Abstract: The present disclosure provides a model for deep learning based image feature extraction considering a range of useful negative features. Conventional methods are either considering only positive features or considering all negative features along with positive features which leads to bias in feature extraction. The present disclosure overcomes the problem of the conventional methods using a bounded Rectified Linear activation Unit (B-ReLU) activation function based Bounded-Rectifier Network (B-RectNet). Initially, the present disclosure receives an image pertaining to an object. Further, the received image is preprocessed to remove a plurality of anomalies associated with the image a preprocessing technique. Further, a plurality of image features are extracted based on the preprocessed image using a trained B-RectNet.

Abstract: A method and system for synthesizing smartphone cue-cards representing socio-technical system (STS) service design prototyping based on a plurality of constraints has been provided. The system creates just in time, a dynamic visual design for senior and junior designers for displaying of patterns as digital Cue Cards based on human configured time constraint and novelty constraints all the while avoiding repeatability for the designer. Smartphone is utilized as a mechanism to host multiple cue cards and an interaction model which allows multiple cue-card-connectedness to jump across constraints of local-maxima/minima towards a global-maxima/minima. The method allows young designers get access to better long term memory (LTM) and senior designer getting access to faster LTM. The present disclosure helps senior designer get faster access to new patterns to reduce time for novel new interventions.

Abstract: Traditional approaches for recommending optimum combination of quantum circuits are experimentation based approaches, and require manual efforts or are cumbersome, effort intensive and iterative processes. Method and system disclosed herein generally relates to quantum experimentation, and, more particularly, for recommending optimum combination of quantum circuits. In this approach, a high-level combination of experiments are initially generated, which are further prioritized using a graph based approach, which then forms a training data. The training data is then used for generating a GNN data model, which is further used for recommending optimum combination of quantum circuits.

Abstract: The present invention relates to a method and system for early detection of COVID-19. Existing methods require data from multiple sensors for training a prediction model whose output is considered as final prediction which is actually the prediction for a particular day or time instance. However, this prediction doesn't detect actual infection of COVID-19 since it requires monitoring the change in health of the user over consecutive days. Embodiments of present disclosure overcome these challenges by a prediction model for COVID-19 which requires only data from Photoplethysmography (PPG) sensor seamlessly collected from a wearable device still able to provide accurate COVID-19 prediction with application of a post processing technique on the predictions of the prediction model. Since COVID-19 symptoms have an effect on heartrate and oxygen saturation which are effectively captured by PPG sensor data, studying these dynamics during infection period gives insights to perform early detection of COVID-19.

Abstract: Existing semi-supervised and unsupervised approaches for intent discovery require an estimate of the number of new intents present in the user logs. The present disclosure receives labeled utterances from known intents and update parameters of a pre-trained language model (PLM). Representation learning and clustering is performed iteratively using labeled and unlabeled utterances from known intents and unlabeled utterances from unknown intents to fine-tune PLM and a plurality of clusters is generated. Cluster merger algorithm is executed iteratively on generated plurality of clusters. A query cluster is obtained by randomly selecting one cluster from the plurality of clusters and by obtaining a corresponding plurality of nearest neighbors based on a cosine-similarity. A response for merging the query cluster and corresponding plurality of nearest neighbors is obtained, and a new cluster is created.

Abstract: This disclosure relates generally to identification and mitigation of bias while training deep learning models. Conventional methods do not provide effective methods for bias identification, and they require pre-defined concepts and rules for bias mitigation. The embodiments of the present disclosure train an auto-encoder to produce a generalized representation of an input image by decomposing into a set of latent embedding. The set of latent embedding are used to learn the shape and color concepts of the input image. The feature specialization is done by training an auto-encoder to reconstruct the input image using the shape embedding modulated by color embedding. To identify the bias, permutation invariant neural network is trained for classification task and attribution scores corresponding to each concept embedding are computed. The method also performs de-biasing the classifier by training it with a set of counterfactual images generated by modifying the latent embedding learned by the auto-encoder.

Abstract: Embodiments disclosed herein model lifelong intent detection as a class-incremental learning where a new set of intents/classes are added at each incremental step. To address the issue of catastrophic forgetting during lifelong intent detection (LID), an incremental learner is provided with Prompt Augmented Generative Replay, wherein unlike existing approaches that store real samples in replay memory, only concept words obtained from old intents are stored, which reduces memory consumption and speeds up incremental training still enabling not forgetting the old intents. Joint training of an incremental learner is carried out for LID and a pseudo-labeled utterance generation with objective is to classify a user utterance into one of multiple pre-defined intents by minimizing a total Loss function comprising a LID loss function, a Labeled Utterance Generation loss function, a Supervised Contrastive Training loss function, and a Knowledge Distillation loss function.

