Abstract:Abstract: Malaria remains a major global health problem, particularly in tropical countries such as Indonesia. Accurate early diagnosis is essential for reducing malaria-related morbidity and mortality. Conventional microscopic…
oscopic examination is time-consuming, highly dependent on expert personnel, and prone to human error. This study compares the performance of two Convolutional Neural Network (CNN) architectures, ResNet-50 and DenseNet-121, for malaria image classification. The Cell Images for Malaria dataset provided by the National Institutes of Health (NIH) through Kaggle was used, consisting of 27,558 microscopic blood cell images categorized into Parasitized and Uninfected classes. The dataset was divided into 80% training data and 20% testing data. Image preprocessing included resizing to 224 × 224 pixels, normalization, labeling, and data augmentation using RandomFlip, RandomRotation, RandomZoom, and RandomContrast. Experimental results showed that the ResNet-50 model trained for 100 epochs achieved the highest performance, with an accuracy of 95.54% and precision, recall, and F1-score of 0.96. The confusion matrix indicated 5,272 correctly classified images out of 5,510 testing samples. These findings demonstrate that ResNet-50 outperformed DenseNet-121 and has strong potential for supporting accurate, reliable, and efficient computer-aided malaria diagnosis based on microscopic blood smear images.
Keywords: computer-aided diagnosis; convolutional neural network (CNN); densenet-121; early detection; image classification; malaria; microscopic blood smear images; resnet-50;
Abstrak : Malaria masih menjadi masalah kesehatan global yang serius, terutama di negara tropis seperti Indonesia. Diagnosis dini yang akurat sangat penting untuk menurunkan angka morbiditas dan mortalitas. Metode konvensional berupa pemeriksaan mikroskopis memiliki keterbatasan karena memerlukan waktu yang relatif lama, bergantung pada tenaga ahli, dan berpotensi menimbulkan kesalahan manusia. Penelitian ini bertujuan membandingkan kinerja arsitektur Convolutional Neural Network (CNN) yaitu ResNet-50 dan DenseNet-121 dalam klasifikasi citra malaria. Dataset yang digunakan berasal dari Cell Images for Malaria yang disediakan oleh National Institutes of Health (NIH) melalui platform Kaggle, terdiri dari 27.558 citra dengan pembagian 80% data latih, 20% data validasi. Tahap praproses meliputi cleaning, resizing citra menjadi 224×224 piksel, normalisasi, labeling, serta data augmentasi menggunakan RandomFlip, RandomRotation, RandomZoom, dan RandomContrast. Hasil pengujian menunjukkan bahwa model ResNet-50 pada epoch 100 memperoleh akurasi sebesar 95,54% dengan nilai precision, recall, dan F1-score masing-masing sebesar 0,96. Confusion matrix menunjukkan jumlah prediksi benar sebanyak 5.272 dari total 5.510 data uji. Hasil ini menunjukkan bahwa arsitektur CNN mampu mengklasifikasikan citra malaria dengan tingkat akurasi yang tinggi dan memiliki kemampuan generalisasi yang baik terhadap data baru. Penelitian ini memberikan kontribusi dalam evaluasi performa arsitektur CNN untuk mendukung pengembangan sistem diagnosis malaria berbasis citra mikroskopis yang lebih cepat dan akurat.
Kata kunci: convolutional neural network (CNN); citra mikroskopis hapusan darah; densenet-121; diagnosis berbantuan komputer; deteksi dini; klasifikasi citra; malaria; resnet-50
Abstract:Abstract: Breast cancer is the leading cause of death for women globally, exacerbated by late detection. This study proposes a breast cancer risk prediction framework using XGBoost with SelectKBest feature selection. It…
aims to improve the accuracy and efficiency of early detection through exploratory data analysis, coding, SMOTE to address class imbalance, and feature selection (k=29). As a result, the XGBoost model achieved 98.1% accuracy, 98.1% recall, 98.1% f1-score, and 98.2% precision on test data, highlighting the importance of feature selection. These results are promising in patient prioritization (triage) for further examination, helping medical personnel identify high-risk patients, thus improving resource allocation efficiency. These findings validate SelectKBest and pave the way for the development of a machine learning-based clinical decision support system for breast cancer early detection workflows. This research contributes significantly to the application of machine learning to support early breast cancer detection.
Keywords: breast cancer; feature selection; machine learning; risk prediction; XGBOOST.
