Tata Consultancy Services Patente

In automotive ecosystem, modem vehicles are being exposed to broad range of cyberattacks through software components connected in network environment leading to unwanted events. Embodiments of the present disclosure provide method and system for dynamically managing intrusion with secure context aware over the air (OTA) update. A data associated with event detected at vehicles connected in network environment is received and classified either as normal event or qualified security event (QSEV). An adaptive intrusion prevention unit (IPU) sanitized data is generated by populating a knowledge graph for training contextual analysis model based on input data through which appropriate context aware OTA update is identified. The context aware OTA update corresponding to vulnerability associated with the QSEV is determined based on the adaptive IPU sanitized data. Information associated with appropriate context aware OTA update corresponding to the vulnerability is fetched from patch database and triggered for mitigation of the corresponding QSEV.

Textual data from social platforms captures various aspects of mental health through discussions around and across issues, while users reach out for help and others sympathize and offer support. Present disclosure leverages Natural Language Processing (NLP) and Generative AI techniques to identify and assess mental health disorders, detect their severity, and create recommendations for behavior change and therapeutic interventions based on input data associated with users. To classify the disorders, the system leverages Large Language Models (LLMs) to filter relevant data from input data, the relevant data pertains to health disorder of users. Further, from the relevant data, various features are extracted to create user profiles and different summaries. The summaries are then aggregated to obtain a final summary for generation of actionable health disorder specific recommendations.

Volume solids (VS) is considered to be a very important and critical property of paint in paint related industries. Conventional methods for VS measurement are usually cumbersome, time-consuming and laborious. The present disclosure resolves the problems of the conventional approaches by providing a system and method for predicting volume solids measurement of paints based on non-invasive photoacoustic sensing. The present disclosure provides a non-invasive and compact photoacoustic (PA) sensing method with artificial intelligence (AI) model to predict volume solid measurements of paint samples. In the method of the present disclosure, a time domain photoacoustic (PA) signal obtained from the paint is used to predict the volume solids measurements. A temporal shift of the time domain PA signal is used as a feature and a regression based prediction model is trained to predict volume solids measurements of the paint samples.

The disclosure relates generally to methods and systems for bundle purchase probability estimation and revenue-maximized bundles recommendation to customer segment. Conventional techniques mostly focused on customer-item, customer-bundle, or customer-item-bundle interactions, but do not model interactions among customer segments, items, and prices to form the bundles. The present disclosure discloses an approach for ancillary bundle recommendation using an item-level purchase data for a given customer segment. Firstly, the item-level sales data is converted into the bundle-level sales data having a plurality of ancillary bundles. Then, a nested MLP network is trained which can predict the probability of purchase of a given ancillary bundle at a given price for a specific customer segment. Further, the ancillary bundles are priced for given customer segment by maximizing the revenue. Finally, the recommendations are provided for given customer segment by ranking ancillary bundles based on their estimated revenue by selecting the top-N bundles.

Enterprises are exploring the option of multi-cloud setup to avoid the vendor lock in and cloud concentration index. This process of migration to multi cloud setup for the applications throws up various challenges in terms of identity management. The Cloud Service Providers (CSP) do not provide portability and endorse their vendor specific identity credentials. As a result, there is a need for common Identity Access Management (IAM) capable of mapping this heterogenous identities and giving the enterprise a common view of identities among the CSPs. This also solves the identity silos and helps consolidating identities in various permission and access evaluation metrics to check for access sprawl. Here, a plurality of attributes is merged based on a privacy-based weight. Further, a weighted sum-based confidence score is computed for the plurality of merged identity tuples and optimal merged identity tuples are identified based on the associated weighted sum-based confidence score.

