ILKOM Jurnal Ilmiah (Fakultas Ilmu Komputer, Universitas Muslim Indonesia)
Not a member yet
653 research outputs found
Sort by
IMPLEMENTASI METODE SPEECH RECOGNITION DAN METODE LINEAR SEARCH PADA SISTEM PENCARIAN ISTILAH BERBASIS WEB
Get PDFPemahaman akan istilah medis memungkinkan pasien untuk berkomunikasi secara efektif dengan dokter dan tenaga medis lainnya, sehingga dapat menggambarkan keluhan dengan lebih akurat, mengajukan pertanyaan yang tepat, dan memahami penjelasan yang diberikan oleh dokter. Di Inggit Medika Clinic, seringkali terjadi situasi dimana pasien bertanya mengenai istilah medis, yang membutuhkan waktu ekstra untuk dijelaskan oleh perawat atau staf. Penelitian ini bertujuan mengembangkan sebuah aplikasi berbasis web yang dapat membantu menjelaskan istilah medis secara spesifik kepada pasien, serta menjadi media informasi bagi masyarakat umum. Aplikasi ini menggunakan metode linear search sebagai algoritma pencarian istilah medis dalam database. Fitur Speech Recognition atau Automatic Speech Recognition (ASR) digunakan untuk memungkinkan pengguna mencari istilah medis secara langsung menggunakan suara. ASR menggunakan Acoustic Model dan model bahasa untuk mengenali dan memahami ucapan pengguna. Hasil penelitian menunjukkan bahwa sistem berbasis web ini efektif dalam melakukan pencarian istilah medis dan dapat diakses oleh masyarakat umum sebagai sumber pengetahuan dan sarana pembelajaran. Metode linear search dan speech recognition telah diterapkan dengan baik dalam aplikasi ini.Istilah medis merupakan kosakata khusus yang digunakan oleh para profesional kesehatan untuk menggambarkan kondisi medis, prosedur medis, obat-obatan, dan konsep-konsep yang berkaitan dengan kesehatan manusia. Pemahaman istilah medis memungkinkan pasien untuk berkomunikasi secara efektif dengan dokter dan profesional kesehatan lainnya. Pasien yang memahami istilah medis dapat menggambarkan keluhan mereka dengan lebih akurat, mengajukan pertanyaan yang tepat, dan memahami penjelasan yang diberikan oleh dokter. Demikian pula, pemahaman istilah medis juga penting bagi tenaga medis dalam menyampaikan informasi kepada pasien dengan jelas dan terperinci. Inggit Medika Clinic merupakan fasilitas kesehatan yang menyediakan pelayanan medis dasar dan spesialis. Klinik ini melayani berbagai kebutuhan medis seperti gawat darurat, kunjungan rumah, khitanan, konsultasi keluarga berencana, vaksinasi, dan pemeriksaan laboratorium. Dalam sehari, klinik ini melayani lebih dari 100 pasien. Dalam pengalaman di Inggit Medika Clinic, terdapat beberapa pasien yang sering menanyakan istilah medis kepada perawat atau staf, yang membutuhkan waktu ekstra untuk menjelaskan. Oleh karena itu, penulis membuat sebuah aplikasi berbasis web untuk membantu menjelaskan istilah medis secara spesifik kepada pasien dan juga sebagai media informasi untuk khalayak umum. Aplikasi ini menggunakan metode linear search, yaitu algoritma pencarian yang cocok untuk mencari istilah medis tertentu dalam database. Fitur Speech recognition atau Automatic Speech recognition (ASR) menggunakan teknologi dari Mozilla Developer. ASR memungkinkan pengguna web untuk mencari istilah medis secara langsung menggunakan suara. ASR menggunakan Acoustic Model dan model bahasa untuk mengenali dan memahami ucapan pengguna. Dalam penelitian ini, peneliti melakukan penelitian tentang aplikasi tersebut. Hasil penelitian menunjukkan bahwa sistem berbasis web ini dapat melakukan pencarian istilah medis dan dapat diakses oleh masyarakat umum sebagai sumber pengetahuan dan sarana pembelajaran. Metode linear search dan speech recognition telah digunakan dengan baik dalam aplikasi ini
The Implementation of GLCM and ANN Methods to Identify Dragon Fruit Maturity Level
Get PDFThe identification of the maturity level of dragon fruit in this study was divided into two groups of ripeness: the unripe and the ripe. This study aims to classify the maturity level based on dragon fruit images using the feature extraction method, the gray level co-occurrence matrix (GLCM). This research method consists of converting RGB data to grayscale, image normalization, detection of dragon fruit maturity, feature extraction, and identification. Data collection from real data totaled 60 images used in this study consisting of 40 training data and 20 testing data which are RGB image data in JPG format. Each data consists of 2 maturity categories. Training data consists of 20 images of 99% ripe dragon fruit and 20 images of 85%. Meanwhile, the testing data consisted of 10 of 99% ripe dragon fruit images and 10 of 85% ripe dragon fruit images. The image data is processed into a grayscale image which then detects the ripeness of the dragon fruit. After the maturity of the dragon fruit is obtained, segmentation is carried out on the location of the dragon fruit found. Then the feature calculation is performed using the Gray Level Co-Occurrence Matrix (GLCM). The Artificial Neural Network (ANN) algorithm is used for the identification process. The final test results show that the proposed method has been able to detect dragon fruit maturity level with an accuracy of = 9/10* 100% = 90%, calculated using the confusion matrix. Thus, implementing the Gray Level Co-Occurrence Matrix and Artificial Neural Network methods to the maturity level problem dragon fruit needs to be developed