Abstrak: Kanker payudara menjadi penyebab utama kematian wanita global, diperparah deteksi yang terlambat. Penelitian ini mengusulkan kerangka prediksi risiko kanker payudara menggunakan XGBoost dengan seleksi fitur SelectKBest. Tujuannya meningkatkan akurasi dan efisiensi deteksi dini melalui analisis data eksploratif, pengkodean, SMOTE untuk mengatasi ketidakseimbangan kelas, dan seleksi fitur (k=29). Hasilnya, model XGBoost mencapai akurasi 98.1%, recall 98.1%, f1-score 98.1%, dan presisi 98.2% pada data uji, menyoroti pentingnya seleksi fitur. Hasil ini menjanjikan dalam penentuan prioritas pasien (triage) untuk pemeriksaan lebih lanjut, membantu tenaga medis mengidentifikasi pasien berisiko tinggi, sehingga meningkatkan efisiensi alokasi sumber daya. Temuan ini memvalidasi SelectKBest dan membuka jalan bagi pengembangan sistem pendukung keputusan klinis berbasis machine learning untuk alur kerja deteksi dini kanker payudara. Penelitian ini berkontribusi signifikan dalam penerapan machine learning untuk mendukung deteksi dini kanker payudara.
Kata kunci: kanker payudara; pembelajaran mesin; prediksi risiko ; seleksi fitur; XGBOOST.
Abstract:Abstract: Gambir Baru Kisaran Community Health Center is the only one in the Gambir Baru range. Data on visits by BPJS Health participants to the Gambir Baru Kisaran Community Health Center in 2023 from January – December…
December there are 3,048 BPJS participants. If the puskesmas services provided to the community are very good for BPJS patients, more and more BPJS participants will utilize health services and share information with the community about the benefits of BPJS Health serving General Polyclinics, Dental Polyclinics, Pharmacy Installations, Nutritionists, Outpatient and Maternity Care. Based on future problems such as the length of service time at the patient reception counter that patients receive is longer than the estimated time in the clinic SOP, namely 10 minutes, clinic staff must behave 5S (Smile, Greet, Regards, Polite and Polite) when serving patients, the process of taking medicines takes a long time after the patient has completed a health examination, the health center must provide services according to the wishes and understand the needs of patients, medical personnel and other staff, and can help if there are problems with patients, medical personnel take appropriate action and quickly, so it is necessary to carry out an evaluation as an effort to improve the quality of clinical services. he results of calculating the reality answers and expectations of patients/respondents at the Gambir Baru Health Center to 16 questions, the results of the decision recommendations are that 4 attributes must be improved and 12 more attributes must be maintained from 201 respondents-patients/patients at the Gambir Health Center.
Keywords: bpjs patient satisfaction; servqual method; web-based.
Abstrak:. Puskesmas Gambir Baru Kisaran adalah satu satunya yang berada di gambir baru kisaran. Data kunjungan peserta BPJS Kesehatan di Puskesmas Gambir Baru Kisaran Tahun 2023 dari bulan Januari – Desember ada 3.048 peserta BPJS. Jika pelayanan puskesmas yang diberikan pada masyarakat sangat baik tehadap pasien BPJS, maka akan semakin banyak peserta BPJS yang memanfaatkan pelayanan kesehatan dan berbagi informasi kepada masyarakat tentang manfaat dari BPJS Kesehatan melayani Poli Umum, Poli Gigi, Instalasi Farmasi, Ahli Gizi, Rawat Jalan dan Bersalin. Berdasarkan permasalahan di masa yang akan datang seperti lama waktu layanan di loket penerimaan pasien yang diterima pasien lebih lama dari waktu estimasi yang ada pada SOP klinik yaitu 10 menit, petugas klinik harus berprilaku 5S (Senyum, Sapa, Salam, Sopan dan Santun) pada saat melayani pasien, proses pengambilan obat yang memakan waktu lama setelah pasien selesai melakukan pemeriksaan kesehatan, pihak puskesmas harus memberikan pelayanan sesuai dengan keinginan dan memahami kebutuhan pasien, tenaga medis dan petugas lainnya, serta dapat membantu jika ada permasalahan pasien, tenaga medis melakukan tindakan secara tepat dan cepat, sehingga perlu dilakukan evaluasi sebagai upaya peningkatan kualitas layanan klinik. Hasil dari perhitungan jawaban realita dan harapan pasien/responden Puskesmas Gambir Baru terhadap 16 pertanyaan, hasil rekomendasi keputusan adalah 4 atribut harus ditingkatkan dan 12 atribut lagi harus dipertahankan dari 201 responden- pasien/pasien di Puskesmas Gambir.
Kata kunci: berbasis web; kepuasan pasien bpjs; metode servqual.
