• A 91-Channel Hyperspectral LiDAR for Coal/Rock Classification 

      Shao, Hui; Chen, Yuwei; Yang, Zhirong; Jiang, Changhui; Li, Wei; Wu, Haobo; Wen, Zhijie; Wang, Shaowei; Puttnon, Eetu; Hyyppä, Juha (Journal article; Peer reviewed, 2019)
      During the mining operation, it is a critical task in coal mines to significantly improve the safety by precision coal mining sorting and rock classification from different layers. It implies that a technique for rapidly ...
    • CIR-Net: Automatic Classification of Human Chromosome based on Inception-ResNet Architecture 

      Lin, Chenguang; Zhao, Gansen; Yang, Zhirong; Yin, Aihua; Wang, Xinming; Guo, Li; Chen, Hanbiao; Ma, Zhaohui; Zhao, Lei; Luo, Haoyu; Wang, Tianxing; Ding, Bichao; Pang, Xiongwen; Chen, Qiren (Peer reviewed; Journal article, 2020)
      Method: This paper focuses on chromosome classification because it is critical for chromosome karyotyping. In recent years, deep learning-based methods are the most promising methods for solving the tasks of chromosome ...
    • Doubly Stochastic Neighbor Embedding on Spheres 

      Lu, Yao; Corander, Jukka; Yang, Zhirong (Journal article; Peer reviewed, 2019)
      Stochastic Neighbor Embedding (SNE) methods minimize the divergence between the similarity matrix of a high-dimensional data set and its counterpart from a low-dimensional embedding, leading to widely applied tools for ...
    • Feasibility Study on Hyperspectral LiDAR for Ancient Huizhou-Style Architecture Preservation 

      Shao, Hui; Chen, Yuwei; Yang, Zhirong; Jiang, Changhui; Li, Wei; Wu, Haohao; Wang, Shaowei; Yang, Fan; Chen, Jie; Puttnon, Eetu; Hyyppä, Juha (Journal article; Peer reviewed, 2020)
      Huizhou-style ancient architecture was one of the most important genres of architectural heritage in China. The architecture employed bricks, woods, and stones as raw materials, and timber frames were significant structures. ...
    • Learning Image Relations with Contrast Association Networks 

      Lu, Yao; Yang, Zhirong; Kannala, Juho; Kaski, Samuel (Chapter, 2019)
      Inferring the relations between two images is an important class of tasks in computer vision. Examples of such tasks include computing optical flow and stereo disparity. We treat the relation inference tasks as a machine ...
    • Machine Learning for Hydropower Scheduling: State of the Art and Future Research Directions 

      Bordin, Chiara; Skjelbred, Hans Ivar; Kong, Jiehong; Yang, Zhirong (Peer reviewed; Journal article, 2020)
      This paper investigates and discusses the current and future role of machine learning (ML) within the hydropower sector. An overview of the main applications of ML in the field of hydropower operations is presented to show ...
    • Non-uniform Temperature Distribution's Impact on Downhole Weight on Bit Measurement (DWOB) and the Novel Compensatory Method 

      Wang, Chao; Liu, Gonghui; Li, Jun; Zhang, Tao; Yang, Zhirong; Jiang, Hailong; Ren, Kai; Wu, Zhe (Peer reviewed; Journal article, 2020)
      Non-uniform temperature distribution of DWOB measuring devices has a great effect on the accuracies of weight on bit (WOB) readings. To study the influence, two types of non-uniform temperature distributions of the WOB ...
    • A Simple and Novel Method to Predict the Hospital Energy Use Based on Machine Learning: A Case Study in Norway 

      Xue, Kai; Ding, Yiyu; Yang, Zhirong; Nord, Natasa; Barillec, Mael Roger Albert; Mathisen, Hans Martin; Liu, Meng; Giske, Tor Emil; Stenstad, Liv-Inger; Cao, Guangyu (Peer reviewed; Journal article, 2020)
      Hospitals are one of the most energy-consuming commercial buildings in many countries as a highly complex organization because of a continuous energy utilization and great variability of usage characteristic. With the ...
    • Word Embedding based on Low-Rank Doubly Stochastic Matrix Decomposition 

      Sedov, Denis; Yang, Zhirong (Chapter, 2018)
      Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, ...