Embodiments herein provide a method and system for an information technology (IT) service management using AIOps. The system integrates diverse data sources, such as events, logs, metrics, health checks, change requests, and traces into a centralized platform. This enables the system to create detailed blueprints of IT entities, using dependency data to improve issue analysis. The system employs advanced algorithms, including deep learning and predictive models, to analyze the collected data and identify a wide range of anomalies, that include univariate, multivariate, and complex anomalies. Additionally, the system includes a Human-in-the-Loop (HITL) mechanism that allows users to provide feedback and contribute to problem resolution, ensuring that the system continuously learns and adapts. This proactive approach not only predicts and prevents potential issues but also empowers users with automated resolution tools, reducing dependency on service desks. Overall, the system transforms IT operations by making them more proactive, integrated, and user centric.

Phase gradient metasurface surface plays a crucial role in wireless and satellite communication, radars and remote sensing applications. However, conventional approaches for obtaining high gain of an incident wave suffer a low phase variation. The present disclosure provides a ring loaded alford-loop based phase gradient metasurface lens for x-band applications to achieve 0-360° transmission phase variation. The phase gradient metasurface lens of present disclosure includes a twodimensional periodic array of a plurality of unit cells arranged as a M*N matrix along x-axis and y-axis. Each of the plurality of unit cells is a four layered slot typed structure with a periodicity. Each of a plurality of unit cell layers in the four layered slot typed structure comprises a modified alford-loop structure with four L-shaped arcs and it is enclosed by an outer square ring. The four layered slot typed structures are identical and separated by an air gap.

This disclosure relates generally to a method and system for identification of mobility trends of group of users in an indoor environment. State-of-the-art methods provide capture of localization data of users. However, analysis of collective user data, specifically understanding the mobility of group that reveals macroscopic trends is not yet achieved. The present disclosure addresses these problems through a method of identifying mobility trends among multiple groups of users in real-time using location data of each user within the group. The method involves creating pairs within the group of users based on current location of each user, and a pre-defined threshold value of distance between the current location of paired users. Mobility similarity metric is calculated for each pair of the one or more users. Based on the mobility similarity metric, users are segregated into one or more clusters, each cluster representing a similar mobility trend.

Every product in the market is associated with a lifecycle stage. It is crucial to identify the current life cycle stage of a product from a business perspective. Conventional approaches fails to identifying the lifecycle stages of the product. The primary reason being the unavailability of the data. The present disclosure looks at continuous capture of supply chain data of a product from procurement to manufacturing to distributor to end customer using smart sensors and various other electronic modes. The data as available for the product is stored in the data warehouse and subsequently taken through data classification and preprocessing steps to apply necessary data science models that involve use of segmentation/clustering algorithms, classification models, demand forecasting and prediction algorithms, as well as other required Deep Learning models that are relevant to the product under preview to design and develop association rules to provide the predictions on life cycle stages.

The embodiments of the present disclosure herein address unresolved problems of predicting future fund rate in the next meeting of a financial regulatory body responsible for regulation of interest rate based on current economic conditions and data of last meeting happened. Embodiments herein provide a method and system for predicting change in a future fund rate by a financial regulatory body responsible for regulation of interest rates. Herein, textual data as well as numerical data are collected to extract useful textual summary of forward-looking statements from large corpus of text data using a pre-trained Large Language Model (LLM) which will contribute to predicting future fund rate. A domain insight matrix is used as a comprehensive framework for guiding the pre-trained LLM on how to approach a task and validate the outputs based on predefined categories and parameters set by domain experts. With prompt optimization efforts, a good quality summary of forward-looking statements is achieved.

Existing works perform subsurface imaging without paying attention to the presence of surface undulation, which can cause irregular travel paths for waves emitted by a Radar and may produce defocusing effects in the reconstructed image. The present disclosure estimates noise level of a LiDAR (216) in a stationary mode by considering the standard deviation of a LiDAR sensor data. Successive LiDAR values at every position are tracked for a pre-defined time intervals and if it satisfies a LiDAR stabilization criterion, the LiDAR is considered stable and the LiDAR value obtained is logged as a LiDAR elevation data. A two-layer velocity model is estimated from the LiDAR elevation data and a phase shift operator of a Phase shift migration (PSM) is modified by incorporating the two-layer velocity model. Surface normal information is extracted from the LiDAR elevation data and an amplitude correction factor is formulated using the extracted surface normal information.

