Abstract:Abstract: Non-performing loan (NPL) is a risk that credit unions must face and to avoid that, prospective debtors need to be surveyed. With previous loan data, support vector machine and naïve bayes can be used as classification…
ssification methods to give a decision about NPL. We use a data set with 61 data and process the data with orange 3.30 application to see the difference between SVM using linear (SVM-L), polynomial (SVM-P), RBF (SVM-R) and sigmoid (SVM-S) kernel with naïve bayes. We use a cross validation technique with various folds to measure the classification results and a convusion matrix to measure the data training classification results. Naïve bayes scores the highest in terms of accuracy and SVM-R scores the highest in terms of F1, precision and recall. SVM-P scores the lowest in terms of accuracy, F1, precision and recall. Naïve bayes scores the highest in terms of proportion of predicted for true negative class and proportion of actual for true positive class. SVM-S scores the highest in terms of proportion of predicted for true positive class and proportion of actual for true negative class. SVM-P scores the lowest in both proportion of predicted and proportion of actual.
Keywords: classification; naïve bayes; non-performing loan; support vector machine
Abstrak: Kredit macet merupakan resiko yang sering dialami koperasi simpan pinjam, sehingga perlu dilakukan survei terhadap calon debitur agar kredit menjadi sehat. Dengan menggunakan data pemberian kredit sebelumnya, support vector machine dan naïve bayes digunakan sebagai metode klasifikasi untuk memberikan keputusan macet atau tidaknya kredit anggota koperasi Mutiara Sejahtera. Data set yang berjumlah 61 data diolah menggunakan aplikasi Orange 3.30 dan dilihat perbandingan antara metode SVM dengan kernel linear, polynomial, RBF dan sigomoid dengan metode naïve bayes. Cross validation dengan jumlah fold bervariasi digunakan sebagai nilai ukur klasifikasi dan convusion matrix digunakan sebagai nilai ukur klasifikasi data training. Hasil yang diperoleh adalah naïve bayes memiliki nilai accuracy tertinggi dan SVM kernel RBF memiliki nilai F1, precision dan recall tertinggi. SVM kernel polynomial memiliki nilai terendah untuk accuracy, F1, precision dan recall. Naïve bayes memiliki nilai tertinggi untuk proportion of predicted (PoP) kelas true negative dan proportion of actual (PoA) kelas true positive. SVM kernel sigmoid memiliki nilai tertinggi untuk PoP kelas true positive dan PoA kelas true negative. SVM kernel polynomial memiliki nilai terendah baik untuk PoP maupun PoA true negative dan kelas true positive.
Kata kunci: klasifikasi; kredit macet; naive bayes; SVM
Abstract:Abstract: Patient’s symptoms could be used as features in Covid-19 classification. Using multi layer perceptron, the classification uses data set that contains patient’s diagnosis which has Covid-19 symptoms dan processes…
s dan processes the data set to see if the patient is Covid-19 positive or not. This paper compare four activation function such as identity, logistic, ReLu and tanh and combined them with optimizer such as L-BFGS-B, SGD and Adam. Using 5-fold and 10-fold cross validation technique to get the accuracy, F1, precision and recall values, the result that we get is that logistic function with L-BFGS-B optimizer and ReLu function with L-BFGS-B optimizer are the best combinations. The logistic function with SGD optimizer, ReLu function with Adam optimizer and tanh function with Adam optimizer are the worst combinations according to their accuration values. The logistic function with SGD optimizer is the worst combination according to its F1 value. The logistic function with SGD optimizer and tanh function with L-BFGS-B optimizer are the worst combinations according to their precision values. The logistic function with SGD optimizer, ReLu function with Adam optimizer and tanh function with Adam optimizer are the worst combinations according to their recall values.
