Abstract: An activity recognition method and a computer-readable media are disclosed. The activity recognition method is applied to an activity recognition system configured to recognize several activities. The activity recognition method includes: obtaining an original activity image corresponding to a first time point, wherein the original activity image includes several pixels indicating whether several sensors are triggered; determining an image feature according to a second activity corresponding to a second time point, wherein the second time point is prior to the first time point; integrating the original activity image and the image feature to generate a characteristic activity image; and determining a first activity corresponding to the first time point according to the characteristic activity image.

Abstract: A resident activity recognition method is provided. The method comprises: receiving a plurality of first testing data from a plurality of sensors by a processor, wherein the first testing data includes a present weight set of sensors and present trigger statuses of sensors; determining an activity of a non-target resident at a present time by the processor according to a non-target resident model and the first testing data; reducing a part of the present weight set to generate an updated weight set and a second testing data including the updated weight set and the present trigger statuses by the processor according to the activity of the non-target resident at the present time, the first testing data and the non-target resident model; determining an activity of a target resident at the present time by the processor according to a target resident model and the second testing data.

Abstract: A resident activity recognition method is provided. The method comprises: receiving a plurality of first testing data from a plurality of sensors by a processor, wherein the first testing data includes a present weight set of sensors and present trigger statuses of sensors; determining an activity of a non-target resident at a present time by the processor according to a non-target resident model and the first testing data; reducing a part of the present weight set to generate an updated weight set and a second testing data including the updated weight set and the present trigger statuses by the processor according to the activity of the non-target resident at the present time, the first testing data and the non-target resident model; determining an activity of a target resident at the present time by the processor according to a target resident model and the second testing data.

Abstract: A transmitting power level control method and system are provided, whereby the power of a terminal device in a wireless sensor network is saved and the lifetime thereof is extended. The control method includes the steps of: (A) broadcasting a plurality of transmitting power level (TPL) messages, each of which represents a respective TPL and the respective TPLs are different from one another, wherein each of the plurality of TPL messages is broadcasted at the respective TPL thereof; and (B) setting a TPL for the terminal device at a minimum one of the TPLs represented by the TPL messages received by the terminal device.

Abstract: A transmitting power level control method and system are provided, whereby the power of a terminal device in a wireless sensor network is saved and the lifetime thereof is extended. The control method includes the steps of: (A) broadcasting a plurality of transmitting power level (TPL) messages, each of which represents a respective TPL and the respective TPLs are different from one another, wherein each of the plurality of TPL messages is broadcasted at the respective TPL thereof; and (B) setting a TPL for the terminal device at a minimum one of the TPLs represented by the TPL messages received by the terminal device.

Abstract: Disclosed is a system and method for locating a mobile node in a network. The system comprises a plurality of beacon nodes, at least a router, a location host, and at least a mobile node. Each beacon node broadcasts at least a beacon signal at a first channel. A mobile node receives a plurality of beacon signals, and sends a corresponding packet's information to the location host at a second channel through a router. According to the packet's information, the location host may compute the location for the mobile node. This system distributes the communication loading to different groups and channels, which may estimate the locations for lots of mobile nodes at the same time, and gives a high communication quality and a good location estimation result.

Abstract: Disclosed is a system and method for intelligent traffic control using wireless sensor and actuator networks. The system comprises a control center, M regional gateways, and N sensor and actuator nodes. The N sensor and actuator nodes and L cluster heads form L clusters. Each cluster includes a cluster head and at least a sensor and actuator node. The control center, the M regional gateways, and the N sensor and actuator nodes form a multi-layer structure. Each N sensor and actuator node may real-time detect traffic states, and exchange information with other nodes via a wireless communication having a self-recovery function. The system and method applies a distributed computing strategy to automatically adjust the traffic control on each traffic flow, thereby achieving an efficient traffic control.