Waeisul Bismi’s research while affiliated with Bina Sarana Informatika and other places

The fig plant, known as Ficus carica, has been cultivated worldwide, including in Indonesia. It has nutritional benefits and medicinal properties. However, there are still difficulties in growing it, making the plant scarce. The scarcity of fig plants in Indonesia is mainly due to the threat of diseases and viruses that affect them. There are various diseases that affect fig plants, including leaf rust (Cerotelium fici), mosaic disease, and Bemisia tabaci (whitefly) disease. Infected fig plants become unhealthy, experiencing stunted growth and deformed fruits thus it is necessary to identify the diseases accurately using technological assistance. This research aimed to automatically identify diseases in fig leaves. The method started by digitizing fig leaf images and confirming with botanical experts specializing in fig plants to label the types of diseases present. The research produced a dataset of fig leaf images consisting of four classes of fig leaves: Cerotelium fici, mosaic disease, whitefly, and healthy fig leaves. The dataset resulted in confirmed 300 fig leaf images. The augmentation techniques were applied to increase images to 3,300 fig leaf images. This dataset was then divided into subsets for training, validation, and testing. For the classification and identification, a Deep Learning approach was used with three models: VGG16, VGG19, and MobileNet. Among these models, MobileNet achieved the highest accuracy of 98.79%. Subsequently, the identification system was implemented by converting the generated model into TensorFlow Lite and integrating it into the Android Studio software, enabling it to function as a mobile application on Android devices.

The development of Website-based information systems has provided significant benefits in terms of distance, time, and accessibility, particularly in the construction industry for finding skilled and experienced construction workers. However, challenges arise in finding qualified workforce due to the phenomenon of globalization. To overcome this issue, SIPAKUPROY is designed as an information system that supports these needs. Through SIPAKUPROY, users can access multiple construction worker teams, obtain detailed pricing information, and follow an efficient payment process. The transition process from manual to digital sales systems, known as digitalization, is a crucial key in implementing SIPAKUPROY, which requires suitable and reliable software and hardware. In the design of SIPAKUPROY, user-friendly design is the main focus, aiming to provide an easy and comfortable user experience. Overall, SIPAKUPROY offers a solution for individuals seeking reliable construction workers without personal connections in the industry. Thus, SIPAKUPROY makes a positive contribution in addressing the challenges faced in finding trustworthy construction workers in this era of globalization.

This research aims to develop an image classification method for the panthera genus using a deep learning approach based on Convolutional Neural network (CNN). The panthera genus includes large species such as tigers, lions, leopards, and jaguars, which share similarities in appearance but also differences in fur patterns, body size, and habitat. Image classification of the panthera genus is important in various applications, including wildlife conservation and biological research. In this study, image datasets of tigers, lions, and leopards were collected from various sources to a total of 6,290 images. The proposed method involves image pre-processing, such as resizing, converting and normalization, and the use of a Convolutional Neural network (CNN) model to perform classification. The CNN model is implemented and trained using training data to recognize specific visual patterns in the images of each species. The results of this study show that the CNN-based deep learning approach can achieve high accuracy in the classification of panthera genus images of 85.21%. This method can correctly distinguish between tiger, lion, and leopard images based on unique visual features. In addition, the deep learning approach also offers advantages in efficiency and scalability to cope with the large number of images in the dataset. This research makes an important contribution to the development of wildlife image classification methods using a CNN-based deep learning approach.

Semakin tingginya angka penduduk tahun 2022 di Indonesia sebanyak 275.361.267 jiwa sangat berpengaruh pada hunian yang akan dijadikan tempat tinggal baik berupa apartemen, villa, kontrakan, kos-kosan maupun perumahan yang saat ini masih banyak kita temui dijalanan masih berbentuk media cetak seperti brosur, baliho, maupun mulut ke mulut. Perumahan merupakan bangunan yang meliputi keterangan tanah beserta bangunan properti diatasnya dan memiliki hak berupa, milik, guna atau sewa seseorang. Pada era globalisasi saat ini dengan adanya kemajuan serta semakin berkembangnya teknologi yang begitu cepat dan pesat begitu banyak hal yang kita rasakan seperti manfaat dan kelebihan dari teknologi tersebut, salah satu nya di bidang bisnis perumahan yang bertujuan mempermudah dalam pencarian maupun pemasaran. Maka dari itu dibutuhkan platform untuk menjadi pendukung dalam proses bisnis pencarian maupun pemasaran secara digital dengan membuat SICAPERBET yakni sebuah sistem informasi cari perumahan berbasis website. Dalam pembuatan sistem informasi ini menggunakan Android Studio Code berupa software untuk melakukan pemrogramman serta Codeigniter yang digunakan sebagai kerangka kerja atau framework dengan model MVC (Model, View, Controller) dan perancangan sistem yang digunakan ada berupa usecase dan activity diagram serta rancangan database menggunakan ERD dan LRS. Sehingga diharapkan para penjual serta para pencari perumahan dapat mengiklankan, memasarkan dan mencari perumahan dengan mudah dan tentunya lengkap.

