Abstract:Automatic text summarization is challenging research in natural language processing, aims to obtain important information quickly and precisely. There are two main approach techniques for text summary: abstractive and extractive…
tractive summary. Abstractive Summarization generates new and more natural words, but the difficulty level is higher and more challenging. In previous studies, RNN and its variants are among the most popular Seq2Seq models in text summarization. However, there are still weaknesses in saving memory; gradients are lost in long sentences so resulting in a decrease in lengthy text summaries. This research proposes a Transformer model with an Attention mechanism that can fetch important information, solve parallelization problems, and summarize long texts. The Transformer model we propose is GPT-2. GPT-2 uses decoders to predict the next word using the pre-trained model from w11wo/indo-gpt2-small, implemented on the Indosum Indonesian dataset. Evaluation assessment of the model performance using ROUGE evaluation. The study's results get an average result recall for R-1, R-2, and R-L were 0.61, 0.51, and 0.57, respectively. The summary results can paraphrase sentences, but some still use the original words from the text. Future work increase the amount of data from the dataset to improve the result of more new sentence paraphrases.
Abstract:Abstract: The poor community is a condition in which the community does not have adequate facilities and infrastructure and an adequate environment, with the quality of housing and settlements far below the eligibility standard…
tandard and uncertain livelihoods covering all multidimensional dimensions. The Pasiran Village Office, Sei Dadap District, is one of the agencies located in the Pasiran area, Sei Kamah. Where the Pasiran Village Hall Office carries out activities to distribute assistance to village communities who are declared to be underprivileged or have low incomes below 3.5 million. With such a large number of village people, an in-depth analysis is needed to determine which poor people are entitled to receive Non-Cash Food Assistance from the government. The solution to this problem is to use data mining with the Naïve Bayes algorithm for data classification. Data mining is the science of extracting information by utilizing data sets to obtain valuable information with a large enough data size through the process of extracting data or filtering data. The classification application uses the naïve Bayes algorithm used at the Pasiran Village Office to produce a classification of beneficiaries, namely Worthy and Unworthy based on the attributes of Citizenship, Family Group, ASN Status, and Having a Healthy Family Card.
Keywords: data mining; naïve bayes; classification, beneficiary
Abstrak: Masyarakat miskin merupakan suatu kondisi dimana keadaan masyarakat yang tidak memiliki sarana dan prasarana serta lingkungan yang memadai, dengan kualitas perumahan dan pemukiman yang jauh dibawah standar kelayakan serta mata pencaharian yang tidak menentu yang mencakup seluruh multidimensi. Kantor Balai Desa Pasiran Kecamatan Sei Dadap merupakan salah satu instansi yang berada di daerah Pasiran, Sei Kamah. Dimana Kantor Balai Desa Pasiran melakukan kegiatan pembagian bantuan terhadap masyarakat desa yang dinyatakan kurang mampu atau memiliki penghasilan rendah dibawah 3,5 juta. Dengan jumlah masyarakat desa yang begitu banyak, diperlukan analisis yang mendalam untuk menentukan masyarakat tidak mampu yang berhak untuk mendapatkan Bantuan Pangan Non Tunai dari pemerintah. Solusi dari permasalahan tersebut adalah menggunakan data mining dengan algoritma naïve bayes untuk klasifikasi data. Data mining merupakan suatu ilmu untuk menggali informasi dengan memanfaatkan kumpulan data untuk mendapatkan berbagai informasi yang berharga dengan ukuran data yang cukup besar melalui proses penggalian data atau penyaringan data. Aplikasi klasifikasi menggunakan algoritma naïve bayes yang terapkan pada Kantor Balai Desa Pasiran menghasilkan klasifikasi warga penerima bantuan yaitu Layak dan Tidak Layak berdasarkan atribut Kewarganegaraan, Golongan Keluarga, Status ASN dan Memiliki Kartu Keluarga Sehat.