Keywords: activation function, covid-19; multi layer perceptron; optimizer algorithm
Abstrak: Diagnosa gejala yang dialami pasien dapat digunakan sebagai fitur dalam klasifikasi penderita Covid-19. Dengan multi layer perceptron, klasifikasi dilakukan menggunakan data set yang berisi hasil diagnosa pasien yang memiliki gejala Covid-19 dan selanjutnya diolah untuk melihat apakah memang pasien tersebut menderita Covid-19 atau tidak. Penelitian ini membandingkan fungsi aktivasi identity, logistic, ReLu dan tanh yang dikombinasikan dengan algoritma optimasi L-BFGS-B, SGD dan Adam. Hasil evaluasi cross validation menggunakan 5-fold dan 10-fold digunakan sebagai dasar menentukan kombinasi yang terbaik dan terburuk, dengan hasil yang menunjukkan bahwa kombinasi fungsi logistic dengan optimasi L-BFGS-B dan fungsi ReLu dengan optimasi L-BFGS-B merupakan kombinasi terbaik. Kombinasi fungsi logisctic dengan optimasi SGD, fungsi ReLu dengan optimasi Adam dan fungsi tanh dengan optimasi Adam merupakan yang terburuk dari nilai accuracy. Kombinasi fungsi logistic dan optimasi SGD merupakan kombinasi terburuk dari nilai F1. Kombinasi fungsi logistic dengan optimasi SGD dan fungsi tanh dan optimasi L-BFGS-B merupakan yang terburuk dari nilai precision. Kombinasi fungsi logisctic dengan optimasi SGD, fungsi ReLu dengan optimasi Adam dan fungsi tanh dengan optimasi Adam merupakan kombinasi terburuk dari nilai recall.
Kata kunci: algoritma optimasi; covid-19; fungsi optimasi; multi layer perceptron
Abstract:Abstract: The technique of multiclass classification based on SVMs has been widely used. SVM optimization will be accomplished by examining the extraction features of Principal Component Analysis (PCA), Box-Cox Transformation,…
ation, and Recursive Feature Elimination (RFE). The dataset contains 13,611 rows and 17 variables, generated from the UCI repository's multiclass dry bean data. Barbunya, Bombay, Cal, Dermas, Horoz, Seker, and Sira are just a few of the dry bean kinds available. The dataset was tested using SVM Linear kernel and SVM Radial Basis.According to the results, the combination of scale-center-BoxCox-SVM Radial extraction achieves the maximum accuracy of 93.16 percent and the shortest processing time of 6.10 minutes. 96.00 percent, 100 percent, 96.71 percent, 95.16 percent, 97.60 percent, 97.74 percent, and 91.95 percent, according to bean class.RFE-SVM Radial has a 91.18 percent accuracy and a processing time of 6.55 minutes. BoxCox outperforms conventional techniques in terms of prediction accuracy while requiring less training time.
Keywords: Bean, PCA, BoxCox, SVM, RFE
Abstrak: Klasifikasi Multikelas menggunakan SVM telah banyak digunakan. Pada penelitian ini akan diuji fitur ekstraksi Principal Component Analysis, Box Cox Transformation dan fitur eliminisi Recursive Feature Elimination untuk mendapatkan optimasi SVM. Dataset berasal dari data multikelas kacang kering UCI repository dengan jumlah 13.611 baris dan 17 variabel. Kelas kacang kering yakni : Barbunya, Bombay, Cal, Dermas, Horoz, Seker dan Sira. Dataset diuji menggunakan kernel SVM Linier dan SVM Radial Basis. Didapatkan hasil, bahwa kombinasi fitur ekstraksi : scale-center-BoxCox-SVM Radial memiliki akurasi terbaik yakni 93,16% dan waktu proses 6,10 menit. Klasifikasi berdasarkan kelas kacang berturut-turut 96,00%,100%, 96,71%, 95,16%, 97,60%, 97,74% dan 91,95%. RFE- SVM Radial hanya memberikan akurasi sebesar 91,18 % dengan waktu proses sebesar 6.55 menit. Penggunaan BoxCox dibandingkan dengan lainnya, memberikan hasil prediksi lebih baik dan namun tidak mempercepat waktu pelatihan.
