Jurnal Transformatika
Not a member yet
319 research outputs found
Sort by
Prediksi Kepuasan Mahasiswa Terhadap Pelayanan Akademik Menggunakan Model Decision Tree
Full text linkPerguruan Tinggi merupakan sebuah lembaga pendidikan dimana didalamnya mempunyai tugas dalam pelayanan akademik. Kepuasan mahasiswa dalam memperoleh pelayanan akademik merupakan hal yang sangat penting dalam menilai sebuah Perguruan Tinggi. Tujuan dari penelitian ini adalah agar dapat mengetahui bagaimana tingkat kepuasan mahasiswa program studi Teknik Informatika dalam hal memperoleh pengajaran oleh dosen, mengenai sarana dan prasarananya. Metode klasifikasi dan prediksi yang digunakan pada penelitian ini diambil dari salah satu model Decision Tree yaitu algoritma C4.5. Algoritma C4.5 berfungsi untuk mengekspolari data, menemukan hubungan tersembunyi antara sejumlah calon variabel input dengan sebuah variabel target. Hasil pengukuran yang didapat adalah nilai akurasi sebesar 94,23%. Nilai recall dari setiap kelas sebesar 94,12% untuk kelas Ya dan 100% untuk kelas Tidak. Sedangkan nilai presisi setiap kelas adalah sebesar 100% untuk kelas Ya dan 25% untuk kelas Tidak
Penerapan Data Mining Dalam Strategi Bisnis Menggunakan Algoritma Apriori
Full text linkStrategi yang diambil dalam mengelola bisnis kuliner sangat penting dalam memenangkan persaingan. Data transaksi penjualan dari Chicken Brotus selama tahun 2016 hingga 2023 memberikan gambaran penting mengenai pengelolaan strategi pemasaran dan manajemen persediaan. Dalam penelitian ini, algoritma Apriori digunakan untuk mencari hubungan antar item penjualan dalam satu dataset. Hasil pengujian terhadap 11.123 record data, dengan kombinasi nilai minimum support 8% dan minimum confidence 25% serta minimum support 10% dan minimum confidence 25%, menghasilkan pola analisis frekuensi dan aturan asosiasi. Analisis menunjukkan bahwa item terlaris adalah es teh jumbo dengan nilai support 46,5%. Selain itu, ditemukan bahwa jika konsumen membeli ayam geprek biasa komplit, maka 63,1% kemungkinan mereka juga akan membeli es teh jumbo. Hasil ini memberikan wawasan berharga bagi Chicken Brotus untuk mengembangkan strategi pemasaran dan pengelolaan persediaan yang lebih efektif dan efisien. Dengan demikian, Chicken Brotus dapat meningkatkan penjualan dan kepuasan pelanggan melalui strategi yang didasarkan pada data yang akurat dan analisis yang mendala
Analisa Forensik Kontainer Podman Terhadap Backdoor Metasploit Menggunakan Checkpointctl
No full textContainer systems are type of virtualization technology with isolated environment. The isolated environment in container system does not make cyber attacks impossible to occur. In this research, containers in which a cyber incident occurred were forensically tested on the container\u27s memory to obtain digital evidence. The forensic process is carried out using standards from NIST framework with the stages of collection, examination, analysis and reporting. The forensic process begins by performing a checkpoint on the container to obtain information from the container\u27s memory. In Podman the checkpoint process is carried out on one of the containers and will produce a file in .tar.gz form, where this file contains the information contained in the container. After the checkpoint process is complete, forensics is then carried out by reading the checkpoint file using a tool called checkpointctl. Forensic results showed that the container was running a malicious program in the form of a backdoor with a PHP extension
Bootstrapped Aggregating Optimization in Random Forest for Hepatitis Risk
Full text linkThis research optimizes the Random Forest model with Bootstrapped Aggregating to predict hepatitis risk. The global significance of hepatitis as a health problem is underscored by its widespread impact. Using a Kaggle dataset comprising 596 records and 20 attributes, including age categories and gender, the study identifies limitations in predicting hepatitis risk. Through hyperparameter optimization, such as adjusting the number and depth of trees, the Random Forest model with bootstrapped aggregate achieves an accuracy of 96%, surpassing the standard model\u27s 88%. The results demonstrate a significant improvement in precision, recall, and f1 score, particularly in reducing false negatives. The conclusion highlights the practical potential of this model for a more accurate assessment of hepatitis risk. While acknowledging limitations related to the size of the dataset, these findings provide a foundation for developing predictive models in the context of hepatitis risk, emphasizing the importance of employing ensemble techniques to improve model performance
Decision Tree Implementation in IT Job Recommendation System
Full text linkEmployment is the primary activity that humans engage in to generate income. With the advancement of technology and research, there are many new job opportunities leading to confusion in choosing a job path. This leads to individual confusion in making job choices. Ignorance of one\u27s own talents and personality, as well as ignorance of the various options available, can be the source of this ignorance. This research aims to develop a Decision Tree model to assist users in determining the appropriate IT field. The system uses AI Project Cycle and data processing tools such as Google Collaboratory, which is based on Python programming language. The results show that the Decision Tree algorithm can be applied to recommend jobs in the IT field to help users find suitable fields in the IT field
DECISION SUPPORT SYSTEM PEMBUKAAN LOKASI BARU JASA SERVIS MOTOR BERBASIS PROFILE MATCHING
Full text linkAs the volume of motorbikes increases, the number of motorbike service outlets also increases. However, not all service places get customers equally, from the customer\u27s side various variables really determine visits such as location, level of spare parts availability, level of service to consumers and price. Likewise, in terms of service owners, when opening a new service location, they need to pay attention to various variables such as proximity to residential areas, number of competitors, capacity of passing vehicles, and proximity to spare parts suppliers. To collaborate several influential variables to produce a decision regarding the right place, a method is needed that is capable of carrying out calculations to produce a ranking of locations that will have an influence. One method that can be offered is profile matching. This method performs by finding the difference between the weight value determined at the beginning and the input value for each location object. The ranking results of all location objects can be used as alternative locations for appropriate service locations.