Traditional algorithms for computing/estimating project completion time often fail to provide accurate project duration estimates. Pre-existing methods rely on project size and team size to estimate project duration and overlook the complex interdependencies between tasks and the variability in task execution times. System and method of proposed approach fetches a requirement vector of a target project as input. Further, a plurality of instance precedence graphs of the target project are generated by processing the requirement vector along with a merged probability graph. The merged probability graph represents a transition likelihood between different types of tasks based on a historical project data. Further, a plurality of projects that are similar to the target project are determined. Further, a completion time of the target project represented by the requirement vector is computed based on completion time of the plurality of projects that are similar to the target project.

Applying large language models (LLMs), even with very large token-sized prompts, does not achieve the task planning performance required for a domain-specific industrial use case (DSU). The method and system disclosed overcome the obstacles of a robotic task planner for DSUs by introducing a task planning framework. Central to the framework is a robotic system ontology that organizes the components of the robotic system in a coherent and systematic manner. This ontology empowers the planning framework to efficiently capture a contextual representation of a DSU using the LLM. Additionally, the research introduces a LLM-tuning regimen referred as chain of hierarchical thought (CoHT), specifically crafted to complement the robotic system ontology. Integrating these two components enables enhancing accuracy, robustness, and throughput of the robot in a cost-effective manner. Furthermore, provided is an empirical methodology to generate LLM-tuning datasets size for a guaranteed performance, leveraging a heuristics-based method.

This disclosure relates generally to a method and system for generating feed recommendations based on vocalization patterns of an animal. State-of-the-art methods based on analysis of the vocalization patterns are limited to livestock monitoring, individual identification, physiological states determination, and health diagnosis. However, precise identification of hunger state not yet achieved. The disclosed method involves a deep learning model to identify hunger state and one or more hunger state level of the animal from audio chunks. A state machine maps a plurality of emotions and behaviors associated with the hunger state levels. Further, one or more emotions and behaviors associated with the hunger state level are detected. The large language model (LLM) utilizes the identified state, level, emotions and behaviors to make feed recommendations to the animal.

The disclosure relates generally to methods and systems for automated personalized de-stressor recommendation based on stressor estimation. Conventional techniques for detecting the stress and the stressors are mostly manual and employ only some of the influencing parameters such as physiological parameters, behavioral parameters, and so on, thus leading to inaccurate detection of stressors. The present disclosure solves the technical problems in the art by detecting the stress using multi-model evaluation design including physiological changes, psychological changes, behavioral changes, environmental changes, and a bio-chemical indicator. Next, the stressors related to stress detection are identified using a large language model (LLM), which correlates with stress patterns to create a personalized model. Then, appropriate de-stressors are recommended using a recommendation lookup table.

AI systems, while have excelled in environments defined by clear rules and singular tasks, have been found to be struggling to handle Knowledge works which encompass tasks requiring judgment, interpretation, and creative problem-solving. Method and system disclosed herein provide an Artificial Intelligence (AI) agent training approach. In this approach, the system 100 achieves collaboration between different AI agents that are part of a network, for handling each task. During the training, randomly initialized weights associated with a plurality of edges are used, based on an action that is dynamically decided, based on one or more activation levels of one or more of the plurality of AI agents identified as active based on the decided action.

This disclosure relates generally to a method and system for modeling a three-dimensional (3D) wearable device assisting nasal administration of drugs. State-of-the-art methods include leaflets or manuals with a set of instructions for administering the drug. However, this may result in improper administration due to variations in the nasal geometry and manual operations. The disclosed method involves the 3D wearable device that aids in achieving maximum concentration of the drug at the target site. The modeling facilitate an introduction of a collared geometry that provides customed passage to the drug within the nasal cavity based on a plurality of nasal spray specifications. Further, the 3D wearable device model is transformed to a scale based on the CT scan data of the nose to obtain a 3D printable wearable device for the nose.

