The very dense breast of mammogram image makes the Radiologists often have difficulties in interpreting the mammography objectively and accurately. One of the key success factors of computer-aided diagnosis (CADx) system is the use of the right features. Therefore, this research emphasizes on the feature selection process by performing the data mining on the results of mammogram image feature extraction. There are two algorithms used to perform the mining, the decision tree and the rule induction. Furthermore, the selected features produced by the algorithms are tested using classification algorithms: k-nearest neighbors, decision tree, and naive bayesian with the scheme of 10-fold cross validation using stratified sampling way. There are five descriptors that are the best features and have contributed in determining the classification of benign and malignant lesions as follows: slice, integrated density, area fraction, model gray value, and center of mass. The best classification results based on the five features are generated by the decision tree algorithm with accuracy, sensitivity, specificity, FPR, and TPR of 93.18%; 87.5%; 3.89%; 6.33% and 92.11% respectively.
STORET is one method to determine the river water quality into four classes (very good , good, medium and bad) based on the data of water for each attribute or feature. The success of the formation of pattern recognition model much depends on the quality of data. There are two issues as the concern of this research as follows: the data having disproportionate amount among the classes (imbalance class) and the finding of noise on its attribute. Therefore, this research integrates the SMOTE Technique and bootstrapping to handle the problem of imbalance class. While an experiment is conducted to eliminate the noise on the attribute by using some feature selection algorithms with filter approach (information gain, rule, derivation, correlation and chi square). This research has some stages as follows: data understanding, pre-processing, imbalance class, feature selection, classification and performance evaluation. Based on the result of testing using 10-fold cross validation, it shows that the use of the SMOTE-bootstrapping technique is able to increase the accurate value from 83.3% to be 98.8%. While the process of noise elimination on the data attribute is also able to increase the accuracy to be 99.5% (the use of feature subset produced by the information gain algorithm and the decision tree classification algorithm).
Mammographic density is a novel independent risk factor of breast cancer that reflects the amount of fibroglandular tissue. Breast Imaging Reporting and Data System (BIRADS) density is one of the mammographic density classification schemes which are most widely used by radiologists. Initially, the method used for assessing mammographic density was subjective and qualitative. Recently however, the measurement of mammographic density is more objective and quantitative. In this paper, we propose an alternative model of breast cancer risk factor assessment based on a quantitative approach of density mammogram. This model consists of pre-processing, breast area counting, fibroglandular tissue area counting that uses maximum entropy and multilevel thresholds, and finally breast density counting to determine the risk factor of breast cancer. The proposed model has been tested on a private database from Oncology Clinic Kotabaru, Yogyakarta, Indonesia consisting of 30 mammograms and has been analyzed by some radiologists using the semiautomatic threshold. The result shows that percentage of mammographic density counted by maximum entropy threshold method has the accuracy, sensitivity and specificity of about 87%, 73% and 91% respectively compared to the semiautomatic thresholding method. On the other hand, the accuracy, sensitivity and specificity resulted from using multilevel threshold is about 93%, 87% and 96% respectively. The obtained results suggest that multilevel threshold is perfectly suited for getting quantitative measurement of mammographic density as one of the strongest risk factors for breast cancer.