Kata kunci: data mining; naïve bayes; klasifikasi, penerima bantuan
Abstract:Abstract: Glaucoma is the second leading eye disease of blindness after cataracts. An ophthalmologist does a glaucoma examination with an eye screening that will produce a retinal image. The diagnosis's result of the retinal…
inal image is subjective because each doctor has dissent and a condition experienced. This research builds a system to identify retinal images in the category of glaucoma or normal patients. The purpose of this system as a tool is to help ophthalmologists diagnose glaucoma. This process begins by changing the colour of an image to validity. The image is extracted using the Gray Level Co-occurrence Matrix (GLCM) and produces five features than the result of the five features used as input to neural network Learning Vector Quantization (LVQ). The amount of retinal image data used 60 data for learning and 20 for testing. And the number of neurons used is 12, and the epoch of as many as 1000 was obtained based on the results comparison of variations against 8, 10, 12, 18, and 20 neurons with 500, 900, 1000, and 1100 epochs. The learning process results from the value of weights that will be used in the testing process. The results of this study obtained an accuracy rate of 85%, a precision of 89%, and a recall of 80%.
Keywords: glaucoma; LVQ; GLCM
Abstrak: Glaukoma merupakan penyakit mata penyebab kebutaan nomor dua setelah katarak. Pemeriksaan penyakit glaukoma dilakukan oleh dokter spesialis mata dengan cara skrining mata yang akan menghasilkan citra retina. Hasil diagnosa citra retina oleh dokter bersifat subjektif karena setiap dokter memiliki pendapat yang berbeda serta kondisi yang dialami. Penelitian ini membangun sistem untuk mengidentifikasi citra retina mata kedalam kategori penderita glaukoma atau normal. Tujuan pembuatan sistem ini sebagai alat bantu bagi dokter mata dalam mendiagnosa glukoma. Proses ini diawali dengan mengubah warna citra menjadi keabuan, kemudian citra tersebut diekstraksi menggunakan Gray Level Co-occurrence Matrix (GLCM) dan menghasilkan lima nilai fitur yang kemudian hasil dari kelima fitur tersebut digunakan sebagai masukan jaringan syaraf tiruan Learning Vector Quantization (LVQ). Jumlah data citra retina yang digunakan sebanyak 60 data untuk learning dan 20 data untuk testing. Dan untuk jumlah neuron yang digunakan yaitu 12 dan epoch sebanyak 1000 yang didapat berdasarkan hasil perbandingan variasi terhadap neuron sejumlah 8, 10, 12, 18, 20 dengan jumlah epoch sejumlah 500, 900, 1000 dan 1100. Hasil dari proses learning yaitu nilai bobot yang akan digunakan sebagai bobot di proses testing. Hasil penelitian ini diperoleh tingkat akurasi sebesar 85%, presisi sebesar 89% dan recall sebesar 80%.
Kata kunci: glaukoma; LVQ; GLCM
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: The application of information technology is currently growing so rapidly. One of them is the application of technology that can be applied in the industrial world, namely to evaluate the company's performance.…
Evaluation is a necessity for companies to move forward and develop in facing business competition. One method of evaluating that can be used objectively is extracting information through a stored database. This study intends to analyze the factors that affect profit outcomes based on profit-based data. The data will be analyzed using method Bayes. Through this method will get a pattern that affects profits. However, it is not easy to analyze data with this method because of the large amount of data that will cost a lot of time and time. So to simplify the analysis, researchers use tools in analyzing the data the results of the benefits of rapidminer software. Based on the results of the analysis carried out, rapidminer software can help and make it easier to produce probabilities to be predicted. The results of this study are from the set test conducted, the prediction of profit results can be ascertained to be achieved and the possibility of certainty is reached 0.59% and the possibility of not reaching 0.41%.
