Tata Consultancy Services Patente

Zusammenfassung wird geladen …

This disclosure relates generally to system and method for molecular property prediction. The disclosed method includes mapping node embeddings of a molecular graph to a graph-level embedding characterizing the molecular graph. The graph level representation is acquired by pooling characteristics of hidden states of the nodes in the molecular graph by performing an iterative content based attention in a plurality of iterations. The content based attention is performed by considering an edge information fused transformed hidden state vector of the nodes of the molecular graph. The graph level embedding is fed through the linear projection to predict the molecular properties of the molecular graphs.

Zusammenfassung wird geladen …

Conventional task planners assume that the task-plans provided are executable, hence these are not task-aware. Present disclosure alleviates the downward refinability assumption, that is, planning can be decomposed separate symbolic and continuous planning steps by introducing bi-level planning, a plan which is a series of actions that the robot needs to take to achieve the goal task is curated. Firstly, abstract symbolic actions are converted to continuous vectors and used therein to enable interaction with an environment. Images of objects placed in the environment are captured and concepts are learnt from the captured images and attributes of objects are detected. A hierarchical scene graph is generated from the concepts and attributes wherein the graph includes interpretable sub-symbolic representations and from these interpretable symbolic representations are obtained for identifying goal task. Anomalies are detected from the scene graph and robotic actions are generated to correct the detected anomalies.

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.

Zusammenfassung wird geladen …

Post pandemic, retailers are adopting more contactless services for shopper's checkout such as self-checkout, hybrid checkout and mobile checkout, and these touchpoints have become the potential areas for fraudulent activity during check out process. For detecting fraud carried out by a customer at the time of self-checkout, existing approaches require respective customer identity and his purchase history. Embodiments of the present disclosure do not require customer identity and information about his historical shopping carts and provide a method and system for approving a user shopping cart for self-checkout from the items picked by the customers in real time.

State of the art telescope designs require increasing number of sub-apertures for optimum performance, however, with the increasing number of sub-apertures, number, and amplitudes of the sidelobes increase along with that of the primary maxima, resulting in a trade-off of the imaging quality. Disclosed herein are three configurations using a central sub-aperture and a plurality of peripheral sub-apertures, encompassing the central sub-aperture. Size of the central sub-aperture and the plurality of peripheral sub-apertures is in a proportionate relationship. Further, the plurality of the peripheral sub-apertures forms at least two concentric zones, wherein each concentric zone has equal number peripheral sub-apertures from among the plurality of peripheral sub-apertures, and the sizes of the peripheral sub-apertures in each two adjacent concentric zones have a proportionate relationship. This way there is significant side lobe suppression compensating for the imaging performance loss due to reduced aperture area.

Zusammenfassung wird geladen …

Coarse resolution satellite data has limited information content of land captured in the images and small area field boundary detection is technically challenging. Embodiments of the present disclosure provide a method and system for detection of field boundaries using coarse resolution satellite data and GIS. Multi-layer crop segmentation approach is used over RoI, wherein agricultural land related segments are derived from a soil layer, a temporal stack for a current season and a temporal change layer from the coarse resolution satellite data of the RoI. Segmentation based on different aspects captures various details at each segmentation layer. The segments are then combined, which aggregates all information related to the land to accurately detect the field boundaries in the RoI. The field boundaries are further refined using GIS topology operations. Baseline cadastral maps are updated using information from maps generated using refined field boundaries identified in real time for each season.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Method and system for assignment of traversal tasks under imperfect sensing of autonomous vehicles. With imperfect sensing, most of the assignment and scheduling algorithm may not be effective during actual execution of the tasks. The present disclosure solves the technical problems in the art by providing an analytical model which estimates the basic performance metrics such as an expected travel duration and collision probability on its path, under imperfect sensing, for optimal assignment of the tasks. An analytical model is integrated with a performance estimator as implemented by the systems of the present disclosure, which tracks, predicts, and alerts on any major deviations from its intended performance of safety parameters.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

A method and system of a re-assembly middleware in FPGA for processing TCP segments into application layer messages is disclosed. In recent years, the communication speed in digital systems has increased drastically and thus has brought in a growing need to ensure a good/high performance from the FPGA services. The disclosure proposes a re-assembly middleware in the FPGA for processing TCP segments into application layer messages at a pre-defined frequency for a good/high performance. The pre-defined frequency is a high frequency performance feature of the re-assembly middleware, wherein the FPGA's implementation frequency is at atleast 300 MHz based on a memory optimization technique. The memory optimization technique includes several strategies such registering an output and slicing memories.

