Abstract: This disclosure relates to method and system for providing an explanation for a prediction generated by an artificial neural network (ANN) model for a given input data. The method may include receiving the given input data and the prediction generated by the ANN model. The ANN model may be built and trained for a target application. The method may further include determining a plurality of relevant portions of the given input data. For each of the plurality of relevant portions, the method may further include fetching a portional prediction and a portional prediction score generated by the ANN model, and determining a degree of influence score based on the portional prediction score and a comparison between the portional prediction and the prediction. The method may further include providing the explanation for the prediction based on the degree of influence score of each of the plurality of relevant portions.

Abstract: A method and system for summarizing multimedia content is disclosed. The method includes the steps of extracting a set of video files from a multimedia content such that each of the set of video files comprises a plurality of frames, and summarizing each of the set of video files to generate a set of summarized video files. Summarizing includes modifying a number of frames in each of the set of video files while retaining a caption generated for each of the set of video files. The method further includes generating sets of bridge frames for the set of summarized video files, based on a deep learning model. A set of bridge frames from the sets of bridge frames maintains continuity between corresponding adjacent summarized video files. The method includes generating a summarized multimedia content based on the set of summarized video files and the sets of bridge frames.

Abstract: Disclosed herein is a method and a failure prediction system for predicting failures in a diverse set of asset types in an enterprise. In an embodiment, asset information related each assets are analyzed for determining an asset type and a failure mode of each of the assets. Thereafter, one of a plurality of prediction models is selected for predicting failures in each of the assets based on the asset type and the failure mode of each of the assets. Finally, selected one of the plurality of prediction models is used to analyze the asset information for predicting the failures in each of the assets. In an embodiment, the present disclosure provides a universal failure prediction system for predicting failures in the diverse set of asset types and thereby eliminates requirement of using multiple prediction systems for predicting failures in each type of the assets.

Abstract: The present invention relates to a method for safely parking an autonomous vehicle on sensor anomaly. Based on current position of the AV, an angular velocity and curvature required for the AV to reach a safe parking space may be determined, upon detecting non-working of at least one primary sensor associated with the AV. Further, one or more obstacles proximal to the AV may be detected using one or more secondary sensors attached to the AV. Furthermore, based on detection of the one or more obstacles, the AV may be navigated in a track by maintaining a safe distance from the one or more obstacles. Finally, the AV may be navigated along the determined curvature upon detecting absence of the one or more obstacles to reach the safe parking space at the edge of the road.

Abstract: The present invention relates to a method and device for navigating an autonomous vehicle. The autonomous vehicle generates a first trajectory based on a path of navigation and determines a current velocity and present load of the autonomous vehicle. Further, the autonomous vehicle measures a curvature of a curved segment in the first trajectory and matches the measured curvature of the curved segment with a plurality of curvatures of a second trajectory from a trajectory performance profile of the autonomous vehicle. The second trajectory is obtained by applying a plurality of linear and angular velocities to the autonomous vehicle on a test track. Further, the autonomous vehicle selects an optimal trajectory from the trajectory performance profile based on the matching and the current velocity and the present load of the autonomous vehicle. Further, the autonomous vehicle navigates along the optimal trajectory.

Abstract: A method for detecting outliers is provided, the method comprising: receiving a digitized text corpus comprising a plurality of data points; identifying k clusters of the plurality of data points; sampling a data point among the plurality of data points as a first cluster center of the k clusters; determining sampling probability of each of remaining data points of the plurality of data points; sampling the next cluster center based on the sampling probability and iterate the process of determining sampling probability and the process of sampling the next cluster center until k cluster centers are sampled; generating weightage for each of the k cluster centers; determining sensitivity scores of the data points belonging to each of the k cluster centers; and labeling a data point having a sensitivity score greater than a threshold value as an outlier and removing the outlier from the digitized text corpus.

