers.

Comparative Spatio-temporal Analysis Using NDVI, NDBI, and SAVI based on Landsat 8/9 OLI (2013, 2018 and 2024)

Yerik Afrianto Singgalen — 2024-08-14

The research on the comparative spatio-temporal analysis of NDVI, NDBI, and SAVI values for Kumo Island, Kakara Island, and Tagalaya Island from 2013, 2018, and 2024 offers insights into environmental dynamics influenced by human activities, particularly tourism. Key findings indicate that NDVI values, reflecting vegetation health, improved across all three islands, with Kumo Island showing the most significant increase from -0.0549 in 2013 to 0.2456 in 2024. NDBI values, indicative of urban development, also rose on all islands. Kumo Island's NDBI increased from -0.8734 in 2013 to -0.6561 in 2024, and Kakara Island's NDBI rose from -0.8838 in 2013 to -0.7183 in 2024. Tagalaya Island saw a more moderate rise in NDBI values from -0.8818 in 2013 to -0.7118 in 2024, suggesting controlled urban expansion. SAVI values, reflecting soil and vegetation conditions, also improved. Kumo Island's SAVI increased from -0.0365 in 2013 to 0.1138 in 2024, Kakara Island's from -0.1161 to -0.0319, and Tagalaya Island's from -0.1652 to -0.0732. These trends indicate effective soil conservation and sustainable land use practices. The findings highlight the dual impact of urbanization and environmental conservation, suggesting that while urbanization progresses, vegetation health and soil conditions are concurrently improving. This underscores the potential for balancing development with ecological sustainability through targeted conservation efforts. Future research should identify specific practices and policies contributing to these positive trends, ensuring economic development and environmental preservation can continue to coexist harmoniously on these islands

Kombinasi Metode MOORA dan Rank Order Centroid dalam Sistem Pendukung Keputusan Pemilihan Supplier Produk Sepatu

Siti Fatimah — 2024-08-14

The selection of shoe product suppliers is an important process in the shoe industry, which requires careful consideration to ensure price, quality, availability, and delivery. In addition, the ability of suppliers to adapt to changing market demands and the ability to collaborate in the development of new products are also important factors. The problems that arise are uncertainty in assessing supplier quality and performance, difficulty in comparing supplier alternatives objectively, and difficulty in calculating various relevant criteria thoroughly. This study aims to apply a combination of ROC and MOORA weighting methods in determining the selection of shoe product suppliers so that it becomes a recommendation for companies in choosing the right supplier for the sustainability of the business run by the company. The combination of ROC and MOORA can provide deeper and more thorough insight into the alternatives evaluated. Using this approach, decision makers can address some of the weaknesses of each method simultaneously, resulting in more optimal and measurable decisions. The use of a combination of ROC and MOORA can help organizations in achieving their goals in a more efficient and effective manner. The recommendation for the selection of shoe product suppliers shows the ranking results of each supplier based on the final value of the MOORA and ROC calculations, the ranking results show rank 1 with a value of 0.093 obtained by Supplier F, rank 2 with a value of 0.0827 obtained by Supplier A and Supplier E, and rank 3 with a value of 0.0458 obtained by Supplier H.

Deteksi Jenis Penyakit Pada Tanaman Padi Menggunakan Yolo V5

Muhammad Deden Miftah Fauzi — 2024-08-14

The problem of disease in rice plants is an obstacle faced by farmers after planting. One of the rice diseases that really worries farmers is disease brown spot, Bacterial Blight, and blast, which causes the leaves to turn yellow prematurely, spots and rice stalks rot. One farmer in Parigi Village whose rice field was attacked by disease suffered a loss of Rp. 6,000,000 to Rp. 8,000,000 per hectare. From all the rice fields of Parigi Village residents. This research aims to detect types of disease in rice plants by applying methods deep learning using YOLO v5 (You only Look Once). The trained model is able to recognize Brown Spot, Bacterial Blight and Blast diseases with a high level of accuracy. In this analysis, two epochs stand out as the best candidates, namely epoch 250 and epoch 200. At epoch 250, the model shows the highest precision (0.802) and a strong mAP@0.5 value (0.702), indicating excellent model performance without overfitting. Meanwhile, at epoch 200, although precision and recall were slightly lower, the highest mAP@0.5:0.95 value (0.393) indicated better generalization ability. Based on these metrics, epoch 150 is identified as the optimal epoch, although epoch 200 also shows strong performance, especially in generalization over a wide range of threshold IoU. The calculation results show the following performance metrics: Precision: 92.5%; Recall: 90.8%; F1-Score: 91.6%; Mean Average Precision (mAP): 93.2%.

