Abstract: A data processing method applied in a data center is provided.

Abstract: The federated learning system includes a moderator and client devices. Each client device performs a method for verifying model update as follows: receiving a hash function and a general model; training a client model according to the general model and raw data; calculating a difference as an update parameter between the general model and the client model, sending the update parameter to the moderator; inputting the update parameter to the hash function to generate a hash value; sending the hash value to other client devices, and receiving other hash values; summing all the hash values to generate a trust value; receiving an aggregation parameter calculated according to the update parameters; inputting the aggregation parameter to the hash function to generate a to-be-verified value; and updating the client model according to the aggregation parameter when the to-be-verified value equals the trust value.

Abstract: The present disclosure provides a method including: generating a first private key and a public key according to a parameter set of full homomorphic encryption; encrypting test data and label by the public key to generate test data ciphertext and label ciphertext; generating a smart contract executed by a blockchain system, and transferring control of an amount of cryptocurrency from a first cryptocurrency account to the blockchain; receiving a result of a verification to a model ciphertext; when the result indicates that the model ciphertext does not pass the verification, retrieving the control of the amount of cryptocurrency; and when the result indicates that the model ciphertext passes the verification, receiving the model ciphertext and a second private key from the blockchain system, and decrypting, according to the first and second private keys, the model ciphertext to generate a model to infer the test data.

Abstract: A method for evaluating robots in simulation, when executed on a computing device, involves the following steps: obtaining a robot description file created based on the physical properties of a robot, obtaining an environment description file created based on an environment, and obtaining an obstacle description file. A physics simulation engine creates a virtual environment based on the environment description file and obstacle description file. A virtual robot is created based on the robot description file. When the virtual robot navigates from the starting area to the ending area within the virtual environment based on navigation information, the physics simulation engine outputs simulation information. The robot navigation program generates and sends navigation information to the physics simulation engine based on the simulation information. When the virtual robot reaches the ending area, the physics simulation engine outputs evaluation information.

Abstract: A method of establishing application permissions includes utilizing a computing device to execute the following steps: requesting a first permission; determining whether the first permission exists in a plurality of application permissions in a permission table; obtaining the first permission when the first permission exists in the plurality of application permissions in the permission table; and reviewing the first permission when the first permission does not exist in the plurality of application permissions in the permission table.

Abstract: A segmentation model training method is disclosed. The segmentation model includes the following operations: inputting several first sample groups of a large sample set to a data augmentation model to generate several augmentation sample groups; generating several mix sample groups based on several second sample groups of a small sample set; inputting several mix sample groups to the data augmentation model to generate several augmentation mix sample groups; and training a segmentation model according to several augmentation sample groups and several augmentation mix sample groups, including: performing pre-training to the segmentation model according to several augmentation sample groups; and performing fine-tuning training to the segmentation model corresponding to several augmentation mix sample groups.

Abstract: A data processing method applied in a data center is provided.

Abstract: A system for real-time animation interactive editing is provided. The system for real-time animation interactive editing includes a physics simulation platform and an animation processing device. The animation processing device includes an animation editing circuit and a comparison processing circuit. The animation editing circuit is configured to obtain a motion animation associated with a robot and provide the motion animation to the physics simulation platform, such that the physics simulation platform performs a simulation processing based on the motion animation to generate a simulation result. The comparison processing circuit is configured to real-time obtain the simulation result generated by the physics simulation platform, and compare the simulation result with the motion animation to generate a comparison result.

Abstract: The present disclosure provides a multi-manifold embedding learning method, which includes steps as follows. The ID training data are used to train the multi-manifold embedding learning model, and then the parameters of the multi-manifold embedding learning model are frozen to obtain the trained multi-manifold embedding learning model; the test data are fed to the trained multi-manifold embedding learning model, so as to use a threshold to distinguish out-of-distribution samples from ID samples.

Abstract: An optimization method for data flow includes converting a plurality of extract-transform-load (ETL) scripts into a data flow diagram, wherein the data flow diagram includes a plurality of data lineages, with each data lineage including a plurality of data nodes; performing a first merging process, which repeatedly identifies at least two data lineages with the same nodes and merges them into a data family until any two of the data lineages do not have the same nodes; performing a second merging process, which calculates a column similarity of a pair of node, wherein the pair of nodes includes two adjacent data nodes within a data lineage; when the column similarity exceeds a threshold, merging the two data nodes; when the column similarity of the pair of nodes falls below the threshold, the data flow diagram is optimized, which is then converted into ETL scripts accordingly.

