Abstract: A network attack pattern determination apparatus, method, and non-transitory computer readable storage medium thereof are provided. The apparatus is stored with several attack patterns and access records. Each access record includes a network address, time stamp, and access content. Each attack pattern corresponds to at least one attack access relation. Each attack access relation is defined by a network address and access content. The apparatus retrieves several attack records according to at least one attack address. The network address of each attack record is one of the attack address(s). The apparatus divides the attack records into several groups according to the time stamps and performs the following operations for each group: (a) creating at least one access relation for each attack address included in the group and (b) determining that the group corresponds to one of the attack patterns according to the at least one access relation of the group.

Abstract: A behavior inference model building apparatus and a behavior inference model building method thereof are provided. The behavior inference model building apparatus converts a plurality of program operation sequences of a plurality of program operation sequence data into a plurality of word vectors through a word embedding model, and inputs the first M word vectors of the word vectors, corresponding to each program operation sequence data, into a generative adversarial network (GAN) model to train and optimize the GAN model. The behavior inference model building apparatus integrates the word embedding model and the generator of the optimized GAN model to build a behavior inference model.

Abstract: A system and method for monitoring qualities of teaching and learning are provided. The system includes at least one receiving interface, a processor, and an output apparatus, wherein the processor is electrically connected to the at least one receiving interface and the output apparatus. The at least one receiving interface receives at least one digital image. The processor identifies at least one facial message from the at least one digital image, identifies at least one body message from the at least one digital image, and determines at least one teaching and learning quality index according to the at least one facial message and the at least one body message. The output apparatus outputs the at least one facial message, the at least one body message, and the at least one teaching and learning quality index.

Abstract: A computer device and a method of identifying whether container behavior thereof is abnormal are provided. The computer device detects container behavior of a container in a time interval, and identifies whether the container behavior of the container is abnormal according to a container behavior identification module, thereby determining whether there is an intrusion. In addition, a decoy container can be installed in the computer device to attract attacking or invading from a third party so as to reduce the risk of the container being attacked, and the container behavior identification module can be updated according to the container behavior of the decoy container.

Abstract: A system and method for simulating facial expression of a virtual facial model are provided. The system stores a plurality of three-dimensional facial models corresponding to a plurality of preset sentiments one-to-one. The system identifies a present sentiment according to an acoustic signal and selects a selected model from the three-dimensional facial models according to the present sentiment, wherein the preset sentiment corresponding to the selected model is same as the present sentiment. The system predicts an upper half face image according to a lower half face image, combines the lower half face image and the upper half face image to form a whole face image, and generates a plurality of feature relationships by matching the facial features of the whole face image with the facial features of the selected model so that a virtual facial model can simulate an expression based on the feature relationships.

Abstract: The embodiments of the present invention provide a three-dimensional point cloud tracking apparatus and method using a recurrent neural network. The three-dimensional point cloud tracking apparatus and method can track the three-dimensional point cloud of the entire environment and model the entire environment by using a recurrent neural network model. Therefore, the three-dimensional point cloud tracking apparatus and method can be used to reconstruct the three-dimensional point cloud of the entire environment at the current moment and also can be used to predict the three-dimensional point cloud of the entire environment at a later moment.

Abstract: The detecting method includes: obtaining a testing signal, perform at least one action according to the testing signal, and transmit a request instruction comprising the testing signal; determining that whether the testing signal of the request instruction represents performing a testing mode by a processor; if the processor determines that the testing signal of the request instruction represents performing the testing mode, the processor requests a testing service device to provide at least one service corresponding to the request instruction; collecting a performing order when the processor performing the at least one action and a performing result of each one of the at least one action, and combine the performing order and the performing result as a to-be classified data; and calculating a detecting result according to the to-be classified data, wherein the detecting result represents that whether a snow ball effect will occur.

Abstract: A user equipment and cell re-selection estimation method thereof for use in a NB-IoT communication system are provided. The user equipment selects a cell re-selection criterion according to a user equipment status, and determines whether a serving RSRP value of a serving base station is greater than a re-selection threshold value based on the cell re-selection criterion. The user equipment performs cell re-selection when the serving RSRP value is greater than the re-selection threshold value. The user equipment does not perform the cell re-selection when the serving RSRP value is not greater than the re-selection threshold value.

Abstract: A vehicle detecting detection assisting method and a vehicle detection assisting system are provided. The vehicle detection assisting method includes the following steps. A scanning range of a lidar unit is obtained. A width of a lane is obtained. A trace of the lane is obtained. A dynamic region of interest in the scanning range is created according to the width and the trace.

Abstract: An optimization method based on feature extraction and machine learning is provided. At least one input parameter is received. Multiple first historical mold data are retrieved. A similarity calculation is performed according to the input parameter and the first historical mold data. Multiple candidate mold data are selected according to the similarity calculation. The mold design parameters of the candidate mold data corresponding to each input parameter are replaced by the input parameter, and multiple first representative mold data for performing a first simulation analysis are generated. Multiple key feature parameters are found, and multiple second historical mold data are retrieved according to the multiple key feature parameters. An expected data is found, and the mold design parameters of the expected data are filtered and optimized to find multiple second representative mold data for performing a second simulation analysis. At least one set of mold production parameters is generated.