Sistem Pakar Deteksi Kerusakan Laptop Menggunakan Algoritma Forward Chaining Dan Backward Chaining

Azis Fikri Marsandi — 2024-08-14

An expert system is an information system that contains the thoughts and knowledge of an expert in solving specific problems. Therefore, expert systems are considered effective and beneficial solutions for diagnosing laptop malfunctions. This application is developed using PHP programming language with MySQL as the database. The data obtained from a field expert and relevant journals on laptop malfunctions is then entered into the database and processed to display analysis results and solutions. The development of this expert system can be used to identify laptop malfunction symptoms, making initial diagnosis easier and providing knowledge to the general public who may not understand the early symptoms of laptop malfunctions. In this study, a software application is designed to assist in diagnosing laptop malfunctions. This application is expected to help users diagnose laptop malfunctions using forward chaining and backward chaining algorithms. Based on expert testing, the confidence level obtained is 87% for the forward chaining algorithm and 81% for the backward chaining algorithm

Analisis Sentimen Terhadap Rangka E-SAF Honda Pada Media Sosial X Dengan Algoritma Naïve Bayes

Akbar Cleary Syafi'i — 2024-08-14

Motorcycles are the best vehicles for traveling when traffic is heavy because motorcycles allow people to save time while going about their daily commute due to their small size and ability to move on narrow streets. An important component in a motorcycle is the motorcycle frame, the motorcycle frame is a useful part to support the weight of these components in the motorcycle vehicle system. However, it is rumored that a motorcycle frame with the E-SAF type has poor quality, so a sentiment analysis is needed. This research aims to collect the number of comments, both positive and negative, from social media users X about the E-SAF framework, and also to determine the accuracy of the application of the Naive Bayes method. The datasets collected from social media X amounted to 756 datasets. Then after going through the stages of data cleaning such as cleansing, tokenize, and stopword filters, the data that can be used for this research amounted to 696 datasets. The next stage is data labeling, namely by dividing the dataset with a ratio of 60:40, namely 60% of the training data totaling 417 datasets that have been manually labeled with the results of 224 negatively charged data, 193 positively charged data while the test data is 40% with a total of 279 datasets which will later be automatically labeled with the implementation of the Naive Bayes method. The next stage is that the test data goes through the data processing stage so that the test data is ready to be implemented into the Naive Bayes method. After implementing the Naive Bayes method, the accuracy obtained was 70.27% with a precision of 76% and also a recall of 79.17%. There was also a true Positive data of 57 and a true Negative data of 21. Data Visualization also displays words that appear frequently in the dataset. Here it shows that the Naive Bayes method is quite effective for the classification of sentiment analysis

Sistem Pakar Diagnosa Penyakit Pada Tanaman Sawi Menggunakan Metode Convolutional Neural Network Berbasis Android

Muhammad Yusuf — 2024-08-14

Mustard greens are one of the vegetable crops that are very easy to cultivate, because they are able to grow in the highlands and lowlands, mustard greens are also susceptible to diseases that can reduce yields and quality, identifying mustard diseases manually is difficult and requires in-depth knowledge of the symptoms. and causes of disease in mustard plants. The aim of this research is to build a system that can be used to identify mustard plant diseases. The diseases used consist of 3 types, namely, leaf miner, leaf rot, and armyworm. With current technological developments that can help farmers minimize errors in determining diseases in mustard plants, Deep Learning is a field of machine learning that utilizes artificial neural networks to solve problems with large datasets. One algorithm that is often used in deep learning systems is Convolutional Neural Network (CNN). The results obtained with the dataset used were with the highest accuracy of 100% train accuracy and 97.78% validation accuracy, and obtained the highest accuracy results using f1-score, namely 95.56%.

Integrating Remote Sensing and Spatial Data for Ecological Sustainability through Spatio-temporal Analysis

Yerik Afrianto Singgalen — 2024-08-14

This research underscores the pivotal role of integrating spatial data and remote sensing technologies within a spatio-temporal analysis framework for regional development planning. Analyzing NDVI, NDBI, and SAVI values from 2013, 2018, and 2024 provided significant insights into vegetation health, urbanization, and soil conditions on Kumo Island. The NDVI values exhibited changes from a minimum of -0.0549, a mid-value of 0.1782, and a maximum of 0.4690 in 2013 to a minimum of 0.2456, a mid-value of 0.8296, and a maximum of 0.9416 in 2024. Similarly, the NDBI values shifted from a minimum of -0.8734, a mid-value of -0.5779, and a maximum of 0.0009 in 2013 to a minimum of -0.6561, a mid-value of -0.4304, and a maximum of 0.0247 in 2024. The SAVI values showed notable changes from a minimum of -0.0365, a mid-value of 0.1245, and a maximum of 0.3814 in 2013 to a minimum of 0.1138, a mid-value of 0.4953, and a maximum of 0.6160 in 2024. These findings highlight the importance of ecological sustainability in decision-making processes, demonstrating how advanced spatial analysis within a spatio-temporal framework can effectively monitor and manage land use changes. The urgency of this research lies in addressing rapid environmental changes and escalating human activities, necessitating timely and accurate monitoring techniques. The study reveals the utility of the NDVI, NDBI, and SAVI indices in assessing vegetation health, urbanization, and soil conditions, which are instrumental in identifying trends and informing sustainable development strategies. The research advocates for the continued use of remote sensing and spatial data to ensure balanced and informed regional development, emphasizing the necessity of sustainable practices to preserve ecological integrity while supporting socio-economic growth. Integrating remote sensing into the decision-making process enhances the accuracy and reliability of spatial data, leading to more effective and responsible regional development

Sistem Informasi Pengelolaan Donasi Sembako Panti Asuhan Menggunakan Metode Simple Additive Weighting