The disclosure relates generally to methods and systems for predicting explainable drug dosage of a subject. Conventional techniques for advising drug dosage are mostly manual processes and the drug dosage advised by physician may not be effective as such dosages are not validated. The present disclosure solves the technical problems in the art with the methods and systems for predicting explainable drug dosage of the subject. According to the present disclosure, current clinical data and historical data are received from a patient repository. Drug dosage possibilities are generated based on the historical information available in the art. The possibilities and the scenarios are generated and evaluated using a possibility evaluation engine. The possibility score of each drug dosage and a weightage for each treatment decision scenario is computed. An explainability for each of the ranked possibilities is then generated to predict the explainable drug dosage of the subject.

Hallucinations in LLMs pose significant challenges and it is hard to accurately identify hallucinated predictions of LLMs in the absence of references. The present disclosure utilizes sample responses from LLMs and classifies them using a model trained on Natural Language Inference (NLI) scores. The plurality of NLI scores include an entailment, a neutrality and a plurality of contradiction scores. Post computing NLI scores, an average NLI score is computed based on the plurality of NLI scores. Further, a plurality of individual response predictions are obtained by classifying the plurality of responses based on the NLI scores using a hallucination classifier. Simultaneously, overall response predictions are obtained and a confidence score is computed for the overall prediction of hallucination classifier Finally, an optimal response is predicted based on the confidence score associated with the overall prediction of the hallucination classifier and the plurality of NLI scores.

With increasing focus on observability and analytics, organizations are flooded with analytics insights and often struggle to sift through these insights to identify the relevant ones. When it comes to defining the relevance of an insight, there is no single answer. Different users may have different preferences, and these preferences may change with time. Furthermore, when it comes to data-driven insights, user journey does not stop at one single insight but often leads to a chain of insights to create a story. Present disclosure addresses these technical problems in the context of insights derived for IT operations. More specifically, insights are recommended based on user preferences, wherein the system adapts the insight search based on user's likes and dislikes, and chain insights together to form data stories to serve different use cases.

Current networks provide extremely low latency and high data rate, but it is not clear how they are to be orchestrated and managed efficiently with optimal utilization of the available resources. There is a need for orchestration method which can adapt to prevailing conditions, implement pre-defined policies, and respond to dynamic changes in the network. Hence, embodiments of present disclosure provide method and system for cognitive resource aware orchestration of services in communication networks which works on top of the underlying SDN and NFV orchestration solutions for enabling better operational efficiency in communication networks.

This disclosure relates generally to a method and system for performing multi-fold operations on complex data. Conventional methods do not have plug and play reusable components for processing high volume complex data concurrently. Also, these do not consider distributed or interactive data processing using optimal resources. The disclosed method performs operations on complex data with optimal execution time, memory and computation resource. The input data fed into the disclosed system are packaged into data chunks and distributed across available resources for preprocessing. The data chunks are pre-processed and converted into machine readable binary format. The data is again traversed to generate operation data chunks. The operation is performed for each operation data chunk, using the converted machine-readable binary format to generate the result of the operation. The disclosed method is used for operations such as search, comparison and so on in image processing.

Preparing for live music performances such as curating and sequencing list of tracks and remixing them with musical loops can be challenging. The present disclosure predicts a first set of features relevant to an event. One or more music tracks are generated using at least a subset of the predicted first set of features. The one or more music tracks are split into one or more individual arrangement tracks. One or more segments are generated by identifying one or more repetitive patterns for each of the one or more individual arrangement tracks. A second set of features are extracted from each of the one or more segments. One or more loops are generated based on at least a subset of extracted second set of features. The one or more loops are provided for one or more loop sequencers for usage in the event.

Embodiments herein provide a method and system for current density maps reconstruction by jointly optimizing x-direction, y-direction and z-direction magnetic field maps. Herein, the method of reconstruction of current image is leveraging state of the art iterative reconstruction techniques along with deep learning techniques. The quality of the current reconstruction depends on the signal to noise ratio (SNR) of the magnetic field observed. Since the noise model is difficult to characterize, a deep neural network is trained to learn the complex noise model from the data itself. To simulate the realistic scenarios, training data is created by introducing various kinds of noise that may appear in the system and collecting the training data pairs, i.e., pair of noisy and denoised x-direction and y- direction current density maps. The DNN is trained on this paired data to learn the noise model.