Fuzzy C-Means with Borda Algorithm in Cluster Determination System for Food Prone Areas in Aceh Utara
Get PDFIn this research, the clustering of food prone areas in Aceh Utama is based on the Index Ketahanan Pangan (IKP) indicators compiled by Badan Ketahanan Pangan (BKP) using Fuzzy C-Means (FCM) and Borda algorithms. The fuzzy C-Means algorithm was used to classify food-prone areas with three clusters: very prone, moderately prone, and prone. The Borda algorithm was used to choose the most prone area from very prone clusters, which are considered urgently to be followed up by decision-makers. Based on the research results, it was found that in the aspect of food availability, four sub-districts are moderately prone, 10 are prone, and 13 are very prone. Regarding food affordability, it found that 12 sub-districts are moderately prone, seven are prone, and eight are very prone. Regarding food utilization, one sub-district is moderately prone, three are prone, and 23 are very prone. The results of voting using the Borda algorithm in very prone clusters are obtained Sawang District from the aspect of food availability, Syamtalira Aron District from the aspect of food affordability, and Lapang District from the aspect of food utilization. The clustering system is built based on the web using the PHP programming language
Naïve Bayes and K-Nearest Neighbor Algorithm Approach in Data Mining Classification of Drugs Addictive Diseases
No full textIndonesia, with its very large population, is a potential market for drugs trafficking. Hence, seriousness is needed in cracking down or preventing drug trafficking. Narcotics are substances or drugs that can cause dependence or addicted and other negative impacts on users. The problem is that drug users do not realize and even ignore diseases caused by drug addiction. The diseases can be life-threatening for users, such as inflammation of the liver, heart disease, hypertension, stroke, and others. The prevalence rate of drug abuse in West Nusa Tenggara (NTB) is included in the high category, reaching 292 cases or around 37.24% cases. This study aimed to create an application that can classify various diseases of drug users using the naïve bayes and KNN methods. The results of this study indicated that there was a very close relationship between drug users and various deadly diseases. The prediction results showed that the naive bayes method provided a prediction accuracy of 94.5% while the KNN showed a prediction accuracy of 92.5%. This shows that the naive bayes method provides better predictive performance than the KNN in the data set of drug addicts in NTB
Application of General Regression Neural Network Algorithm in Data Mining for Predicting Glass Sales and Inventory Quantity
Get PDFFF Jaya Glass is a shop that supplies and installs 3 mm to 12 mm glass. The store obtained glass from suppliers to be processed in shape and size according to customers’ order. After completing the customer's order, the shop worker will install the glass at the requested location. Unfortunately, currently stores do not utilize sales data to predict sales either manually or by utilizing technology. As a result, the store cannot predict when the number of glass orders will increase or decrease. In addition, errors often occur when ordering glass for the next period. As a result, stores often run out of glass supplies due to the large number of glass orders so that the achievement of profits is not optimal. This study aims to identify sales variables in glass sales data and build a general regression neural network model as a data mining method. In addition, this study aims to iterate to find the best value in the sales data training process, design and create applications according to user needs, and conduct system validation tests. The general regression neural network method is used to predict sales. The results of this study indicate that the application of general regression neural networks can be used to predict sales. This will make it easier for the store to provide glass supplies in the coming months with an accuracy of 98.1%
Combination of YOLOv3 Algorithm and Blob Detection Technique in Calculating Nile Tilapia Seeds
Get PDFBaby Fish counting must be counted accurately so it will not cause any loss, especially for fish seeds or fingerlings that have a small size. Generally, people still use conventional counting methods that produce low accuracy values. This research will make a Nila Baby Fish fingerlings counter program using the YOLOv3 algorithm and Blobb detection technique. The annotation data process will use LabelImg, and the dataset training will use Google COLABoratory with the Darknet framework in an online environment. Images that will predict in this program will be called and detected with an object detector. The object with a confidence score of more than 0.3 will be converted into a blob. The blob value will be forwarded to the output layer for scaling the bounding box objects. The output of this program is the predicted image, blob value, prediction time, and the number of Nila seeds. The model performance is evaluated using a confusion matrix and got a 98.87% for accuracy score
Classifying BISINDO Alphabet using TensorFlow Object Detection API
Get PDFIndonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well.Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well
