The brain in humans becomes part of the central nervous system of the human body. The use of imaging with MRI is one that can be used as a first step to detect parts of the human brain. The imaging step is the first step in diagnosing brain tumor. By performing feature extraction, which aims to process the classification of brain tumors, between normal and abnormal brain images using the naive Bayes method. Obtained 41 images which then became 39 datasets. Feature extraction results with 2 classes, normal as many as 20 data and abnormal data 19. The calculation results obtained the value of the normal class of 0.513 and the abnormal class of 0.487 the value of the calculation accuracy of 84.17%.
In this study, an automatic diagnosis analysis of the results of pap smear image extraction using neural network algorithms, the analysis included a review of the results of Herlev pap smear extraction level 7 grade, 2 normal and abnormal classes, 3 classes of normal level dysplasia and 4 classes of abnormal dysplasia levels. The problem is that neural networks are very difficult to designate optimal features in diagnosing and difficult to handle class imbalances. This study proposes a combination of particle swarm optimization (PSO) to optimize the features and bagging methods to deal with class imbalances, with the aim that the results of diagnosis using a neural network can increase its accuracy. The results show that using PSO and bagging methods can improve the accuracy of the algorithm of network balance. At level 7 the buffer class increased by 1.64%, 2 classes increased by 0.44%, 3 classes increased by 2.04%, and at level 4 the class increased by 5.47%In this study, an automatic diagnosis analysis of the results of pap smear image extraction using neural network algorithms, the analysis included a review of the results of Herlev pap smear extraction level 7 grade, 2 normal and abnormal classes, 3 classes of normal level dysplasia and 4 classes of abnormal dysplasia levels. The problem is that neural networks are very difficult to designate optimal features in diagnosing and difficult to handle class imbalances. This study proposes a combination of particle swarm optimization (PSO) to optimize the features and bagging methods to deal with class imbalances, with the aim that the results of diagnosis using a neural network can increase its accuracy. The results show that using PSO and bagging methods can improve the accuracy of the algorithm of network balance. At level 7 the buffer class increased by 1.64%, 2 classes increased by 0.44%, 3 classes increased by 2.04%, and at level 4 the class increased by 5.47%
Cerebrovascular Accidents (stroke) are a disease that threatens and causes death and disability and disability in the world, in Indonesia the number of people affected by stroke is increasing every year. Stroke can be prevented by adopting a healthy lifestyle, eating nutritious food, and doing physical activity. The purpose of this study is to create an effective stroke prediction model, the system uses parameters from lifestyle factors, controllable factors such as medical risk factors, and uncontrollable factors. Four classification algorithms are proposed, namely multi-layer perceptron, KNN, Decision Tree, and Random Forest. The results show that the classification algorithm can work effectively by producing a perfect score of 99.99% accuracy at the 10K-Fold Validation level of validation.
During this time the performance appraisal of PT. Injep Inti Cemerlang has not been implemented optimally, especially in employee performance appraisal. Performance appraisal so far is only determined from the results, there are no clear appraisal criteria. Based on this reason, a decision support system is needed to help find the best alternative for the employees selection. In this research a decision support system for employee performance appraisal will be developed based on Attitude, Responsibility, Attendance, Discipline and Collaboration. This research aims to design a decision support system for employee performance appraisal using data collection methods by observation, interviews and giving questionnaires to employees of PT. Injep Inti Cemerlang. The data collected is carried out the process of analyzing data and looking for weighting values using the AHP method and for ranking using the TOPSIS method, where each criterion is appraisal factors and alternatives in this case employees are compared the criteria that have been weighted through the process of calculating the AHP and TOPSIS method starting from giving the weighting of criteria by calculating with Ms. Excel and calculating with Expert Choice software. The results have been obtained from weighting the next ranking by the TOPSIS method. thus providing a value output that results in a system that employees appraisal. This decision support system helps the employee performance apprasial at PT. Injep Inti Cemerlang in determining the employee who has the best performance
Masalah kemiskinan di Indonesia masih menjadi fokus utama pemerintah dalam menetaskannya, program keluarga harapan (PKH) menjadi program prioritas pemerintah dalam upaya memberantas kemiskinan di Indonesia, fokus utama PKH adalah memberikan bantuan kepada Rumah Tangga Sangat Miskin (RTSM) untuk bisa mengakses pendidikan, kesehatan dan kesejahteraan sosial. Dalam menentukan keluarga yang berhak menerima bantuan PKH sering mengalami masalah, seperti kurang tepat sasaran dalam menentukan RTSM, ini di dasarkan kepada kelalaian petugas sehingga kurang akurat dalam validasi data yang banyak. Sistem otomatis yang dapat memprediksi RTSM dapat menjadi solusi atas permasalahan ini, sistem yang didasarkan pada model machine learning. Penelitian ini bertujuan untuk menganalisis model machine learning Decision Tree (DT), Support Vector Machine (SVM), Naive Bayes (NB) dan Logistic Regression (LR) dalam memprediksi RTSM yang akurat. Hasil menunjukkan bahwa Logistic Regression menjadi model yang optimal untuk di implementasikan dengan nilai AUC sebesar 0,999
Breast cancer is still a major health problem for women around the world, the population of Indonesia is 237.8 million in 2010 and detected by cancer patients is estimated at 1.02 million. The purpose of this study is to reconstruct the image of the MRI scan to clarify the object of cancer so that it can be more easily identified whether a person really has breast cancer or not, in this study using the morphological reconstruction method with the k-means algorithm to segment the image, the results obtained sensitivity of around 92.86%, specificity of 78.57%, and accuracy of 85.71%.
Pemilihan jurusan yang tepat bagi siswa baru akan berdampak besar pada kemampuan siswa itu sendiri. Pemilihan jurusan menjadi sangat penting, karena siswa dapat menentukan jurusan yang akan membawa ke passion-nya di masa depan. Dalam Memilih jurusan, biasanya siswa bertanya kepada yang bukan ahli pada bidang tersebut seperti orang tua, teman sebaya dan orang-orang terdekat atau bahkan menentukan jurusan dengan berlandaskan kepopuleran suatu jurusan, padahal jurusan tersebut bukan menjadi passion calon siswa tersebut. Metode simple adaptive weighting dapat membantu siswa membuat rekomendasi jurusan yang tepat berdasarkan kriteria-kriteria terukur dari kemampuan siswa itu sendiri. penelitian ini mengusulkan metode Simple Additive Weighting (SAW) karena perhitungan yang simple dan berlandaskan bobot kemampuan siswa itu sendiri. Hasilnya siswa mendapatkan rekomendasi-rekomendasi dari hasil perhitungan bobot dari setiap alternatif jurusan sesuai dengan kemampuan siswa itu sendiri, dengan metode ini siswa tidak lagi salah mengambil jurusan
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.