Abstract: A dispatching method and system based on multiple levels of steady state production rate in working benches are provided. The dispatching method includes the following steps: receiving a plurality of real-time streaming data regarding a plurality of products being produced by a plurality of productive working benches; grouping the production rate values comprised in each real-time streaming data according to a first data binning technique, so as to produce a first steady state production rate value corresponding to each real-time streaming data; grouping the production rate values comprised in each real-time streaming data according to a second data binning technique, so as to produce a second steady state production rate value corresponding to each real-time streaming data; and determining a dispatching message of a to-be-produced product according to a portion of the first steady state production rate values and a portion of the second steady state production rate values.

Abstract: An apparatus and method for determining a target adjustment route for a preset control condition set of a production line are provided. The apparatus establishes at least one candidate adjustment route for the preset control condition set according to the historical control condition sets. Each candidate adjustment route includes at least one adjustment control condition set arranged in an adjustment order. Each adjustment control condition set is one of the historical control condition sets. Within the same candidate adjustment route, the historical yield related values corresponding to the adjustment control condition sets are all greater than the preset yield related value and increase in the adjustment order. Within the same candidate adjustment route, the numbers of the adjustment control condition(s) included in the adjustment sets increase in the adjustment order. The apparatus selects one of the candidate adjustment route(s) as the target adjustment route.

Abstract: A model building device and a loading disaggregation system are provided. The model building device disaggregates total aggregated data outputted from a total electricity meter and measured during a unit processing period. The model building device includes a usage pattern-analyzing module, an information mapping module, and a time series-analyzing module. After receiving the total aggregated data, the usage pattern-analyzing module analyzes the total aggregated data based on detection conditions and generates usage pattern information accordingly. The information mapping module maps the usage pattern information to form encoded data. The time series-analyzing module analyzes time correlation of the encoded data to generate synthesized simulation data.

Abstract: A monitoring system applied to a shaping machine having a high speed electricity meter. The monitoring system includes a current obtaining device and an analyzing device. The current obtaining device is coupled to the high speed electricity meter to obtain a plurality of current signals from the operated shaping machine and in respond to the shaping machine executes a machining program, the current obtaining device extracts current variation data from the current signals. The machining program corresponds to a piece of the current variation data. The piece of the current variation datum comprises a maximum current and an occurring time that the maximum current being recorded. The analyzing device is configured to calculate a gap, based on the maximum currents and the occurring times corresponding to at least two successive machining programs. In respond to the gap time exceeding a predetermined threshold, the analyzing device generates a warning signal.

Abstract: A system and method for identifying application layer behavior are disclosed. In order to detect intrusion into an industrial control system, the system and method determine a current status of application layer behavior of the industrial control system by analyzing a current packet which is propagated between a master device and a slave device in the industrial control system, and identify whether the current status of the application layer behavior is normal according to a normal behavior status list.

Abstract: The present disclosure provides a multimedia interacting system. The multimedia interacting system comprises a first display device, a second display device, and a server. The server communicatively connects with the first display device and the second display device. The server is configured to receive a first playback time that the first display device plays a first tour video; obtain an unsheltered area associated with the first tour video based on the first playback time; obtain a second tour video corresponding to the unsheltered area; and transmit an interacting data to the first display device and the second display device if the second display device plays the second tour video.

Abstract: A monitor apparatus, method, and non-transitory computer readable storage medium thereof are provided. The monitor method is adapted for an electronic computing apparatus, wherein the electronic computing apparatus stores a smart contract and a blockchain ledger of a blockchain system. The monitor method periodically executes the following steps: (a) obtaining a piece of behavior information of a first electronic apparatus at a time point, (b) retrieving, via the smart contract, a plurality of pieces of previous behavior information within a time interval from the blockchain ledger, wherein the time interval is defined by the time point, and each piece of previous behavior information corresponds to one of a plurality of second electronic apparatuses and the first electronic apparatus, (c) determining a legality of the piece of behavior information according to the pieces of previous behavior information, and (d) writing the behavior information into the blockchain ledger.

Abstract: The present invention provides a method for acquiring the load operation probability of an electric power consumer and a method for acquiring the load operation probability of electric power consumer groups. The load information and the total power consumption information of an electric power consumer and the load information and the total power consumption information of electric power consumer groups can be given. The time-segment power consumption information of an electric power consumer and electric power consumer groups can be given. The load operation probability of an electric power consumer and electric power consumer groups can be given by calculations using algorithms.

Abstract: An object detection and tracking method and system are provided. The object detection and tracking method includes the following steps: (i) selecting one of a plurality of frames of a video as a current frame, (ii) searching in an object tracker searching area of the current frame to generate a current object tracker, (iii) searching in each auxiliary tracker searching area of the current frame to individually generate a current auxiliary tracker, (iv) when the current object tracker is located at a block different from the blocks located by the generated object trackers, generating a new auxiliary tracker at the central position of the current frame, and (v) repeating the above steps until all the frames have been processed.

Abstract: An image processing method and an image processing device are provided. The image processing method includes the following steps. A light source is projected onto a 3D model via a plurality of projecting locations to generate a plurality of facial shadow pictures. The facial shadow pictures are superimposed to generate a composite shadow picture. An eye-eyebrow location, a nose location and a mouth location in a 2D facial map are obtained by way of analyzing according to the composite shadow picture. A plurality of characteristic points are calculated according to the eye-eyebrow location, the nose location and the mouth location in the 2D facial map.