Keywords: Data Mining, Neive Bayes, Rapidminer, Benefits
Abstrak: Penerapan teknologi informasi saat ini berkembang begitu pesat. Salah satunya penerapan teknologi yang dapat diterapkan didunia industri yaitu untuk evaluasi terhadap kinerja perusahaan. Evaluasi merupakan suatu keharusan bagi perusahaan untuk terus maju dan berkembang menghadapi persaingan usaha. Salah satu cara mengevaluasi yang dapat dugunakan secara objektif yaitu penggalian informasi melalui database yang tersimpan.Penelitian ini bermaksud untuk menganalisa faktor yang mempengaruhi hasil keuntungan berdasarkan data hasil keuntungan. Data tersebut akan dianalisis menggunakan metodeneive bayes. Melalui metode ini akan mendapatkan pola yang mempengaruhi keuntungan.Namun tidaklah mudah dalam menganalisis data dengan metode ini dikarenanakan banyaknya data yang akan menghabiskan biaya dan waktu yang cukup lama. Maka untuk mempermudah analisis tersebut, peneliti menggunakan alat bantu dalam menganalisis data hasil keuntungan yaitusoftware rapidminer.Berdasarkan hasil analisis yang dilakukan, software rapidminer dapat membantu dan mempermudah menghasilkan probabilitas untuk dijadikan prediksi. Hasil penelitian ini adalah dari uji set yang dilakukan, prediksi hasil keuntungan dapat dipastikan tercapai dan kemungkinan kepastian tercapai 0,59% serta kemungkinan tidak tercapai 0,41%.
Kata Kunci : Data Mining, Neive Bayes, Rapidminer, Keuntungan
Abstract:Kutai Kartanegara Regency, East Kalimantan Province, has long depended on coal mining and petroleum as its primary economic drivers. This dependence creates structural vulnerability to global commodity price fluctuations…
and long-term sustainability challenges. This article presents a systematic literature review examining tourism as an alternative sector for regional economic transformation in Kutai Kartanegara. Drawing on 15 peer-reviewed studies from 2016–2024, the review synthesizes evidence on: (1) the role of tourism-led growth and its multiplier effects on local economies; (2) community-based tourism (CBT) as an inclusive development model; (3) structural transformation theory as a framework for economic diversification; and (4) the specific potentials and constraints facing tourism development in resource-dependent regions. The review finds that tourism exhibits significant forward and backward economic linkages, stimulates SME growth and creative economy, and can meaningfully reduce reliance on extractive industries. Key barriers include infrastructure gaps, limited human resource capacity, and suboptimal governance coordination. The findings provide a theoretical and empirical foundation for the ongoing field research into tourism's transformative role in Kutai Kartanegara's regional economy.
Abstract:Cayenne pepper (Capsicum frutescens L.) is a horticultural commodity with high economic value and continuously increasing market demand. The success of cayenne pepper production is largely determined by vegetative growth…
in the early stages, which is influenced by the availability of nutrients and plant growth regulators. The use of manure as a source of organic matter and natural Plant Growth Regulators (PGRs) is expected to enhance vegetative growth. This study aimed to determine the effect of manure application and natural PGRs on the vegetative growth of cayenne pepper and to identify the treatment that produces the best growth.The research was conducted from December to January 2026 at the land of the Kopbun Suka Tani Sejahtera Business Research Center, Kota Juang District, Bireuen Regency. The study used a factorial Randomized Block Design (RBD) with a 4 × 3 pattern and three replications. The first factor was the dosage of manure consisting of 0 kg (control), 1 kg, 1.5 kg, and 2 kg per plant. The second factor was the type of natural PGR, consisting of shallot extract, rice water, and coconut water. The observed parameters included plant height, number of leaves, leaf width, and number of branches at 15, 30, and 45 days after planting (DAP). Data were analyzed using the F-test and continued with the Honestly Significant Difference (HSD) test at a 5% significance level if the results were significant.The results showed that manure application had no significant effect on all vegetative growth parameters up to 45 DAP. The application of natural PGRs also showed no significant effect at 15, 30, and 45 DAP, as well as on other parameters. There was no significant interaction between manure and natural PGRs on all observed parameters.
