743 results about "Optimal weight" patented technology

Detachable wearable electronic eyeglasses and head mounted gear with a plurality of electronic functions and interchangeable electronic function, and a wearable computer with optimal weight distribution and stretchable arms.

Detachable wearable electronic eyeglasses and head mounted gear with a plurality of electronic functions and interchangeable electronic function, and a wearable computer with optimal weight distribution and stretchable arms.

An exemplary wireless communication network that includes a base that communicates with remote units located in a cell of the network. A base concatenates information symbols with a preamble corresponding to a destination remote unit. One or more remote units communicating with a base each concatenates information symbols with a preamble corresponding to that remote unit. An adaptive receiver system for a base unit rapidly adapts optimal despreading weights for reproducing information symbols transmitted from multiple remote units. A transmitter system for a base unit concatenates information symbols with a preamble associated with a remote unit in the cell. An adaptive receiver system for a remote unit in a communication network rapidly adapts optimal weights for reproducing a signal transmitted to it by a specific base unit in the network. A transmitter system for a remote unit in a cell of a communication network which concatenates information symbols with preamble associated with the remote unit. A base initiates communication with a desired remote unit by transmitting an initiation codeword in a selected entry slot. One or more remote units each initiates communication with a bse by transmitting an initiation codeword associated with the remote unit in a selected entry slot. A remote unit synchronizes in time and frequency to the base using a sequence of synchronization signals transmitted by the base in a number of entry slots.

A device, system and method for anchoring a device to a stomach is provided. The device may be, among other things, a sensor for sensing various parameters of the stomach or stomach environment, or may be a therapeutic delivery device. The anchor of the device is constructed to resist pull out forces. An anchor has an optimal weight to surface area ratio.

An exemplary wireless communication network that includes a base that communicates with remote units located in a cell of the network. A base concatenates information symbols with a preamble corresponding to a destination remote unit. One or more remote units communicating with a base each concatenates information symbols with a preamble corresponding to that remote unit. An adaptive receiver system for a base unit rapidly adapts optimal despreading weights for reproducing information symbols transmitted from multiple remote units. A transmitter system for a base unit concatenates information symbols with a preamble associated with a remote unit in the cell. An adaptive receiver system for a remote unit in a communication network rapidly adapts optimal weights for reproducing a signal transmitted to it by a specific base unit in the network. A transmitter system for a remote unit in a cell of a communication network which concatenates information symbols with preamble associated with the remote unit. A base initiates communication with a desired remote unit by transmitting an initiation codeword in a selected entry slot. One or more remote units each initiates communication with a base by transmitting an initiation codeword associated with the remote unit in a selected entry slot. A remote unit synchronizes in time and frequency to the base using a sequence of synchronization signals transmitted by the base in a number of entry slots.

Detachable wearable electronic eyeglasses and head mounted gear with a plurality of electronic functions and interchangeable electronic function, and a wearable computer with optimal weight distribution and stretchable arms.

A system and method that enables a person to unobtrusively quantify the effect of mobility, physical activity, learning, social interaction and diet on cognitive function. The method records on the electronic device one of global positioning system longitude and latitude coordinates, accelerometer coordinates, and gyroscope coordinates, one of outgoing and incoming phone calls, outgoing and incoming emails, and outgoing and incoming text messages, one of URLs visited on an internet browser application, books read on an e-reader application, games played on game applications, and the nutritional content of food consumed, performs the step of learning a function mapping from those recordings to measurements of cognitive function using a loss function to identify a set of optimal weights that produce a minimum for the loss function, uses those optimal weights to create the function mapping, and performs the step of computing the variance of the cognitive function measurements that is explained by the function mapping to assign an attribution to the effect of physical activity on measured changes in cognitive function.