Harianto Saragih — 2024-08-15

In this modern era, the development of technology and information systems greatly affects various sectors, including social sectors such as orphanages. This research aims to develop a Food Donation Management Information System at Orphanages using the Simple Additive Weighting (SAW) method. The SAW method was chosen because of its ability to simplify the complexity of multi-criteria assessments by giving weights to each criterion and determining the best alternative based on the weighted sum of the performance ratings on each attribute. This research applies descriptive quantitative methods by collecting data through observation, interviews, and literature studies. System development uses the Waterfall model which involves the stages of needs analysis, design, implementation, testing, and maintenance. In this case study, seven orphanages in Deli Serdang were assessed based on the criteria of access to location, routine programs, facilities, and number of children. The results show that by applying the SAW method, the developed information system can help orphanage managers in making better decisions, stock monitoring, distribution planning, and optimizing the use of resources. The weight values for the criteria are determined as follows: C1 = 0.1, C2 = 0.2, C3 = 0.3, and C4 = 0.4. The final ranking shows that the best alternative is the orphanage coded A7 with the highest score of 0.855. Thus, this information system is expected to be an effective model for donation management in orphanages, increase transparency and accountability, and support the welfare of children in orphanages through more efficient management of basic necessities.

Analisis Sentimen Terhadap Program Kampanye Desak Anies Di X Menggunakan Naïve Bayes

Dimas Arya — 2024-08-15

Information technology provides many influences including political, economic, artistic, cultural, social and educational. In 2023 the number of internet users in Indonesia will reach 215.63 million. This increase shows how important social media platforms like X are in public discussions. All attention is focused on political campaigns ahead of the Indonesian presidential election in 2024. This research was conducted to determine public sentiment towards two-way campaigns such as "Desak Anies" in X. Using the Naive Bayes algorithm, researchers divided public sentiment into 3 categories, namely positive, negative, and neutral. This shows public opinion and the effectiveness of campaign strategies. This research analyzes public opinion as much as 1401 comment data. The Naive Bayes algorithm is known to be very good at classifying text, followed by text pre-processing which is useful for cleaning text data so that it can be processed further. Next, TF-IDF is used to extract features. Using the Naive Bayes algorithm, sentiment classification shows the distribution of public opinion towards the "Desak Anies" campaign. The results provide useful suggestions for Amin's team in improving their strategy. The classification results show an accuracy of 90%, precision of 96%, recall of 93%, and F1-score of 95%. With more positive comments than neutral and negative comments.

Implementasi Algoritma Genetika Proses Mutasi Differential Evolution Pada Sistem Penjadwalan Mata Pelajaran

Meiliya Cahya Yustina — 2024-08-22

Making schedules at SMAN 2 Purwakarta requires extra effort due to the large number of classes and teachers. The current scheduling system uses two different software namely Asc Timetables and Microsoft Excel. The use of both software is inefficient and error-prone. The two software cannot be connected to each other so that the creation of schedules must be separate and requires a lot of time in synchronization which has an impact on the quality of learning obtained by students. To overcome this problem, an integrated scheduling system is needed that can work automatically and efficiently in one system. This research aims to create a scheduling system that is made automatically with optimization methods. One of the optimization methods is Genetic Algorithm and Differential Evolution. The terminology used is the initial population, calculate fitness, selection, crossover, mutation and iteration. So that the implementation of the system in this study uses a genetic algorithm with a differential evolution mutation process. The method used is using the Software Development Life Cycle (SDLC) with a waterfall development model. The results of the application of the genetic algorithm with the differential evolution mutation process show that the schedule generation meets the limitations for more optimal results. The limitation is that there should be no schedule clashes between teachers in the same hours and days. Based on the test results using SUS, the system gets a score from the SUS calculation which is 69.1. From this score get the weight of the SUS Grade Scale score “B” and Adjective Rating “Good”. So that it requires further development on the system. However, with this category the system is feasible to use if based on SUS testing.

Kombinasi Principal Component Analysis dengan Algoritma K-Means untuk Klasterisasi Data Stunting

Gladys Fouriza Ibanez — 2024-08-22

Dompu Regency in West Nusa Tenggara ranks as the fourth highest regency in terms of stunting prevalence among toddlers in the NTB province in 2022, with a rate of 34.5%. This study utilizes data from the Dompu Regency Health Office in 2023, covering 81 villages and six variables that influence the prevalence of stunting. The objective of this research is to determine and understand the characteristics of areas based on stunting factors in Dompu Regency using the K-Means Clustering method combined with Principal Component Analysis (PCA). The K-Means method produces clusters that represent areas with different characteristics, derived from the data reduction results of PCA, which form the principal components. The optimization of the number of clusters using the Elbow method indicates 3 clusters, consisting of Zone Type 1 with 42 villages, Zone Type 2 with 12 villages, and Zone Type 3 with 27 villages. Subsequently, an evaluation phase using the Silhouette method resulted in 2 clusters: Zone Type 1 with 54 villages and Zone Type 2 with 22 villages, with a Silhouette Score of 0.53, indicating a fairly good cluster structure. PCA produced two principal components with the highest eigenvalues, each explaining 58.7% and 14.28% of the variance, with a cumulative variance of 72.9%. This demonstrates that these two principal components can effectively represent the factors influencing stunting prevalence in Dompu Regency.

