Hongjun Bi

Learn More
We investigate a near-infrared (NIR) imaging method for capturing the interior of vehicles, the purpose of which is to automatically monitor and count vehicle occupants. The proposed NIR imaging method can effectively deal with the challenge due to windshield reflection and operate during both day and night. Our goal is to improve the clarity of the(More)
Multi-hop is widely used in wireless sensor networks to deliver packets; however, biased energy consumption rate (BECR) always happens when using this delivery method. BECR can cause energy hole and isolate some nodes, which would decrease the connectivity of the wireless sensor networks, and reduce nodes' sensor effectiveness and network lifetime. Hence,(More)
Adaptive kernel learning is a Bayesian learning technique developed recently, which can be viewed as a variant of the well known relevance vector machine (RVM). The purpose of adaptive kernel learning is to automatically optimize the parameters associated with the kernel basis functions in a predictive model. In this paper, we explore the use of adaptive(More)
  • 1