Kata kunci: BoxCox; Kacang; PCA; RFE; SVM
Abstract:Abstract: This study uses the C4.5 classification algorithm to determine creditworthness, clasification aims to divide the assigned object intoin a number of categories called classes. In this study, the authorusing data…
mining and C4.5 algorithm as the selection method. The criteria used are loan installments, prospective customer income, termloan time, status of prospective customers. This study resulted in a classification modeldecision tree using the C4.5 algorithm is included in the Excellent category Classification with an accuracy value of 98.33% and a classification error of 1.67%,so that this study uses 70% training data and 30% test data. From resultthe calculation obtained shows that the C4.5 algorithm can be usedto determine the feasibility of granting credit to Koperasi Jaya customers Together (KORJABE).
Keywords: Analysis, Credit Eligibility, C4 Algorithm, Data Mining, Method
Abstrak: Penelitian ini menggunakan metode Algoritma C4.5 klasifikasi untuk menentukan kelayakan kredit, klasifikasi bertujuan untuk membagi objek yang ditetapkan ke dalam satu nomor kategori yang disebut kelas. Dalam penelitian ini, penulis menggunankan data mining dan algoritma C4.5 sebagai metode pemilihannya. Kriteria yang digunakan yaitu , angsuran pinjaman,penghasilan calon nasabah,jangka waktu pinjaman ,status calon nasabah. Penelitian ini menghasillkan model klasifikasi pohon keputusan menggunakan algoritma C4.5 termasuk dalam kategori Excellent Classification dengan nilai akurasi sebesar 98,33% dan klasifikasi eror 1,67%, sehingga penelitian ini kan menggunakan data latih 70% dan data uji 30%. Dari hasil perhitungan yang diperoleh menunjukan bahwa algoritma C4.5 dapat digunakan untuk menen tukan kelayakan pemberian kredit kepada nasabah Koperasi Jaya Bersama (KORJABE).
Kata kunci: Algoritma C4.5, Analisis, Data Mining, Kelayakan Kredit, Metode
Abstract:Abstract: Question classification is a computer science system, which aims to analyze questions and can label each question based on existing categories. Questions can be collected from several materials or topics that are…
re many and different. Therefore, the researcher intends to create a classification system for quiz questions Data Warehouse and Business Intelligence which can be grouped into topics Data Warehouse, Business Intelligence, Data Analytics, and Performance Measurement. One way to solve this problem is by approach machine learning. In this study, researchers used a comparison of machine learning algorithms, namely the algorithm NaïveBayes and SupportVectorMachine using SMOTE and methods Cross-Validation The results of this study show the best accuracy results and are very helpful. The results obtained in the method cross-validation before SMOTE resulted in an accuracy rate of 82.02% for the results after going through the SMOTE stage of 94.79% on the algorithm Naïve Bayes, while the algorithm SupportVectorMachine get accuracy of 81.39% in the process before SMOTE for the results after going through SMOTE of 96.52%.
Keywords: Cross-Validation; Machine Learning; Naive Bayes; Support Vector Machine; Question Classification
Abstrak: Klasifikasi pertanyaan merupakan sebuah sistem ilmu komputer, yang bertujuan untuk menganalisis pertanyaan serta dapat memberi label pada setiap pertanyaan berdasarkan kategori yang ada. Pertanyaan soal dapat dikumpulkan dari beberapa materi atau topik yang banyak dan berbeda. Oleh karena itu, bermaksud untuk membuat sistem klasifikasi pertanyaan soal kuis Data Warehouse dan Business Intelligence yang dapat dikelompokkan menjadi topik Data Warehouse, Business Intelligence, Data Analitik, dan Pengukuran Kinerja. Cara yang dapat dilakukan untuk permasalahan ini dengan menggunakan pendekatan MachineLearning. Pada penelitian kali ini menggunakan perbandingan algoritma MachineLearning yaitu algoritma NaïveBayes dan SupportVectorMachine menggunakan metode SMOTE dan Cross-Validation. Hasil penelitian ini menunjukkan hasil akurasi yang terbaik dan sangat membantu. Hasil yang diperoleh pada metode cross-validation sebelum SMOTE menghasilkan tingkat akurasi sebesar 82.02% untuk hasil sesudah melalui tahap SMOTE sebesar 94.79 % pada algoritma Naïve Bayes, sedangkan pada algoritma Support Vector Machine menghasilkan akurasi sebesar pada proses sebelum SMOTE 81.39% untuk hasil sesudah melalui SMOTE sebesar 96.52%.