Sentiment and Toxicity Analysis of Digital Content Using Perspective, Vader, and TextBlob: Tourism and Birdwatching

Yerik Afrianto Singgalen — 2024-08-22

This research investigates the impact of digital content on specialized tourism activities, focusing on birdwatching, using tools such as Communalytic and RapidMiner. By analyzing 1,021 posts, the study reveals an average toxicity score of 0.13839, with VADER identifying 32.78% negative sentiment and TextBlob identifying 17.07% negative sentiment. Despite these negative interactions, over 50% of the posts convey positive sentiment, highlighting the potential for digital content to foster a supportive and engaging community. The findings underscore the urgent need to address toxicity to maintain a positive online environment, crucial for enhancing educational outreach and participant engagement. This research emphasizes the critical and immediate role of digital platforms, analyzed through Communalytic and RapidMiner, in promoting environmental awareness and conservation, thereby driving the growth and sustainability of niche tourism sectors such as birdwatching. Prompt action is essential to leverage these insights to benefit the environment and local economies.

Analisa Performa Convolutional Neural Network dalam Klasifikasi Citra Apel dengan Data Augmentasi

Dzalfa Tsalsabila Rhamadiyanti — 2024-08-22

Augmentation is creating new samples from an original dataset by applying small random transformations to the original dataset but retaining its labels. This research applies Data Augmentation to the Convolutional Neural Network model for apple image classification. The apple images used are Braeburn apples which have orange to red skin with a yellow background, Crimson Snow apples which have red skin, and Pink Lady apples with bright pink skin and yellow and green hues. There are 675 apple images used, divided into three classes, each with 225 photos. Four augmentation techniques are applied, namely flipping, cropping, rotation, and noise injection. This research carried out six scenarios, namely without augmentation, using each augmentation technique separately and combining two augmentation techniques, which produced the highest accuracy values. From the six scenarios, it was found that the augmentation technique that produced the best accuracy value was noise injection, namely 98.82%, followed by flipping with an accuracy of 72.78%, then rotation with an accuracy value of 68.64% and an augmentation technique that produced an accuracy value. The lowest is cropping, namely 67.46%. The two best augmentation techniques, noise injection, and flipping, were combined and produced an accuracy value of 84.02%. The accuracy value obtained by this combination could be more optimal due to the effect of noise injection, which can erase consistent changes in orientation from flipping. This needs to be improved so that the model can learn consistent features. It is hoped that future research can maximize the effectiveness of augmentation techniques by choosing augmentation techniques that complement each other and suit the characteristics of the data being processed

Penerapan Logika Fuzzy Untuk Peramalan Penjualan Cumi–Cumi Menggunakan Metode Fuzzy Time Series Cheng

Chaterine Agustina — 2024-08-29

The utilization of fishery resources, especially marine, is currently dominated by community fisheries businesses that usually have a small scale. One of these resources is squid. Squid sales sometimes experience ups and downs, where the ups and downs of sales are influenced by several factors, one of which is bad weather. Therefore, the stock on the market is also getting smaller and the high price also makes buyers decrease. The uncertain need for squid sales every month makes it difficult to determine the amount of squid that will be brought in each month. The main objective of this study is to improve the accuracy of squid sales forecasting and to assist warehouse owners in managing production according to market needs. The results of this study are expected to provide a more accurate picture of squid sales trends in the future, so that they can help in making better business decisions. Fuzzy time series is a data forecasting method that uses fuzzy principles as its basis. In this study, all data amounted to 59 data per day for 3 months. The study was conducted using MATLAB software and using the R programming language to carry out the forecasting process. Compared to the previous one, the next sales increased because the forecast was obtained with a fairly rapid increase. The next squid sales forecasting process based on the dataset owned was 403 Kg. By using the MAPE technique, it is known that the prediction process carried out has an accuracy of 82.3%.

Analisis Tingkat Pemahaman Siswa Terhadap Mata Pelajaran Matematika Menggunakan Algoritma C4.5

Faby Apella Prayetno Putri — 2024-08-29

Education is a fundamental aspect of human life that gives every individual in Indonesia the opportunity to develop optimally. Schools as formal institutions have an important role in educating students and shaping a learning environment that is relevant and beneficial for their future. Students' understanding of subjects, especially mathematics, is one of the main indicators of educational success. Given the abstract and multilevel nature of mathematics, many students at the school level experience difficulties in understanding this subject. Therefore, it is necessary to analyze the level of students' understanding of mathematics in order to improve the effectiveness of learning. This research aims to analyze the factors that influence students' level of understanding of mathematics subjects at Pematang Siantar State Junior High School 2 by applying data mining techniques using the C4.5 algorithm. This research also aims to measure the accuracy and performance of the C4.5 algorithm in classifying students' level of understanding, with data analyzed using the Python programming language through the Google Colab platform. The method used in this research involves applying the C4.5 algorithm to process and classify data. This algorithm enabled the researcher to identify learners' comprehension levels with a measured accuracy of 93.83%, indicating that the technique was effectively used in the analysis. Thus, the application of data mining using the C4.5 algorithm in SMP Negeri 2 Pematang Siantar can be an efficient tool in identifying obstacles in learning mathematics and potentially improving the quality of education in the school

Aplikasi Pemesanan Tiket Di Wisata Alam Tranding Camp Menggunakan Metode Periodic Review System Berbasis Android

Louliq Rifky Alfachry — 2024-08-30

The rapid development of information and communication technology has brought significant changes in the tourism sector. One of the innovations that has developed is the use of an android application-based information system to facilitate access to information and needs more quickly, practically and precisely. One that needs it is Tranding Camp. Tranding Camp is one of the natural tourist attractions located in North Sumatra where ticket purchases there still use manual methods without the help of technology. This is certainly less effective, if there are many visitors who come, there will be a queue and of course this limits the ability of ticket managers to monitor ticket inventory and make timely decisions. This study builds an android-based ticket booking application using the Periodic Review System method. The Periodic Review System method is able to solve these problems by calculating predictions to manage ticket inventory efficiently in a certain period. The application built is android-based, this application aims to make it easier for visitors to buy tickets and assist managers in stock management. The results of the study showed an increase in operational efficiency and ticket management at Tranding Camp, supporting the use of information technology to improve the quality of tourism services. From the results of testing carried out with a blackbox testing approach, the system that was built can run well.