The invention relates to an infrared behavior identification method based on adaptive fusion of an artificial design feature and a depth learning feature. The method comprises: S1, improved dense track feature extraction is carried out on an original video by using an artificial design feature module; S2, feature coding is carried out on the extracted artificial design feature; S3, with a CNN feature module, optic flow information extraction is carried out on an original video image sequence by using a variation optic flow algorithm, thereby obtaining a corresponding optic flow image sequence; S4, CNN feature extraction is carried out on the optic flow sequence obtained at the S3 by using a convolutional neural network; and S5, a data set is divided into a training set and a testing set; and weight learning is carried out on the training set data by using a weight optimization network, weight fusion is carried out on probability outputs of a CNN feature classification network and an artificial design feature classification network by using the learned weight, an optimal weight is obtained based on a comparison identification result, and then the optimal weight is applied to testing set data classification. According to the method, a novel feature fusion way is provided; and reliability of behavior identification in an infrared video is improved. Therefore, the method has the great significance in a follow-up video analysis.

The invention discloses a method for extracting an image region of interest based on eye movement data and bottom-layer features. On one hand, the image region of interest, namely, eye movement ROI (Region Of Interest), for reflecting human real semanteme is extracted by visual point tracking experimental data of an eye movement instrument, and on the other hand, the image region of interest, namely, feature ROI, in a general sense is extracted in a form of bottom-layer feature weighted combination, and weight combination with highest similarity, namely, optimal weight, is found out by similarity analysis of the feature ROI and the eye movement ROI. The region of interest of other image of the same type, extracted by using the weight, can more comply with the semantic demands of users.

The invention discloses an improved visual attention model-based method of a natural scene object detection, which mainly solves the problems of low detection accuracy rate and high false detection rate in the conventional visual attention model-based object detection. The method comprises the following steps of: (1) inputting an image to be detected, and extracting feature saliency images of brightness, color and direction by using a visual attention model of Itti; (2) extracting a feature saliency image of a spectrum of an original image; (3) performing data sampling and marking on the feature saliency images of the brightness, the color, the direction and the spectrum and an attention image of an experimenter to form a final rough set information table; (4) constructing attribute significance according to the rough set information table, and obtaining the optimal weight value of the feature images by clustering ; and (5) weighing feature sub-images to obtain a saliency image of the original image, wherein a saliency area corresponding to the saliency image is a target position area. The method can more effectively detect a visual attention area in a natural scene and position objects in the visual attention area.

The invention provides a face recognition method and device. The method includes the steps of extracting clustering features of preprocessed template face images and face images to be recognized; inputting the extracted clustering features into a clustering category model trained in advance, and determining a clustering category; extracting N recognition features of the preprocessed template face images and the face images to be recognized, wherein N is a natural number larger than 1; calculating similarity between N the recognition features of the face images to be recognized and N recognition features of the template face images, selecting the optimal weight combination and a dynamic threshold determined in advance according to the determined clustering category, carrying out weight fusion on similarity of the N extracted recognition features, and obtaining comprehensive similarity scores of the face images to be recognized and the template face images; selecting the highest comprehensive similarity score of the face images to be recognized and the template face images to be compared with the dynamic threshold; carrying out recognition if the highest comprehensive similarity score is not smaller than the dynamic threshold; refusing to recognize if the highest comprehensive similarity score is smaller than the dynamic threshold.

A system and method that enables a person to unobtrusively assess their cognitive function from mobile device usage. The method records on the mobile device the occurrence and timing of user events comprising the opening and closing of applications resident on the device, the characters inputted, touch-screen gestures made, and voice inputs used on those applications, performs the step of learning a function mapping from the mobile device recordings to measurements of cognitive function that uses a loss function to determine relevant features in the recording, identifies a set of optimal weights that produce a minimum of the loss function, creates a function mapping using the optimal weights, and performs the step of applying the learned function mapping to a new recording on the mobile device to compute new cognitive function values.

