Abstract: Unlike existing methods, using LIDAR and 2D-cameras for detection and limit in providing robust tracking of objects, the method disclosed addresses the technical challenge by utilizing 3D-LIDAR points clouds, 2D-camera images and additionally 2D-BEV from 3D LIDAR point clouds to provide, robust, seamless, 360 tracking of objects. The method independently detects, and tracks objects captured by each of the LIDAR, 2D-camera set up mounted on an autonomous vehicle. Detection and tracking is performed on 2D-Camera and 2D-BEV and fused with 3D-Lidar tracker, Additionally, non-occluded area of an object in 2D-bounding boxes, is identified by superimposing panoptic segmentation output with 2D-BB, that helps to eliminate the lidar points falling on the irrelevant objects and provides accurate real world position of the detected objects in the point cloud. An enhanced 2D object detector based on a customized NN architecture employing MISH activation function is also introduced.

Abstract: State of the art approaches being used for material replenishment planning have the disadvantage that they fall short in addressing the realities of evolving demand mixes and product utilization. The technologies leverage inflexible statistical models which are tightly coupled to specific industries, business processes, and deeper assumptions and therefore the model and any optimization produce results where the quality of results is heavily curtailed as real business processes deviate from the model assumptions and unforeseen scenarios arise the business and the broader ecosystem evolve. The method and system disclosed in the embodiments herein facilitate generating simulation of various material replenishment scenarios based on a user input. The method and system further generates one or more recommendations for material replenishment, based on an optimization process carried out.

Abstract: The present disclosure relates to methods and systems for time-series classification using a reservoir-based spiking neural network, that can be used at edge computing applications. Conventional reservoir based SNN techniques addressed either by using non-bio-plausible backpropagation-based mechanisms, or by optimizing the network weight parameters. The present disclosure solves the technical problems of TSC, using a reservoir-based spiking neural network. According to the present disclosure, the time-series data is encoded first using a spiking encoder. Then the spiking reservoir is used to extract the spatio-temporal features for the time-series data. Lastly, the extracted spatio-temporal features of the time-series data is used to train a classifier to obtain the time-series classification model that is used to classify the time-series data in real-time, received from edge devices present at the edge computing network.

Abstract: State of art techniques existing method refer to handling multiple objectives such as accuracy and latency. However, the reward functions are static and not tunable at user end. Further, for NN search with hardware constraints, approaches combine various techniques such as Reinforcement learning, Evolutionary Algorithm (EA) etc., however hardly any work attempts to disclose combining different NAS approaches in unison to reduce the search space of other. Embodiments of the present disclosure provide a method and system for automated creation of tiny Deep Learning (DL) models to be deployed on a platform having a set of hardware constraints. The method performs a coarse-grained search using a Fast EA NAS model and then utilizes a fine-grained search to identify customized and optimized tiny model. The coarse-grained search and the fine-grained search performed by agents based on a weighted multi-objective reward function, which are tunable at user end.

Abstract: Assessing sustainability performance of an enterprise is a challenging task. Embodiments of present disclosure provide a method and system for SDG performance assessment of an enterprise with a conceptually simpler data model and processing pipeline. Enterprise data collected from hard and soft sensors is mapped to appropriate indicators of the SDGs. Further, a semantic network is constructed with nodes corresponding to each indicator and edges connecting nodes belonging to same SDG. Each node of the semantic network is further linked to a first layer of a neuro fuzzy network which calculates degree of impact of the indicator on Social, Economic and Environment values. Output of the first layer activates second layer of the neuro fuzzy network which determines BBV scores indicating whether the indicator is a burden, benefit, or vulnerability. The BBV scores are transformed to a colour space to generate a colour that indicates SDG performance of the enterprise.

Abstract: Traditionally, strategies are carried out based on customer intention indicated from surveys, transactional data, location of the store and customer profile. They have limitations such as partial capture of customer intention, absence of transactional data, challenges in defining catchment area associated with store location and lack of customer profiles. This disclosure relates to determining unified user intention from digital environment for plurality of strategies. An information associated with user is received. The information associated with the user is processed to derive weights associated with the user. The weights are integrated and mined through a variable reduction technique to determine at least one significant latent variable from a plurality of significant latent variables and associated significant attribute values.