Combination of Weighted Product Method and Entropy Weighting in the Best Warehouse Employee Recommendation

Muhammad Waqas Arshad — 2024-08-30

The best warehouse employees are individuals who show exceptional dedication and precision in carrying out their duties. Not only do they ensure that every process, from receipt to delivery, is carried out with high accuracy, but they are also proactive in finding ways to improve operational efficiency. The main problem lies in the proper assessment of employees' technical skills and soft skills, such as rigor, time management ability, and teamwork. Additionally, the selection process can be complicated when it comes to balancing previous work experience and adaptability to new technologies. Without effective assessment methods, the risk of selecting the wrong employee can negatively impact the overall productivity and operational efficiency of the warehouse. The purpose of the study, which combines entropy weighting method with the WP method is an approach that can increase objectivity and accuracy in multi-criteria decision-making. In this combination, the Entropy method is used first to objectively determine the weight of the criteria based on the degree of variation or information contained in the data of each criterion. The weights generated by the Entropy method reflect the importance of criteria based on how much information is provided, assuming that criteria with more variety have more information. Once the weights are determined, the Weighted Product method is used to evaluate and rank alternatives. Based on the results of the recommendation for the selection of the best warehouse employee Hadi occupies the top position in the selection of the best warehouse employee with a score of 0.07194. His position was followed by Putri who got a score of 0.07082, showing a performance that was also very good and only slightly below Hadi. Budi is ranked third with a score of 0.06621, while Deni is ranked fourth and Kiki is fifth with a score of 0.06544 and 0.06524, respectively. The score obtained by each employee shows a relatively small difference, reflecting the fierce competition and high quality of performance among the employees

Hybrid Logarithmic Percentage Change-Driven Objective Weighting and MOORA in Salesperson Performance Assessment

M. Kasyif Gufran Umar — 2024-08-30

A salesperson is an individual who is responsible for selling a company's products or services to customers, either directly or through various marketing channels. The main problem in determining the best salesperson is often related to the complexity of assessing various aspects of performance comprehensively and fairly. While metrics such as sales volume are easy to measure, other important aspects such as the ability to build long-term relationships with customers, customer satisfaction, and contribution to team dynamics are more difficult to measure objectively. The purpose of this study was to combine LOPCOW and MOORA in the performance appraisal of salespeople. This study aims to address several challenges associated with the assessment of sales force performance, including heteroscedasticity in sales data and complexity in evaluating relevant multi-criteria criteria. By integrating LOPCOW to manage heteroscedasticity in sales data and MOORA to consider various aspects of sales force performance, resulting in a weighting method that can provide more accurate and comprehensive performance appraisals. The results of the salesperson performance ranking the 1^st rank with the final value of MOORA 0.35861 with the name Salesperson HS, the 2^nd rank with the final value of MOORA 0.34241 with the name Salesperson FT, and the 3^rd rank with the final value of MOORA 0.3347 with the name Salesperson TS.

Implementasi Metode Certainty Factor Untuk Mendiagnosis Penyakit Malaria

Linda Perdana Wanti — 2024-08-30

Malaria is a disease caused by the plasmodium parasite transmitted through the bite of an infected female anopheles mosquito. This disease often occurs in tropical and subtropical areas, including Indonesia. Symptoms of malaria generally appear between 10-15 days after the bite of an infected mosquito and include high fever, chills, sweating, headache, nausea, vomiting, muscle aches, and fatigue. The first identification is carried out when the patient comes to a health facility and perhaps the disease is already in a severe phase. A system that can identify malaria quickly and precisely is needed for emergencies so that patients receive early treatment, and this is one of the preventive measures to reduce casualties due to malaria. The right system built to overcome this is expert. The certainty factor (CF) method was chosen for the malaria diagnosis expert system because it handles uncertainty in decision-making. CF is a numerical value used to represent confidence or confidence in a hypothesis or conclusion based on existing evidence. The result of this research is that the level of accuracy of expert system diagnosis using the certainty factor method is 98,35% when compared with expert diagnosis. This means that the certainty factor method has been proven to be able to diagnose malaria accurately according to the symptoms experienced by the patient.

