Artificial intelligence technology has dramatically improved the quality of services for human needs, one of which is technology to improve the quality of services for the blind and visually impaired, particularly technology that can help them understand visual sights to facilitate navigation in their daily lives. This study developed an image captioning model to aid the blind and visually impaired in outdoor navigation. The image captioning model employs the encoder-decoder method, with the convolutional neural network (CNN) feature extraction and attention layer as encoders and the long short-term memory (LSTM) as decoders. ResNet101 and ResNet152 are used in the encoder to extract image features. The results of the extraction and caption are forwarded to the attention layer and the LSTM network. The attention layer uses the Bahdanau attention mechanism. The accuracy of the model is calculated using the bilingual evaluation understudy score (BLEU), metric for evaluation of translation with explicit ordering (METEOR) and recall-oriented understudy for gisting evaluation-longest common subsequence (ROUGE-L). ResNet101 performed the best on BLEU-4, scoring 91.811% and 94.0337% in the METEOR evaluation. The captioning results show that the model is quite successful in displaying a simple caption that is suitable for each image.

Eight years since the implementation of the Regional Management Information System (SIMDA), there has been no specific research to analyze the information system both in terms of implementation, system quality, user acceptance, and the success of the system in its implementation. This study aims to determine the success of implementing the program at the Bengkulu Provincial DPMD office using the DeLone And McLean IS Success Model and Technology Accepeance Model (TAM) with seven research variables (system quality, information quality, perceived usefulness, perceived ease of use, service quality, user satisfaction, and net benefits). Furthermore, this research provides recommendations that can be used to update SIMDA so that it suits user needs. The seven variables of this study resulted in twelve proposed hypotheses (six were rejected and another was accepted). Six paths of accepted hypothetical relationships are: system quality with ease of use; relationship between information quality and perceived usefulness; relationship between information quality and net benefits; relationship between service quality and perceived ease of use; relationship between perceived ease of use and user satisfaction; and relationship between perceived usefulness and user satisfaction. Meanwhile, the relationship path of the rejected hypotheses is the relationship between system quality and perceived usefulness, the relationship between system quality and net benefits, the relationship between information quality and perceived ease of use, the relationship between service quality and user satisfaction, the relationship between perceived ease of use and perceived usefulness, and the relationship between user satisfaction and net benefits.

As a maritime country that consist of 17.504 islands, data collection and central monitoring have been a pressing concern in Indonesia. An efficient data collection process can help the decision maker to collect the accurate data to be processed as a decision and policy in the future. With conservation mobile used by all of the forest ranger in Indonesia, not only the biodiversity and wildlife could be managed properly but the performance of the conservation activity could be measure easily. In this paper, we develop an application for forest rangers to capture the data of biodiversity and conservation in Indonesia. This development was based on the latest law and policy in Indonesia to monitor the performance of conservation activity in Indonesia. It was developed by using Java programming language. The method we used is System Development Life Cycling (SDLC) and Unified Modelling Language (UML) 2.0 as the design model. The application was tested by using the method of the black box and the white box methodology.

Kemajuan disetiap bidang usaha tak lepas dari teknologi sebagai penunjangnya, terutama teknologi informasi [1][2]. Akan tetapi hal tersebut harus dimbangi dengan adanya sebuah evaluasi ataupun audit terhadap sistem informasi sehingga ancaman atau kerugian dapat dihindari[3][4][5]. Penelitian ini bertujuan untuk mengetahui sejauh mana kinerja sistem informasi repositori yang ada di UPT Perpustakaan Universitas Bengkulu sebagai layanan publik yang telah diterapkan pada Universitas Bengkulu. Dari penelitian ini diharapkan dapat memberikan rekomendasi tata kelola inovasi setelah mengetahui kesenjangan antara tatakelola saat ini dengan tatakelola yang diharapkan sesuai dengan framework yang digunakan. Framework yang digunakan dalam penelitian ini adalah COBIT versi 5 khusus pada domain Deliver and Support (DS) [1][6][7]. Teknik pengumpulan data yang dilakukan oleh penulis yaitu dengan studi literatur, observasi, wawancara dan kuisioner [8][9][10]. Hasil dari penelitian ini adalah untuk mengetahui tingkat kematangan (maturity level) pada implementasi sistem informasi repository khusus pada Domain DS, yaitu berada pada level 4 yang berarti sudah terukur dan terintegrasi antar proses yang berlangsung. Dan analisa GAP antara kondisi yang diharapkan dengan kondisi saat ini rata-rata sebesar 0,6.

Indonesia is an agricultural country with 29% of the workforce working in the agricultural sector, however, farmers' knowledge and practices depend on informal local wisdom based on inherited past practices. Moreover, identifying diseases in plants is difficult to do with human vision so that intelligent technology is needed. In this paper, an architecture of CNN models such as MobileNetV2, ResNetV50, InceptionV3 and DenseNet121 will be built to detect diseases based on leaf images of several crops obtained from the agroai dataset containing multiple crops namely bean, chili, corn, potato, tomato and tea. The model is used through transfer learning for feature extraction of the trained model with imagenet weights, with 4 fully connected layers. Each model for each crop will be compared to get the best model based on the accuracy of training, evaluation and testing. ResNet50 has the best performance for four type of plants, including bean plants with training accuracy of 99.49%, validation of 99.52%, testing of 98.96%, chili plants with training accuracy of 98.03%, evaluation of 98.75%, testing of 100%, tea plants with training accuracy of 99.62%, evaluation of 99.6%, testing of 99.74% and tomato plants with training accuracy of 99.62%, validation of 99.7%, testing of 99.37%. Moreover, MobileNetV3 has the best performance for 2 types of crops that is corn with training accuracy of 99.22%, validation of 99.69%, testing of 99.55%, and potato with training accuracy of 99.62%, evaluation of 99.60%, testing of 99.74%.

Citra penginderaan jauh merupakan objek hasil perekaman sensor ataupun suatu aplikasi pemantau penginderaan jauh. Namun terkadang citra yang dihasilkan memiliki kualitas yang rendah. Metode High-Frequency Emphasis (HFE) dan Contrast Limited Adaptive Histogram Equalization (CLAHE) merupakan algoritme yang baik dalam memperbaiki kualitas citra penginderaan jauh (remote sensing). Metode HFE bersifat mempertahankan frekuensi tinggi dan menekan frekuensi rendah. Pada penelitian ini, metode CLAHE mampu meningkatkan 8 citra dari 20 citra SAS-planet yang diujikan. Sedangkan pada metode HFE hanya 4 citra yang memiliki PSNR di atas 30 dB. Hasil penelitian ini mengindikasikan bahwa performa CLAHE lebih baik dibanding metode HFE dalam meningkatkan kulitas citra penginderaan jauh. Kata kunci: Citra Penginderaan Jauh, HFE, CLAHE