Publication

Journal papers

  1. S. Maya, K. Ueno, and T. Nishikawa. dLSTM: a new approach for anomaly detection using deep learning with delayed prediction. International Journal of Data Science and Analytics, 2019, pp:1-28.(paper)
  2. Y. Toyama, K. Yoshioka, K. Ban, S. Maya, A. Sai, and K. Onizuka. An 8 Bit 12.4 TOPS/W Phase-Domain MAC Circuit for Energy-Constrained Deep Learning Accelerators. IEEE Journal of Solid-State Circuits, 2019.(paper)

Conference papers (referred)

  1. S. Maya, A. Yamaguchi, K. Nishino, and K. Ueno. Lag-Aware Multivariate Time-Series Segmentation, SIAM SDM, 2020.(paper)
  2. A. Yamaguchi, S. Maya, K. Maruchi, K. Ueno. Learning Time-series Shapelets for Optimizing Partial AUC, SIAM SDM, 2020.(paper)
  3. A. Yamaguchi, S. Maya, T. Inagi, and K. Ueno. OPOSSAM: Online Prediction of Stream Data Using Self-adaptive Memory. 2018 IEEE International Conference on Big Data (Big Data). IEEE, 2018. (paper)
  4. K. Yoshioka, Y. Toyama, K. Ban, D. Yashima, S. Maya, A. Sai, and K. Onizuka. PhaseMAC: A 14 TOPS/W 8bit GRO based Phase Domain MAC Circuit for In-Sensor-Computed Deep Learning Accelerators. 2018 IEEE Symposium on VLSI Circuits. IEEE, 2018. (paper)
  5. S. Maya, K. Morino, H. Murata, R. Asaoka, and K. Yamanishi. Discovery of glaucoma progressive patterns using hierarchical MDL-based clustering. In Proceeding of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2015. (paper) (video)
  6. S. Maya, K. Morino, and K. Yamanishi. Predicting glaucoma progression using multi-task learning with heterogeneous features. In Proceeding of the 2014 IEEE International Conference on Big Data (Big Data). (paper)

Workshop papers (referred)

  1. S. Maya and K. Ueno. DADIL: Data Augmentation for Domain-Invariant Learning. Utility-Driven Mining, ACM SIGKDD workshop, 2018. (paper)
  2. S. Maya, K. Ueno, and T. Nishikawa. dLSTM: a new approach for anomaly detection using deep learning with delayed prediction. BigMine, ACM SIGKDD workshop, 2017. (video)

Conference papers (non-referred)

  1. S. Maya, A. Yamaguchi, T. Inagi, and K. Ueno. Flexible segmentation for multi-dimensional time series data (in Japanese). The 33rd Annual Conference of the Japanese Society for Artificial Intelligence, 2019. (paper)
  2. S. Maya, T. Koiso, and K. Ueno. A method to identify disease-related SNP combinations using mutual information ( in Japanese). SIG-FPAI, The Japanese Society for Artificial Intelligence, 2016. (paper)