Abstract: The disclosure relates to a system and method for providing enhanced security of physical assets within a physical infrastructure. The method includes receiving an overall layout of the physical infrastructure and multi-modal input with respect to the physical asset from a plurality of sensors installed within the physical infrastructure. The multi-modal input includes acoustic signal generated by or reflected off the physical asset and captured by a set of acoustic sensors. The method further includes generating a digital asset corresponding to the physical asset by determining an identification, a location, a shape, a size, and a behavior of the physical asset based on the multi-modal input and the overall layout, detecting one or more events of interest involving the digital asset based on the behavior of the physical asset, and simulating the one or more events of interest to evaluate a possible fault or a possible security threat.

Abstract: Methods, devices, and non-transitory computer readable media that add interoperable BOTs to a stored BOT inventory. Each of the BOTs is associated with a BOT type, has a common structure, and automates at least a portion of an enterprise process. Assembly rules are obtained. Each of the assembly rules includes one or more constraints for inclusion of one or more of the BOTs in one or more of a plurality of workflows based on the one of the BOT types associated with each of the one or more of the BOTs. The workflows are assembled based on one or more the assembly rules. Each of the workflows comprises a subset of the BOTs and each BOT of the subsets of the BOTs is included in one or more of the workflows based on at least one of an associated functionality, performance, or service level.

Abstract: Embodiments of present disclosure relates to method and system to accurate detection of partial visual fault in lidar sensor of moving vehicle. Initially, first line cluster data for static objects present within first predefined view of Lidar sensor is determined. Static objects are tracked until viewing angle of Lidar sensor for corresponding static object is 90°. The tracking is performed based on second line cluster data corresponding to first line cluster data for static objects present within second predefined view of Lidar sensor. During tracking, non-observation of second line cluster data corresponding to first line cluster data, for one or more static objects is detected. Angle of non-observation is determined for one or more static objects upon detection. Presence of partial visual fault for Lidar sensor is detected based on angle of non-observation, for notifying navigation system associated with moving vehicle.

Abstract: This disclosure relates generally to an information retrieval technology and more particularly to a creation of a taxonomy to facilitate subsequent search and retrieval of information. In one embodiment, an information retrieval device is disclosed, that comprises a processor and a memory that stores instructions, which, on execution, causes the processor to receive an input corpus. Thereafter, input document clusters are generated from top input n-grams associated with the input corpus. Further, top-ranked input n-grams are determined from the top input n-grams. Thereafter, an external corpus is identified based on the top-ranked input n-grams. An enriched corpus (external and input corpus), is clustered based on top enriched n-grams associated with the enriched corpus to generate enriched document clusters. Further, for each n-gram of the enriched corpus, corresponding n-gram clusters are determined.

Abstract: The present disclosure discloses method and system for extracting relevant entities from a text corpus. The method comprises receiving, by the entity extraction computing device, a text corpus and an entity, determining at least one feature for each block of text from the text corpus, where the at least one feature corresponds to predefined one or more feature heads, calculating a score for each block of text from the text corpus based on training of the entity extraction system, determining a template from one or more templates based on the score, where the one or more templates are generated based on the training of the entity extraction system, and extracting at least one relevant entity from the text corpus, with respect to the entity, based on the template. The method and system disclosed in the present disclosure may be used to extract relevant entities across various domains by training the system.

Abstract: A method and data summarization system for dynamically generating summarised content for visual and contextual text data, is disclosed. The method includes classifying plurality of dataset related to one or more domains based on datatype associated with each dataset. The datatype comprises text, numeric and visual data. Upon classification, one or more usable tokens are determined from the text data using a predefined token learning model. Further, one or more graphical parameters are determined from the visual data by using a pre-trained graphical model. Thereafter, based on the one or more usable tokens and the one or more graphical parameters, a summarized content is generated for the plurality of dataset.

Abstract: The disclosure relates to method and system for training an artificial neural network (ANN) based image classifier using class-specific relevant features. The method includes receiving the ANN based image classifier, training image dataset, and various features of the training image dataset. The method further includes determining a relative relevance value of each of the features corresponding to each of the classes based on the ANN based image classifier, segregating co-occurring features from the features for each of the classes based on the training image dataset and the ANN based image classifier, identifying an imbalance in the class-specific relevant features for each of the classes based on the relative relevance value of each of the features corresponding to each of the classes, and updating the ANN based image classifier based on the imbalance in the class-specific relevant features and the co-occurring features for each of the classes.