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:This research aims to determine the impact of water stress and the use of leaf compost on increasing yields and ideal plant development. This inspection was completed at the Medan City Food Security Center, jl . Selambo…
Ujung and Kramat are beautiful. between May and June 2023. The factorial randomized block design (RAK) used in this study consisted of two treatment factors symbolized by the symbol A at three levels, namely: A1) half KL (A2) 75% KL and (A3) 100 percent KL. The next factorial is with image P which consists of 3 levels, namely; (P1) is 1 g per liter of water, P2 is 2 g per liter, and P3 is 3 g per liter of water. With the aim of obtaining 9 drugs. Each treatment is repeated several times. The perception information is then investigated using the F test for changes at the 5% level. If the problem is large then proceed with the Duncan test. From the results of the examination and discussions carried out, results were obtained, including: 1). The influence of water pressure has a significant effect on plant height, number of leaves, leaf width, wet weight, and influences leaf length, leaf area and stem size of mustard greens (Brassica juncea L.). 2). Giving Gandasil D at a dose of 3 g/l of water basically increases the number of plants, number of leaves, leaf length, leaf width, stem size, new weight per plant, and selling weight. 3). The relationship between water stress treatment and use of leaf compost fundamentally affects plant height, number of leaves, leaf width, and wet load in mustard greens (Brassica juncea L.) while leaf length, leaf area and cross stem distance do not make a big difference.
Abstract:This study expects to determine the impact of cow compost and urea manure to increase yields and ideal plant development. This exploration was completed at the Medan City Food Security Administration, Jl. Delightful Kramat/Selambo…
at/Selambo Ujung. From May to August 2023. This study utilized a factorial randomized bunch plan (RBD) which comprised of 2 treatment factors with the image S which comprised of 3 levels, in particular; ( S1) 1 kg/plot (S2) 2 kg/plot and (S3) 3 kg/plot. The subsequent factorial is the U image which consists of 3 levels to be specific; (U1) 30 g/plot (U2) 40 g/plot and (P3) 50 g/plot. With the goal that 9 medicines were obtained. Every treatment was rehashed multiple times. The perception information was then examined with the F trial of change at the 5% level, in the event that the thing that matters was huge, the test was gone on with the Duncan test. From the aftereffects of the examination and conversation completed, the accompanying ends were obtained: 1). The impact of cow fertilizer application affected plant level, number of leaves, number of blossoms, number of cases and unit weight of bean plants (Phaseolus vulgaris L.) 2). The impact of applying urea manure meaningfully affected plant level, significantly affected the quantity of leaves, fundamentally affected the quantity of blossoms and affected the quantity of cases and unit weight of bean plants (Phaseolus vulgaris L.) 3). The communication between the treatment of cow excrement and urea manure essentially affected plant level, number of blossoms, number of cases and unit weight, but not altogether unique on the quantity of leaves of bean plants (Phaseolus vulgaris L.)
Abstract:This paper aims to analyze the need for the specific criminal procedure for disabled persons in Indonesian criminal justice system. This study employed doctrinal legal research using statute and conceptual approaches. The…
e findings of this research reveal that the criminal justice system is based on the normalcy concept, which holds that everyone is physically and cognitively normal. As a result, the investigation, prosecution, and examination processes in court proceedings are exclusively aimed at and created for regular people. Persons with disabilities have been pushed to the margins and perhaps ignored. Persons with disabilities' rights are frequently infringed, both as perpetrators and as witnesses/victims of criminal activities. The medical method should be abandoned in favor of a social approach for the criminal justice system to be pro-people. What's needed is for law enforcement to do their jobs at each stage of the criminal justice system so that people with disabilities can have a fair trial. In the early phases of the criminal justice process, a profile assessment is required to determine the character, challenges, and requirements of people with disabilities.
Abstract:Coronavirus Disease or COVID-19 is still a concern around the world. After additional examination, it was viewed that as a new strain of Covid was the reason. There is still a lot of controversy surrounding this disease,…
including aspects of diagnosis, treatment, and prevention. Therefore, we conducted a review of studies related to COVID-19 which have been widely published from early 2020 to the end of March 2020. Until now, definitive treatment for COVID-19 has not been found, patients with COVID-19 are only given supportive therapy. The method used in this research is a literature study, which is a study whose research object is in the form of library works, either in the form of scientific journals, books, articles in the mass media, as well as statistical data so as to describe the epidemiological trend of COVID 19. The purpose of writing this article is to knowing the distribution trend of COVID-19, which is still a pandemic issue.
Abstract:This study aims to determine the perceptions and reasons or factors underlying community preferences in choosing fracture treatment in Laucimba Village, Kabanjahe District. The study was conducted in Laucimba Village using…
ng a qualitative descriptive method, with data collection techniques including observation, in-depth interviews, and documentation. The results of the study indicate that traditional medicine has a more dominant positive perception compared to modern medicine, traditional medicine is considered more affordable in terms of cost, comfort, and a relatively faster healing process. Meanwhile, modern medicine is perceived as a more certain and safe treatment because it is supported by medical examinations and professional health workers, but some people consider this treatment expensive and high risk because it requires surgery. Community preferences are generally influenced by factors such as cost, distance and accessibility, personal experience, and the influence of family and social environment. Community decision-making in choosing fracture treatment is a rational action that is adjusted to conditions, needs, and beliefs