ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
INTEGRATION OF FUZZY LOGIC METHOD AND COCOMO II ALGORITHM TO IMPROVE PREDICTION TIMELINESS AND SOFTWARE DEVELOPMENT COST
Get PDFThis study discusses improving the prediction of timeliness and cost of software development using the Constructive Cost Model II (COCOMO II) method and the application of Fuzzy Logic. And aims to obtain accurate time and cost prediction estimates on software development projects to obtain maximum cost results for a software development project. This study utilizes an adaptive fuzzy logic model to improve the timeliness of software development and cost estimates. Using the advantages of fuzzy set logic and producing accurate software attributes to increase the prediction of the time and price of software development. The fuzzy model uses the Two-D Gaussian Membership Function (2-D GMF) to make the software attributes more detailed in terms of the range of values. In COCOMO I, NASA98 data set; and four data projects from software companies in Indonesia were used to evaluate the proposed Fuzzy Logic COCOMO II, commonly known as FL-COCOMO II. Using the Mean of Magnitude of Relative Error (MMRE) and the Pred evaluation technique, the results showed that FL-COCOMO II produced less MMRE than COCOMO I, and the Pred value (25%) in Fuzzy-COCOMO II was higher than COCOMO I. In addition, FL-COCOMO II showed an 8.03% increase in prediction accuracy using MMRE compared to the original COCOMO. Using the advantages of Fuzzy Logic, such as accurate predictions, adaptation, and understanding can improve the accuracy of the timeliness and cost estimates of the software
CLASSIFICATION OF STUNTING STATUS IN TODDLERS USING NAIVE BAYES METHOD IN THE CITY OF MADIUN BASED ON WEBSITE
Get PDFStunting pada balita merupakan masalah gizi kronis yang sedang dialami dunia kesehatan. Anak dengan kondisi stunting mengalami kecenderungan penurunan tingkat kecerdasan, gangguan berbicara dan kesulitan dalam menangkap pembelajaran dalam metode yang biasa. Kota Madiun masih menghadapi tantangan dalam permasalahan gizi stunting. Prevalensi angka stunting tahun 2020 sebesar 10,18 persen atau 814 anak dari total 7.996 yang diukur. Penggunaan data mining dapat digunakan dalam berbagai bidang yang berhubungan dengan sekumpulan data yang banyak. Terdapat beberapa teknik pengerjaan data mining dalam pengambilan suatu informasi, diantaranya adalah klasifikasi. Umumnya klasifikasi status stunting menggunakan indeks TB/U atau tinggi badan dibanding usia. Pada penelitian ini, metode yang digunakan adalah metode naive bayes, yakni metode yang digunakan untuk memprediksi berbasis probabilitas, sistem yang dibangun menggunakan bahasa pemrograman python dan flask sebagai framework-nya. Dari hasil pengujian yang dilakukan menunjukkan bahwa metode naive bayes dapat digunakan dalam melakukan klasifikasi terhadap status stunting pada balita. Algoritma Naïve Bayes yang diimplementasikan ini, memiliki performansi nilai rata-rata yaitu akurasi sebesar 58%, precision sebesar 68%, dan recall sebesar 58% dari hasil pengujian confusion matrix dengan 30% data testing dan 70% data training
EVALUATING USER ENGAGEMENT AND READING BEHAVIOR ASPECTS OF WEB VISITORS BY ANALYZING INDICATORS ON GOOGLE ANALYTICS DATA
Get PDFNowadays, web-based technology is used as a source of information and marketing, one of which is educational institutions. This development unintentionally changes people's reading patterns, from paper to online media. However, user engagement and reading behavior on a web-based system is often overlooked while developing the plan. Understanding these two pillars can help the improvement process become more effective. Politeknik Caltex Riau has an official website that provides information about campus life and an introduction to study programs for prospective students. The information provided is quite complete and precise, yet there are many repeated questions. One example is the web visitors who are interested and asks about the registration steps, but the info is clearly on the website. Therefore, it is necessary to evaluate the understanding of the demographics, engagement, behavior, and events by implementing Google Analytics on the website. From the results, it is known that the visitors are on target. The majority of readers are high schoolers who are actively looking for university information. Many of them use smartphones to surf the website, though it is recognized that most readers do not read the content thoroughly. It can be seen from the total scroll event, which is only high at the beginning and keep decreasing while scrolling down the page. But the bounce and sessions number keep rising. This phenomenon shows that the reader's engagement with the content is shallow, and reading comprehension is vague. In addition, there is also an indication of the effect of smaller screen size with the web design model as one of the reasons for the high jump rate. Thus, further studies can focus on deepening and evaluating web design and evaluating more indicators provided on Google Analytics