Abstract: This disclosure addresses the unresolved problems of tackling object disambiguation task for an embodied agent. The embodiments of present disclosure provide a method and system for disambiguation of referred objects for embodied agents. With a phrase-to-graph network disclosed in the system of the present disclosure, any natural language object description indicating the object disambiguation task can be converted into a semantic graph representation. This not only provides a formal representation of the referred object and object instances but also helps to find an ambiguity in disambiguating the referred object using a real-time multi-view aggregation algorithm. The real-time multi-view aggregation algorithm processes multiple observations from an environment and finds the unique instances of the referred object.

Abstract: State of art techniques that utilize spatial association based Table structure Recognition (TSR) have limitation in selecting minimal but most informative word pairs to generate digital table representation. Embodiments herein provide a method and system for TSR from an table image via deep spatial association of words using optimal number of word pairs, analyzed by a single classifier to determine word association. The optimal number of word pairs are identified by utilizing immediate left neighbors and immediate top neighbors approach followed redundant word pair elimination, thus enabling accurate capture of structural feature of even complex table images via minimal word pairs.

Abstract: This disclosure relates to a method and system for real time prediction of tire remaining useful life using a tire digital twin. Herein, the digital twin of the tire monitors a plurality of tires while accounting for runtime as well as parking operation of tires. During runtime, tire goes through multiple operational changes, therefore, the system is configured to estimate the operational changes. The estimation is done in the form of index, which is compared with the manufacturers' recommended value. Similarly, while vehicle is parked, tire still goes through changes which play an important role in its overall health, like, long pending wheel rotation can lead to flat spot. Tire inflation can change owing to cool down effect as well as uncontrolled natural leakages. Further, these parameter indexes are clubbed together to calculate the health index of the tire, which is used to estimate the tire's current remaining useful life.

Abstract: This disclosure relates method and system for systematic disposal and dynamic procurement of recyclable waste resin. Typical systems for disposal and procurement of recyclable resin pose challenges such as lack of segregation and collection of different types of plastics, data on recycling centers in proximity, uncertainty over resin identification codes, and so on. The disclosed system provides a framework having multiple smart collection units that may be communicatively coupled with a server. The smart bins are capable of collecting plastic items and taking multiple images thereof. The system determines information on type, weight, and location of the plastic resin in the plastic item by means of a trained CNN model, and stores in a repository. The system further includes a route optimization model that is enables selection of a set of collection units for procurement of the resin (of a specific type and a specific quantity).

Abstract: Web application generation using conventional predefined template and data model approach is a technical limitation for varying user requirements. Embodiments herein provide a method and system for automated generation of web applications based on wireframe metadata generated from user requirements for a web application received in unstructured data format. The user requirements comprising a description document, and at least one of actor, requirements, use case number, use case name, and data to be collected is parsed to generate the wireframe metadata using NLP and wireframe generation rules. The wireframe metadata provides data structure of webpage details of webpages of the web application comprising a page name, a menu name, field details, a field component type, an action to be performed and an additional information. From the wireframe metadata data models are created dynamically using data modelling rules in accordance with user requirements along with task lists to generate web application.

Abstract: This disclosure relates generally to methods and systems for automated image segmentation of an anatomical structure such as heart. Most of the techniques in literature are using 2-D or slice by-slice data due to lightweight and need of less data for training. These networks lack 3-D contextual information. Further, the conventional techniques are inaccurate and inefficient in the 3-D image segmentation till the last slice of the image. The present disclosure solves automated 3-D image segmentation of the anatomical structure such as heart, by proposing a new Generative Adversarial Network (GAN) based architecture for the 3-D segmentation, with a patch-based extraction technique and a class-weighted generalized dice loss. The proposed 3-D GAN based architecture is capable of storing the 3-D contextual information for the image segmentation of the anatomical structure, with high accuracy.

