Sistem Infomasi

Browse

Recent Submissions

Now showing 1 - 20 of 270
  • Item
    SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN KARYAWAN TERBAIK MENGGUNAKAN METODE PROFILE MATCHING (STUDI KASUS : LABERSA GRAND HOTEL AND CONVENTION CENTER)
    (Elfitra, 2023-11) Hutahaean, Yolli; Sukamto
    Employees are one of the most important assets owned by a company in its efforts to maintain survival, development, the ability to compete and earn profits. Good performance from each employee will certainly make the company benefit from the smooth running of the company. To maintain and improve the quality of each employee, one way is to carry out an assessment to select the best employees. This research aims to build a decision support system for selecting the best employees using the profile matching method with a case study of the Labersa Grand Hotel and Convention Center. This research uses three criteria, namely general, leadership and assessment over the last 6 months, each criterion has sub-criteria. The sub-criteria of the general criteria are quality of work results, quantity of work results, discipline and effectiveness as well as responsibility for work. The sub-criteria of one of the leadership criteria are problem handling and decision making, loyalty and caring, honesty, coordination and cooperation, planning and creation and accountability. The sub-criteria for the assessment criteria for the last 6 months are receiving a warning letter, being absent without permission, permission, illness and receiving a written award from the company. This decision support system produces the best employee ranking with the highest score being alternative A137 with a score of 4.87 and the lowest score being alternative A71 with a score of 3.99. This research has succeeded in building a decision support system for selecting the best employees using the profile matching method, and can help and make it easier for Labersa Grand Hotel and Convention Center in selecting the best employees.
  • Item
    SISTEM PAKAR DIAGNOSA PENYAKIT DAN HAMA PADA TANAMAN PORANG (Amorphophallus muelleri Blume) MENGGUNAKAN METODE DEMPSTER-SHAFER
    (Elfitra, 2023-11) Gani, Suherman Abdul; Fitriansyah, Aidil
    The porang plant (Amorphophallus muelleri Blume) is a type of Indonesian tuber plant that belongs to the family of Araceae plants. In recent years, the demand for porang in the world and domestic markets has continued to increase, this has become a public interest in planting porang because it has quite a large potential opportunity. However, like other plants, porang cultivation cannot be separated from pests and diseases. Porang farmers must be able to quickly identify the types of pests and diseases that attack crops to minimize damage. A quick way that can be used to identify diseases and pests in porang plants is to use a tool in the form of an expert system. One method that can be used in expert systems is Dempster-shafer. This method can help in diagnosing diseases and pests based on the entered symptoms. This study used 3 pest data, 4 disease data, and 22 symptom data on porang plants. This study involved 2 experts with 12 different case data in the field. The results of this study are based on a comparison of expert diagnoses with systems, there are 11 appropriate diagnostic data.
  • Item
    ANALISIS DATA MINING UNTUK MENENTUKAN STRATEGI PENJUALAN PRODUK MENGGUNAKAN ALGORITMA FP-GROWTH (STUDI KASUS : MAZAYA OLEH-OLEH PEKANBARU)
    (Elfitra, 2023-11) Muliyani, Sri; Mahdiyah, Evfi
    Mazaya Souvenir Shop Pekanbaru is a company that operates in the culinary sector to be ranked first in the largest culinary industry in Pekanbaru, starting from processing, raw materials, packaging quality and distribution activities. This shop is experiencing difficulties in determining market strategies, one of which is in arranging products purchased simultaneously. The aim of this research is to carry out data mining analysis to determine product sales patterns using the Fp-Growth algorithm. The data used to carry out calculations using the Fp-Growth algorithm must go through several stages such as preprocessing the data, determining minimum support and confidence, determining the frequent itemset header, forming an fp-tree, creating a conditional pattern base based on the fp-tree, and generating frequent itemsets. In this study, a minimum support value of 1% and a confidence value of 80% were used. The research results showed that there were five rules, two frequent itemsets that had a confidence value of ≥80%, namely the products Risol Mayo Lumer and Talam Durian, Risol Ayam and Talam Durian, Red velvet and Talam Durian, Talam Durian and Risol Ayam, Talam Durian and Risol Mayo Lumer.
