STMIK Pringsewu Lampung (Sekolah Tinggi Manajemen Informatika dan Komputer): Portal OJS
Not a member yet
716 research outputs found
Sort by
THE EFFECTS OF FEATURE SELECTION METHODS ON THE CLASSIFICATIONS OF IMBALANCED DATASETS
Full text linkimbalanced data often results in less than optimal classification. Also, datasets with a large number of attributes tends to make the classification results not too good, and in order get better classification accuracy results, one thing that could be done is to perform pre-processing to select the features to be used in the classification. This research uses information gain and gain ratio feature selection algorithms for the pre-processing stage prior to classification, and Naïve Bayes algorithm for the classification. The test is performed to determine the values of accuracy, precision, recall from the classification process without feature selection; accuracy value with information gain feature selection; accuracy value with gain ratio; and accuracy value with CBFS feature selection. The results are then compared to determine which feature selection algorithm gives the best results when applied to data with imbalanced classes. The results showed that the classification accuracy on the default of credit card client dataset using Nave Bayes algorithm was 64.27%. The information gain feature selection was able to increase the accuracy by 5.27% (from 64.27% to 69.54%), while the gain ratio feature selection was able to increase the accuracy by 14.19% (from 64.27% to 78.46%). In this case, the gain ratio is more suitable for data with greatly varied attribute values
SISTEM PENDUKUNG KEPUTUSANMENENTUKAN KUALITASBIBIT IKAN GURAMEDI PEKON SUKOSARI MENGGUNAKAN APLIKASI VISUAL BASIC 6.0
Full text linkIkan gurame (Osphronemus gouramy) merupakan ikan asli perairan Indonesia yang sudah menyebar ke wilayah Asia Tenggara dan Cina. Salah satunya di pekon Sukosari yang saya tempati ini. Merupakan salah satu ikan labirinth dan secara taksonomi termasuk famili Osphronemidae. Ikan gurame adalah salah satu komoditas yang banyak dikembangkan oleh para petani, hal ini dikarenakan permintaan pasar cukup tinggi.Ikan ini merupakan salah satu jenis ikan konsumsi yang sudah cukup dikenal dan banyak diminati di Indonesia. Hal ini karena ikan gurame memiliki kelebihan yaitu rasa daging yang enak, pemeliharaan mudah serta harga relatif stabil. Ikan ini sudah lama dikenal orang dan telah banyak dibudidayakan.Untuk menentukan jenis bibit gurame saya menggunakan aplikasi visual basic 6.0, jadi dengan mudah kita mengetahui kualitas bibit gurame dengan aplikasi ini
Application of Dijkstra’s Algorithm in Searching the Shortest Path of Coal Production Locations
No full textTo exploit coal the company needs to hold discussions and it takes time to reach the location, each coordinate point traveled has a different distance, the shorter the distance, the faster the time it will take. In this problem the company does not yet have hauling distance data at each coordinate point, the solution to this problem is how to build an application for determining coal production points using the dijkstra algorithm. There are three stages used to collect data, namely, literature study, observation, and interviews. The development of the system used to build this application uses the prototype method whose stages consist of communication, rapid planning, rapid design modeling using flowcharts, prototype formation, and submission of the customer system in the form of an application that analyzes the determination of PIT location distances using algorithms dijkstra, the output of this application is a description of the track map display, the destination location and its node points with detailed routes with a distance of kilometers. At this stage, the application is tested using the blackbox test, by checking whether the buttons can function properly and the expected result from this test is a success
FINANCIAL DATA MANAGEMENT INFORMATION SYSTEM FOR THE UMRAH AND HAJJ CONGREGATION
Full text linkRecording data on congregation and finances on Travel AJA is currently still using the manual method, namely by recording on a ledger. The manual data entry process caused difficulty in the data search process, and this became a problem in Travel AJA. The research method used in this research is literary study, and field research such as observation, interviews, and documentation. The system development methodology used is waterfall, where stages carried out in the research is requirement analysis, design, coding, and testing. With the development of this system, congregation only need to confirm congregation installment and payment processes that have been made to the system. Congregation who have paid the Umrah or Hajj fees will get proof of installments and can be printed by the congregation
PERFORMANCE ASSESSMENT OF VILLAGE APPARATUS "WARINGINSARI TIMUR" WHEN WFH USING WEIGHTED PRODUCT AND SIMPLE ADDITIVE WEIGHTING METHODS
Full text linkOne of the ways that the government can improve the quality of village apparatus performance is to conduct a performance assessment. The performance assessment aims to provide morale to village apparatus to continue to improve their performance. The problem that occurs is the number of assessment criteria used in the performance appraisal. The method used in assessing the performance of village apparatus uses the Weighted Product and Simple Additive Weighting methods to provide recommendations for assessing the performance of village apparatus. In accordance with the results of the tests that have been carried out, the calculation results of the preference value of Simple Additive Weighting have a performance that can be said to be better than the Weighted Product because Simple Additive Weighting is able to minimize the preference value on the same alternative. From the results of the comparison between the calculation of Simple Additive Weighting and Weighted Product, the results of testing the application of the Weighted Product (WP) and Simple Additive Weighting (SAW) methods in the decision support system for assessing the performance of village apparatus is that decision support using two methods can produce the best alternative and has accuracy which is high when combined with using a website-based application using criteria that are tailored to the needs of village apparatus, especially during the work period using the current WFH (Work From Home) model. Application Test Results can be used as a basis for structured decision making to support the quality assurance process for Village services in Waringinsari Timu