Penerapan Metode Analytical Hierarchy Process Untuk Seleksi Usaha Penangkapan Ikan Komoditas Unggulan

Hariati Husain — 2024-08-30

The superior commodity fishing business assistance program is one of the Maritime Affairs and Fisheries Service programs aimed at fishermen in the Gorontalo area. Gorontalo Province has abundant marine resources, the fisheries sector plays a vital role in the regional economy and community welfare. However, fishing businesses often face various challenges, such as fish stock fluctuations, climate change, overfishing, and environmental impacts. Therefore, selecting superior commodities in the fishing business is crucial to ensure the sustainability of marine resources and optimal economic benefits. This research aims to apply the Analytical Hierarchy Process Method in selecting superior commodity fishing businesses in Indonesia. By identifying and evaluating various relevant criteria, it is hoped that this research can provide appropriate and sustainable recommendations for stakeholders in the fisheries sector. The results of testing the application of the AHP method in determining the selection of fishermen's fishing business on behalf of the senses with the alternative Fair on the Criteria for Receiving Assistance, the Alternative Good on the Equipment Ownership Criteria, the Alternative Good on the Criteria of Operational Skills and Total Income obtained a calculation result of 0.7648 > the Size Value namely 0.60, with the conclusion that these fishermen can be accepted as recipients of fishing business assistance. Based on the research results, it can be concluded that the application of the Analytical Hierarchy Process (AHP) method for fishing business selection has proven effective in assisting complex decision making involving various criteria and sub-criteria

Analisis Klasifikasi Teks Pada Kata Slang di Media Sosial Menggunakan Pengolahan Bahasa Alami untuk Trending Topik

Shabrina Rasyid Munthe — 2024-08-30

This study aims to analyze trending topics related to the use of slang words on social media by utilizing natural language processing (NLP) techniques. The main focus of this research is to understand the patterns and trends of slang use on social media platforms, which can uncover important social and linguistic dynamics. The dataset used consisted of tweets in Indonesia and United Kingdom containing slang words, collected from Twitter over a six-month period. The analysis process begins with data cleansing to eliminate irrelevant elements, followed by tokenization and lemmatization to normalize the text. Furthermore, the Support Vector Machine (SVM) and Random Forest classification models are applied to detect and classify slang words in the dataset. The results show that the SVM model achieves a slang detection accuracy of 88% with an F1-score of 0.87, while the Random Forest model achieves an accuracy of 85% with an F1-score of 0.84. Further linguistic analysis showed that 60% of slang words are most commonly used in informal contexts such as everyday conversation, while the other 40% are related to popular culture trends, including music, movies, and fashion. In addition, these findings indicate that there is a variation in the use of slang between Indonesian and United Kingdom-speaking Twitter users, where slang in Indonesian tends to be more creative and contextual, while in United Kingdom it is more standardized and spread globally. This study confirms the effectiveness of both models in classifying slang words as well as identifying key trends in their use on social media. The contribution of this research is important for the study of digital linguistics because it expands the understanding of the dynamics of online slang use, and shows the great potential of NLP applications in linguistic analysis in the digital age. With the results obtained, this research can be a valuable guide for researchers and practitioners interested in understanding the evolution of language on social media, while providing a foundation for the development of more sophisticated and adaptive NLP technologies in handling language variations on digital platforms.

Sentiment and Toxicity Analysis in the Narratives of Wamena's Cultural Heritage: Understanding Community Perspectives and External Influences

Yan Dirk Wabiser — 2024-08-30

This study analyzes digital narratives surrounding Wamena's cultural heritage using the Digital Content Reviews and Analysis Framework, focusing on sentiment, toxicity, and thematic content. The research explores the complex interplay between community perspectives, cultural preservation, modernization, and external influences such as tourism. Toxicity analysis revealed that while most online discourse is supportive, there are instances of harmful language that could disrupt social cohesion, with toxicity scores peaking at 0.50790. These findings highlight the need for continuous moderation to foster a positive digital environment. Sentiment analysis provided a deeper understanding of emotional tones, showing a predominance of positive sentiments and highlighting frustration and dissent related to cultural erosion. The study employed machine learning algorithms for sentiment and toxicity classification, with the Support Vector Machine (SVM) enhanced by Synthetic Minority Over-sampling Technique (SMOTE) demonstrating superior accuracy at 87.29%. Content analysis identified vital themes such as community dynamics, cultural resilience, and the dual impact of tourism as both an economic catalyst and a potential threat to cultural integrity. The findings underscore the importance of maintaining an inclusive digital environment that promotes constructive dialogue and cultural preservation. This framework provides valuable insights for policymakers and community leaders, emphasizing the need for culturally sensitive strategies to manage digital content and support sustainable cultural tourism. Future research should expand this framework to other contexts to enhance the understanding of digital communication dynamics in diverse cultural settings.

Pengembangan Website Edukasi Kesehatan Balita dengan Menggunakan Metode Iterative Incremental

Abidzar Zulfa Arifa Kusyono — 2024-08-30

This study aims to develop a health education website for toddlers in Indonesia that provides relevant and comprehensive information to the community, especially parents. The study identifies issues in providing toddler health information and designs a website that facilitates access to this information. It also explores the technologies and methods needed for developing the website. The research methodology includes the Information Systems (IS) environment, which is divided into actors, organizations, and technology, as well as theories encompassing UML concepts, Laravel, and PHP. An Iterative Incremental approach is used for website development, including stages such as initial planning, planning, requirement, analysis and design, implementation, testing, and deployment. Testing is conducted using the Black Box Testing method. Data collection is carried out through literature studies, online surveys, and interviews with parents and health science students. Literature studies help build the theoretical foundation, provide current data, and identify best practices. Online surveys measure user needs and community awareness regarding toddler health issues, while interviews delve into user preferences and behaviors. The results show that the development of the toddler health education website in Indonesia successfully provides complete and relevant information, facilitating easy access for parents. The implementation using the Laravel framework and PHP programming language, along with testing using the Black Box Testing method, proved effective. Iterative evaluation improved the website's functionality based on user feedback. This study significantly contributes to the development of toddler health education media that meets the needs of the Indonesian community.