  • Item
    STEMMING BAHASA MELAYU OCU KAMPAR MENGGUNAKAN ALGORITMA LEVENSHTEIN DAN ANALISA MORFOLOGI
    (Elfitra, 2023-11) Khairani, Natasya; Bahri, Zaiful
    The Ocu language is among the dialects utilized by the residents of Kampar Regency for communication. The indigenous community of Kampar has a responsibility to preserve the sustainability of the Ocu language as an effort to maintain the identity and distinctive characteristics of the Kampar region. Terms in the Ocu language have many affixes in the arrangement of words, resulting in change in words and meanings. This research aims to assess the process and accuracy level of Ocu Kampar Malay stemming. This study used Levenshtein algorithm and morphological analysis, which is created by applying UML diagrams, PHP programming language and MySQL database. Based on the results of tests that have been carried out on Ocu language document files consisting of 2.262 words, obtained an accuracy rate of 71.37%. The majority of errors in testing are caused by root words not found in the dictionary and overstemming
  • Item
    ANALISIS VALUE CHAIN UNTUK PEMATAAN STRATEGI SISTEM INFORMASI MENGGUNAKAN METODOLOGI WARD AND PEPPARD (STUDI KASUS: MAN 1 PEKANBARU)
    (Elfitra, 2023-11) M, Muna Putra Yuda; Risanto, Joko
    MAN 1 Pekanbaru is a secondary level of formal education in Indonesia, equivalent to Senior High School (SHS), located in the city of Pekanbaru, Riau. The strategic information system planning uses the Ward and Peppard method, aiming to win and stay ahead of competition for MAN 1 Pekanbaru. This research employs SWOT analysis, value chain analysis, and PEST analysis to gather internal/external data, as well as the McFarlan matrix to depict the application portfolio. Based on the SWOT analysis results, MAN 1 Pekanbaru is positioned in quadrant 1, supporting an Aggressive strategy. The analysis indicates that the school can leverage its resources, competencies, or advantages to exploit existing opportunities. The value chain analysis identifies and links various strategic activities within the school, analyzing activities that create value both from within the school and externally. The PEST analysis results suggest that MAN 1 Pekanbaru can enhance its use of technology in education. The school can design a strategy to integrate this technology into their curriculum and improve the student learning experience. Meanwhile, the McFarlan matrix generates eight proposed information systems that should be developed and enhanced in the future.
  • Item
    PREDIKSI HARGA EMAS DENGAN METODE LONG SHORT-TERM MEMORY
    (Elfitra, 2023-11) Sholeh, Muhammad; Alfirman, Alfirman
    Predicting gold prices holds significant importance in the realms of finance and investment, enabling market participants to make wiser decisions amidst gold price fluctuations. The training results of the Long Short-Term Memory (LSTM) model displayed remarkable performance, with a Mean Squared Error (MSE) value of 0.0034 and a Mean Absolute Percentage Error (MAPE) value of 7.13%. According to the MAPE criterion, this LSTM model's predictive capabilities can be categorized as highly accurate. These outcomes affirm the potential of the LSTM model in providing precise gold price predictions, aiding market participants in more informed decision-making. The forecasted gold prices using LSTM from January 1, 2023, to March 1, 2023, indicate a daily decrease in gold prices. Consequently, a prudent approach for market participants would be to engage in future gold purchases during the predicted gold price decrease in 2023.
  • Item
    SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN PENERIMA BANTUAN RUMAH LAYAK HUNI MENGGUNAKAN METODE ANALYTICAL HIERERCHY PROCESS
    (Elfitra, 2023-11) Septiani, Monika; Sukamto, Sukamto
    The problem of poverty in Indonesia is very urgent to be addressed. Especially in areas that are difficult for the government to reach, one of which is Kubu Babussalam District, Rokan Hilir. One of the general characteristics of the physical condition of poor people is that they do not have adequate access to basic environmental infrastructure and facilities, with the quality of housing and settlements being far below adequate, as well as uncertain livelihoods. Almost all government departments spend funds to help reduce poverty. Especially regarding houses that are unfit for habitation. In selecting a livable house, what is needed is criteria. Criteia are requirements for selecting a habitable house. The aim achieved is to create a decision support system that can help and provide information for recipients of livable housing assistance. The problem solving method used in this system is by using the Analytical Hierarchy Process (AHP) method. In this method, data collection, data processing, data analysis, system design, implementation and system testing will be carried out. Data collection and processing was obtained from observations, interviews and questionnaires totaling 60 data. Then the data analysis carried out is determining the eigen criteria and subcriteria, determining the calculation results between the eigen criteria and sub-criteria and finally ranking. The results obtained are that the system can produce alternative ranking values for potential recipients of livable housing assistance which have been ranked from 3 highest to lowest with ranking values namely 0.485, 0.474 and 0.474.