The invention belongs to the technical field of natural language processing, and discloses multi-label text classification processing method and system and an information data processing terminal. Themethod comprises the steps of: obtaining a data set; preprocessing the data set and dividing the data set into a training set and a test set; finely adjusting and extracting global feature vectors ofwords in the text sequence through a BERT pre-training model, and aggregating the global feature vectors by adopting a convolutional neural network to obtain semantic vectors of the words in the textsequence; constructing an attention weight coefficient matrix, and respectively weighting the semantic vector of each word and a weight coefficient vector in the optimal weight coefficient matrix toobtain an attention vector of the label; and normalizing the attention vectors of the tags to obtain the probability of each tag, and selecting several tags with the maximum probability as the category of the text. According to the method, global and local features of the text sequence are extracted, the influence of keywords in the text on tag categories is considered, and the classification accuracy is improved.

The invention discloses a bilateral constraint self-adaptive wavebeam forming method for a multiple-input-multiple-output (MIMO) radar, which can constrain both transmitting signals and receiving signals. Firstly, a plurality of transmitting signal data can be recorded, and the corresponding echo signals can be sampled, all vectors which are obtained by the recorded transmitting signal data and the sampled echo signals are respectively ranked by row to form a data matrix, and an optimal weight vector required for forming the wavebeam is calculated by the dual iterative calculation method, finally, the calculated optimal weight can be used to form the wavebeam. The method can overcome the shortcomings of large sample number and complex calculation in traditional self-adaptive wavebeam-forming method which is applied to the MIMO radar. Compared with the traditional self-adaptive wavebeam-forming method, the obtained antenna array pattern is provided with lower side lobe and better wavebeam shape preserving ability. The performance by using the method to perform Doppler frequency detection for movable object after the received MIMO radar data is filtered in spatial field also exceeds that of the traditional self-adaptive wavebeam-forming method.

This invention relates to a signal processing method and apparatus for an adaptive array antenna. The objective is to suggest an adaptive procedure of computing the suboptimal weight vector for an array antenna system that provides a beampattern having its maximum gain along the direction of the mobile target signal source in a blind signal environment, where the transmitted data are not known (or not to be estimated) at the receiver. It is the ultimate goal of this invention to suggest a practical way of enhancing both the communication quality and communication capacity through the optimal weight vector of the array system that maximizes SINR(Signal to Interference+Noise Ratio). In order to achieve this goal, the method of Lagrange multiplier is modified in such a way that the suboptimal weight vector is produced with the computational load of about O(8N), which has been found to be small enough for the real-time processing of signals in most land mobile communications with the digital signal processor (DSP) off the shelf, where N denotes the number of antenna elements of the array.

The invention relates to a high spectral image target detection method based on high order statistics, which comprises the following steps: (1) reading data of a high spectral image in the environment of MATLAB R2008b by a computer; (2) preprocessing (i.e. de-equalization and whitening) the data by the computer; (3) constructing high order statistics for minimizing output data under the constraint that the spectral gain of the detection filter for the target is 1, and solving the optimal weight vector of the detection filter; and (4) setting an appropriate threshold, and acquiring the detection result image. The invention overcomes the defects in the prior art, and has good detection effect by fully utilizing the high order statistics of the data. In particular, the invention can enhance the detection probability on the premise of low false alarm rate. Thus, the invention has high practical value and wide application prospects in the technical field of target detection of high spectral remote sensing images.

