Hasil Pencarian  ::  Simpan CSV :: Kembali

"Artikel ini akan mencoba membahas pemecahan masalah penjadwal kuliah dengan pendekatan ilmu Intelegensia Semu (Artificial Intelligence), yakni dengan menggunakan Constrain Satisfaction Problem. Penulis telah merancang dan menguji sebuah teknik baru pencarian solusi dengan intelligent search yang dikombinasikan dengan algoritma Smart Backtracking.Algoritma yang kami kembangkan ini telah dicoba dengan sejumlah studi kasus berskala kecil (7 dosen 7 matakuliah 23 kelas 2 ruang 35 jam perkulaiahan tiap minggu dan lebih dari 1380 mahasiswa) dan menghasilkan output yang diinginkan dalam waktu yang sangat singkat.Percobaan dengan real data (1198 dosen, 1457 matakuliah, 2311 kelas, 122 ruang, 40 jam perkuliahan tiap minggu dan lebih dari 20000 mahasiswa) telah menghasilkan solusi yang baik meskipun tidak dapat mencapai solusi 100% lengkap. Sejumlah constraint terutama yang berkaitan dengan dosesn dan mahasiswa kelas paket seringkali sulit dipenuhi karena adanya sejumlah kelas yang merupakan gabungan beberapa paker (dapat mencapai 12)"

"Perkembangan Artificial Intelligence (AI) sudah berkembang pesat. Dari ketiga arah pengembangan AI yakni computer vision, speech processing dan natural language processing. Speech processing memiliki tren paling rendah di antara ketiga pengembangan tersebut. Meskipun begitu pengembangan di bidang speech processing seperti speech recognition dan keyword spotting sudah banyak di implementasikan seperti model keyword spotting menggunakan Convolutional Neural Network (CNN) di microcontroller, mobile device dan perangkat lainnya. Namun CNN saja belum tentu menghasilkan akurasi yang tinggi maka dicoba Depthwise Separable Convolutional Neural Network (DSCNN) untuk mendapatkan hasil dengan akurasi yang lebih tinggi. Pengembangan model keyword spotting belum banyak diimplementasikan di edge device lainnya, yang dimaksud dengan edge device yaitu perangkat sederhana di sisi pengguna yang kemampuan komputasinya terbatas. Dengan menggunakan DSCNN menunjukkan nilai F1 score yang dibandingkan dengan model CNN. Model DSCNN menghasilkan model dengan nilai F1 score paling optimal dengan 4 layer konvolusi depthwise separable, menggunakan filter konvolusi sebanyak 256 dengan jumlah filter konvolusi depthwise 512 menggunakan optimizer RMSprop dan menggunakan batch size berukuran 126. Dari hasil pengujian dapat diketahui bahwa secara umum DSCNN menghasilkan F1 score yang lebih baik dibandingkan CNN yaitu sebesar 31,8% dengan CNN sebesar 28,35%. Namun DSCNN menggunakan sumber daya yang lebih banyak dan lebih lama waktu responsnya.

---

The development of Artificial Intelligence (AI) has grown rapidly. Of the three directions of AI development, namely computer vision, speech processing, and natural language processing. Speech processing has the lowest trend among the three developments. However, many developments in speech processing such as speech recognition and keyword spotting have been implemented, such as the keyword spotting model using the Convolutional Neural Network (CNN) in microcontrollers, mobile devices, and other devices. However, CNN alone does not necessarily produce high accuracy, so a Depthwise Separable Convolutional Neural Network (DSCNN) is used to get results with higher accuracy. The development of the keyword spotting model has not been widely implemented in other edge devices, which is meant by edge devices, namely simple devices on the user's side with limited computing capabilities. Using DSCNN shows the F1 score which is compared with the CNN model. The DSCNN model produces a model with the most optimal F1 score with 4 layers of convolution depthwise separable, using a convolution filter of 256 with a convolution depthwise filter of 512 using the RMSprop optimizer and using a batch size of 126. From the test results, in general DSCNN produces F1 score which is better than CNN, which is 31,8% with CNN at 28,35%. However, DSCNN uses more resources and a longer response time."

"Perkembangan dunia pariwisata menjadi salah satu poin penunjang pertumbuhan ekonomi. Berkaitan dengan hal tersebut, Bali mengambil bagian penting dalam perkembangan pariwisata Indonesia. Seperti halnya industri lain, efisiensi dan efektifitas dalam dunia pariwisata semakin dituntut, yang berakhir pada kepuasan pengunjung dan peningkatan potensi pariwisata. Sejalan dengan isu mengenai pariwisata tersebut, penelitian ini bertujuan untuk mengaplikasikan salah satu algoritma Tourist Trip Design Problem (TTDP) di Bali. Melalui studi kasus tersebut, diharapkan rekomendasi perjalanan untuk turis maupun rekomendasi perkembangan daerah Bali untuk pemerintah dapat diberikan. Metode yang digunakan adalah metode Greedy Randomized Adaptive Search Procedure with Path Relinking (GRASP-PR), yang dimodifikasi menggunakan bahasa pemrograman Java. Penelitian ini menunjukkan bahwa metode GRASP PR menghasilkan rekomendasi yang diharapkan dalam studi kasus tersebut yaitu rekomendasi durasi kunjungan, rekomendasi rute, dan juga rencana pengembangan untuk beberapa kabupaten di Bali.