KOMPARASI ALGORITMA DECISION TREE, RANDOM FOREST, SVM DAN K-NN DALAM KLASIFIKASI KEPUASAN PENUMPANG MASKAPAI PENERBANGAN
Get PDFPada era globalisasi ini telah mengubah berbagai paradigma dalam sektor bisnis yang berdampak pada meningkatnya persaingan antar maskapai penerbangan. Seiring dengan minat calon konsumen yang terus tumbuh, berbagai cara telah dilakukan oleh setiap maskapai penerbangan dalam meningkatkan tipe atau standar kualitas pelayanan. Dalam mengevaluasi kualitas layanan yang diberikan oleh maskapai penerbangan dari perspektif bisnis, aspek layanan ini harus dievaluasi berdasarkan indikator kepuasan konsumen. Teknik data mining adalah salah satu metode yang dapat digunakan dalam menentukan tingkat kepuasan konsumen. Evaluasi ini dapat dilakukan dengan menggunakan model klasifikasi. Algortima klasifikasi yang digunakan dalam penelitian ini antara lain: Decision Tree, Random Foreset, Support Vector Machine (SVM) dan K-Nearest Neighbor (K-NN). Adapaun tahapan dalam penelitian ini melakukan analisis data, data preprocessing, pembuatan model, melakukan uji model dan mengevaluasi hasil dari model yang dibuat. Dari hasil penelitian yang dilakukan dapat diketahui bahwa Random Forest merupakan algortima klasifikasi yang paling baik dalam studi kasus ini, dengan nilai tingkat akurasi yaitu 96%. Adapun untuk Decision Tree, Support Vector Machine (SVM) dan K-Nearest Neighbor masing-masing memiliki tingkat akurasi 94%, 95% dan 93%
DISEASE DETECTION EXPERT SYSTEM IN WATERMELON PLANTS USING CERTAINTY FACTOR METHOD BASED ON MOBILE
Get PDFWatermelon is one of the fruit commodities currently being developed in West Nusa Tenggara by making Central Lombok Regency as its production center. The problems that are often faced by farmers in watermelon farming, apart from pests, watermelon plants are also often affected by diseases that cause the plants to wilt and then dry, white spots on the flesh, the growth of leaves and small fruit so that it has an impact on decreasing productivity caused by lack of knowledge farmers in recognizing and dealing with diseases in watermelon plants so that they are often mishandled. This research was conducted with the aim of producing an expert system that can be used to detect diseases in watermelon plants and provide solutions for handling them so that watermelon farmers can make prevention and treatment efforts quickly before the disease is transmitted to many other watermelon plants. This expert system was built with the Mobile-based Certainty Factor Method with the Android operating system so that it can be downloaded in the Playstore by watermelon farmers or anyone who needs it so that it is expected to help farmers detect diseases in watermelon plants and provide appropriate handling steps based on related theories
COMPARISON OF LEXRANK ALGORITHM AND MAXIMUM MARGINAL RELEVANCE IN SUMMARY OF INDONESIAN NEWS TEXT IN ONLINE NEWS PORTALS
No full textThe presence of online media has shifted print media for news readers to get information that is fast, accurate, and easy to access. However, the problem arises because the length of the news text makes the reader bored to search for the news as a whole so the news that is obtained will be less accurate. For this reason, it is necessary to have an automatic text summary that was raised in this study as well as to compare the Maximum Marginal Relevance (MMR) algorithm and the LexRank algorithm to the summary of Indonesian news texts on the online news portal graphanews. com. the results of the comparison test of text summarization using f-measure , precision and recall show the performance of text summarization with the MMR algorithm is better where f-measure is 91.65%, precision is 91.08% and recall is 92.23%
SENTIMENT ANALYSIS ON THE TWITTER PSSI PERFORMANCE USING TEXT MINING WITH THE NAÏVE BAYES ALGORITHM
Get PDFSocial media has developed rapidly today, so social media is no longer just a place to interact and socialize but also to express opinions or criticize a particular party or institution. After the incident at the Malang Kanjuruhan stadium in October 2022, many netizens criticized the performance of PSSI as Indonesia's number one organization that oversees football competitions in Indonesia. For this reason, sentiment analysis was carried out on the official PSSI account on Twitter to assess the performance of PSSI by grouping them as Satisfied and Unsatisfied using the Naïve Bayes Classifier. Sentiment analysis took tweets from the official PSSI account and as many as 1000 comments to be used as a dataset. Then preprocessing is carried out in the GATA Framework using the Annotation Removal, Remove Hashtag, Transformation Remove URL, Regexp, Indonesian Steaming, and Indonesian Stopword Removal methods. The results obtained were 82.82% for accuracy, 78.69% for precision, 90.33% for recall, and 0.866 for AUC. With these results, the value obtained is at a good classification level
