Abstract: System and method for diagnosing a disease using image classification is provided. The method includes receiving diagnostic images associated with a subject. The diagnostic images comprise a first image and a second image captured at a first instance of time and at a second instance of time, respectively. The method further includes extracting feature maps from the first image and the second image, using a first pipeline and a second pipeline of stacked convolutional layers of a temporal convolutional neural network (CNN) model respectively. The method further includes identifying relevant feature maps from the feature maps using temporal CNN layer of the temporal CNN model, generating a concatenated feature map based on the relevant feature maps, determining an image class corresponding to the second image using fully connected layers of the temporal CNN model, and diagnosing the disease associated with the subject based on the image class.

Abstract: This disclosure relates to method and system for providing user-specific explanations for an output generated by an Artificial Neural Network (ANN) model. The method may include receiving a training dataset, and identifying one or more relevant features from the training dataset. The method may further include distributing the one or more relevant features into a plurality of groups. The plurality of groups may correspond to a plurality of levels of domain knowledge of users. The method may further include generating a plurality of vocabularies of explanations for an output generated by the ANN model for the training dataset corresponding to the plurality of groups, using the one or more relevant features.

Abstract: A method and system for generating user driven adaptive object visualizations using Generative Adversarial Network (GAN) models is disclosed. The method includes the steps of generating a first set of object vectors for an object based on at least one input received from a user. The first set of vectors corresponds to a first set of visualizations for the object The method further includes capturing at least one tacit reaction type of the user in response to user interaction with each of the first set of visualizations, computing a score for each portion of each of the first set of visualizations, identifying a plurality of portions from at least one of the first set of object visualizations, generating a second set of object vectors, and processing the second set of object vectors sequentially through a plurality of GAN models to generate a final object visualization of the object.

Abstract: The disclosure relates to a system and method of configuring and validating multi-vendor and multi-region Internet-of-Things (IoT) devices using reinforcement learning. In some embodiments, the method includes generating a matching table for each of a plurality of IoT sensors based on a plurality of sensor attributes extracted from a product data associated with an IoT sensor; acquiring an identification information and operational information associated with the IoT sensor and a set of neighboring IoT sensors for each of the plurality of IoT sensors; identifying an appropriate set of IoT sensors from the plurality of IoT sensors, based on a user requirement, the matching table, the identification information and the operational information, using a Reinforcement Learning (RL) model; and dynamically configuring each of the appropriate set of IoT sensors based on a vendor type.

Abstract: The present invention relates to a method of purchasing one or more goods from a physical store through a virtual environment. The method includes obtaining one or more physical store details and one or more user details from a user device for authenticating a physical user. Further, a unique avatar indicative of a virtual user corresponding to the physical user is generated. Furthermore, the virtual environment comprising one or more virtual stores is generated from a real-time video. The virtual environment is provided to the user device. Subsequently, an optimal path for traversing the virtual user in the virtual environment is determined in real-time based on one or more shopping details and a time period associated with the one or more shopping details. Finally, the virtual user is navigated in the one or more virtual stores through the optimal path for purchasing the one or more goods.

Abstract: Disclosed herein is method and fault detection system for detecting faults in one or more products. In an embodiment, method comprises generating plurality of wavelet coefficients corresponding to transformed images of each of the one or more products and determining a set of invariant features from the plurality of wavelet coefficients. Further, a dynamic set of invariant features is generated by grouping invariant features into a set of groups based on type of the one or more products. Subsequently, the dynamic set of invariant features is quantized based on a predetermined quantization threshold and a representative coefficient signature is associated for each group in the dynamic set of invariant features. Finally, faults in the one or more products are detected by comparing coefficient signatures associated with the one or more products with the representative coefficient signature of each group in the dynamic set of invariant features.

Abstract: This disclosure relates to method and system for building ensemble models using competitive reinforcement learning (CRL). The method may include creating a plurality of clusters, each including a set of predictive models forming the ensemble model. For each of the plurality of clusters, the method may further include initializing each of the set of predictive models with random values for a set of first parameters to obtain a first accuracy score, categorizing each of the set of predictive models into a first associated category based on a first accuracy score, calculating a first reward for each of the set of predictive models based on the first associated category, and determining a set of second parameters for each of the set of predictive models using CRL to obtain a second accuracy score.

Abstract: The disclosure relates to method and system for performing optimized image search. The method includes receiving an input image and user requirements with respect to an image search, identifying a sub-section from various sub-sections of the input image based on semantic parameters corresponding to each sub-section and the user requirements, and determining an optimal resolution of the sub-section based on a pixel density of various image formats derived for the sub-section. The method further includes identifying an optimal set of layers from a plurality of layers of an Artificial Neural Network (ANN) based image search model for performing the image search based on the semantic parameters for the sub-section, the optimal resolution of the sub-section, and historical data, and performing the image search to identify a set of output images similar to the sub-section based on a modified ANN based image search model comprising the optimal set of layers.

Abstract: A method and system for allocating resources to containers includes receiving a plurality of resource allocation requests from a plurality of containers, receiving a preference of a container from each of the plurality of containers, determining a priority-sequence for the plurality of containers, allocating a first associated resource for an associated first time-period to each container of the plurality of containers, determining a current consumption of the first associated resource by each container of the plurality of containers during the associated first time-period, and allocating a second associated resource to each container of the plurality of containers based on the current consumption of the first associated resource by each container of the plurality of containers.