---

The development of tourism is one of the main support for a country's economic growth. Bali, which is identified as the biggest entrance point to Indonesia, have an important part in the development of Indonesian tourism. Like other industries, the demand for efficiency and effectiveness in tourism as an effort to minimize costs and increase productivity is highly increasing, which in the end will actually result to tourists’ satisfaction and an increase in tourism potential. In line with the issue of tourism as have been stated above, this study aims to apply one of the Tourist Trip Design Problem (TTDP) algorithm in Bali. TTDP is one variety of Orienteering Problems (OP), which is still rarely discussed in Indonesia. Through the case study, it is hoped that travel recommendations for tourists and recommendations for the development of the Bali region for the government can be given. The method used is the Greedy Randomized Adaptive Search Procedure with Path Relinking (GRASP-PR), which is one of the algorithms that is often used to solve OP and in this research is modified using the Java programming language. This research shows that the GRASP-PR method produces the recommendations that was expected from the case study, including the duration of the visit, recommended routes, and also development plans for several districts in Bali."

"This book constitutes the refereed proceedings of the International Conference on Artificial Intelligence and Computational Intelligence, AICI 2012, held in Chengdu, China, in October 2012. The 163 revised full papers presented were carefully reviewed and selected from 724 submissions. The papers are organized in topical sections on applications of artificial intelligence; applications of computational intelligence; data mining and knowledge discovering; evolution strategy; intelligent image processing; machine learning; neural networks; pattern recognition."

"Data mining is one of the most rapidly growing research areas in computer science and statistics. Areas of application covered are diverse and include healthcare and finance. We wish to introduce some of the latest developments to a broad audience of both specialists and non-specialists in this field."

"Perkembangan teknologi Artificial Intelligence (AI), terkhusus AI text generators (AITGs), telah membawa perubahan signifikan dalam kehidupan manusia di Indonesia. Kehadiran AITGs berhasil mengubah perilaku seseorang mencapai berbagai tujuan, misalnya sebagai sumber belajar dan berpotensi menggantikan popularitas Google SE sebagai penyedia informasi paling populer saat ini. Penelitian ini bertujuan untuk memahami lebih jauh fenomena perpindahan dari Google SE ke AITGs dan memahami faktor-faktor yang memengaruhi terjadinya perilaku ini. Penelitian ini menggunakan kerangka PPM sebagai acuan pembentukan model. Penelitian ini melakukan analisis kualitatif terhadap 11 responden dan analisis kuantitatif terhadap 491 responden. Analisis data dilakukan dengan menggunakan grounded theory dan PLS-SEM modelling menggunakan bantuan aplikasi SmartPLS 4. Hasil penelitian ini mengungkapkan bahwa faktor low searching performance, explainability, inertia, perceived usefulness, social interaction, dan adaptability berpengaruh terhadap intensi berpindah dari Google SE ke AITGs. Sebaliknya, faktor privacy concern, intrusiveness of advertisement, perceived risk, dan perceived ease of use tidak berpengaruh secara signifikan terhadap intensi berpindah dari Google SE ke AITGs. Hasil tersebut diharapkan dapat membuka peluang bagi pengembangan ilmu pengetahuan secara umum dan terkhusus dalam konteks AITGs sebagai sumber belajar. Penelitian ini diharapkan dapat menjadi sumber informasi bagi masyarakat terkait AITGs sebagai sumber belajar, acuan bagi akademisi dan pengajar dalam penyusunan kurikulum dan aturan, serta bermanfaat bagi pelaku bisnis dan pengembang untuk meningkatkan fungsionalitas yang sesuai dengan kebutuhan masyarakat.

---

The development of Artificial Intelligence (AI) technology, especially AI text generators (AITGs), has brought significant changes to human life in Indonesia. The presence of AITGs has succeeded in changing a person's behavior to achieve various goals, for example as a learning resource, and has the potential to replace the popularity of Google SE as the most popular information provider today. This research aims to understand further the phenomenon of moving from Google SE to AITGs and understand the factors that influence this behavior. This research uses the PPM framework as a reference for model formation. This research conducted a qualitative analysis of 11 respondents and a quantitative analysis of 491 respondents. Data analysis was carried out using grounded theory and PLS-SEM modeling using the SmartPLS 4 application. The results of this study revealed that the factors of low searching performance, explainability, inertia, perceived usefulness, social interaction, and adaptability influenced the intention to switch from Google SE to AITGs. On the other hand, the factors of privacy concern, intrusiveness of advertisement, perceived risk, and perceived ease of use do not significantly influence the intention to switch from Google SE to AITGs. It is hoped that these results will open up opportunities for the development of knowledge in general and specifically in the context of AITGs as a learning resource. It is hoped that this research can be a source of information for the community regarding AITGs as a learning resource, a reference for academics and teachers in preparing curricula and regulations, as well as being useful for business people and developers to improve functionality by community needs."

"The International Conference on Engineering Research and Applications (ICERA 2018), which took place at Thai Nguyen University of Technology, Thai Nguyen, Vietnam on December 1-2, 2018, provided an international forum to disseminate information on latest theories and practices in engineering research and applications. The conference focused on original research work in areas including Mechanical Engineering, Materials and Mechanics of Materials, Mechatronics and Micro Mechatronics, Automotive Engineering, Electrical and Electronics Engineering, Information and Communication Technology. By disseminating the latest advances in the field, The Proceedings of ICERA 2018, Advances in Engineering Research and Application, helps academics and professionals alike to reshape their thinking on sustainable development."