  • Item
    PEMETAAN SKENARIO (MAPPING SCENARIO) COBIT 5 DALAM AUDIT SIKUDA BKPSDM INHIL
    (Elfitra, 2023-11) Dibah, Jihan Para; Risanto, Joko
    BKPSDM Indragiri Hilir Regency launched an Administration Management Information System for a reliable, accurate, orderly and informative Database in the service of Personnel Data Information. This personnel administration information system is known as SIKUDa (General Personnel Information System and Data). In reality, the implementation of the SIKUDa application does not always run smoothly. Since its launch, SIKUDa has never received a capability level measurement, so it is not yet known with the use of SIKUDa whether the needs of ASN have been met, so it is necessary to conduct an Information System Audit on SIKUDa. The COBIT 5 framework was chosen because it can draw what to do in the development of SIKUDa. Data collection in the form of questionnaires using the Likert scale was distributed to respondents who had been mapped using the RACI Chart. The research focused on the APO4, BAI04, and BAI05 domains. Based on results, it can be concluded that the level of capability achieved by SIKUDa at UPT Puskesmas Kotabaru is level 1 for APO04, BAI04, and BAI05.
  • Item
    PENERAPAN DATA MINING DALAM PREDIKSI PENGANGGURAN BERDASARKAN TINGKAT PENDIDIKAN MENGGUNAKAN ALGORITMA BACKPROPAGATION NEURAL NETWORK
    (Elfitra, 2023-11) Hasanah, Hasanah; Indra, Zul
    Unemployment is still widely found in Riau province. There are many factors that influence unemployment, one of which is the level of education completed. Therefore, unemployment prediction is needed to overcome the problem. Prediction is done by using backpropagation neural network method. The purpose of this research is to determine the best model in predicting unemployment based on education in Riau. The best model is determined from the evaluation results of the smallest mean squared error (MSE) and mean absolute percentage error (MAPE) values. From the test results, the best architecture model is obtained, namely model C with an architecture of 8 input layers, 4 hidden neurons, 1 output layer (8-4-1) with 0.01 learning rate. From the evaluation result, model C produces MSE value of 0.0027 and MAPE value of 16.99%. Thus, model C is able to predict unemployment based on education level in Riau well and can be used for further prediction of unemployment based on education.
  • Item
    TOPIC MODELLING ADUAN MASYARAKAT PEKANBARU MENGGUNAKAN METODE LATENT DIRICHLET ALLOCATION
    (Elfitra, 2023-11) Hafifah, Hafifah; Sastria, Gita
    The people of Pekanbaru can submit complaints to the Pekanbaru City Government through SP4N-LAPOR via the website or application. Based on data from this system, it is evident that the issues faced by the community still occur frequently. This is confirmed by the recurring nature of similar complaints over time, indicating that the issues have not been maximally resolved, and the relevant agencies do not have a deep understanding of the trends in community issues. Therefore, this research will model topics using Latent Dirichlet Allocation (LDA) to group the data into topics that represent the most frequently emerging issues. By understanding these topic trends, the government and relevant agencies can be more responsive in addressing emerging problems. The data used consists of 345 text data obtained from the Pekanbaru City Information and Communication Office. The collected data then undergoes preprocessing stages, including text cleaning, tokenization, normalization, stopword removal, and stemming. After preprocessing, word weighting is performed using Term Frequency-Inverse Document Frequency (TF-IDF). In building LDA, coherence scores are used to determine the most optimal number of topics for topic modeling. Experiments are conducted with 50 and 100 iteration tests. Different numbers of topics, namely 3, 5, and 7, are used for each iteration test. Based on these experiments, the analysis results show that 5 is the most suitable number of topics. The topics identified are, These topics are public services, order, Covid-19, public services, government assistance, and data management.