An imaging processing system and method. In accordance with the invention, the illustrative method includes the steps of providing a transfer function between scene excitations and voltage returns based on geometry, beam pattern and / or scan rate; ascertaining a set of scene excitations that minimize a penalty function of the transfer function; and ascertaining a set of scene intensities based on the scene excitations, and a set of optimal weights for the penalty function based on the scene reflectivities. The inventive method provides significantly enhanced image sharpening. In the illustrative embodiment, the inventive method uses an iterative convergence technique which minimizes a penalty function of the sum of square errors between the scene excitations corrupted by the radar system (i.e. the antenna pattern and processing) and the radar voltage returns. The innovation significantly enhances radar imagery by iteratively deriving a best scene solution, which reduces corruption introduced by the radar system. The novel technique for enhanced discrimination by the radar imagery is an iterative technique, which models the true scene signal corruption and derives a solution for the scene intensities, which minimizes the errors in the derived image. The novel technique finds the scene scatterer powers, which best match the original image pixel powers. The effect of the antenna pattern is taken into consideration when computing the derived image, which is matched against the original image. The constraint is implemented iteratively by adding a weighted sum of scene powers to the penalty function. The weights are adjusted at each iteration.

The invention discloses a pH (potential of hydrogen) value predicting method of a BP (back propagation) neutral network based on a simulated annealing (SA) algorithm optimization. The pH value predicting method comprises the following steps: step one, selecting a sample according to a sample selecting strategy and inputting; step two, according to the BP theorem, determining the structure of the BP neutral network; step three, according to a network training strategy, applying the simulated annealing algorithm to optimize the BP network weight parameter; training the BP network by using the input sample, and determining the optimal weight and optimal hidden node number of the BP network; step four, according to the well trained BP neutral network, structuring a predicting model of the pH value. The pH value predicting method overcomes the randomness of the BP network in terms of weight selection, improves the rate of convergence and study ability of the BP neutral network. Besides, the method optimizes the selection of the training sample and the network hidden neutral element number, and improves the generalization ability of the BP neutral network. Moreover, the pH value predicting method is high in predicting accuracy of pH value and good in nonlinear fitting ability.

The invention provides a multi-source information fusion based rainfall estimation method. The multi-source information fusion based rainfall estimation method includes: combining ground station observation rainfall data in a study area with a multi-source satellite rainfall data body in the study area to form a multi-source data set in the study area; establishing a dynamic Bayesian theory basedBayesian rainfall prediction model; using the maximum entropy method to obtain a nonlinear optimal solution of the Bayesian rainfall prediction model, and then determining the optimal weight and uncertainty information of each satellite data source; and generating an estimation result using the multi-source information fusion rainfall in the study area. The advantages of the invention are that theresult of multi-data source fusion analysis can reduce the uncertainty of the regional rainfall estimation due to the inaccuracy of a single type of rainfall information; and more reliable data inputand richer and more refined modeling data are provided for strengthening regional high-precision disaster warning, avoiding the flood risk or small watershed rainstorm flood estimation.

The invention discloses a BP neutral network heavy machine tool thermal error modeling method optimized through a genetic algorithm. Through the establishment of the structure of a BP neutral network, global optimization is conducted on the initial weight and threshold of each layer of the BP neutral network through a training sample. After the error objective is set, global optimization is conducted on the initial weight and threshold of the BP neutral network structure through the genetic algorithm, and the optimal weight and threshold found by the genetic algorithm is substituted into the BP neutral network to be conducted with sample training. Based on the decline principle of the error gradient, quick search is conducted near the extreme point until the training is end and thermal error prediction model is obtained. Finally, robustness testing is conducted on the obtained thermal error prediction model. The global optimization is conducted on the initial weight and threshold of the BP neutral network structure through the utilization of the genetic algorithm, the self-characteristics of the BP neutral network is overcome, and the quickness, the accuracy and the robustness of convergence when the optimal weight and threshold is trained can be improved.

The invention discloses a multi-label text classification method and system. The method comprises the following steps: obtaining a training set comprising a text sequence and a label space, extractingglobal feature vectors of all words in the text sequence by adopting a long-short time memory network, and aggregating the obtained global feature vectors by adopting a convolutional neural network to obtain a semantic vector of each word in the text sequence; respectively calculating weight coefficients of each label in the note space and all words in the text sequence, constructing an attentionweight coefficient matrix, and processing the attention weight coefficient matrix to obtain an optimal weight coefficient matrix; respectively weighting the semantic vector of each word and the weight coefficient vector in the optimal weight coefficient matrix to obtain an attention vector of the tag; and performing normalization processing on the attention vectors of the tags to obtain the probability of each tag, and selecting several tags with maximum probabilities to classify the text.