Abstract: A machine learning training device is disclosed. The machine learning training device includes a virtual hard anchor generation circuit, a classification circuit and a training circuit. The virtual hard anchor generation circuit is configured to generate several virtual hard anchors according to several easy samples classified into several types. The virtual hard anchors respectively correspond to one of the several types. The classification circuit is configured to classify several hard samples into several types according to virtual hard anchors. Parts of the hard samples classified into several types are several clean hard samples. Another parts of the hard samples that are not classified into several types are several noisy hard samples. The training circuit is configured to perform machine learning training according to several easy samples and several clean hard samples.

Abstract: An operating method of a fully homomorphic encrypted neural network model is provided, wherein the fully homomorphic encrypted neural network model includes a plurality of layers, and the method performed by a processor includes: for one of the plurality of layers, encrypting a plaintext input with a first encryption algorithm to generate a ciphertext vector, performing a convolution operation according to the ciphertext vector to generate a result vector, transforming the result vector into a plurality of result ciphertexts adopting a second encryption algorithm, inputting the plurality of result ciphertexts into an activation function to generate a plurality of encrypted activation values, and repacking the plurality of encrypted activation values to generate an output vector adopting the first encryption algorithm.

Abstract: A system for assessing a cardiac condition includes an electrocardiogram (ECG) sensor, a photoplethysmography (PPG) sensor, and a processing circuit. The ECG sensor obtains an ECG signal related to a user. The PPG sensor obtains a PPG signal related to the user. The processing circuit generates a cardiac assessment result based on the PPG signal sensed during a first time period and the ECG signal sensed during a second time period. The first time period is longer than the second time period.

Abstract: A service plan generation method performed by a computing device includes: receiving a service request, wherein the service request includes a plurality of feature labels; selecting a plurality of recommended items from an item database according to the plurality of feature labels; calculating a plurality of item failure rates according to a plurality of historical execution records of the plurality of recommended items; calculating a plurality of redo counts corresponding to the plurality of recommended items according to the plurality of item failure rates; generating a plurality of buffer items corresponding to the plurality of recommended items according to the plurality of redo counts; and performing a scheduling according to the plurality of recommended items and the plurality of buffer items to generate a service plan.

Abstract: A system for detecting an event occurrence period of cyclical event includes an image monitoring device and a period judgment device. The image monitoring device captures monitoring images respective in image capturing times. The period judgment device extracts feature vectors from the monitoring images to calculate vector values to accordingly generate a vector value time domain signal, executes a short-time Fourier transform (STFT) with a window width time to transform the vector value time domain signal to a spectrogram, makes the spectrogram be denoised to generate a representative frequency time domain signal, and calculates an event-cycle achievement rate and a product term accumulation number after each window width time, so as to accordingly calculate event occurrence time and the event occurrence period.

Abstract: An inference method for encrypted deep neural network model is executed by a computing device and includes: encoding a message according to a quantization parameter to generate a plaintext, encrypting the plaintext according to a private key to generate a ciphertext, sending the ciphertext to a deep neural network model to generate a ciphertext result, decrypting the ciphertext result according to the private key to generate a plaintext result, and decoding the plaintext result according to the quantization parameter to generate an inference result.

Abstract: A data processing method applied in a data center is provided.

Abstract: A data processing system is for uploading an upload data, wherein the upload data comprises a data content and a table name. The data processing system comprises a relational database; a NoSQL database; a data processing unit, coupled to the relational database and the NoSQL database, configured to execute a program code; and a storage unit, coupled to the data processing unit, configured to store the program code to instruct the data processing unit to execute a data processing method. The data processing method comprises determining a structure type of the upload data according to the data content; determining a first table of a first database according to the structure type, the data content and the table name of the upload data; and storing the upload data in the first table of the first database; wherein the first database is the relational database or the NoSQL database.

Abstract: A data searching method for a data dictionary, comprising obtaining an input word and performing a word embedding operation on the input word to generate a word vector of the input word, calculating a degree of correlation between the input word and a plurality of words in the data dictionary according to the word vector of the input word, and determining at least one recommendation synonym from the plurality of words in the data dictionary according to the degree of correlation between the input word and the plurality of words in the data dictionary, wherein the step including when determining that the cosine similarity between the word vector of the input word and a word vector of a first word of the plurality of words in the data dictionary is greater than a threshold value, determining the first word as a recommendation synonym.

Abstract: A method for permission management includes: generating a plurality of job roles with different permissions according to organization permission table; generating first permission structure directed graph according to the job roles; selecting one of the job roles in first permission structure directed graph as target job role; generating minimum directed spanning graph in first permission structure directed graph according to target job role; determining whether permission of each of the job roles in first permission structure directed graph matches job of each of the job roles in first permission structure directed graph; and adjusting permission and job of each of the job roles to generate second permission structure directed graph if it is determined that permission of each of the job roles in first permission structure directed graph does not match job of each of the job roles in first permission structure directed graph.