Traditional deep learning techniques are performed by high-performance system with direct access to the data to train large models. An approach of training the model from a collaboration of similar stakeholders where they pool together their data in a central server. However, data privacy is lost by exposing said models and data security while accessing heterogeneous data. Embodiments of the present disclosure provide a method and system for a cross-silo serverless collaborative learning among a plurality of clients in a malicious client threat-model based on a decentralized Epsilon cluster selection. Protocols are initialized and considered to iteratively train local models associated with each client and aggregate the local models as private input based on the multi-party computation to obtain global model. Non-linear transformation of a silhouette score to an Epsilon probability without implementing a server to select r^th model from an active set to assign as the global model.

The embodiments of present disclosure herein address unresolved problem of how to make optimized decisions jointly on ancillary bundles recommendation and optimal ancillary bundle pricing using data in order to increase the traffic and maximize revenues remains challenging. Embodiments herein provide a method and system for generating ancillary bundled offers by jointly optimizing the customer bundle preferences of ancillary product bundles and revenue maximizing bundle prices for segmented customers using customers' historical ancillary purchase data. The historical ancillary purchase data can include historical bundles purchase data, or historical items purchase data depending upon the service provider, whether they offer bundles or items only. The overall flow of the disclosure for recommending top-k ancillary bundle offers for segmented customers by jointly optimizing the ancillary bundle products/services and bundle pricing for existing and new customers is provided.

This disclosure relates generally to a unified platform for domain adaptable human behaviour inference. The platform provides a unified, low level inference and high level inference of domain adaptable human behaviour inference. The low level inferences include cross-sectional analysis techniques to infer location, activity, physiology. Further the high inference that provide useful and actionable for longitudinal tracking, prediction and anomaly detection is performed based on several longitudinal analysis techniques that include welch analysis, cross-spectrum analysis, Feature of interest (FOI) identification and time-series clustering, autocorrelation-based distance estimation and exponential smoothing, seasonal and non-seasonal models identification, ARIMA modelling, Hidden Markov models, Long short term memory (LSTM) along with low level inference, human meta-data and application domain knowledge. Further the unified human behaviour inference can be obtained across multiple domains that include health, retail and transportation.

Zusammenfassung wird geladen …

The present disclosure is related to method and system for identifying and utilizing frugal markers for classification of biological sample. Discovering an optimal and/ or frugal set of features/ biomarkers form a large set of features measured through high-throughput screening techniques, which can characterize a disease/ anomaly with sufficient accuracy, still remains a challenge. According to the present disclosure, given a set of measurements of multiple features characterizing biological samples obtained from disease cases and healthy controls, a classification model combining the measured values of a small subset of the features is computed. The classification model is then used for classifying between disease cases and healthy controls.

Zusammenfassung wird geladen …

Computer-aided diagnosis algorithms require a large volume of training data. The existing methods for simulating artificial biomedical signals are mostly based on physics driven mathematical models that require too many assumptions, making them challenging to simulate on a large scale. Alternatively, conventional deep learningbased approaches are pure data driven and hence, do not have physiological interpretation. The present disclosure provides a method that effectively combines both physiological domain knowledge and deep learning to enable simulation of realistic cardiovascular disease specific biomedical signals. An ensemble Generative Adversarial Network (GAN) including a Long Short-Term Memory GAN (LSTM-GAN) configured to generate a Heart Rate Variability (HRV) pattern associated with the cardiovascular disease condition and a Deep Convolutional GAN (DCGAN) configured to create a morphology of a representative cardiac cycle is provided. A complete waveform is simulated by combining an output from each GAN.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …