University is an organization that obliged to provide higher education, research, and community service (Tri Dharma), it has autonomy to manage their institutions. In order to realize Tri Dharma, University should made a planning of information technology (IT) infrastructure to support alignment process between organization business strategy and IT strategy. University of Lampung (Unila) as a government university in Lampung Province, already had IT infrastructure and managed by special unit. IT management on Unila nowadays more complicated, disintegrated of IT management has an effect that IT infrastructure was not adaptive to response the quick change of business needs. This research aimed to design an adaptive IT infrastructure based on enterprise architecture framework The Open Group Architecture Framework (TOGAF) Architecture Development Method (ADM) on Unila. The results of this research found that there are 3 core business activities, and 6 supporting activities identified on this campus. We also proposed 12 application to developed, all applications should be modular and integrated with other.
Oral diseases are a global health issue affecting billions of people worldwide. Early detection using artificial intelligence technology, particularly Convolutional Neural Networks (CNN), can enhance the accuracy of oral disease diagnosis. This study compares the performance of three CNN architectures—ConvNeXt Tiny, MobileNetV3 Large, and EfficientNet B0—in classifying oral diseases based on a medical image dataset. The evaluation considers accuracy, computational efficiency, and processing time. The results show that EfficientNet B0 achieved the highest accuracy (98.21%) with fewer parameters than ConvNeXt Tiny. However, ConvNeXt Tiny demonstrated the best absolute accuracy (96.96%) despite higher computational resource consumption. MobileNetV3 Large exhibited high efficiency in parameter usage with competitive accuracy (96.44%). Thus, the choice of CNN architecture depends on the trade-off between high accuracy and computational efficiency in clinical implementation.
1 October 2019 in Journal of Physics: Conference Series
Micro, Small, and Medium Enterprises (MSMEs) is one of a great contributor for Indonesian economy, but there are still many MSME actors who have difficulties in developing their business due to lack of knowledge about the use of technology to promote their products. On the other hand, the government also has difficulty obtaining MSME data because MSME actors are not all cooperative. This research offers a solution of the problems that have been described previously by developing Mobile Based Geographic Information System for Mapping Micro, Small, and Medium Enterprises. It is expected to help not only MSME actors to promote their products but also the government to collecting data. In addition, this system is also expected to assist users in obtaining information along with the location of MSME. This research has successfully generate Mobile Based Geographic Information System for Mapping Micro, Small, and Medium Enterprises by using Android platform. System testing result shows that Mobile Based Geographic Information System for Mapping Micro, Small, and Medium Enterprises has been successfully built and match the expected requirements.
10 March 2023 in Jurnal Pengabdian Kepada Masyarakat (JPKM) TABIKPUN
Sejak tahun 2020 Pekon Wonodadi, Kecamatan Gadingrejo, Kabupaten Pringsewu, Provinsi Lampung telah memanfaatkan teknologi informasi untuk pelayanan masyarakat dengan memanfaatkan aplikasi SIAP (Sistem Administrasi dan Pelayanan) sebagai salah satu implementasi Smart Village pada domain Smart Government. Berdasarkan penilaian Pemkab Pringsewu pekon Wonodadi memiliki kesiapan sumberdaya untuk melaksanakan Pemilihan Kepala Pekon dengan E-Voting bersama 10 pekon lainnya. Kegiatan PKM ini bertujuan untuk mendampingi aparatur pekon dalam menyiapkan dan menggunakan teknologi E-Voting untuk pemilihan Kepala Pekon. Tahapan kegiatan PKM ini adalah Pelatihan Instalasi Sistem E-Voting, Pelatihan Instalasi Teknologi Perekaman KTP Elektronik, Pelatihan Trouble Shooting Sistem, Pendampingan pelaksanaan Pemilihan Kepala Pekon, dan diakhiri dengan Evaluasi Kegiatan. PKM dinilai berhasil karena pelaksanaan pemilihan kepala pekon dengan sistem E-voting telah terlaksana secara baik dan lancar. Hasil ini dipengaruhi sikap positif masyarakat yang setuju terhadap pelaksanaan E-voting sebanyak 71,69%. Masyarakat menilai bahwa E-voting mudah digunakan, lebih cepat dan murah, menjamin prinsip LUBER JURDIL dan hasilnya realtime.
Dengue fever is a one of the dangerous diseases and very often causes casualties every year, especially in the tropics or subtropics countries. Dengue fever cases increase during the rainy season, many factors affect the spread of dengue fever, such as vegetation, population and landfills. The aim of this research is to predict the number of cases of Dengue fever using support vector machine. The data used are dengue data in Bandar Lampung City, weather data, population data and distance matrix data between dengue fever events with each other. The amount of data used is 1,080 data with 3 kernels: linear, gaussian and polynomial. In this study four experiments were carried out, the first two experiments were carried out without Feature Selection and the next two experiments were carried out with Feature Selection. After the experiment was found The best performance in the experiment with Feature Selection with 44 Variables. From the experiments conducted, Gaussian kernel achieved the highest R2 value which is 75.52%, while the Linear kernel and Polynomial Kernel achieved R2 value of 74.61% and 75.15%, respectively
30 June 2022 in International Journal of Electronics and Communications Systems
Smart Village innovatively uses information technology to improve quality of life and efficiency. This study seeks to cover research gaps, contribute to the research field, and serve as a platform for primary probabilistic research by overcoming a proposed concept about The Community Reporting application as a solution for mobile phones. This application development uses the DART language with the Flutter Framework. The research stages are divided into four parts: problem analysis, literature study, system development, and report writing. The UAT test on the community reporting application got a score of 81.43 percent from community respondents. Furthermore, the community reporting administration system scored 88.3% of the village apparatus respondents. Therefore, the developed application could be well received. The government and community should contribute to implementing government and developing villages based on information technology.