Kata kunci: Klasifikasi Pertanyaan; Pembelajaran Mesin; Naive Bayes; Support Vector Machine; Cross-Validation
Abstract:Abstract: The Presidential general election on 2019 became one of the most popular topics on twitter nowdays. The society give their opinion about the pair of candidates that they are support through the social media.…
ia. This research was predicts about the society sentimens toward the candidates of President and Vice President of Republic of Indonesia. The data was used based on the tweet on the @jokowi twitter account. The retrieval of data by using the Tweepy library with the Python 2.7 programming language. This research was classified became of two of society sentiments classes, namely positive and negative. The modeling was used of the weighting method Unigram, Bigram, Trigram, N-Gram (1-2) and N-Gram (1-3) that used the Naïve Bayes Algorithm on the Weka Application. The modeling data was used by the dataset of 646 sentences. The highest results of this reseach were obtained by Unigram Weighting, namely: 81.4% accuracy, 81.5% precision, 81.3% recall with a time of 0.3 s.
Keywords: classification, naïve bayes, 2019 presidential election, twitter, unigram
Abstrak: Pemilihan Umum tentang Pilpres 2019 menjadi salah satu topik yang ramai diperbincangkan di Twitter. Adu pendapat di sosial media oleh masyarakat mengandung opini terhadap pasangan calon yang didukungnya. Penelitian ini memprediksi sentimen masyarakat kepada pasangan calon Presiden dan Wakil Presiden Republik Indonesia. Data yang digunakan adalah tweet yang ada pada akun Twitter @jokowi. Pengambilan data menggunakan library Tweepy dengan bahasa pemrograman Python 2.7. Penelitian ini mengklasifikasi sentimen masyarakat menjadi 2 kelas, yaitu positif dan negatif. Kemudian dilakukan pemodelan dengan metode pembobotan Unigram, Bigram, Trigram, N-Gram (1-2) Dan N-Gram (1-3) menggunakan Algoritme Naïve Bayes pada Aplikasi Weka. Pembuatan model menggunakan dataset yang berjumlah 646 kalimat. Hasil tertinggi yang diperoleh pada penelitian ini adalah dengan menggunakan Pembobotan Unigram, yaitu : akurasi 81,4%, presisi 81,5 % , recall 81,3 % dengan catatan waktu 0,3s.
Kata kunci: klasifikasi, naïve bayes, pilpres 2019, twitter, unigram.
Abstract:Abstract: The human eye can distinguish objects from digital images, however, computers do not have the ability as human eyes that can directly distinguish objects from digital images. Therefore the bag of visual words method…
ethod was created. Bag of visual words is a method for presenting digital images based on local features. Bag of visual words illustrates how an image can be taken its characteristics, so that computers can distinguish objects on digital images. The test results show that the bag of visual words are still not maximal in classifying digital image categories, especially the chair category, which is only able to produce the most accurate accuracy of 75%. To improve the performance quality of bag of visual words in classifying digital image categories, especially the chair category, you can add an approach to determine the good number of K in clustering the visual words pattern.