Abstract: Current inspection processes employed for pipeline networks data acquisition aided with manually locating and recording defects/observations, thus leading labor intensive, prone to error and a time-consuming task thereby resulting in process inefficiencies. Embodiments of the present disclosure provide systems and methods for that leverage artificial intelligence/machine learning models and image processing techniques to automate log and data processing, reports and insights generation thereby reduce dependency on manual analysis, improve annual productivity of survey meterage and bring in process and cost efficiencies into overall asset health management for utilities, thereby enhancing accuracy in defect identification, analysis, classification thereof.

Abstract: This disclosure relates generally to method and system to estimate performance of session based recommendation model layers on FPGA. Profiling is easy to perform on software based platforms such as a CPU and a GPU which have development frameworks and tool sets but on systems such as a FPGA, implementation risks are higher and important to model the performance prior to implementation. The disclosed method analyses a session based recommendation (SBR) model layers for performance estimation. Further, a network bandwidth is determined to process each layer of the SBR model based on dimensions. Performance of each layer of the SBR model is estimated at a predefined frequency by creating a layer profile comprising a throughput and a latency in one or more batches. Further, the method deploys an optimal layer on at least one of a heterogeneous hardware based on the estimated performance of each layer profile on the FPGA.

Abstract: Conventional gesture detection approaches demand large memory and computation power to run efficiently, thus limiting their use in power and memory constrained edge devices. Present application/disclosure provides a Spiking Neural Network based system which is a robust low power edge compatible ultrasound-based gesture detection system. The system uses a plurality of speakers and microphones that mimics a Multi Input Multi Output (MIMO) setup thus providing requisite diversity to effectively address fading. The system also makes use of distinctive Channel Impulse Response (CIR) estimated by imposing sparsity prior for robust gesture detection. A multi-layer Convolutional Neural Network (CNN) has been trained on these distinctive CIR images and the trained CNN model is converted into an equivalent Spiking Neural Network (SNN) via an ANN (Artificial Neural Network)-to-SNN conversion mechanism. The SNN is further configured to detect/classify gestures performed by user(s).

Abstract: State of the art mechanisms being used for achieving diagnostic-quality images under low-dose settings for general CT imaging have the disadvantages that CT images are fixed during the optimization process to generate perfusion maps, which can lead to suboptimal CT images with respect to the perfusion maps generated, although they might appear spatially smooth or denoised. The disclosure herein generally relates to Computer Tomography (CT) scanning, and, more particularly, to a method and system for CT image reconstruction. The system performs modelling an optimization problem for joint estimation of a set of structural CT images and a perfusion map, and further solves the optimization problem for the reconstruction of the CT images of a subject.

Abstract: This disclosure relates generally to method and system for maximizing space utilization in a building. Due to current pandemic scenario many organizations eventually need to plan for the return of employees to office space ensuring biosafety. The challenge of maximizing the office space utilization ensuring occupants biosafety and comfort thereby minimizing HVAC energy consumption is necessary. The method utilizes two heuristic approaches for determining maximum allowable occupants placement in the open plan space using an optimal occupant placement technique. This minimizes the HVAC energy if the actual count is lesser than the possible maximum occupants can be placed which further optimizes energy using a joint actuator control technique. Additionally, the proposed two heuristic approaches improve space utilization for the infection rate ensuring bio safety.

Abstract: A processor implemented method of evaluating at least one potential tastant from a plurality of tastants is provided. The processor implemented method includes at least one of: receiving, information associated with a plurality of molecular activities; generating, a plurality of data-based models based on the known taste index associated with at least one tastant and information from associated molecular structure/descriptors; classifying, a new molecule based on the generated data-based models for the at least one tastant; screening, the one or more classified new molecules in an applicability domain of the generated data-based models based on the physics-based models by at least one molecular modeling technique; and evaluating, the at least one potential tastant from the screened molecules based on at least one of a bioavailability and a toxicity. In an embodiment, the plurality of molecular activities corresponds to a taste index and a binding energy.

Abstract: Disadvantage of these existing approaches for spike encoding optimization are that they fail to process multivariate data and perform energy-efficient time series classification at edge. The disclosure herein generally relates to spike encoding optimization, and, more particularly, to a method and system for Mutual Information (MI) based spike encoding optimization. Before performing spike data optimization for a given input multivariate time series data, the system ensures by iteratively adding gaussian noise to the input data that the input data has achieved a maximum MI value. After the input data has achieved a maximum MI value, spike train optimization is done by the system, to generate optimized spike data and in turn a spike reservoir.

