Abstract: For effective monitoring of battery health, it is important that the temperature characteristics of the battery are monitored. However, in certain battery pack designs, the number of batteries in the stack can be high, so sensors for measurement will not be able to monitor all the batteries in the stack. Existing battery monitoring approaches fail to tackle this problem. The disclosure herein generally relates to battery monitoring, and, more particularly, to method and system of predicting temperature distribution in a battery pack. In this approach, the system calculates a lumped conductance value for a battery pack being monitored, and in turn uses the value of the lumped conductance to predict a temperature distribution value in the battery, which is indicative of health of the battery pack.

Abstract: The disclosure relates generally to methods and systems for determining heat transfer rates between battery pack and coolant channel with varying coolant flow rate in a real-time. A lumped conductance generated between the battery pack and a coolant channel is used to determine the heat transfer rates between the battery pack and the coolant channel. Conventional techniques for calculating the lumped conductance between the battery and the coolant channel either use experimental methods or rely on the heat transfer correlations in simple geometry. The present disclosure calculates the lumped conductance by understanding an internal structure of a cylindrical battery pack using a high-fidelity computational fluid dynamic (CFD) simulation. This will help in determining the heat transfer rates of the battery pack in the real-time at the battery core especially when the coolant channel side hydrodynamic conditions change with time due to the variable coolant flow rates.

Abstract: In the Iris based biometric recognition systems, iris needs to be segmented before comparison and hence iris segmentation is a crucial process in iris based biometric recognition systems. Existing techniques are unable to segment iris due to occlusions and require complex and time consuming algorithms to remove these occlusions. Other deep learning based solutions require precise annotations of the iris regions along with eyelids and eyelashes. The present disclosure initially generates polygons on the iris and pupil area using a pre-trained detection model. Internally covered vertices and externally exposed vertices of the generated polygons are computed to construct curvature of the iris region. A pupil region is generated by filtering the plurality of vertices lying inside pupil circle region from the plurality of externally exposed vertices. Further, a segmented iris image is generated by removing the pupil region from the input image based on the curvature of the iris region.

Abstract: The embodiments of present disclosure herein address unresolved problem of key capabilities that an intelligent robot must possess to perform complex and long-horizon object manipulation tasks without human intervention. The present disclosure overcomes above mentioned challenges by decoupling imitation learning task into two parts using a decouple neural network architecture comprising two modules. A high-level module that segments out sequence of primitive actions from video of human demonstration of a complex task and a low-level module that executes those primitives sequentially on robot. The high-level module, Task Sequencing Network (TSNet), is a hybrid neural network composed of Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) with Connectionist Temporal Classification (CTC) loss, while low-level controller is built using dynamic movement primitives (DMP). The network is trained in a supervised learning setting.

Abstract: The disclosure herein relates to a method and system for time series forecasting incorporating seasonal correlations using scalable architecture. The scalable architecture comprises parallel encoders, a neural network layer and a decoder. The neural network layer is either an attention layer or RNN layer. Each of the encoders and the decoder comprises multiple sequential encoder and decoder units, respectively. The parallel encoders encode seasonal correlations in a time series to generate summary vectors which are then processed along with state of a previous decoder unit by the neural network layer to generate a feature vector whose size is independent of order of seasonality of the time series. The feature vector is then processed by a next decoder unit to forecast a seasonal time series data at a subsequent time step. This process is repeated for all the decoder units to train the deep neural network model for time series forecasting.

Abstract: Early-stage design for complex engineering systems is a difficult task with significant impact on the final design and is performed under time constraints which restricts the number of options being considered. Present disclosure provides a framework for an early-stage generative design of engineering systems by performing systematic design space exploration and targeted design space exploration. Diverse design configurations are generated for given requirements following a systematic design space exploration of the entire architectural design space of the early-stage problem. In the targeted design space exploration stage, potential regions of the design space are identified to generate different alternatives to the diverse design configurations already generated during the systematic design space exploration stage for early-stage generative design of a given engineering system.

Abstract: State of art techniques, need a decoder following the encoder to encode EEG signals, whose morphology is undefined. Embodiments herein disclose a method and system for a Spiking Neural Network (SNN) based low power cognitive load analysis using electroencephalogram (EEG) signal. The method receives a raw EEG signal from multichannel EEG set up, wherein each of the raw EEG signal is re-referenced and encoded into a spike train using a Light-Weight-Lossless-Decoder less-Peak-based (LWDLP) encoding. Further, the spike trains are processed by the SNN architecture using backpropagation based supervised approach, wherein the spatial information and the temporal information are learnt by the SNN in form of neuronal activity and synaptic weights. Post learning the SNN architecture applies an activation function on the neuronal activity for classifying a cognitive load level experienced by a subject from among a plurality of predefined cognitive load levels using a SNN classifier.