A receiver produces optimal weights for cancelling multipath interference. An SINR measurement module generates SINR measurements corresponding to soft symbol estimates produced by a baseband receiver from a received multipath signal. Each soft symbol estimate is replaced with either a hard estimate or a weighted soft estimate based on how each corresponding SINR measurement compares to a predetermined threshold. The received multipath signal and estimated interference signals generated from the hard symbol estimates and / or the weighted soft symbol estimates are combined to produce interference cancelled signals that may be combined via maximum ratio combining to produce an interference-cancelled MRC signal.

The present invention discloses a visual saliency object detection method. The method comprises the steps: (1) inputting an image to be detected, extracting saliency maps of the improved color, the brightness and the direction on the basis of an Itti visual attention model through adoption of spectral residual and a frequency modulation model; (2) obtaining the comparison difference of a saliency area and a non-saliency area in each channel saliency image through k-means clustering, and obtaining the optimal weight of each channel saliency image; and (3) weighting of the saliency image of each channel, and obtaining the saliency image of an original image, wherein the saliency area of the saliency image is an object area. The visual saliency object detection method is able to improve the deficiency of the visual attention model, effectively highlight the saliency area and inhibit the non-saliency area so as to simulate the location of human vision attention for a natural scene target.

An apparatus and method are provided for simply estimating joint channel and Direction-of-Arrival (DOA) to efficiently estimate a channel impulse response associated with a spatially selective transmission channel occurring in a mobile radio channel, and performing efficient beam forming using the simplified joint channel and DOA estimation are provided. A receiver estimates the total interference power using power for each interference signal, estimates a spectral noise density, calculates steering vectors considering predetermined DOAs, and jointly calculates optimal weight vectors for each DOA of each user by applying the interference power and the spectral noise density to the steering vectors. The beam forming reduces implementation complexity of a TDD system such as a TD-SCDMA and increases beam forming efficiency in a mobile environment by efficiently using spatial diversity.

A tool has an adjustable lie angle, face angle, weight, and shaft length and is used by a golfer to adjust a putter to the optimal lie angle, face angle, weight and shaft length for that golfer. The tool head has a face plate and a sole disposed normal to one another. An angle member has a vertical wall disposed parallel to the face plate and a horizontal wall that overlies the sole. A hosel is pivotally mounted to the vertical wall and a first protractor is fixedly secured to the vertical wall. A marker on the hosel indicates the lie angle on the first protractor. A second protractor secured to the sole indicates a face angle when the shaft of the club is rotated about its axis. Weights are selectively added to the toe, heel, or mid-point of the putter head to determine an optimal weight and weight distribution.

The invention discloses a particle swarm optimization neural network model-based method for detecting the moisture content of wood. A particle swarm is combined with a back propagation (BP) algorithm to finish neural network training, so that the training accuracy of a network model is enhanced; and the model is applied to the detection of the moisture content of wood, so that high detection accuracy is achieved. The method has the advantages that: 1) by the properties of randomized global optimization search and high convergence rate of a particle swarm optimization algorithm, overall optimization is performed on the weight of a network, so that the defects of low convergence rate and easy local minimum existing in the BP algorithm are overcome; 2) in the BP algorithm, an approximately optimal weight provided by the particle swarm optimization algorithm is taken as an initial value and further optimization is performed by using the characteristics of nonlinear mapping capability and high local optimization capability of the BP algorithm, so that an optimal value of a network weight is obtained; and 3) the moisture content of wood and an environmental temperature parameter are detected based on an electrical measuring method, a particle swarm optimization neural network model is established and is applied to the detection of the moisture content of wood, and the effectiveness of the method is verified.