Abstract: This disclosure relates generally to method and system for live video streaming with integrated encoding and transmission semantics. The system receives a set of frames associated with a live video stream encoded to generate a set of data fragments using a reference encoder and a delta encoder. Transmitter unit of the live video streaming protocol transmits each packet of the set of full frames and the set of delta frames in sequence with a payload specific header based on a packet mode. Further, the receiver unit receives each packet of the full frames and each packet of the delta frames based on the packet mode to reconstruct an original sequence from the foreground pixels by estimating a total number of packets expected at each frame interval and loss incurred in each packet of the set of full frames and the set of delta frames.

Abstract: Phishing attacks cause financial frauds and credential thefts. The conventional blacklist, whitelist and Machine Learning (ML) based methods fail to provide an accurate detection of phishing attacks. The present disclosure provides a layered approach wherein a URL domain name is compared with blacklist domains and whitelist domains. Further, the URL undergoes Internet Protocol (IP) address checking followed by context checking. A clicked context is verified based on the number of search results from a popular search engine. Otherwise, the typed context is checked for non-ASCII characters in the domain name. Further, the URL is checked for any brand name. Further, the domain is checked for any misspelling. Further, the URL is examined using a Machine Learning (ML) model. Finally, the URL is classified as phishing if a number hits in a popular search engine is less. Here a phishing alert is generated in each layer based on the corresponding decision.

Abstract: Strategic competitive intelligence data generation systems and methods are provided. The system stores internal intellectual property data of an entity, receives external technology development data from predefined sources and intellectual property data from the internal portfolio database of the entity, stores a set of relevant rules, executes them, filters the technology development data and the intellectual property data, based on the rules executed by the rule engine. It stores in one of an entity aligned cluster database, the filtered technology development data and the intellectual property data. The entity aligned cluster databases are created against predefined entity aligned clusters. The system executes an input query, determines one relevant entity aligned cluster database for executing the search query, and populates relevancy scores in two matrices, aggregates the relevancy scores through multiplication of the matrices.

Abstract: Recognizing mental states from physiological signal is a concern not only for medical diagnostics, but also for cognitive science, behavioral studies as well as brain machine interfaces. Embodiments of the present disclosure utilize respiration signals to decipher mental states wherein non-linear baseline drifts in signal is implemented to extract the respiratory features in most effective way. Presence of class imbalance, is effectively rectified using Synthetic Minority Oversampling Technique (SMOTE) to resolve class imbalance problem, which not only increased the classification accuracy, but also reduced classifier bias towards the majority class, which in turn exceedingly enhanced the classifier sensitivity.

Abstract: This disclosure relates generally to method and system for draping a 3D garment on a 3D human body. Dressing digital humans in 3D have gained much attention due to its use in online shopping and draping 3D garments over the 3D human body has immense applications in virtual try-on, animations, and accurate fitment of the 3D garment is the utmost importance. The proposed disclosure is a single unified garment deformation model that learns the shared space of variations for a body shape, a body pose, and a styling garment. The method receives a plurality of human body inputs to construct a 3D skinned garments for the subject. The deep draper network trained using a plurality of losses provides efficient deep neural network based method that predicts fast and accurate 3D garment images. The method couples the geometric and multi-view perceptual constraints that efficiently learn the garment deformation's high-frequency geometry.

Abstract: This disclosure relates generally to configuring/building of applications. Typically, a deep learning (DL) application having multiple models composed and interspersed with corresponding transformation functions has no mechanism of efficient deployment on underlying system resources. The disclosed system accelerates the development of application to compose multiple models where each model could be a primitive model or a composite model itself. In an embodiment, the disclosed system optimally deploys a composable model application and transformation functions on underlying resources using performance prediction models, thereby accelerating the development and deployment of the application.

Abstract: This disclosure generally relates to method and system for asset inspection using unmanned aerial vehicles. Regular inspection of assets in any environment is time consuming and involves physical risk and injury to the property. The method includes receiving a plurality of input images of an asset using unmanned aerial vehicle and generates a 3D point cloud based on overlapped images identified from the plurality of input images of the asset being inspected. Further, anomalies are detected and defects are observed in the one or more objects of interests based on the change observed in each 2D image frame from the plurality 2D image frames in a specific view with an identical objects of interest of the 2D image frame. A pyramidal view map is created for the plurality 2D image frames by mapping each pixel of the plurality 2D image frames with the plurality of input images.