Systems and methods for the detection and analysis of road markings and other road objects are described. A method for detection of road markings comprises identifying image data including lane markings associated with a road segment, defining a plurality of subsections for the road segment, identifying boundary recognition observations for the lane markings from the image data corresponding to the at least one of the plurality of subsections for the road segments, calculating one or more clusters for the boundary recognition observations according to color or intensity, and outputting a lane marking indicator indicating the color or the intensity, for the at least one of the plurality of subsections for the road segments, in response to the one or more clusters.

Techniques are disclosed for assisted learning with enhanced privacy. A method comprises: sending first statistical information from a first agent to a second agent in an architecture having at least two agents, wherein a first set of sample weights correspond to training the first machine learning model, wherein the first statistical information comprises the second set of sample weights determined from a first model weight; receiving, from the second agent, second statistical information comprising the second model weight and updated first set of sample weights or, from a third agent of the architecture, third statistical information comprising a third model weight and a next iteration of the first set of sample weights; and updating the first machine learning model using the second statistical information or the third statistical information.

A method and a system for model training are provided. The method can include training a first classifier, a second classifier, and a third classifier with subsets of a labeled dataset. The method can also include predicting a pseudo labeled dataset from an unlabeled dataset using the first classifier, the second classifier, and the third classifier. The method further includes assigning a role to the first classifier, to the second classifier, and to the third classifier. The method can further include selecting a teaching sample dataset from the pseudo labeled dataset based on the role assigned to the third classifier, wherein the third classifier is assigned a role of a student. The method can also include retraining the third classifier with the teaching sample dataset in conjunction with a subset of the labeled dataset.

Embodiments for implementing enhanced ensemble model diversity and learning by a processor. One or more data sets may be created by combining one or more clusters of data points of a minority class with selected data points of a majority class. One or more ensemble models may be created from the one or more data sets using a supervised machine learning operation. An occurrence of an event may be predicted using the one or more ensemble models.

A hybrid rule-based Artificial Intelligence (AI) document processing system processes a non-editable document with at least one invoice to accurately extract data from tables in the invoices. The non-editable document is preprocessed for conversion into a markup format and pages including the invoice are identified. The invoice is processed via a document process by parsing the pages in different directions to generate a first set of predictions and via a block process wherein logical information blocks from the invoice are processed to generate a second set of predictions. The missing entries from a selected table are identified by applying rules to the first set of predictions and the second set of predictions. Any discrepancy between the missing entry values between the first and second set of predictions are resolved and the resulting data is exported to downstream systems for further uses.

A method includes screening, by a video-clip screening module in a video description model, a plurality of video proposal clips acquired from a video to be analyzed, to acquire a plurality of video clips suitable for description. The plural video proposal clips acquired from the video to be analyzed may be screened by the video-clip screening module to acquire the plural video clips suitable for description; and then, each video clip is described by a video-clip describing module, thus avoiding description of all the video proposal clips, only describing the screened video clips which have strong correlation with the video and are suitable for description, removing the interference of the description of the video clips which are not suitable for description in the description of the video, guaranteeing the accuracy of the final descriptions of the video clips, and improving the quality of the descriptions of the video clips.

Systems, methods, and other embodiments associated with detecting severity levels of risk in an electronic correspondence are described. In one embodiment, a method includes inputting, into a memory, a target electronic correspondence that has been classified as being litigious by a machine learning classifier. An artificial intelligence rule-based technique is applied to the target electronic correspondence that identifies high and medium risk level keywords. The technique is also configured to generate a litigious score based on a sum of term frequencies-inverse document frequencies using the remaining keywords. An electronic notice is transmitted to a remote computer over a communication network that identifies the target electronic correspondence and the level of litigation risk.

Systems, methods, and other embodiments associated with a machine learning system that monitors and detects risk in electronic correspondence related to a construction project are described. In one embodiment, a method includes monitoring email communications over a network to identify an email; tokenizing text from the email into a plurality of words and initiating a machine learning classifier configured to identify construction terminology and to classify text with a risk as being litigious or non-litigious. The machine learning classifier processes the words from the email by at least corresponding the words to a set of defined litigious vocabulary and defined non-litigious vocabulary. The email is labeled as litigious or non-litigious. An electronic notice is generated and transmitted to a remote device in response to the email being labeled as being litigious to provide an alert in near-real time in relation to receiving the email over the network.

A method for predicting a medical condition in a patient, the method comprising: receiving, with respect to each of a plurality of subjects, a plurality of clinical parameters, and an outcome indication with respect the said medical condition; applying to said plurality of clinical parameters one or more feature selection algorithms, to select a subset of said plurality of clinical parameters as the most relevant predictors; at a training stage, training a machine learning model on a training set comprising: (i) said relevant predictors with respect to each of said subjects, and (ii) labels associated with said outcome indication in said subject; and at an inference stage, applying said trained machine learning model to a target subset of said relevant predictors with respect to a target patient, to predict said medical condition in said target patient.

A method according to the present disclosure includes (a) generating N pieces of input data from one target object, (b) inputting the input data to a machine learning model and obtaining M classification output values, one determination class, and a feature spectrum, (c) obtaining a similarity degree between a known feature spectrum group and the feature spectrum for the input data, and obtaining a reliability degree with respect to the determination class as a function of the reliability degree, and (d) executing a vote for the determination class, based on the reliability degree with respect to the determination class, and determining a class determination result of the target object, based on a result of the vote.