Abstract: A method and device for determining operation of an autonomous device is disclosed. The method includes receiving pixel data and sound data associated with an environment at an instance of time, wherein the pixel data is received from least an image sensor associated with the autonomous device, and wherein the sound data is received from at least four sound sensors placed in a quadrilateral configuration on the autonomous device. Each quadrant of the pixel data is associated with each of the at least four sound sensors. The sound data received is mapped the to the matrix to identify one or more pixels in the matrix corresponding to the sound data based on a difference in amplitude between a first sound sensor of the at least four sound sensors recording maximum sound amplitude with a plurality of second sound sensors of the at least four sound sensors.

Abstract: This disclosure relates to method, device, Wand system for clustering document objects based on information content. The method may include identifying a plurality of object chunks from at least one document based on semantic context of each of the plurality of object chunks, determining at least one document portion from the at least one document as a base document based on a plurality of parameters applied to the plurality of object chunks, determining a plurality of hierarchies within the base document, and categorizing the plurality of object chunks based on the plurality of hierarchies and information in each of the plurality of object chunks. It should be noted that each of the plurality of object chunks may include at least one object selected from the at least one document.

Abstract: The present invention discloses a method and a system for rendering content in low light condition for field assistance. The method comprising receiving real-time input data from a user device in a low light condition, identifying at least one object from the real-time input data and corresponding operational state of the at least one object based on a correlation of the at least one object in the input data and corresponding operational state of the at least object with pre-stored objects and corresponding operational state of the pre-stored objects, predicting at least one action to be performed on the identified at least one object, extracting an Augmented Reality (AR) object associated with the identified at least one object on which the selected action is to be performed, and rendering the location, the selected at least one action to be performed, and the AR object on the user device.

Abstract: A method and system for managing interference between transmission sources in an Optical Camera Communication (OCC) network is disclosed. The method includes receiving interference information associated with a set of transmission sources. Each of the set of transmission sources include a set of light sources configured to display one of a plurality of colors. The method further includes assigning a unique guard band to each of the set of transmission sources. The method includes sharing details of the unique guard band assigned to a first transmission source within the set of transmission sources with the camera. The camera is configured as the receiver of the first transmission source. The method further includes instructing the camera to accept data transmitted by the first transmission source based on the assigned unique guard band and drop data transmitted by the remaining set of transmission sources.

Abstract: This disclosure relates to method and system for improving performance of an artificial neural network (ANN). The method may include receiving a weight matrix comprising an original weight of each neural node in each layer of the ANN. For each unique combination of at least two neural nodes in each layer, the method may further include determining a relative advantage value for one of the at least two neural nodes in a given layer with respect to remaining of the at least two neural nodes in the given layer based on actual inputs and standard inputs to the at least two neural nodes, and determining a modified weight of each of the at least two neural nodes based on the relative advantage value. The method may further include executing an elimination decision for each neural node in each layer based on a corresponding final modified weight, and updating the weight matrix based on the final modified weight of each remaining neural node in each layer.

Abstract: This disclosure relates to method and system for annotating tokens for natural language processing (NLP). In one embodiment, the method may include segmenting a plurality of corpus based on each of a plurality of instances, deriving a plurality of entities for each of the plurality of instances based on at least one of a machine learning technique or a deep learning technique, determining a word vector for each of the plurality of entities associated with each of the plurality of instances, and labelling a plurality of tokens for each of the plurality of instances. It should be noted that the plurality of tokens associated with the plurality of entities may be identified based on a frequency of each of the plurality of entities.

Abstract: A method and a system of determining a relation between two or more entities in a text document is disclosed. In an embodiment, the method may include receiving training text data annotated with two or more entities, and creating one or more n-grams based on the training text data. The method may further include generating a Convolutional Neural Network (CNN) model using the one or more n-grams, and creating an entity vector using at least one of a word embedding and a numeric embedding based on the training text data. The method may further include generating a relation-entity model using the CNN model and the entity vector.