The embodiments of the present disclosure herein address unresolved problems of unavailability of a scalable framework to enable large spectrum of optical response-design combination with reduced computing time. Further, there are limitations in the choice of features to obtain the desired sensitivity. Embodiments herein provide a method and system for a generative artificial intelligence (GenAl) based sensor design synthesis of metamaterial. Herein, the sensor design synthesis framework is based on deep generative models. The GenAl based design synthesis model would provide that unknown information that would immensely be useful for optimizing the design towards the highest sensitivity, addressing the limitations in the choice of features using numerical simulator and easiest fabrication-feasibility following sensitivity response (SenR). The SenR is the sensitivity relationship between the physical properties of the ambient medium and the property of the sensor.

Monitoring and detection of oedema severity is crucial for effective treatment of the underlying ailments. Conventional methods involve setups that require harmful radiation, are expensive, tedious, and bulky. The present disclosure provides a system and method for unobtrusive oedema severity classification and quantification using microwave sensing. A vector network analyzer, a microstrip RF patch antenna customized for operation at 4 GHz under dielectric loading of a numerical human phantom and associated RF components are used for oedema severity monitoring of a sample under test. For oedema severity classification, a machine learning (ML) based approach is implemented making use of reflection parameters, and accordingly physics-based electromagnetic features are extracted. The physics-based electromagnetic features are used to classify the sample under test into a specific oedema severity category. Further, a water percentage is quantified using regression models for the sample under test based on the oedema severity category.

Polarization is a parameter that plays a pivotal role in communication during transmission and reception of signals. Presence of lumped elements along a signal path or around a region of interaction of incoming waves with surface may trigger distortion in the signals, leading to loss or damage of information. Generally, electronic lumped components are used but their functional abilities are limited during practical operations. The present disclosure addresses the unresolved problems of the conventional system by providing a system and method for real time multi-frequency operation using metasurface-based mechanically controlled tunable polarization conversion. In the present disclosure, a multi-band polarization converter design is provided whose operational parameters including (i) bands of operation, (ii) bandwidth, and (iii) number of bands are controlled together by modulating an air-gap of a reflective unit cell of a two-dimensional array structure of a metasurface using a motorized mechanical arrangement.

Existing therapeutic methods lack interactivity and adaptability to individual needs. The present disclosure retrieves from a database, a hardware component design as an interactive table comprising a grid of sensor(s) to detect input(s) from a user. The detected one or more inputs from user are passed to a gaming engine connected to the hardware component. Reflex time of user is recorded, when user provides the inputs to the sensors. Reflex time is compared with predefined time T_n and at least one of following is performed based on comparison that includes incrementally changing position of object, resetting timer, increasing timer with a first delta value and moving position of object closer to initial position with a second delta value. An average response time, a progression metric and adjustments to timer are calculated. A cognitive function to assess the severity of cognitive decline of user is derived.

A method and system that builds a regression model from a personalized structural and functional Cardiac Digital Twin (CDT) for assessment of cardiopulmonary endurance of an athlete is disclosed. The personalized Cardiac Digital Twin (CDT), which replicates echo like functionality under dynamic conditions integrates subject specific kinematics data real time acquired to run personalized CDT and generate intrinsic metrices to evaluate performance in different phases of exercise or endurance activity. Most of existing works are focused on computing mere metrices for entire activity as whole. However, without judicial combination of these metrices obtained in different phases, no meaningful inference can be drawn on performance evaluation.