Abstract: A system and method for navigation of a robot from a first area to a second area in a facility is provided. The present disclosure is providing robot navigation using the ‘Areagoal’ Navigation technique. ‘Areagoal’ class of problem is divided into two subtasks: identifying the area; and navigation from one area to another. The robot starts in first location and goes out of the current area if it is not in the target area. If there are multiple openings from the first area, it needs to select the most statistically close one to the target area and go there. If the target area is not reached, it backtracks to an earlier viable branch position to continue the target area search. The system takes input from RGB-D camera and odometer, while the output is action space (left, right, forward) with goal of moving to target area.

Abstract: Nanomaterials are an important class of materials for sunscreens. Conventional metal oxide nanoparticles are toxic in nature and leave white patches on skin after application. This disclosure provides a sunscreen composition containing biodegradable antimicrobial polymer nanoparticles as UV filter. The sunscreen composition comprising chitosan nanoparticles, at least one flavoring agent, at least one coloring agent, at least one stabilizer, and at least one preservative, in a defined form, wherein size of the chitosan nanoparticles is ranging from 200 to 900 nm. The size of the chitosan nanoparticles ranging from 200 to 400 nm for air medium, 500 to 700 nm for water medium and 700 to 900 nm for ethanol medium. The chitosan polymer is derived from chitin, a glucosamine polymer. The sunscreen composition is available in the defined form selected from a group consisting of a skin cream, a skin lotion, a powder, a gel, and a sprayable liquid.

Abstract: State of the art techniques used for document processing and particularly for handling processing of images for data extraction have the disadvantage that they have large computational load and memory footprint. The disclosure herein generally relates to text processing, and, more particularly, to a method and system for generating a data model for text extraction from documents. The system prunes a pretrained base model using a Lottery Ticket Hypothesis (LTH) algorithm, to generate a LTH pruned data model. The system further trims the LTH pruned data model to obtain a structured pruned data model, which involves discarding filters that have filter sparsity exceeding a threshold of filter sparsity. The structured pruned data model is then trained from a teacher model in a Knowledge Distillation algorithm, wherein a resultant data model obtained after training the structured pruned data model forms the data model for text detection.

Abstract: This disclosure relates generally to automated packing of objects, and, more particularly, to a method and system for packing products with increased efficiency across packaging levels. While conventional methods of improving packaging efficiency focus on only one of the multiple levels in the packaging process, most commonly the tertiary level, the present disclosure attempts increasing packaging efficiency across packaging levels. Embodiments of present disclosure achieves increased efficiency across packaging levels by identifying standard size of secondary packages for packing a plurality of primary packages, packing the secondary packages within tertiary packages using a Mixed Integer Linear Programming (MILP) optimization model based on packing heuristics, and providing a feedback between tertiary and secondary packaging levels to identify standard secondary packages which can pack the primary packages with higher packing efficiency.

Abstract: Industrial processes and equipment are prone to operational changes and faulty operation of such processes and equipment can adversely affect output of the overall setup. Existing systems for monitoring and fault detection consider individual instances of data for fault detection, which may not be suitable for industrial processes. Disclosed herein is a system and a method for anomaly detection in an industrial enterprise. The system collects data from a plurality of sensors as input. The system processes the collected data along temporal dimension, during which the data is split to multiple segments of fixed window size. Data in each segment is processed to identify anomalous data, and data in segments identified as containing the anomalous data is further processed to identify one or more sensors that are faulty and are contributing to the anomalous data.

Abstract: The present disclosure addresses unresolved problem of monopoly in content authoring, creation of dependency loop by providing a single, scalable, one-stop knowledge platform offering high degree of customization by multiple users and leveraging emerging technologies for rapid end-to-end game or learning solutions development. Embodiment of the present disclosure provides methods and systems for providing customized game-based learning and assessment framework. The present disclosure provides a mechanism to configure custom content into a readymade learning and assessment platform. The framework proposed in the present disclosure is custom built to support scalable architecture of a modular digital learning platform, and its functionalities. The system of the present disclosure allows content creators to author custom content to create immersive learning experience that could range from Spatial three-dimensional (3D) technologies, Augmented Reality (AR) and Virtual Reality (VR) or games at one place.

Abstract: State of the art approaches of exception management are reactive, manual, and intuition-driven. Command center teams often react to exceptions. They also use BI tools which only provide statistical observation, but fail to mine domain-aware insights and actionable recommendations. The disclosure herein generally relates to analyzing process exceptions, and, more particularly, to a method and system for generating a data model to analyze and predict process exceptions. The system generates a data model by using information on rules, associated properties and exceptions, as training data. The data model is further used to process information on different rules to identify exceptions, and then to generate recommendations in response to identified exceptions.