Abstract: Multi-object tracking (MOT) in video sequences plays a critical role in various computer vision applications. The primary objective of MOT is to accurately localize and track objects across consecutive frames. However, existing MOT approaches often suffer from computational limitations and low frame rates in commodity machines, which hinders real-time performance. Present disclosure provides method and system for performing content aware multi-object tracking. The system first classifies video into slow and fast moving object content videos depending on features of objects to be tracked in frames. Then, system applies a computationally intensive deep sort algorithm to perform tracking of objects by selectively skipping frames.

Abstract: The disclosure relates generally to methods and systems for predicting water quality of a river having a varying river ecosystem. Due to multiple and diverse factors, understanding and estimating the water quality of the river stream (river itself) is extremely and technically challenging. The present disclosure discloses a development of a river digital twin model utilizing a multi-modeling approach to comprehensively model the river and its varying ecosystems. The agents encompass entities that directly or indirectly introduce effluents or withdraw water from the river. Agents and their interactions are defined using a combination of behavior rules, correlations, and physics principles, creating the digital twin model that closely mimics the real river system. Physics-based equations are also employed in the present disclosure to capture the dynamics of the river, while relationships between different agents are established.

Abstract: This disclosure relates generally to a method and system for three-dimensional (3D) merchandising and space planning. State-of-the-art methods providing the merchandising and space planning for store management in three-dimensional visualization is limited to a specific fixture or to a specific area of the store. However, planning the merchandising and the space for an entire store in three-dimensional hyper-realistic visualization is not yet done. The disclosed method provides three-dimensional hyper-realistic visualization for planning the merchandize and space for an entire store by integrating data analytics capturing real-time information required during planning, and the in-house libraries facilitating quicker and easier design of the layouts for the store. The method includes importing the products from the product library, receiving real-time performance analytics for the products, and creating layout by placing the products on the fixtures imported from the fixture library.

Abstract: The uncertainty of availability and risk associated with the cost of power procurement hinders the consumer from using new sources of supply/storage devices or taking part in the competitive power markets or procuring power from green energy resources. Present disclosure provides a method and a system for optimal scheduling of power sources for meeting electricity demand of enterprise. In particular, the system performs portfolio optimization formulation for cost, risk and carbon emission minimization for the enterprise. The portfolio optimization formulation simulates market scenario and guides in providing effective power purchase strategy for enterprise along with real-time adjustments. In particular, the level of risk to be considered along with cost of power procurement and carbon footprint determine portfolio allocation for each time block in portfolio optimization formulation.

Abstract: Image analysis is a vital field since images can provide contextual, environmental, and emotional factors. Conventional methods are facing challenges in analyzing an image accurately when the image is having lesser data or if the image is having less resolution. Conventional machine learning architectures are computationally intensive when run on high power computing devices for training and inference. The present disclosure provides a robust deep learning model to inference in any given environmental condition. Initially, image data is generated using a pre-trained Generative Adversarial Network (GAN). The GAN receives a plurality of images of varying domain and generates image data. The image data is annotated and segmented to obtain a contextual label map. The contextual label map is given as input to a pre-trained transfer learning model to obtain a plurality of image attributes including number of objects and activity performed by each object.

Abstract: Technical challenge in unusual human activity detection task is to rightly identify only unexpected or unusual movements from constant regular movements present in a scene, with most techniques built on understanding that camera is static. However, ego view camera of mobile surveillance robot is in motion as robot navigates. Embodiments herein provide a method and system for anomalous activity detection for mobile surveillance robots by mimicking ‘Konio-Parvocellular-Magno’ cells of the human brain into a NN model, which are responsible for detecting slow, normal, and swift changes in perceived scenes. To detect anomalous activity, the static or normal movements of scene captured by ego view camera are identified as redundant information and only RoI is forwarded for further processing using the Optical flow and SSIM techniques. The NN model mimicking KPM is trained only on the RoI to detect normal or anomalous activity.

Abstract: This disclosure relates generally to method and system for determining myocardial ischemia severity based on hemodynamic parameters estimation. Many patients suffer from myocardial ischemia due to narrowing of coronary artery resulting poor oxygen supply in cardiac muscles. The method includes receiving Electrophysiology (EP) signal from a simulated heart surface model to generate a single lead ECG template. The method further estimates hemodynamic parameters using a hemodynamic module based on the single lead ECG template and then estimates cardiac pressure-volume loop variables. The myocardial ischemia severity of the heart surface model is determined which includes one of moderate ischemia, severe ischemia and silent ischemia. Here, the cardiac source module is coupled with the hemodynamic module to determine cardiac transmembrane potential (TMP) of the heart surface model through contractility function.