Abstract: This disclosure relates generally to a system and method to identify a plurality of noises or their combination to suppress them and enhancing the deteriorated input signal in a dynamic manner. It identifies noises in the audio signal and categorizing them based on the trained database of noises. A combination of deep neural network (DNN) and artificial Intelligence (AI) helps the system for self-learning to understand and capture noises in the environment and retain the model to reduce noises from the next attempt. The system suppresses unwanted noise coming from the external environment with the help of AI based algorithms, by understanding, differentiating, and enhancing human voice in a live environment. The system will help in the reduction of unwanted noises and enhance the experience of business and public meetings, video conferences, musical events, speech broadcasts etc. that could cause distractions, disturbances and create barriers in the conversation.

Abstract: Electronic sensing systems and methods are disclosed. The electronic sensing system (ESS) receive an olfactory product and one or more smell characteristics of the olfactory product are detected and extracted by identifying a headspace of the olfactory product. A comparison of the extracted smell characteristics with one or more smell characteristics associated with a historic training data stored in a database is performed and a match between the extracted smell characteristics and the one or more smell characteristics associated with the historic training data is determined using machine learning technique(s). Further, the ESS generates a report for the olfactory product comprising at least one of type of the consumable, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, and classifies the olfactory product into one or more categories based on the report and/or the historic training data.

Abstract: Systems and methods for assessing quality of input text using recurrent neural networks is disclosed. The system obtains input text from user and performs a comparison of each word from input text with words from dictionary (or trained data) to determine a closest recommended word for each word in the input text. The input text is further analyzed to determine context of each word based on at least a portion of input text, and based on determined context, at least one of correct sentences, incorrect sentences, and/or complex sentences are determined from the input text. Each word is converted to a vector based on concept(s) by comparing each word across sentences of input text to generate vectors set, and quality of the input text is assessed based on vectors set, the comparison, determined context and at least one of correct sentences, incorrect sentences, complex sentences, or combinations thereof.

Abstract: Systems and methods for providing adaptive virtual reality (VR) assistant in VR environments. The system is configured to receive input from users within an interactive communication session, wherein text from the input is extracted and analyzed by a Natural Language Processing (NLP) engine, and context is determined based on the input text extracted. Based on the determined context and input, the adaptive VR assistant generates a VR environment that is integrated within the same interactive communication session. The system enables a communication session between a virtual character created for the user and other virtual users within the generated VR environment based on the determined context.

Abstract: Statistical modeling techniques based neural network models for generating intelligence reports is provided. The system obtains test dataset and training dataset, each of which include at least one of images and elements. Statistical modeling techniques are identified and selected based on the test dataset for normalizing the test dataset to obtain normalized dataset. The system further associates, using one or more clustering techniques a unique cluster head to at least one of (i) normalized elements set and (ii) normalized images set in the normalized dataset to obtain a labeled dataset. The labeled dataset is further analysed by integrated trained modeling techniques into neural network model(s) and intelligence reports are generated.

Abstract: A system and method to create an intelligent cartoon comic strip based on the dynamic content. Herein, the input is conversation-based text or speech files. The system identifies scenes, objects, sequence and flow for generating the comic strip along with gender of characters appearing in the entire conversation. Text is analyzed to create the situational based background image for the scenes that needs to be rendered. Emotion and placement of characters in the scene is decided by the NLP algorithms along with voice emotional and sentimental analysis. Characters are placed in plain canvas and then text dialog is embedded into corresponding text bubbles. Once this image is obtained, it is overlaid on top of the background based on the context. Further, the scenes are joined into a strip of images in a pattern, which depends on the number, and order of scenes, which is decided, based on the input.

Abstract: This disclosure relates generally to a system and method for analyzing live activity on the conductive fabrics with intelligent touch. The system comprises a plurality of modules and these modules are in sync with the processor of the system to take action based on a plurality of instructions of the memory. Further, the system comprises fabrics, which are of conductive in nature, are used as a conductive touch pads for inputs to the system. The input data from touch pads are analyzed to determine pattern of actions. These patterns are associated with the IoT devices and the system uses them to trigger at least one action on the at least one IoT device based on a predefined training data set.