Penerapan Metode KNN dalam Memprediksi Hasil Panen Kebun Tebu di Kab Takalar
Get PDFpertahun yang berasal dari perkebunan tebu yang menjadi komoditas unggulan produksi tanaman perkebunan, namun berdasarkan data BPS terjadi penurunan produktifitas tanaman tebu tahun 2015–2020. Hal ini dikarenakan infrastruktur yang masih terbatas, kesulitan dalam permodalan, terbatasnya penguasaan teknologi baik dalam usaha tani sehingga pengelolaan tanaman tebu menjadi terhambat. Penelitian ini bertujuan untuk mengetahui hasil prediksi kebu tebu pertahunnya dengan memanfaatkan data mining. Data mining yang digunakan dalam penelitian ini adalah metode K-Nearest Neighbour (KNN) yang merupakan metode klasifikasi terhadap obyek baru berdasarkan (K) tetangga terdekatnya. KNN termasuk algoritma supervised learning, dimana hasil dari query instance yang baru, diklasifikasikan berdasarkan mayoritas dari kategori pada KNN. Hasil penelitian menunjukkan dari tahap pengujian dengan jumlah data training sebanyak 13 data didapatkan nilai persentase tertinggi pada nilai K=7 dengan persentase akurasi sebesar 76.92%
Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN
Get PDFIndonesia is a tropical country with a diverse range of plants that ancient people used for traditional medicines. However, the similarity in shape of the leaves became an obstacle to distinguishing them. Therefore, technological advancements are expected to help identify the herbal leaves to use them right on target according to their efficacy. In this research, image classification of katuk (Sauropus Androgynus) and kelor (Moringa Oleifera) leaves is applied using 3 different algorithms i.e hybrid of Gray Level Co-Occurrence Matrix (GLCM) feature extraction and Support Vector Machine (SVM) implementing 4 kernels namely linear, RBF, polynomial, and sigmoid; hybrid of GLCM and Convolutional Neural Network (CNN); and pure CNN. A dataset of 480 images has been collected with 2 different scenarios, including bright and dark intensities. Based on the result, a hybrid of GLCM and SVM showed the highest accuracy of 96% in the dark intensity test using a linear kernel, while sigmoid obtained the lowest accuracy of 35%. On the other hand, it has been discovered that CNN obtained the highest performance in the bright intensity test with an accuracy of 98%. While in the dark intensity test, a hybrid of GLCM and CNN is superior, obtaining 96% accuracy. In conclusion, CNN is more powerful for image classification with bright intensity. For dark intensity images, both the hybrid of GLCM+SVM (linear) and the hybrid of GLCM+CNN are fairly recommended.Indonesia is a tropical country that has various types of plants which ancient people used them for traditional medicines. However, the similarity of leaves shape became an obstacle to distinguishing them. Therefore, technological advances are expected to help identify the herbal leaves in order to use them right on target according to their efficacy. In this research, image classification of katuk (Sauropus Androgynus) and kelor (Moringa Oleifera) leaves is applied using 3 different algorithms i.e hybrid of Gray Level Co-Occurrence Matrix (GLCM) feature extraction and Support Vector Machine (SVM) implementing 4 kernels namely linear, RBF, polynomial, and sigmoid; hybrid of GLCM and Convolutional Neural Network (CNN); and pure CNN. A dataset of 480 images has been collected with 2 different scenarios including bright and dark intensities. Based on the result, the hybrid of GLCM and SVM showed the highest accuracy of 96% in the dark intensity test using a linear kernel while the sigmoid obtained the lowest accuracy of 35%. On the other hand, it has been discovered that CNN obtained the highest performance in the bright intensity test with an accuracy of 98%. While in the dark intensity test, the hybrid of GLCM and CNN is superior obtaining 96% accuracy. In conclusion, CNN is more powerful for image classification with bright intensity. Whereas for the dark intensity images, both hybrids of GLCM+SVM (linear) and GLCM+CNN are fairly recommended
Design and Build of IoT Based Flood Prone Monitoring System at Semani’s Pump House Drainage System
Get PDFFloods are a common disaster in watersheds, and flood control is difficult. However, losses can be reduced by quickly disseminating alert status information. This paper proposes a prototype of a monitoring system that can determine the status of flood alerts in real time and quickly disseminating to the community, allowing people to be better prepared for flood disasters. The system was developed using the RD method and consists of hardware and software development. The hardware comprises several sensor modules to read the discharge, temperature, humidity, and water level and to transmit the readings to the software. The software is divided into two applications: a website application and a Telegram application. The public can find the flood alert status history data from the website and obtain flood alert status warning messages and the latest alert status from Telegram. The results of the tests indicated that the sensors were very accurate, with a MAPE value of less than 10%. The software test also showed that the input and output were according to design. The proposed system can potentially reduce flood losses by providing early warning information to the community. The system is also scalable and adaptable to other watersheds