In the world of modern energy, Lithium-Ion batteries reign supreme, offering rechargeability, sustainability, and long-term energy storage. However, their lifespan is not infinite, calling for accurate prediction of remaining life under various conditions. Deep learning shines in this domain, with the Transformer architecture blossoming as a powerful tool for time series forecasting. This research dives into data collection, processing, model design, training, and evaluation, making key methodological contributions to battery life prediction. Notably, the SGEformer model, a Transformer enhanced with growth and seasonal embedding, emerges as a groundbreaking innovation. Comparing SGEformer to ETSformer, Informer, Reformer, Transformer, and LSTM reveals its unique strengths. With an impressive MSE score of 0.000117, SGEformer establishes itself as a highly effective tool for battery life prediction, highlighting the value of growth and seasonal embedding in boosting accuracy. This research propels the state-of-the-art Lithium-Ion battery state-of-health prediction, offering a robust methodological foundation for precise and reliable forecasts. Code can be accessed at https://github.com/MRifqiFz/SGEformer .
Optimasi pemilihan rute merupakan masalah yang banyak dibahas padapenelitian ilmu komputer. Antar jemput laundry dengan pelanggan yang memiliki waktukhusus untuk menerima barang adalah salah satu contoh kasus pemilihan rute.Penghitungan rute tercepat memegang peranan penting karena harus tepat waktu dansemua pelanggan dapat dilayani. Berbeda dengan traveling salesman problem (TSP)konvensional yang bertujuan untuk meminimalkan jarak, kasus ini juga harusdipertimbangkan waktu ketersediaan setiap pelanggan. Pencarian solusi untukpermasalahannya adalah dengan mengkombinasikan solusi-solusi (kromosom) untukmenghasilkan solusi baru dengan menggunakan operator genetika (seleksi, crossover danmutasi). Untuk mencari solusi terbaik digunakan beberapa kombinasi probabilitascrossover dan mutasi serta ukuran populasi dan ukuran generasi. Dari hasil pengujiankombinasi probabilitas crossover yang terbaik adalah 0,4 dan mutasi adalah 0,6sedangkan untuk ukuran generasi optimal adalah 2000. Dari nilai-nilai parameter inididapatkan solusi yang memungkinkan untuk melayani semua pelanggan dengan time window masing - masing.
Rainfall Prediction in Indonesia is very important for agricultural sector. However, obtaining an accurate prediction is difficult as there are too many input parameters including the world climate change that affect the accuracy. An accurate prediction is required to arrange a good schedule for planting agricultural commodities. A good approach is required to obtain a good model as well as the accurate prediction. This paper proposes Tsukamoto fuzzy inference system (FIS) to solve the problem. An intensive effort is put in building fuzzy membership function based on rainfall data in Tengger region from ten years ago. A series of numerical experiments prove that the proposed approach produces better results comparable to those achieved by other approach. In Tutur region Tsukamoto fuzzy inference system obtain Root Mean Square Error (RMSE) of 8.64, it is better than GSTAR-SUR method that obtain RMSE of 10.89.
1 March 2016 in TELKOMNIKA (Telecommunication Computing Electronics and Control)
This study investigates Particle Swarm Optimization (PSO) hybridization with Simulated Annealing (SA) to optimize Support Vector Machine (SVR). The optimized SVR is used for software effort estimation. The optimization of SVR consists of two sub-problems that must be solved simultaneously; the first is input feature selection that influences method accuracy and computing time. The next sub-problem is finding optimal SVR parameter that each parameter gives significant impact to method performance. To deal with a huge number of candidate solutions of the problems, a powerful approach is required. The proposed approach takes advantages of good solution quality from PSO and SA. We introduce SA based acceptance rule to accept new position in PSO. The SA parameter selection is introduced to improve the quality as stochastic algorithm is sensitive to its parameter. The comparative works have been between PSO in quality of solution and computing time. According to the results, the proposed model outperforms PSO SVR in quality of solution
30 April 2017 in Journal of ICT Research and Applications