FEATURE EXTRACTION AND K-MEANS CLUSTERING APPROACH TO CLASSIFY THE COVID-19 LUNG CT-SCAN IMAGE
Full text linkFeature extraction is the most important step in the classification process. Feature extraction is a method to obtain some statistical features about the image. The level of accuracy in the classification depends on the feature extraction. For detecting COVID-19, there are many features that can be used to classify them, including morphological feature extraction, first-order and second-order textures (GLCM). In this research, some features are used such as eccentricity, metric, mean, variance, skewness, contrast, correlation, energy, and homogeneity, which are then classified by the K-Means Method. The morphological feature data for cluster 1 is 98 data points and cluster 2 is 32 data points. The first-order texture feature data for cluster 1 is 88 data points, and cluster 2 is 42 data points. The last one uses GLCM data for cluster 1, and there are 75 data points, while cluster 2 has 55. From the calculation of accuracy, sensitivity, specificity, precision, and recall, the highest value is 50% for first-order texture extraction data, while the morphological feature extraction and GLCM data are 49.23% and 47.69%
THE EFFECT OF PERCEIVED USEFULNESS AND PERCEIVED EASE OF USE ON THE GOOGLE CLASSROOM AGAINST LEARNING MOTIVATION
Full text linkThis study aims to determine: (1) the effect of Perceived Usefulness on the use of Google Classroom on learning motivation, (2) the effect of Perceived Ease of Use on the use of Google Classroom on learning motivation, (3) the effect of Perceived Usefulness and Perceived Ease of Use on the use of Google Classroom on learning motivation. This research consists of several constructs. Those are Perceived Usefulness (X1), Perceived Ease of Use (X2) Learning Motivation (Y). The data collection method used is a research questionnaire whose data are analyzed using the SPSS 25 program with 75 respondents from Class 2017, students of Office Administration Education, Faculty of Economics, Surabaya State University. This research will be conducted with quantitative methods using multiple linear regression analysis. The results of this study indicate that there is a significant effect of Perceived Usefulness on learning motivation. It can be seen from the T-test results on X1, which is significant (X1) 0.001 <0.05, so that H1 is accepted. Perceived Ease of Use has a considerable influence on learning motivation. It can be seen from the T-test results on X2 with a significant value of 0.003 <0.05, so that H2 is accepted. The influence of Perceived Usefulness and Perceived Ease of Use on learning motivation has a percentage of 51.3%. Meanwhile, other variables that influence and are examined yet in this study amounted to 48.7%. It shows that if the respondent feels that Google Classroom is valuable and easy to use, the respondent will use Google Classroom.
PENGGUNAAN PLATFORMANDROID UNTUK MENINGKATKAN PERDAGANGAN KELAPA DIMASA PANDEMI
Full text linkThe use of technology in agriculture or in terms of assisting the state in helping to increase the trade-in coconut commodities can be very helpful, especially for those of the lower class who have commodity trading businesses. Small traders and natural coconut collectors marketed coconut commodities during the Covid-19 pandemic. During the pandemic, commodity prices soared but in terms of marketing, it was still not efficient, especially in small villages. So it can be expected that with this research an application system is built. can help coconut traders promote and market commodities more efficiently with a wider reach. The method used in designing application systems is the waterfall method, which uses the Java programming language in designing applications that are more efficient. The types of payment methods that can be done can use the method by credit card or in cash where consumers can also directly review the place. With this transaction, consumers can have more confidence in the quality of the commodities presented and can establish a relationship with the business owner directly. already done using an Android-based trading application showing the application can run well with the payment methods provided with product promotion features that can be reviewed directly by the buyer
COMPARISON OF K-NEAREST NEIGHBOR AND NAÏVE BAYES FOR BREAST CANCER CLASSIFICATION USING PYTHON
Full text linkClassification is widely used to determine decisions according to new knowledge gained from processing past data using algorithms. The number of attributes can affect the performance of an algorithm. Several data mining methods that are widely used for classification include the K-Nearest Neighbor and naïve Bayes algorithm. The best algorithm for one data type is not necessarily good for another data type. It is even possible that a good algorithm will be horrendous for other data types. To overcome this issue, this study will analyze the accuracy of the K-Nearest Neighbor and Naïve Bayes algorithms for the classification of breast cancer. So that patients with existing parameters can be predicted which are malignant and benign breast cancer. This pattern can be used as a diagnostic measure so that the cancer can be detected earlier and is expected to reduce the mortality rate from breast cancer
DIAGNOSIS OF SKIN DISEASES IN TODDLERS USING NAÏVE BAYES AND FORWARD CHAINING METHODS
Full text linkThe Center for Public Health is a functional organizational unit that implements health care that is thorough, integrated, evenly acceptable, and affordable to the community. The purpose of this research is to create an Expert System Application to detect skin diseases in toddlers according to the data in the public health center. The system development method used is the Extreme Programming (XP) method with working stages including planning, design, coding, and testing. The system is designed using Unified Modeling Language (UML) which includes use cases, activity diagrams, and chart classes, the software used is PHP (Hypertext Preprocessor) with MySQL databases and uses the Naïve Bayes and Forward Chaining methods. The end result of the creation of this App is to make it easier for users or the public in detecting skin diseases for toddlers