Sistem Pendukung Keputusan Menentukan Sales Terbaik Menerapkan Metode Simple Additive Weighting

Rasni Alex — 2024-08-30

In this research, the author uses the SAW (Simple Additive Weighting) Method to determine the best salesperson at company. The SAW method is considered appropriate because it performs a weighted sum of the performance ratings for each alternative on all attributes. This research involves structured steps, starting with determining criteria, alternatives and weights that are relevant to the company context. The next process involves matrix preparation, normalization, and preference calculation. First of all, significant criteria for assessing sales performance have been determined. The sales alternatives to be evaluated have also been identified, and the weight given to each criterion is according to its importance in the company context. Then, a matrix containing sales performance data is created for the next calculation process. Each value in the matrix is normalized so that it can be compared fairly. After the normalization process is complete, the next step is to calculate preferences for each sales alternative. This involves multiplying each normalized value by the appropriate weight, then adding them to get a total preference value for each alternative. From these results, the best alternative is determined through a ranking process. The research results show that the 6th alternative, represented by Rahman Rianto, has the highest score with 0.879, making it the best seller. These recommendations are based on detailed analysis using the SAW Method, which provides valuable insight for company management in making decisions regarding the assessment and development of their sales performance. Thus, this research not only provides an understanding of the best sales performance, but also provides a strong foundation for sustainable decision making in the context of this company.

Analisis Penerapan Logika Fuzzy Pada Sistem Diagnosis Infeksi Saluran Pernapasan Akut Berbasis Android

Ifriandi Labolo — 2024-08-30

Acute respiratory tract infection is a health problem that often occurs and requires a fast and accurate diagnosis to prevent further complications. The high incidence of ARI raises the need for a more accurate and faster diagnosis system. This research aims to analyze the application of fuzzy logic in an expert system so that it can diagnose acute respiratory infections (ARI) in Android-based applications. This expert system uses a fuzzy logic method to handle uncertainty and variability in the symptoms experienced by patients. The method used in this research involves collecting symptom data from patients, which is then processed using fuzzy rules to produce a diagnosis. This system is designed to provide easy access for users via Android devices by facilitating users in entering the symptoms experienced by the patient and providing an initial diagnosis along with the level of confidence in each diagnosis given so that the patient can carry out an initial examination independently before consulting with professional medical personnel. The research results show that the application of fuzzy logic to this expert system is able to provide fairly accurate diagnosis results, seen from the Deviation results. Patients suffering from mild acute respiratory infections with a final score of 4,804. Apart from that, this system also received a positive response from users because of its ease and speed in use. This research concludes that fuzzy logic is effectively applied to expert systems for the diagnosis of respiratory tract infections and has the potential to be further developed to improve health services in the community.

Sistem Pendukung Keputusan Menentukan Mutasi Karyawan Menggunakan Metode ORESTE

Diah Sawitri — 2024-08-30

Employee transfer is one aspect that influences employee performance in a company. PT PLN (Persero) ULP Labuhan is one of the agencies or companies that implement transfers with the aim of improving employee performance. With the increasingly advanced development of technology, every company is competing to keep up with the times. Employee transfers at PT PLN (Persero) ULP Labuhan are still carried out manually and decisions are made only based on individual or group opinions. Therefore, determining which employees will be transferred takes a long time and produces less than optimal results. This study aims to help PT PLN (Persero) ULP Labuhan identify employee transfers that will provide maximum results. In this study, the waterfall model was applied to build a system that includes the stages of analysis, design, implementation, and testing. This research stage was carried out by collecting data through interviews. The data is then input into a decision support system, calculated using the ORESTE method, and stored in a database. This allows decision making with the final results sorted by system from the smallest to the largest value. The results of the study based on the ORESTE method are that Rizka Utami's alternative is the first alternative with a final value of 6.82211. This is because Rizka Utami's alternative meets almost all criteria starting from Performance Assessment, Organizational Needs, Education and Training, Length of Service and Age.

Sentiment Analisis Opini Masyarakat Sistem Ganjil Genap di Twitter Menggunakan Algoritma Naive Bayes Classifier dan Algoritma K-NN

Acep Setiawan — 2024-08-31

This journal's abstract addresses sentiment analysis of public opinion in relation to the odd-even system's implementation on Twitter, utilizing the K-NN and Naïve Bayes Classifier algorithms. The odd-even system was discussed in tweets by Twitter users, which served as the source data. The tweets were categorized into three sentiment categories: positive, negative, and neutral. The analysis's findings indicate that, of the total number of tweets gathered, 391 were categorized as neutral, 50 as negative, and 59 as positive. In addition, it was found that the Naïve Bayes algorithm and the K-Nearest Neighbor algorithm both had an average accuracy rate of approximately 79.72%. This suggests that both algorithms do similarly well when it comes to classifying the sentiment of the tweets under discussion. With respect to sentiment analysis of public opinion on the Twitter platform, this conclusion clarifies the performance comparison between the Naïve Bayes and K-Nearest Neighbor algorithms.