Abstract: A method, device and system for managing collaboration amongst robots is disclosed. The method may include assigning a color tag from a set of predefined color tags to each of a plurality of robots, based on associated functional capabilities. The method may further include dynamically creating a plurality of groups for a plurality of tasks based on at least one attribute associated with each of the plurality of tasks and functional capabilities associated with the plurality of robots. The method may include electing a plurality of chief robots for the plurality of groups based on a first predefined logic. The method may include selecting a prime robot from the plurality of chief robots based on a second predefined logic and the selected prime robot may be configured to monitor activity of each of the plurality of groups and each robot in each of the plurality of groups.

Abstract: System and method for diagnosing a disease using image classification is provided. The method includes receiving diagnostic images associated with a subject. The diagnostic images comprise a first image and a second image captured at a first instance of time and at a second instance of time, respectively. The method further includes extracting feature maps from the first image and the second image, using a first pipeline and a second pipeline of stacked convolutional layers of a temporal convolutional neural network (CNN) model respectively. The method further includes identifying relevant feature maps from the feature maps using temporal CNN layer of the temporal CNN model, generating a concatenated feature map based on the relevant feature maps, determining an image class corresponding to the second image using fully connected layers of the temporal CNN model, and diagnosing the disease associated with the subject based on the image class.

Abstract: Disclosed herein is method and fault detection system for detecting faults in one or more products. In an embodiment, method comprises generating plurality of wavelet coefficients corresponding to transformed images of each of the one or more products and determining a set of invariant features from the plurality of wavelet coefficients. Further, a dynamic set of invariant features is generated by grouping invariant features into a set of groups based on type of the one or more products. Subsequently, the dynamic set of invariant features is quantized based on a predetermined quantization threshold and a representative coefficient signature is associated for each group in the dynamic set of invariant features. Finally, faults in the one or more products are detected by comparing coefficient signatures associated with the one or more products with the representative coefficient signature of each group in the dynamic set of invariant features.

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 system for generating user driven adaptive object visualizations using Generative Adversarial Network (GAN) models is disclosed. The method includes the steps of generating a first set of object vectors for an object based on at least one input received from a user. The first set of vectors corresponds to a first set of visualizations for the object The method further includes capturing at least one tacit reaction type of the user in response to user interaction with each of the first set of visualizations, computing a score for each portion of each of the first set of visualizations, identifying a plurality of portions from at least one of the first set of object visualizations, generating a second set of object vectors, and processing the second set of object vectors sequentially through a plurality of GAN models to generate a final object visualization of the object.

Abstract: Disclosed herein is a method and a data transfer system for providing seamless data transfer between communication devices. Properties of data to be transferred, status of network parameters and power associated with the communication devices are monitored in real time. Further, communication protocols available at the communication devices and a need to switch between the communication protocols are determined. Splitting of the data into subsets of data and sequencing the subsets of data are performed using a neural network, which is trained based on properties of the data, data storage space of the communication devices, speed of data transfer and a communication channel available for the data transfer. The optimum communication protocols are identified based on order of priority value and contention value. The subsets of data are transferred using identified optimum communication protocols, until a change in the monitored status is detected to switch the optimum communication protocols.

Abstract: A method and dynamic learning system for providing dynamic cross learning is disclosed. The dynamic learning system identifies one or more changes in an environment in which an automated task performing device is scheduled to perform one or more activities. The dynamic learning system initiates a dynamic learning associated with the one or more changes for the automated task performing device based on pre-stored contextual information. Based on the dynamic learning, one or more actions is provided to the automated task performing device to perform the one or more activities in view of the one more changes. Therefore, the present disclosure facilitates dynamic determination and analysis of environment and situation for the automated task performing device for performing the activities. Thus, leading to dynamic decision-making to provide adjustment to the automated task performing device in any situation.

Abstract: Embodiments of the present disclosure relate to a method and an apparatus for alerting threats to users. The apparatus may capture a plurality of signals including at least one of Electro-Magnetic (E-M) signals and sound signals. The E-M signal and sound signals are used to detect objects around the user. A threat to the user is predicted based on the objects around the user and one or more alerts are generated such that the user avoids the threat. The prediction of the threat enables the user to take an action even before the threat has occurred. Also, the alerts are generated based on the prediction such that the user can avoid the threat well in advance of the occurrence of the threat.

Abstract: Disclosed herein is a method and a data transfer system for providing seamless data transfer between communication devices. Properties of data to be transferred, status of network parameters and power associated with the communication devices are monitored in real time. Further, communication protocols available at the communication devices and a need to switch between the communication protocols are determined. Splitting of the data into subsets of data and sequencing the subsets of data are performed using a neural network, which is trained based on properties of the data, data storage space of the communication devices, speed of data transfer and a communication channel available for the data transfer. The optimum communication protocols are identified based on order of priority value and contention value. The subsets of data are transferred using identified optimum communication protocols, until a change in the monitored status is detected to switch the optimum communication protocols.

Abstract: A method and system for summarizing content based on user preferences is disclosed. The method includes identifying a set of relevant objects from a set of objects based on a relevancy score corresponding to each of the set of objects extracted from a plurality of sentences. The method further includes generating a link graph between each of the plurality of sentences. The method further includes assigning a weight to each of the plurality of sentences based on a retention probability. The method further includes generating a summarized content from the plurality of sentences based on the user preferences, the link graph, and the weight associated with each of the plurality of sentences.

Abstract: The present invention discloses a method and a system for assisting user with product handling in a retail shopping. The method comprising identifying one or more products from a list of products that user intends to purchase, neighbouring products and orientations of the one or more products and the neighbouring products from a plurality of image frames and rack information, comparing the identified orientations with historic orientations of products and neighbouring products associated with the rack information, identifying at least one product from the one or more products and the neighbouring products that is improperly oriented based on comparison, determining product safety handling instructions of the identified at least one product and assisting the user in real-time with handling of the identified at least one product based on the product safety handling instructions.