Abstract: A method for processing breast tomosynthesis images includes: obtaining multiple breast images, performing binarization operation and pooling operation to at least one marked breast image to obtain a lesion mask; training a convolutional neural network (CNN) according to the breast images and the lesion mask; obtaining multiple cropped images from the breast images of different layers according to a particular two-dimensional position, and inputting each cropped image into the CNN to obtain cropped heat maps; inputting the cropped heat maps into a recurrent neural network (RNN) in an order of the levels to obtain output heat maps, and combining the output heat maps to obtain a integrated heat map, and training the RNN according to the integrated heat map and the lesion mask.

Abstract: A method of deploying microservice includes: determining whether a current load of a task queue of a target edge host is not smaller than a load alert level; if the current load is not smaller than the load alert level, calculating a task migration number of a first queue of the task queue to deploy a microservice corresponding to the first queue at at least one of a first available edge host and a cloud host; if the current load is smaller than the load alert level, calculating a long-term load according to a history pushing rate, a history consumption rate and a default time period; and when a sum of the long-term load and a current load of a second queue of the task queue is not smaller than the load alert level, deploying a microservice corresponding to the second queue at a second available edge host.

Abstract: An RF fingerprint signal processing device configured for executing a machine learning algorithm on a plurality of input signals. The RF fingerprint signal processing device includes a receiver-feature determination circuit and a classifying determination circuit. The receiver-feature determination circuit is configured to compute on the plurality of input signals in a neural network. The classifying determination circuit is coupled with the receiver-feature determination circuit, and the classifying determination circuit is configured to send feedback information of a receiver-feature component to the receiver-feature determination circuit. The receiver-feature determination circuit decreases the receiver-feature weight of the neural network. The receiver-feature weight is associated with the receiver-feature component, and the receiver-feature weight which is decreased is applied for computing an output value of the neural network.

Abstract: A data processing method based on Trojan circuit detection includes controlling a processor, in a testing stage, to perform following steps: obtaining a plurality of characteristic values corresponding to a logic gate circuit; performing a distribution adjustment operation on the characteristic values to generate a plurality of adjusted characteristic values; and performing classification on the adjusted characteristic values to generate a logic identification result.

Abstract: A one-way data processing system includes a conveyor device, an image capturing device, a trigger device, a first processing device and a second processing device. The first processing device identifies a type of the target object according to image data captured by the image capturing device. The first or the second processing device obtains a weight of the target object, and obtains exit information according to a level-exit correspondence table and the type and the weight of the object. The second processing device drives a swing arm of the conveyor device at least according to a trigger signal generated by the trigger device triggered by the target object and the exit information, to unload the target object through a target exit location. A data transmission direction between the first processing device and the second processing device only includes a direction from the first processing device to the second processing device.

Abstract: A method of estimating greenhouse gas emission, performed by a processing device, includes: obtaining at least one time period of a number of working stations for a target manufacturing process of a product; obtaining a number of first power consumption data of the target manufacturing process, wherein the first power consumption data correspond to the working stations respectively; calculating a number of second power consumption data based on the at least one time period and the first power consumption data; searching for a number of target coefficients corresponding to the plurality of working stations respectively in coefficient database based on the target manufacturing process; and calculating greenhouse gas emission data of the target manufacturing process based on the second power consumption data and the target coefficients.

Abstract: A virtual machine backup method, performed by a first host, includes: capturing a request to write data from a virtual machine to a hard disk image file, wherein the request includes written data and input and output location information, copying the written data to a temporary storage area, calculating a first key of the written data, storing the first key, the input and output location information into a first resource location structure, pausing an operation of the virtual machine and generating a second resource location structure according to the first resource location structure, the first key and a second key, and outputting a backup data set to a second host according to the second resource location structure, wherein the backup data set includes the second resource location structure and only one of existing data and the written data when the first key and the second key are the same.

Abstract: A landmark identification and marking system for a panoramic image is provided. The system includes a storage device and a back-end processor. The storage device stores an initial panoramic image, attitude information, motion tracking information, and a landmark list. The back-end processor performs steps of: adjusting a visual angle of the initial panoramic image to a designated angle according to a difference value between the visual angle and the designated angle; providing the adjusted initial panoramic image to a front-end processor for calculating and generating a panoramic image integrated with landmark objects in the virtual space.

Abstract: An image synchronization method for multiple cameras, comprising the following steps: receiving a first video of a first camera and a second video of a second camera; capturing a first object in the first video and a second object in the second video; determining whether the first object is the same as the second object; if yes, transferring a first coordinate of the first object and a second coordinate of the second object to a uniform coordinate; regulating a timing sequence of the second video to calculate a plurality of multi-object tracking accuracy values for the second video and the first video and identifying a maximum multi-object tracking accuracy value; generating a time compensation value according to a time different corresponding to the maximum multi-object tracking accuracy value and synchronizing the first camera and the second camera according to the time compensation.

Abstract: A federated learning method includes: providing importance parameters and performance parameters by client devices respectively to a central device, performing a training procedure by the central device, wherein the training procedure includes: selecting target devices from the client devices according to a priority order associated with the importance parameters, dividing the target devices into training groups according to a similarity of the performance parameters, notifying the target devices to perform iterations according to the training groups respectively to generate trained models, transmitting the trained models to the central device, and updating a global model based on the trained models, performing the training procedure again or outputting the global model to the client devices based on a convergence value of the global model and the number of times of performing the training procedure.