Rancang Bangun Sistem Informasi Akuntansi Berbasis Web Menggunakan Metode Waterfall

Febriani Sulistiyaningsih — 2024-08-31

The use of information systems and information technology today greatly facilitates and helps in daily work. The rise of MSMEs, CVs and Startups in various fields of expertise certainly have their own business financial records. However, most of the company's financial records are still manual, so an accounting or financial information system was designed to facilitate the company's financial records. The creation of this company's accounting or financial information system certainly has several stages that must be passed. The waterfall method, which is one of the software development methods, is used in the creation of this accounting or financial information system. This is because by using the waterfall method, each stage can be done easily and clearly. The results of this study in the form of a company's accounting or financial information system will certainly make it easier for companies to help record company finances.

Pengembangan Sistem Pemantauan dan Pengendalian Jarak Jauh Berbasis IoT pada Penerangan Jalan Permukiman

Ichsan Wasiso — 2024-08-31

Street lighting in residential areas, mainly rural or suburban areas, is vital in improving public safety, comfort, and security. However, many existing lighting systems still need to be more efficient, with high energy consumption and manual monitoring. This causes delays in repairs when damage or disruption occurs. This study aims to develop a Remote Monitoring and Control System for Street Lighting (SITERANG) based on the Internet of Things (IoT) to overcome these problems. The SITERANG system allows real-time and centralized monitoring of street lighting conditions. It offers energy-saving solutions through lighting intensity settings that can be adjusted according to needs, such as at night when community activity is reduced. SITERANG has lighting asset management features, automatic ON/OFF control, and a centralized monitoring system, allowing efficient energy consumption and cost analysis. The test results show that this system has been proven to save energy consumption by up to 49.17% compared to conventional lighting systems, directly reducing operational costs and electricity bills. The implementation of SITERANG offers a sustainable and efficient solution, providing significant energy savings and facilitating the maintenance of street lighting infrastructure in densely populated residential areas.

Analisa Qos (Quality Of Service) Jaringan Wireless Outdoor Client Kgsnet

Ahmad Rivaldi — 2024-08-31

Internet availability is absolute in the digital era like today. The need for fast information makes the internet very important, this need must be supported by the availability of internet that is always available and stable. For that, network performance must be prepared as well as possible in order to get a stable internet connection. Currently, the use of ISP or Internet Service Provider is very common in the business world because it has effective and flexible services. KGSNet is one of several ISPs available. KGSNet offers a stable and fast internet connection, unlimited internet without quota and as much as you like. Currently, some of the customers connected to KGSNet using outdoor wireless devices still experience problems with delays in data delivery and connection instability when accessing data communication services. Therefore, a study was conducted to see the performance of the KGSNet outdoor wireless client service with the Quality Of Service (QOS) method, the Reliability, Maintainability And Availabilty (RMA) method and also the Quality Of Experience (QOE) method to be able to minimize and identify network disruptions early so that the outdoor wireless client network can always be in maximum performance to support KGSNet customer service. The QOS parameters used to measure are bandwidth, throughput, delay, packet loss and jitter, which are then compared with the Telecommunications and Internet Protocol Harmonization Over Network (TIPHON) version standardization. The RMA parameters are MTTF, MTTR and MTBF. While the QOE parameters used are Round Trip Time (RTT).

Vehicle Counting Detection on Roadways using YOLO Algorithm with PyTorch Transfer Learning

Prihandoko — 2024-08-31

This research discusses the implementation of a vehicle counting detection system on roadways utilizing the YOLO (You Only Look Once) algorithm, integrated with PyTorch's transfer learning and fine-tuning techniques. The study is motivated by the rapid increase in private vehicle ownership in Indonesia, which has heightened concerns regarding traffic congestion and accident risks. The primary objective of this research is to develop an efficient vehicle counting system based on Convolutional Neural Networks (CNN), designed to process images and videos. The methodology encompasses a literature review, system analysis, design, implementation, and evaluation. The system is built using YOLOv8, tailored with transfer learning to enhance object detection, focusing on cars. To track and count vehicles, the Centroid Tracker algorithm is employed. A dataset of 1,667 images was used, partitioned into training (1,488 images), validation (118 images), and testing (61 images) sets. The model achieved a detection accuracy of 97.92%, though minor detection errors were observed. In video-based testing, the system effectively detected and tracked vehicles, assigning unique IDs to individual cars. In conclusion, the YOLOv8-based model, combined with the Centroid Tracker algorithm, demonstrates strong performance in detecting and counting vehicles, offering potential contributions to traffic monitoring systems and providing a foundation for more sophisticated applications in future research.

Sistem Aplikasi Presensi dengan Foto Selfie dan Koordinat GPS Menggunakan Framework Laravel dan Metode Waterfall

Suhanda Saputra — 2024-08-31

This research focuses on designing a system to overcome the problem of employee attendance when working outside the office area. The scope of this research includes designing and developing a comprehensive Android application that includes rules and information packages. The Waterfall development method is used to ensure a systematic and sequential approach throughout the system life cycle. The proposed system aims to provide presence information and can increase the ease and accuracy of employees in taking attendance when working outside the office area. Apart from taking attendance, employees also have access to various features through this application, including leave and sick leave, attendance history, late attendance and employee profiles. Apart from that, to access as an admin of this application, an admin can access the features in the application's web panel. In this case the admin can carry out monitoring, approve permits (leave) and illness, add employee data, add customer data, attendance location points and summarize attendance reports. The expected result of this research is the successful design and development of a robust, website-based employee attendance application system. This system will effectively assist employees in conducting attendance, providing real time and accurate information. The usability, functionality, and efficiency of the system will be evaluated, and user feedback will be collected to assess its effectiveness.