Keywords: Bag Of Visual Words, Classification, Digital Image, Speed-Up Robust Feature, Support Vector Machine
Abstrak: Secara kasat mata manusia bisa membedakan objek pada citra digital, namun, komputer tidak memiliki kemampuan sebagai mata manusia yang dapat secara langsung membedakan objek pada citra digital. Maka dari itu diciptakanlah metode bag of visual words. Bag of visual words adalah metode untuk menyajikan citra digital berdasarkan fitur lokal. Bag of visual words menggambarkan bagaimana suatu gambar dapat diambil karakteristiknya, sehingga komputer dapat membedakan objek pada citra digital. Hasil pengujian menunjukkan bag of visual words masih belum maksimal dalam mengklasifikasi kategori citra digital khususnya kategori chair, yang hanya mampu menghasilkan akurasi paling akurat sebesar 75 %. Untuk meningkatkan kualitas kinerja bag of visual words dalam mengklasifikasi kategori citra digital khususnya kategori chair, dapat menambahkan pendekatan untuk menentukan jumlah K yang baik dalam mengkluster pola visual words.
Kata kunci: Bag Of Visual Words, Klasifikasi, Citra Digital, Speed-Up Robust Feature, Support Vector Machine
Abstract:Freight forwarding agreements in Indonesia frequently contain exoneration clauses that exempt logistics providers from liability for loss or damage, raising serious concerns regarding consumer protection. While such clauses…
ses are designed to manage contractual risk, they often conflict with the principles enshrined in Law No. 8 of 1999 on Consumer Protection (UUPK), particularly those ensuring fairness, good faith, and legal accountability. This study investigates the legality and ethical implications of exoneration clauses within standard-form freight forwarding contracts used by companies such as JNE, TIKI, and SiCepat. Employing a doctrinal legal research methodology, the study integrates statutory, conceptual, and case-based approaches to analyze primary legislation, judicial decisions, and relevant legal doctrines. It critically evaluates the use of these clauses in light of consumer rights, contract theory, and the economic impact on service quality. Findings reveal that exoneration clauses not only contravene the UUPK but also create systemic contractual imbalances due to the lack of negotiation opportunities and transparency. The study proposes a normative legal framework for reform, including clause classification, interactive consent mechanisms, and regulatory enforcement to ensure contractual fairness. This research contributes to both legal scholarship and policy development by highlighting the urgent need for doctrinal clarity and regulatory oversight in Indonesia's logistics sector.
Abstract:Meat is one of the essential food ingredients in meeting the nutritional needs. The current problem lies in the consumers' lack of knowledge on how to differentiate between pork, beef, goat, and lamb meat. This is because…
e when the meat is already cut, their appearances may seem similar at first glance. Many consumers are unaware of the practice of mixing different types of meat for consumption. One way to classify animal meat is by using image processing. In this research, an image processing system is created to classify meat, specifically pork, beef, goat, and lamb. Support Vector Machine (SVM) is a development of Machine Learning that can be used in classifying images into specific classes. SVM method as a classifier is performed using a confusion matrix. The test results show the highest accuracy value obtained in the class of Goat Meat 91.4%, the highest precision in the class of goat meat 80%, the highest recall in the class of beef 81.3%, and the highest F1-score in the class of beef 0.76.
Abstract:Automatic detection of hate speech and abusive language is crucial for combating online toxicity. This study explores Gaussian Naive Bayes for multi-label classification of hate speech on Indonesian Twitter, including target,…
rget, category, and level. We combined TF-IDF features with contextual BERT embeddings. The model achieved balanced performance for general hate speech and good non-abusive language detection. However, it exhibited limitations with imbalanced data and specific hate speech types. The classifier consistently favored the majority class (non-hateful/non-abusive) across labels, particularly struggling with HS_Gender, HS_Physical, etc. This suggests difficulty detecting less frequent but potentially severe hate speech, likely due to limited training data. Overall accuracy and F1-scores confirm that while Gaussian Naive Bayes is efficient, it lacks robustness for nuanced multi-label classification with imbalanced datasets. This necessitates exploring alternative approaches for effectively detecting specific and less frequent hate speech.