Abstract:This study aims to determine the effect of manure dosage and types of plant growth regulators (PGRs), as well as their interaction, on the generative phase of bird’s eye chili plants (Capsicum frutescens L.) in order to…
o improve productivity, which remains fluctuating due to suboptimal cultivation practices. The research was conducted from February to March 2026 at the experimental field of the Pusat Riset Bisnis Kopbun Suka Tani Sejahtera, Kota Juang District, Bireuen Regency, using a factorial Randomized Block Design (RBD) of 4 × 3 with three replications. The first factor was the dosage of manure (control, 1 kg/plant, 1.5 kg/plant, and 2 kg/plant), while the second factor was the type of natural PGR (onion extract, rice water, and coconut water). Data were collected through direct observations on several parameters, including number of fruits, fruit weight, fresh biomass weight, root fresh weight, and root length, and were then analyzed to determine the effects of treatments and their interactions.
The results showed that certain doses of manure had a significant effect on increasing yield and root growth, while natural PGRs were able to enhance flowering, reduce flower drop, and accelerate fruit formation. The interaction between both treatments indicated that the optimal combination produced higher results compared to single treatments. The novelty of this study lies in the use of a combination of manure and natural PGRs based on local materials as a strategy to improve the generative phase. The implications of this research are expected to serve as a scientific reference for the development of sustainable cultivation techniques, as well as learning material and further research in the fields of agronomy and horticulture.
Abstract:The Supan Supan Laki plant (N. plena Lour) has been used traditionally by a group of people in Pal Batu Village, Paminggir District, North Hulu Sungai Regency as a herbal medicine to increase male sexual activity. Based…
on previous research, this plant has been proven to have a positive effect in increasing fertility in test animals. However, until now, there is no certainty regarding the safety of using this plant. This study aims to examine the effects and safety of consuming Supan Supan Laki extract on the macroscopic appearance of the liver and kidneys in mice. This research was carried out, there were four treatment groups in this study, namely Na-CMC 0.5%; 87.5mg/KgBW; 175mg/KgBW; and 350mg/KgBW, given for 28 days using a Completely Randomized Design (CRD) trial design. On the 29th day, surgery was performed to observe the liver and kidney macroscopically. Measurement of color, surface and relative organ weight parameters of the kidneys and liver of mice. The results of the study showed that administration of Supan Supan Laki leaf extract caused significant changes in the macroscopic appearance of the liver and kidney organs. In the research analysis using the One Way Anova test, the results of the test showed that the liver (p>0.05) did not have a significant level of variation, while the kidney (p<0.05) had a significant level of variation so that it could be concluded that the effect of N.plena Lour leaf extract have different effects on the relative weight of the heart and kidney organs.
Abstract:This study aims to identify the dominant error patterns of students in geometry learning based on Newman's Error Analysis (NEA) and to examine their implications for readiness to understand Non-Euclidean Geometry. The method…
thod employed is a Systematic Literature Review (SLR) of 10 empirical articles published between 2019 and 2026. Data were extracted based on the five stages of NEA — reading, comprehension, transformation, process skill, and encoding — and subsequently analyzed through narrative synthesis, percentage comparison, and descriptive effect size. The results indicate that comprehension errors and encoding errors are the most dominant categories, with the highest percentages of 56.92% and 50%, respectively, followed by transformation errors, which consistently fall within a moderate effect range (20–40%), while reading errors and process skill errors are classified as low. The primary causes of errors include weak understanding of geometric concepts, inability in spatial visualization, limited mathematical language, and lack of procedural precision. The findings contribute as a diagnostic foundation for designing more effective geometry learning, while simultaneously serving as a conceptual bridge toward higher-level geometry