Korelasi CO2 Terhadap Suhu dan kelembapan Dengan Multivariate Linear Regression
No full textSekarang ini keadaan udara di daerah perkotaan sudah sangat tercemar oleh polusi. Semakin banyak gas CO2 yang mulai menyebar ke udara dapat menyebabkan meningkatnya suhu udara.. Hal ini dikarenakan bahwa CO2 dapat meningkatkan suhu di permukaan bumi. CO2 mempunyai peran yang dapat menyebabkan pemanasan global karena gas CO2 mempunyai di udara bebas dan dapat menyerap panas Matahari sehinggs suhu Bumi meningkat dampak pencemaran udara seperti asap kendaraan, asap rokok, asap dari pembakaran pabrik, dan kontribusi terbesar dalam pemanasan global mempunyai pengaruh sebesar 50% dan mempunyai lama hidup 50 200 tahun di atmosfer. Peningkatan suhu udara dan konsentrasi CO2 merupakan masalah yang sering terjadi pada daerah perkotaan dimana salah satunya adalah meningkatnya jumlah kendaraan bermotor sehingga konsentrasi CO2 juga ikut meningkat. Dengan melihat korelasi CO2 Terhadap Suhu dan kelembapan Dengan mengunakan Multivariate Linear Regression, kita dapat melihat bagaiman korelasi antara suhu serta kelembapan. Regresi linier multivariat merupakan model regresi linier dengan lebih dari satu variabel respon Y berkorelasi dan satu atau lebih variabel prediktor X. Hasil penelitian menunjukkan bahwa Dalam penelitian tersebut dikatakan bahwa terdapat korelasi antara CO2 suhu serta cahaya.
MANAJEMEN SISTEM PENILAIAN KINERJA GURU TAMAN KANAK-KANAK DENGAN SIMPLE ADDITIVE WEIGHTING
Full text linkTeacher performance according to Law Number 14 of 2005 includes the main activities of planning, learning, implementing, assessing learning outcomes, mentoring and training children as well as additional tasks related to the main activities in accordance with the main workload. Teacher performance influences student learning outcomes, with good teacher performance it should produce good quality students as well. Therefore, it is natural that teacher performance needs to be measured every period. The assessment certainly contains the main and additional tasks. Based on these problems, it is also necessary to improve the existing performance appraisal system. There needs to be an appropriate method to assist the teacher performance assessment process, one of which is the weighted method, namely simple additive weighting (SAW). Performance assessment every semester using the SAW method will be able to bridge the results of increasingly better teacher performance. The assessment is carried out on a weighted basis for each parameter. The final result is a ranking of the performance of all teachers in descending orde
Sistem Pendukung Keputusan Penyesuaian Nutrisi Makanan Berdasar Rekam Medis Pasien Berbasis Forward Chaining
Full text linkFulfilling nutrition for patients certainly does not only pay attention to the last illness they suffered, but nutritionists also need to pay attention to the patient\u27s medical history. Providing certain foods to support the body\u27s recovery after treatment for certain diseases may not necessarily be in accordance with the history of previous illnesses. Fulfilling nutritional intake according to certain disease conditions is not easy, especially if the patient has a medical history with a variety of diseases, so nutritionists need to be more selective in providing nutritional intake from a number of alternative foods that will be provided. A management decision system based on artificial intelligence is able to choose a food balance that is balanced with the various complaints experienced by patients. The method used in the food management information system for medical records uses the forward chaining method, namely by determining forward, in this case, food nutritional information that is suitable for the patient, by reading the facts that have been arranged as a representation to produce a conclusion. The accuracy value resulting from comparing manual nutrient selection and using forward chaining was 86
Perbandingan Algoritma K-Means dan K-Medoids Untuk Clustering Harga Beras di Provinsi Jawa Tengah
Full text linkBeras merupakan komoditas pangan utama bagi masyarakat di Indonesia khususnya di Jawa Tengah. Sebagai kebutuhan pokok, ketersediaan dan harga beras sangat mempengaruhi stabilitas ekonomi dan kesejahteraan masyarakat. Oleh karena itu, pemantauan dan analisis harga beras menjadi hal yang sangat penting. Salah satu hal dalam memahami harga beras adalah dengan melakukan clustering atau pengelompokan harga berdasarkan harga eceran beras medium. Clustering dapat memberikan gambaran lebih jelas variasi harga di jawa tengah metode yang digunakan yaitu K-Means dan K-Medoid dengan membandingkan metode tersebut diharapkan mendapatkan informasi detail dan pola harga beras di berbagai daerah. Hasil yang didapatkan bahwa validitas DBI K-Means dengan K=3 dan K=5 lebih unggul dari pada menggunakan K-Medoids