Disorders of the eye or also known as eye disease is a condition that can affect vision for some people in their lifetime. There are 40 types of eye disorders or eye diseases, one of which is Myopia. Myopia is a visual disturbance that causes objects that are far away to appear blurry, but there is no problem seeing objects that are near. Myopia or nearsightedness is also known as minus eye. From this description, it is very important to conduct research in detecting eye diseases before the increase in eye minus and blindness. This study aims to classify myopic eye disease using the Deep Learning method with several different architectures, namely the VGG16, VGG19 and InceptionV3V3 models. Where the first is to distinguish normal and abnormal while the other is to classify with Augmented myopia image dataset and non augmented myopia image dataset obtained from the Retinal Fundus Multi-Disease Image Dataset (RFMID). In the implementation of the Deep Learning method using 20 Epochs. The results of the accuracy of the classification of eye diseases using the non augmented myopia image dataset are 66.0% for the VGG16 architectural model, then 95.99% for the VGG19 architectural model and 93.99% for the InceptionV3 architectural model and the accuracy results using the Augmented myopia image dataset are 97.53% for the VGG16 architectural model, 97.53% for the VGG19 architectural model and 99.50% for the InceptionV3 architecture model.

Penyakit Parkinson merupakan gangguan neurodegenerative yang bersifat progresif dan relative umum pada system saraf pusat yang menyebabkan kesulitan dalam bergerak. Biasanya penyakit ini sering terjadi pada individu berusia lebih dari 60 tahun dipengaruhi oleh factor genetic dan lingkungan. Deteksi dini pada penyakit Parkinson dapat mencegah gejala hingga usia tertentu sehingga meningkatkan harapan hidup. Dalam penelitian ini bertujuan untuk menggunakan gambar otak dari Magnetic Resonace Imaging (MRI) untuk mengetahui bagaimana penyakit tersebut menyebar, dengan menggunakan metode deep learning menggunakan model atau arsitektur InceptionV3, VGG16, VGG19, NasnetMobile, dan MobileNet dengan melalui proses Input data - augmentasi - preprocessing - Classification (model a b c d ) - result dan pembelajaran mesin pada kumpulan data klinis dan paraklinis untuk mendiagnosis secara akurat meggunakan dataset yang berasal dari Parkinsons Brain MRI sebanyak 2 kelas yaitu kelas normal dan Parkinson. Hasil dari penelitian menggunakan deep learning berdasarkan kelima algoritma yang digunakan tersebut diperoleh nilai akurasi terbaik dari seluruh model arsitektur adalah arsitektur MobileNet sebesar 99,75% dengan kappa score 99,30% dengan total durasi komputasi selama 2 jam satu menit

Perkembangan teknologi informasi yang semakin pesat di era globalisasi saat ini tidak bisa dihindari lagi pengaruhnya terhadap dunia pendidikan. Tuntutan global menuntut dunia pendidikan untuk selalu dan senantiasa menyesuaikan perkembangan teknologi. Pada penelitian ini bertujuan untuk menguji penerimaan pengajar terhadap penggunaan teknologi dalam pendidikan dengan menggunakan metode Technology Acceptance Model (TAM) sebagai pendekatan analitik. Pada penelitian ini ter-dapat empat faktor TAM, yaitu persepsi kemudahan penggunaan, persepsi kegunaan, sikap terhadap penggunaan kom-puter, dan niat penggunaan. Niat Perilaku sebagai pengguna menjadikan faktor evaluasi untuk mengukur penerimaan teknologi oleh pengajar dan diajukan total enam hipotesis. Kuesioner online digunakan untuk mengekstrak informasi dari pengajar di Jakarta dan terkumpul sebanyak 150 responden. Hasil penelitian menjelaskan bahwa penggunaan komputer ditentukan sebagai faktor kunci dalam penerimaan penggunaan teknologi yang dapat dijelaskan oleh faktor – faktor dan dapat dievaluasi untuk menjelaskan perilaku penggunaan terhadap teknologi dalam pendidikan.The development of information technology that is increasingly rapidly in the current era of globalization cannot be avoided anymore its influence on the world of education. Global demands require the world of education to always and constantly adapt to technological developments. This study aims to test the acceptance of teachers towards the use of technology in education by using the Technology Acceptance Model (TAM) as an analytical approach. In this study, there are four TAM factors, namely perceived ease of use, perceived usefulness, attitudes towards computer use, and usage intentions. Behavioral intention as a user is used as an evaluation factor to measure technology acceptance by teachers and a total of six hypotheses are proposed. An online questionnaire was used to extract information from teachers in Jakarta and collected 150 respondents. The results of the study explain that the use of computers is determined as a key factor in the acceptance of the use of technology which can be explained by factors and can be evaluated to explain the behavior of using technology in education.

Pewarnaan graf adalah teknik pemberian warna pada setiap titik pada graf, yang menyebabkan dua titik yang berdekatan tidak memiliki warna yang sama. Graf dapat diwarnai dengan memberikan warna yang berbeda untuk setiap simpul. Untuk itu peneliti mengimplementasikan pewarnaan graf pada peta provinsi Jawa Barat menggunakan Algoritma Welch-Powell. Algoritma Welch-Powell merupakan algoritma yang digunakan untuk mewarnai simpul-simpul graf berdasarkan derajat sudut tertinggi. Penelitian diawali dengan pemahaman tentang pewarnaan graf dan algoritmanya. Penelitian ini menjelaskan bahwa dalam melakukan pewarnaan graf pada peta Provinsi Jawa Barat terdapat bilangan kromatik yang diperoleh X (G) = 3 dan menghasilkan 20 titik yang membutuhkan tiga warna berbeda yaitu merah, kuning dan biru.