Abstract. The determination of the cattle price is generally agreed through bargaining, it is not based on the weight of the cows being sold. Most people mainly use rough calculation. There are formulas to calculate the weight but they require perimeter information of chest size and body length. It is necessary to measure the cow manually, but in reality it is not easy to do because the cow is difficult to control. Therefore, it requires a tool that can help measure easily. This article represents the early stages of research to determine the weight of cows from the cow image acquisition. It focuses on segmentation and image processing. The image acquisition results are processed using five scenarios. The results of the evaluation show that scenario 3 (Median Blur and Canny) has the best result with the value of 230,051 MSE and 24,524 dB PSNR.Keywords: Edge Detection, Canny, Segmentation, Cow, Image Processing Abstrak. Penentuan harga sapi umumnya disepakati melalui tawar menawar bukan didasarkan pada bobot sapi yang dijual. Kebanyakan menggunakan perhitungan secara kasar maupun secara kira-kira. Terdapat rumus untuk menghitung bobot sapi, rumus yang ada memerlukan informasi terkait lingkar dada dan panjang badan. Untuk mendapatkan nilai lingkar dada dan panjang badan perlu dilakukan pengukuran secara manual, namun di lapangan hal tersebut tidak mudah dilakukan karena sapi sulit dikondisikan. Oleh karena itu diperlukan alat yang dapat mengukur secara mudah. Tulisan ini merupakan tahap awal dari penelitian untuk menentukan bobot sapi dari hasil akuisisi citra sapi. Oleh sebab itu pada tahap awal ini difokuskan pada segmentasi serta pengolahan citra sapi untuk menentukan deteksi tepi terbaik yang nantinya digunakan pada penelitian selanjutnya. Citra sapi hasil akuisisi diproses menggunakan lima buah skenario deteksi tepi. Hasil evaluasi menujukkan bahwa Skenario 3 (Median Blur dan Canny) memiliki hasil yang terbaik dengan nilai MSE sebesar 230.051 dan PSNR sebesar 24.524 dB.Kata Kunci: Deteksi Tepi, Canny, Segmentasi, Sapi, Pengolahan Citra Digital.
<p>Penelitian penentuan calon bantuan siswa miskin ini di Sekolah Dasar Negeri 37 Bengkulu Selatan. Masalah yang terjadi ada ketidaksesuaian dari hasil output dalam pemberian bantuan siswa miskin, belum digunakannya metode keputusan untuk setiap kriteria dan masih menggunakan penilaian prediksi atau perkiraan untuk calon penerima bantuan. Metode penelitian yang dilakukan menggunakan Fuzzy Tsukamoto dengan perbandingan dua metode yaitu rule pakar dan Decision Tree SimpleCart. Tahapan penelitian ini dimulai dengan menganalisis output dengan melakukan seleksi dari sejumlah alternatif hasil, kemudian melakukan pencarian nilai bobot setiap atribut dari Fuzzy Tsukamoto dengan metode perbandingan rule pakar dan Decision Tree SimpleCart. Selanjutnya menentukan parameter batasan fungsi keanggotaan fuzzy meliputi kartu perlindungan sosial, nilai rata-rata raport, tanggungan, penghasilan orang tua, prestasi dan kepemilikan rumah. Analisis hasil yang diperoleh dari pengujian terhadap 75 data siswa dan telah dilakukan klasifikasi menggunakan Fuzzy Tsukamoto didapatkan hasil akurasi dengan metode rule pakar sebesar 72% dan metode Decision Tree SimpleCart sebesar 76%. Hasil akurasi tersebut di simpulkan bahwa metode Decision Tree SimpleCart mempunyai tingkat akurasi yang lebih tinggi dari metode rule pakar sehingga lebih mampu dalam menyeleksi serta mencari nilai bobot penentuan bantuan siswa miskin. </p><p> </p><p><em><strong>Abstract</strong></em></p><p><em>Research on the determination of candidates for assistance from poor students in South Bengkulu 37 Primary School. The problem that occurs is there is a mismatch of the output results in the provision of assistance to poor students, the decision method has not been used for each criterion and is still using predictive or estimated assessments for prospective beneficiaries. The research method used was Fuzzy Tsukamoto with a comparison of two methods, namely expert rule, and SimpleCart Decision Tree. The stages of this research began by analyzing the output by selecting many alternative results, then searching for the weight value of each attribute from Fuzzy Tsukamoto with the method of expert rule comparison and the SimpleCart Decision Tree. Next determine the parameters of the fuzzy membership function limit includes social protection cards, the average value of report cards, dependents, parents' income, achievements, and homeownership. Analysis of the results obtained from testing of 75 student data and classification using Fuzzy Tsukamoto has obtained accuracy with the expert rule method by 72% and the SimpleCart Decision Tree method by 76%. The accuracy results are concluded that the SimpleCart Decision Tree method has a higher level of accuracy than the expert rule method so that it is better able to select and search for the weighting value of determining the assistance of poor students.</em></p><p> </p>
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.