Document grouping is a necessity among a large number of articles published on internet. Several attempts have been done to improve this grouping process, while majority of the efforts are based on word appearance. In order to improve its quality, the grouping of documents need to be based on topic similarity between documents, instead of the frequency of word appearance. The topic similarity could be known from its latency, since the similarity of the word interpretation are often used in the same context. In the unsupervised learning process, SOM is often used, in which this approach simplifies the mapping of multi-dimension data. This research result shows that implementation of the latent structure decreases characteristic dimension by 32% of the word appearance, hence makes this approach more time efficient than others. The latent structure, however, when implemented on SOM Algorithm, is capable to obtain good quality result compared to word appearance frequency approach. It is then proven by 5% precision improvement, recall improvement of 3%, and another 4% from F-measure. While the achievement is not quite significant, the quality improvement is able to put the dominance of grouping process, compared to the original classification defined by the content provider.
Road, as one of the land transportation infrastructure, is important for economic improvement of an area. It needs special and regular maintenance by the local government, in order to keep the road in good condition. For this purpose, the government conducts a survey with the aim of getting criteria for determining priority of road maintenance. The obstacle in implementation of road maintenance is the lack of criterias which make difficulties in determining the priority of road maintenance. Decision-making system is needed to solve the problems of determining the priority of road maintenance. Fuzzy Analytical Network Process (FANP) can solve the problem by calculating the criteria to get priority value. This method consists of many steps, namely weighting among criteria, weighting among sub-criteria, triangular fuzzy number, fuzzy synthesis, weight matrix, and priorities. The results show that the priority order of routine road maintenance is Jl. Jakarta, Jl. Kelud, and Jl. Kyai Tamin. The accuracy rate obtained in this research is 66.67%. Sensitivity test shows that the damage of the roads and the road density are important factors in generating the weight value road maintenance priorities.
Kemajuan teknologi informasi memungkinkan kegiatan peramalan energi listrik dapat dilakukan dengan berbagai metode. Metode jaringan syaraf tiruan perambatan balik dan jaringan syaraf adaptif telah diterapkan pada kegiatan peramalan energi listrik. Keberhasilan peramalan ditentukan ketepatan data yang relevan. Dalam penelitian ini dipilih beberapa data meliputi : Produk Domestik Bruto perkapita, pertumbuhan penduduk, jumlah rumah tangga, jumlah energi total dan daya tersambung. Data yang dipergunakan adalah data yang diperoleh dari Badan Pusat Statistik Malang dan PT PLN APJ Malang. Data untuk pembelajaran diambil mulai tahun 2001-2005, untuk pengujian mulai tahun 2006-2008 dan peramalan tahun 2009. Penelitian ini menyajikan suatu algoritma jaringan saraf adaptif untuk peramalan permintaan energi listrik. Studi empiris menunjukkan bahwa jaringan saraf adaptif algoritma konvergensi lebih cepat dan presisi yang lebih tinggi daripada algoritma jaringan saraf. Hasil peramalan memperlihatkan error rata-rata sangat kecil, yaitu sebesar 1%.<br /><br />Kata kunci : Peramalan, Jaringan Syaraf Adaptif.<br /><br />
Three wheeled omnidirectional robot has been used in industries and academics fields because its ability to move freely and simultaneously both rotation and translation. Free movement in this robot is assisted by omni wheel which consists of wheels and rollers. So, the movement of this robot is a combination of wheel and roller rotation. At present, the task given to the mobile robot is increasingly complex, so it makes microcontroller’s workload heavier. A microcontroller’s workload could be lightened by master-slave configuration to divide the microcontroller’s tasks. The wheel rotating speed control system uses a pid controller to obtain a fast and stable wheel speed response. The PID parameters, kp,ki,kd were obtained by using the hand tuning method. The testing results shown the average error of robot direction is 4,3750 and the direction of the robot’s face changed 5.750.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.