Abstract: The present invention provides an encryption determining method. The method includes the following steps: receiving a side channel signal; generating a filtered side channel signal by filtering noise within the side channel signal; generating a phasor signal by utilizing a filter to covert the filtered side channel signal; locating the encrypted segment by calculating a periodicity of the phasor signal utilizing a standard deviation window; extracting at least one encrypted characteristic from the encrypted segment; and generating an encryption analytic result by recognizing the at least one encrypted characteristic according to a characteristic recognition model; wherein the encryption analytic result includes a position of the encrypted segment within the side channel signal, and an encryption type corresponding to the side channel signal. The present invention is able to automatically and efficiently locate the encryption segment and analyze the encryption type corresponding to the side channel signal.

Abstract: A system and a method for cybersecurity threat detection and early warning are provided. The method includes the following steps: determining whether a network element has an abnormal change according to operation information; if yes, performing a deduction by a cybersecurity event inference model according to the operation information of an abnormal network element to generate a cybersecurity prediction warning; at the same time, collecting and comparing cybersecurity event information and further performing a self-response test on the abnormal network element and a comparison for response result information to finally generate a threat event decision. The cybersecurity prediction warning provides early warning of potential cyberattacks, and the threat event decision provides a robust judgment of the cyberattack event. The present invention solves the problems of long determination time and easily missing judgment and misjudgment.

Abstract: The present disclosure is a method and a system for dynamically switching transmission modes to increase reliability in unlicensed controlled environments (UCEs). The system includes a user equipment (UE) to execute the method. When a next generation Node B (gNB) cannot successfully receive or decode data transmitted by the UE, the UE will receive a dynamic grant (DG) signal transmitted by the gNB. When the UE can receive the DG signal, the UE will start a configured grant (CG) timer and count a CG counter, and the UE will calculate a CG weight. The UE determines communication quality between the UE and the gNB according to the CG weight. When the CG weight is greater than a CG threshold, the UE determines communication quality is bad, and switches to a CG transmission mode to increase reliability for transmitting the data. Therefore, spectrum usage efficiency in the UCEs can be improved.

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 wearable positioning device includes an inertial sensor, a storage device and a processor. The inertial sensor senses an acceleration signal and an angular velocity signal. The storage device stores a previous positioning signal and a current coordinate. The processor is electrically connected to the inertial sensor and the storage device. A wearable positioning method is executed by the processor, which includes: determining whether the wearable positioning device is in one of an under-water mode and an above-water mode according to a pressure sensing signal; calculating, when in the under-water mode, a current acceleration and a current direction according to the acceleration signal, the angular velocity signal, and a swimming posture signal representing a swimming posture; and calculating a current positioning signal according to the current acceleration, the current direction and the previous positioning signal, and updating the current coordinate with the current positioning signal.

Abstract: The present invention is a method and a system for inspecting and scoring vehicle transportation. The system includes a cloud server for performing an intersection analysis, a speed analysis, and a smoothness analysis to generate key features. The cloud server further performs a supervised learning scoring process based on the key features to generate an audit score. Therefore, the present invention can provide a verified reference for the vehicle transport industry to manage drivers, for avoiding human subjective judgments, and auditing and evaluating drivers' driving behaviors in an objective and efficient manner.

Abstract: A user equipment (UE) and a base station (BS) are provided. The UE monitors a plurality of semi-persistent scheduling (SPS) physical downlink shared channel (PDSCH) resources, and determines an SPS Hybrid Automatic Repeat reQuest acknowledge (HARQ-ACK) bit order of a plurality of SPS HARQ-ACK bits, corresponding to the SPS PDSCH resources, in a codebook according to a time-domain position, a component carrier index and a configuration index of each SPS PDSCH resource. Afterwards, the UE generates an HARQ-ACK message including the codebook according to the SPS HARQ-ACK bit order, and transmits the HARQ-ACK message on a physical uplink control channel (PUCCH) resource to the BS.

Abstract: A map scanning method including the following step: scanning, by a scanning device, a location area of a vehicle to obtain location data, wherein the scanning device includes a lidar sensor, and the lidar sensor is configured to scan the location area to obtain a scan point cloud data of the location data; comparing, by a processor, the location data with a basic map to obtain a first point cloud area corresponding to the location data in the basic map; Comparing the scan point cloud data with the first point cloud area to calculate a matching degree value; and when the matching degree value is less than an update threshold, updating the first point cloud area according to the scan point cloud data.

Abstract: A log processing device and a log processing method thereof are provided. The log processing device divides the original log data into a plurality of block data, transforms a numeric variable of each of the block data into a representative code, and determines whether to perform a combination process for continuous block data to generate a plurality of combinational block data according to a data integrity of each of the block data. The log processing data takes the combinational block data as a log template, and each of the combinational block data corresponds to an event.

Abstract: A vehicle data analysis device and a vehicle data analysis method thereof are provided. The vehicle data analysis device receives a sensing data and a controller area network (CAN) message, and performs a similarity comparison on the sensing data and a plurality of bytes of a data field of the CAN message to determine whether the CAN message is a target CAN message corresponding to the sensing data.