Strategi Dan Peranan Kitchen Untuk Meningkatkan Oprasional Di Hotel Best Western Premier The Hive Cawang, Jakarta Timur
Get PDFThe hotel kitchen which functions as a production room that processes food ingredients from raw materials to food ingredients that are ready to be served and sold to hotel guests. What must always be kept clean so that the processed food is not contaminated with germs caused by the equipment used or raw materials used in the kitchen area is responsible for food production within the food & beverage department. This organization shows the positions and titles of kitchen staff from the top to the bottom. By looking at the meaning of the function and role of the kitchen in a hotel, and the parts of the kitchen in the hotel and the organization of staff in the hotel kitchen, the author is interested in taking the title: "Strategy and Role of the Kitchen to Improve Operations at the Best Western Premier Hotel The Hive Cawang , East Jakarta".Kitchen hotel yang berfungsi sebagai ruang produksi yang mengolah bahan makanan dari bahan baku sampai menjadi bahan makanan yang siap disajikan dan dijual kepada tamu hotel. Yang harus selalu dijaga kebersihannya agar makanan yang diolah tidak tercemar bibit penyakit yang ditimbulkan dari peralatan yang digunakan maupun bahan baku yang digunakan di area kitchen bertanggung jawab atas produksi makanan di lingkungan food & beverage department. Organisasi ini memperlihatkan posisi dan jabatan petugas dapur dari yang paling atas sampai yang paling bawah. Dengan melihat arti fungsi dan peranan di kitchen di sebuah hotel, dan ba-gian –bagian kitchen di hotel serta organisasi staff di kitchen hotel penulis merasa tertarik untuk mengambil judul: ”Strategi dan Peranan Kitchen Untuk Meningkatkan Operasional di Hotel Best Western Premier The Hive Cawang, Jakarta Timur”
IMPLEMENTATION OF INFERENCE ENGINE WITH CERTAINTY FACTOR ON POTENTIAL DIAGNOSIS OF BRAIN TUMOR DISEASE
Get PDFAn expert system is a system that has the ability of experts or experts who master a particular field to assist in solving problems. Certainty factor (CF) is one of the methods in an expert system that can define the level of certainty based on facts to show the level of confidence of the expert. This study aims to apply a certainty factor (CF) algorithm to solve the problem of diagnosing potential human brain tumors. Because the symptoms that are felt are not necessarily brain tumors, it is necessary to analyze whether the person has the potential to have a brain tumor or not, even if the potential level is. Brain tumor disease is one of several types of dangerous conditions. This disease is caused by the abnormal growth of cells around the brain. This research produces an application that can diagnose potential brain tumor diseases based on symptom input selected by the user. Then the expert system can display the diagnosis results in percentages and solutions from the results of the diagnosis. The study results indicate that the CF method can solve the problem of uncertainty by giving a degree of confidence from an expert and system user. The accuracy test results resulted in an accuracy value reaching 95%. These results indicate that the system can function and can diagnose potential brain tumor diseases properl
DECISION SUPPORT SYSTEM FOR PURCHASING OF MIRRORLESS CAMERA USING WEIGHTED PRODUCT METHOD
Get PDFA mirrorless camera is a camera that does not have a mirror or a pentaprism with the size and workpiece of a compact camera, but has an equivalent capability to a DSLR camera. There are several mirrorless camera manufacturers widely known in the market, among others: Canon, Sony, Fujifilm, Nikon, Olympus, and Panasonic with the advantages of each manufacturer's specifications highlighted to enhance the attractiveness of consumers. With many types of mirrorless cameras in the market, many consumers are still confused in choosing which mirrorless camera is right and suited to their needs. Therefore, it takes a decision support system for the selection of mirrorless cameras using the weighted product method that can generate decisions about mirrorless cameras that comply with the selection of consumer criteria. The criteria used in this study are price, sensor size, megapixel, maximum ISO, and LCD. The results of this study show that the alternative mirrorless camera which has the highest value is the Olympus PEN E-PL9 camera with a value of 0.148