A computer implemented method of generating a gradient boosting decision tree for obtaining predictions includes finding split points by sorting variable values of a feature by their gradient during training of the gradient boosting decision tree, performing a linear search to find a subset of variables with maximum split gain, and modifying a node of the gradient boosting decision tree to have multiple split points on the node for a feature as a function of the linear search. In a further example, a computer implemented method of controlling overfitting in a gradient boosting decision tree includes combining values of low population feature values into a virtual bin, fanning out the virtual bin into feature values having a low population, and including the low population feature values into multiple split points on a node of the gradient boosting decision tree.

Systems and methods are provided for determining faces and bodies of people in an image by adaptively scaling images and by iteratively using a deep neural network for inferencing. A camera captures an image including faces and bodies of people. A face/body determiner determines faces and bodies of people appearing in the image by resizing the image into a predetermined pixel dimension as input to the deep neural network. A region cropper determines a crop region associated with a low level of confidence in detecting faces and bodies that are too small to determine with an acceptable level of confidence. The region cropper resizes the crop region into the predetermined pixel dimension as input to the deep neural network. The face and body determiner determines other faces and bodies appearing in the resized crop region. An aggregator aggregates locations of the determined faces and bodies in the image.

A method for a system and method for morphometric detection of malignancy associated change (MAC) is disclosed including the acts of obtaining a sample; imaging cells to produce 3D cell images for each cell; measuring a plurality of different structural biosignatures for each cell from its 3D cell image to produce feature data; analyzing the feature data by first using cancer case status as ground truth to supervise development of a classifier to test the degree to which the features discriminate between cells from normal or cancer patients; using the analyzed feature data to develop classifiers including, a first classifier to discriminate normal squamous cells from normal and cancer patients, a second classifier to discriminate normal macrophages from normal and cancer patients, and a third classifier to discriminate normal bronchial columnar cells from normal and cancer patients.

A learning device is configured to perform learning of a decision tree. The learning device includes a branch score calculator, and a scaling unit. The branch score calculator is configured to calculate a branch score used for determining a branch condition for a node of the decision tree based on a cumulative sum of gradient information corresponding to each value of a feature amount of learning data. The scaling unit is configured to perform scaling on a value related to the cumulative sum used for calculating the branch score by the branch score calculator to fall within a numerical range with which the branch score is capable of being calculated.

A Deep-Learning (DL) explainable AI system for Radio Frequency (RF) machine learning applications with expert driven neural explainability of input signals combines three algorithms (A1, A2, and A3). A1 is a neural network that learns to classify spectrograms. During training, A1 learns to map a spectrogram to its paired label. It outputs a label estimate from a spectrogram. Labels account for device number and spectrum utilization. The neural network is built on two-dimensional dilated causal convolutions to account for frequency and time dimensions of spectrogram data. A2 is a user-defined function that converts an input spectrogram into a vector that quantifies human-identifiable elements of the spectrogram. A3 is a random forest feature extraction algorithm. It takes as input the outputs of A2 and A1. From these, A3 learns which elements in the vector output by A2 were most important for choosing the labels output from A1.

A method for cleaning up a background application, a storage medium, and an electronic device are provided. The method includes the following. Collect multi-dimensional feature information associated with an application as samples to construct a sample set associated with the application. Extract feature information from the sample set to construct multiple training sets. Train each training set to generate a corresponding decision tree. Predict, with multiple decision trees generated, current feature information associated with the application and output multiple predicted results when the application is switched to the background, where the predicted results include predicted results indicative of that the application is able to be cleaned up and predicted results indicative of that the application is unable to be cleaned up. Determine whether the application is able to be cleaned up according to the multiple predicted results. Clean up the application when the application can be cleaned up.

A method, an apparatus and an electronic device for processing point cloud data and a computer readable storage medium are disclosed. The method includes: receiving first point cloud data acquired by a laser scanner; classifying the first point cloud data to obtain second point cloud data which is classified; judging if the second point cloud data at least comprises target point cloud data, and whether a distance between other point cloud data in the second point cloud data and the target point cloud data is smaller than a first preset threshold value; if yes, determining the other point cloud data as hazardous point cloud data.

Techniques for synthesizing and analyzing data are disclosed. A ML model anonymizes microdata to generate synthesized data. This anonymizing is performed by reproducing attributes identified within microdata and by applying constraints to prevent rare attribute combinations from being reproduced in the synthesized data. User input selects attributes to filter the synthesized data, thereby generating a subset of records. A UI displays a synthesized aggregate count representing how many records are in the subset. Pre-computed aggregate counts are accessed to indicate how many records in the microdata embody certain attributes. Based on the user input, there is an attempt to identify a particular count from the pre-computed aggregate counts. This count reflects how many records of the microdata would remain if the selected attributes were used to filter the microdata. That count is displayed along with the synthesized aggregate count. The two counts are juxtaposed next to one another.

Described herein are systems and methods for determining if a vehicle is parked. In one example, a system includes a processor, a sensor system, and a memory. Both the sensor system and the memory are in communication with the processor. The memory includes a parking determination module having instructions that, when executed by the processor, cause the processor to determine, using a random forest model, when the vehicle is parked based on vehicle estimated features, vehicle learned features, and vehicle taillight features of the vehicle that are based on sensor data from the sensor system.

The present invention provides a data collection system comprising: a camera; a location module; a plurality of sensors; and a first processor communicatively coupled to the camera and the location module, the first processor programmed to: obtain a plurality of frames from the camera; obtain a plurality of locations from the location module; obtain a plurality of data measurements from the plurality of sensors; apply a previously trained first neural network model for identifying problematic road segments to frames captured by the camera; and if the first neural network model indicates that a frame is a problematic road segment, save the frame in association with a location provided by the location module.