  • Item
    EVALUASI PERFORMA SISTEM PENDUKUNG KEPUTUSAN METODE MABAC (STUDI KASUS: PEMILIHAN MAHASIWA BERPRESTASI FMIPA UNIVERSITAS RIAU)
    (Elfitra, 2023-11) Masyithah, Dhitha An’nissa; Id, Ibnu Daqiqil
    Decision support systems generally apply criteria weighting as an important stage in the resolution process. The method that applies weighting criteria is Multi-Attributive Border Approximation Area Comparison (MABAC). However, the weighting of criteria is mostly done subjectively by the decision maker or team involved. In the case study of selecting outstanding students, there are 10 variations in the weight of the criteria. This makes it difficult to determine the best criteria weight values. Therefore, an evaluation was carried out on the MABAC ranking results based on 10 variations of criteria weights using distance-based methods, namely Manhattan Distance and Euclidean Distance. The method is used to measure the distance between the MABAC ranking and the actual ranking. If the resulting distance is small then the ideal solution can be identified in determining the best weight. The ranking evaluation results of the two methods show that weight 6 has the smallest distance. This means that weight 6 is the best weight because it produces a ranking that is close to the actual ranking
  • Item
    PEMETAAN KEBUTUHAN LAYANAN PADA DINAS PARIWISATA PROVINSI RIAU BERBASI DOKUMEN RENSTRA
    (Elfitra, 2023-11) Wandira, Ayu; Risanto, Joko
    Enterprise architecture planning aims to plan or manage all aspects of IS/IT and business processes in an agency or company. The Riau Province Tourism Office is one of the agencies that is a factor in economic growth and regional development which plays a role in managing tourism resources and promoting tourist destinations. However, the challenges faced by the Tourism Department are that system implementation is not optimal and there is a lack of integration between systems. Therefore, mapping business service requirements is needed to find out services that require enterprise architecture planning. This research produces two business/service needs, namely, improving tourism destination management and increasing tourism promotion.
  • Item
    SISTEM PENDUKUNG KEPUTUSAN PENENTUAN KELANJUTAN MTRA BISNIS PADA PT. AJB MENGGUNAKAN FUZZY MADM METODE WEIGHTED PRODUCT
    (Elfitra, 2023-11) Qomairah, Annisa; ID, Ibnu Daqiqil
    PT. AJB, a company that operates in the transportation rental sector and a company that collaborates with companies in the mining sector. This company has also started with 9 companies. Continuity of business partners is determined by several criteria such as timeliness of payments, number of transactions, responsibility and company image. PT. AJB currently determines the fate of business partners just by looking at transportation reports. The assessment is only subjective, so it is only based on company observations. This can make the assessment of business partners uneven and less effective. A computer-based system that is used to make decisions can make it easier to determine the continuation of business partners and eliminates the need for discussions. The method used is the Fuzzy MADM Weighted Product method. The research results show that with = 0.1394 is the highest rating so that the alternative is considered the best and is recommended as a continuing business partner.
  • Item
    DETEKSI BENIH PADI MENGGUNAKAN METODE YOU ONLY LOOK ONCE (STUDI KASUS: UPT PSBTPH PROVINSI RIAU)
    (Elfitra, 2023-11) Mujahidah, Aliya Izzati; Id, Ibnu Daqiqil
    Seeds circulating in Indonesia are required to have seed eligibility certificates regulated by PERMENTAN No. 12 of 2018. One of the processes to obtain seed feasibility certification is the purity analysis laboratory test. In this process, the seed analyst sorts working samples of seeds that contain several components, including pure seeds and non-pure seeds. The sorting is done manually by identifying the seeds in the working samples based on their morphological appearance. In this study, object detection of rice seeds was conducted using the "You Only Look Once (YOLO)" algorithm. YOLO is a real-time object detection algorithm. The method used is transfer learning with the pre-trained YOLOv5s model, which is one of the models from YOLO version 5. The dataset consists of 235 photos of working examples of rice seeds, with two classes labeled as rice and non-rice. The evaluation results of the overall model performance are as follows: precision of 0.908, recall of 0.808, mAP@0.5 of 0.859, and F1_Score of 0.85.
  • Item
    PENERAPAN FORECASTING PADA PENJUALAN MOBIL SHOWROOM MITSUBISHI MENGGUNAKAN METODE DOUBLE EXPONENTIAL SMOOTHING
    (Elfitra, 2023-11) Rinaldi, Aldo; ID, Ibnu Daqiqil
    PT. Suka Fajar, Pekanbaru district, has a fairly high level of sales in a year, so a sales strategy is needed for the future. Therefore, predictions are made using the Double Exponential Smoothing method, with the results of the research expected to be a decision support for stakeholders in providing product stock for the progress of business processes. The initial data obtained in this study is car sales data from January - December 2022 with a total of 34 items sold at PT. Suka Fajar Pekanbaru. Use of forecasting in Mitsubishi showroom car sales using the Double Exponential Smoothing method with an alpha value of 0.1 to 0.9 produces a different predictive value for each item. This difference is caused by differences in the amount of data each month on each item (car). The Dakar Ultimate 4X4 A/T item produces the smallest MAPE error value with an alpha of 0.6, which is 17% and the prediction result for January 2023 is 9.