Abstract: A system and method to create an intelligent cartoon comic strip based on the dynamic content. Herein, the input is conversation-based text or speech files. The system identifies scenes, objects, sequence and flow for generating the comic strip along with gender of characters appearing in the entire conversation. Text is analyzed to create the situational based background image for the scenes that needs to be rendered. Emotion and placement of characters in the scene is decided by the NLP algorithms along with voice emotional and sentimental analysis. Characters are placed in plain canvas and then text dialog is embedded into corresponding text bubbles. Once this image is obtained, it is overlaid on top of the background based on the context. Further, the scenes are joined into a strip of images in a pattern, which depends on the number, and order of scenes, which is decided, based on the input.

Abstract: This disclosure relates generally to a system and method to identify a plurality of noises or their combination to suppress them and enhancing the deteriorated input signal in a dynamic manner. It identifies noises in the audio signal and categorizing them based on the trained database of noises. A combination of deep neural network (DNN) and artificial Intelligence (AI) helps the system for self-learning to understand and capture noises in the environment and retain the model to reduce noises from the next attempt. The system suppresses unwanted noise coming from the external environment with the help of AI based algorithms, by understanding, differentiating, and enhancing human voice in a live environment. The system will help in the reduction of unwanted noises and enhance the experience of business and public meetings, video conferences, musical events, speech broadcasts etc. that could cause distractions, disturbances and create barriers in the conversation.

Abstract: This disclosure relates generally to a system and method for analyzing live activity on the conductive fabrics with intelligent touch. The system comprises a plurality of modules and these modules are in sync with the processor of the system to take action based on a plurality of instructions of the memory. Further, the system comprises fabrics, which are of conductive in nature, are used as a conductive touch pads for inputs to the system. The input data from touch pads are analyzed to determine pattern of actions. These patterns are associated with the IoT devices and the system uses them to trigger at least one action on the at least one IoT device based on a predefined training data set.

Abstract: An authentication system and method is provided. The system: (a) provides a keyboard comprising a letters in a m×n format, ‘m’ represents rows, and n represents columns, each row or column includes a sub-set of the letters, (b) provides input receiving identifiers, each input receiving identifier specific to at least one row or column, (c) processes an input on at least one input receiving identifier from the set of input receiving identifiers, (d) identifies a first intended letter from a first sub-set of letters from a corresponding row or column based on the input, (e) repeats steps (c) and (d) until a last intended letter from a last sub-set of letters is identified to obtain intended identified letters, (f) performs a comparison between the intended identified letters with a pre-registered set of letters stored in a memory, and (g) triggers at least one action based on the comparison.

Abstract: Systems and methods for multi-dimensional password generation and authentication is provided. The method includes selecting a virtual reality (VR) environment, rendering interactive objects in the VR environment, tracking a first set of activities including user behavior, user interaction with the objects, and changes made to the objects, the behavior including user position(s), head rotation, time spent on a particular position, GPS coordinates, and the changes include one of position, shape, color, and rotation of the objects. The method generates a multi-dimensional password based on the first set of tracked activities, and authenticates based on comparison of a second set of tracked activities and the first set of activities. When the comparison results in mismatch, the system generates a one-time multi-dimensional image, based on which a third set of activities are tracked and compared with the first set of activities for resetting the password or authenticating the user accordingly.

Abstract: A system and a method for virtual reality based interactive learning are provided. The method includes simulation of a 3D interactive scene in a VR environment, and rendering the 3D interactive scene including queries on a VR display platform. Responses to the queries are received in the VR environment. A first cumulative assessment score is computed based on the response and attributes of participants. Also, subsequent 3D interactive scenes are dynamically simulated in the VR environment based on the first cumulative assessment score. Subsequent queries associated with context of the subsequent scenes are rendered, and a second cumulative assessment score is computed based on the subsequent responses to the subsequent queries. Furthermore, an overall assessment score is computed based on the cumulative assessment scores. A 3D interactive scene is rendered till the overall assessment score is equal to or greater than a threshold assessment score.