The invention provides a monocular depth estimation method based on deep learning, and the method is based on an unsupervised convolutional neural network structure for monocular depth estimation, andcomprises an encoder, a multi-scale feature fusion module, a gating adaptive decoder, and a refinement unit. The method comprises the following steps: S1, preprocessing a data set; S2, constructing aloss function of the convolutional neural network, inputting a training set image, calculating a loss value of the loss function by using a back propagation algorithm, and performing parameter learning by reducing errors through repeated iteration to enable a prediction value to be close to a real value so as to obtain an optimal weight model of the convolutional neural network; and S3, loading the weight model trained in the step S2, and inputting the test set into an unsupervised convolutional neural network for monocular depth estimation to obtain a depth prediction image. The method solves the problems of large calculation amount during offline training and poor detail part recovery effect in deep reconstruction.

The invention discloses a wind power prediction method based on a modified particle swarm optimization BP neural network. The method includes the following steps: 1. encoding weight values and threshold values of a BP neural network as particles, and initializing the particles; 2. computing each particle fitness value with the difference between the result obtained from BP neural network training and an anticipated value as a fitness function; 3. comparing the fitness value of each particle and individual optimal particle to obtain a global optimal particle; 4. updating the speed and position of the particle; 5. determining whether the global particle meets termination conditions, if the global particle meets termination conditions, terminating the computing and outputting an optimal weight threshold value, and if the global particle does not meet termination conditions, back to step 2 and carrying out iterative operation; and 6. Using the optimal weight threshold value that is acquired by step 5 to connect an input layer, a hidden layer and an output layer of the BP neural network, and obtaining the result of wind power prediction on the basis of the result of the BP neural network. The method has fast convergence speed, high precision, and is not easily trapped to local extremum.

The invention discloses a short-term electric load prediction method based on improved genetic algorithm for optimizing extreme learning machine. A hill climbing method is used to perform preferentialselection again in the progeny population, an initial individual is selected, another individual in a close area is select, their fitness values are compared, and one individual which has good fitness values is leaved. If the initial individual is replaced or a better individual cannot be found in several iterations, iteration is stopped, the search direction of the genetic algorithm through thehill climbing method is optimized, obtaining an optimal weight value and a threshold value, a network optimization prediction model are obtained, a network optimization prediction model is obtained, the network optimization prediction model and prediction results of BP network and the extreme learning machine are comparative analyzed, including selection of input and output of the prediction network model, algorithm of improved genetic algorithm for optimizing extreme learning machine, and analysis of prediction results. The short-term electric load prediction method based on improved geneticalgorithm for optimizing extreme learning machine has faster training speed and more accurate prediction results, and is suitable for modern short-term electric load prediction with plenty of influence factors and huge data volume.

The invention discloses a local-area joint-dimension-reduction range ambiguity clutter suppression method based on an FDA-MIMO radar so that problems that the existing range ambiguity clutter suppression method has the poor detection performance, the operation load is high, and the requirement on the independent and identically distributed samples is high can be solved. The method comprises: stepone, carrying out matching and filtering on echo data of a radar by using a transmitting waveform; step two, carrying out range dependence compensation on the matched filtered data; step three, constructing a local-area joint dimension reduction matrix and performing dimension reduction on the received data; step three, on the basis of data after dimension reduction, estimating a clutter covariance matrix; step four, on the basis of a minimum variance, non-distortion response to a wave beam forming device is carried out to obtain an optimal weight vector; step five, carrying out weighting on the data after dimension reduction by using an optimal weight, suppressing a range ambiguity clutter, and detecting a target signal. Compared with the existing range ambiguity clutter suppression method, the provided method has the following advantages: the computing complexity is low; the requirement on the independent and identically distributed samples is low; and the clutter suppression performance is good. The range ambiguity clutter suppression on an airborne radar is realized. The method can be applied to ground moving target detection of an airborne radar.