  • Item
    ANALISIS MANAJEMEN RISIKO PENGGUNAAN SISTEM INFORMASI PERPUSTAKAAN UNIVERSITAS RIAU MENGGUNAKAN METODE OCTAVE ALLEGRO
    (Elfitra, 2023-10) Azzahra, Restu; Andriyani, Yanti
    In recent years, the Riau University library has experienced events that have disrupted library operations. For this reason, risk management analysis needs to be carried out with the aim of guiding risk management in the future. This paper presents the findings of a risk assessment at Riau University Library using the OCTAVE Allegro methodology. There are four phases and eight stages in OCTAVE Allegro which have been equipped with worksheets and questionnaires that facilitate researchers. The results showed that membership data and collection data are the most important assets for the library. There are 6 impact areas that become risk measurement criteria, namely Reputation and Customer Confidence, Financial, Productivity, Safety and Health, Fines and Legal Penalties, and IT Risk. Based on the relative risk value, Riau University Library found 5 risks that require action to minimize the risk.
  • Item
    LAYANAN AKADEMIK MENGGUNAKAN METODE FORWARD CHAINING BERBASIS APLIKASI CHATBOT (STUDI KASUS: SMK NEGERI 2 PEKANBARU)
    (Elfitra, 2023-10) Putra, Rafi Perdana; Bahri, Zaiful
    A chatbot is a digital communication application that has the potential to facilitate users in finding information. The limitation of oral communication has been one of the challenges for the academic staff at SMK Negeri 2 Pekanbaru in obtaining information such as scholarships, internship programs, E-repor, and others. This research uses the forward chaining method. With this method, the chatbot can provide answers related to the services of SMK Negeri 2 Pekanbaru based on the collected facts. There are 8 categories in this research that will be incorporated into the application system using forward chaining reasoning techniques. The results of this research show that the forward chaining method has been successfully applied to the academic service chatbot, providing information based on the responses given by the chatbot.
  • Item
    PENGELOMPOKAN KEMISKINAN DI PROVINSI RIAU DENGAN MENGGUNAKAN METODE K-MEDOIDS
    (Elfitra, 2023-10) Wijoanda, Putra Heru; Alfirman, Alfirman
    Poverty is a long-standing problem in Indonesia, and it has been an issue during almost all periods of government. Poverty can cause serious problems in the future when the government does not pay special attention to it. The inability of people to meet their standard of living, lack of access to education and employment will lead to recession. The quality of human resources affects low income productivity. Efforts to fight poverty must be carried out comprehensively, covering all areas of people's lives and coordinating their implementation. Poverty has always been a problem for Indonesia, until now there is no sign that it will stop. Therefore, research was conducted on poverty grouping in Riau province using the K-medoids method. It is expected that the results can provide additional information in optimizing poverty reduction in Riau Province. The research was conducted by forming 2 to 4 clusters, then the best results were obtained where the value close to 1 is the best value, namely in the formation of 2 clusters with 0.314477 in cluster 1 consisting of 3 districts Kuantan singingi, Indragiri Hulu, and Indragiri Hilir with high poverty rates while in cluster 2 consisting of Pelalawan, Siak, Kampar, Rokan Hulu, Bengkalis, Rokan Hilir, Kepulaun meranti, Pekanbaru city, and Dumai city with poverty rates.
  • Item
    IMPLEMENTASI METODE SINGLE MOVING AVERAGE DALAM PERAMALAN PENJUALAN ACCESSORIES HANDPHONE DI RETRO CELLULER BANGKINANG
    (Elfitra, 2023-10) Aulia, Nurul; Alfirman, Alfirman
    Mobile accessories have many different types and functions to be able to help perfect the performance of the phone. Retro cellular Bangkinang is one of the places to provide sales of cellphone accessories. The store sells many types of cellphone accessories that make it difficult to control old inventory that is not sold. With so many types of cellphone accessories, the stock of goods is out of control. This is caused by an error in increasing the number of goods to the accumulation of stock of goods. Product forecasting is a form of inventory control so that the amount of inventory can be controlled. The method used to forecast sales of HP accessories using the single moving average method. The calculation data used is sales data for the last 12 months. The calculation is carried out using periods 5, 7, and 9. Then to measure the error rate that occurs after calculations using equations from MAD, MSE, and MAPE. The forecasting results can be in the form of the number of sales of goods that will be sold in June 2023. The smallest measuring value of the forecasting error rate is forecasting on PowerBank goods with MAD values of 0.99, MSE 1.42, and MAPE 4.24. The measurement value of the largest forecasting error rate is in the type of Case Motive goods with a value of MAD 218.51, MSE 59979.48, and MAPE 74.20.