Unrestricted access to large language models (LLM) based services can lead to potential data leakages, especially for large enterprises providing products and services to clients that require legal confidentiality guarantees. However, a blanket restriction on such services is not ideal as these LLMs boost employee productivity. Objective of the present disclosure is to build a solution that enables enterprise employees to query such external LLMs, without leaking confidential internal and client information. QueryShield platform of the present disclosure is a platform that enterprises can use to interact with external LLMs without leaking data through queries. It detects if a query leaks data and rephrases it to minimize data leakage while limiting the impact to its semantics. A language model is chosen from a set of lightweight model candidates that are identified and fine tuned for this purpose using a huge dataset and evaluated using multiple metrics.

Existing techniques of constructing classical equivalents of QML models expand measurements from QML model as truncated Fourier series and find Fourier coefficients by solving an optimization problem. However, this is computationally expensive and since approximate Fourier coefficients are determined, the resulting classical surrogate does not necessarily give exactly same predictions as that of the QML model. Embodiments of the present disclosure provide a method and system for constructing classical equivalent of trained Quantum Machine Learning (QML) model by distilling knowledge from the QML model to a classical model. The method includes training QML model using a first dataset, creating a second dataset using measurements from the QML model, training classical model using the second dataset and learning a processing function using predictions of the classical model and target outputs. The trained classical model combined with the learned processing function serve as classical equivalent of the QML model.

This disclosure relates generally to processing of gas using packed bed column, and more particularly, a packed bed column with stacked packed channels for processing gas. In current packed bed column configurations, the problems of maldistribution of gaseous stream across the packed beds and channeling associated with the packed beds results in high power requirements and operating expenses. The present disclosure includes gas distribution mechanisms and stacked packed channels for proper gas distribution and channeling of the incoming gaseous stream. The gas distribution mechanisms ensure that the incoming gas gets distributed evenly to the packed bed. This greatly increases the productivity of the process and increases the process efficiency as more area is available for heat and mass transfer to take place. The disclosed configuration is used for gas separation via adsorption, thermal energy storage applications and so on.

This disclosure relates generally to method and system to generate spatio-temporal intercrop layouts using 3D-CNN-LSTM based large vision model. The method is a pretrained spatio-temporal crop interaction model based on a 3D-CNN-LSTM to recommend optimal intercrop combinations. The method initially receives a user request as input which is preprocessed by removing noise and performing normalization. Further, a pretrained 3D-CNN-LSTM model is utilized to generate an optimal spatio-temporal intercrop layout for each intercropping scenario. The method also provides providing dynamic visual insight for the spatio-temporal intercrop layout comprising crop growth and corresponding intercrop interaction. Finally, an user feedback is obtained from at least one of the user or non-invasively in response to the user request for iterative improvements and fine-tuning the 3D-CNN-LSTM model using reinforcement learning.

The disclosure generally relates to methods and systems for multi-frequency fusion for localization of impact induced soundwaves of a target industrial machine. Conventional wideband beamforming-based techniques accurately localize the impact hotspots, however with increased computational time while beamforming-based techniques reduce the computation time but worsens the localization accuracy. In the present disclosure, a composite acoustic map and a single-tone acoustic map of each of the one or more single frequencies obtained at each predefined frequency interval, are generated based on geometric parameters and a characteristic sound signal. Then, the one or more localization regions associated with each experimental trail that are common to the composite acoustic map and the single-tone acoustic map are determined. Lastly an optimal frequency range is determined using a localization loss function, a Kalman filtering technique, and a probability distribution function based on the localization regions, for localization of impact hotspots.

This disclosure relates generally to method and system for identifying frauds in unemployment insurance claims using hybrid weighted decision model. The method combines predictive power of machine learning models with domain knowledge infused key fraud indicators and network analysis to identify false positive claims. Initially, a set of claim information from a request of a claimant is extracted to assess risk affecting eligibility of the claimant to receive benefits. Further, a classification probability for a set of key fraud indicators are predicted for each claim using a set of top features associated with a prescient artificial intelligence (AI) model. Finally, one or more frauds associated with the unemployment insurance claim of the claimant are identified based on the weighted probability of each claim, a network diagram generated using the weighted probability for each claim, a set of filtered claims, and a set of business rules.

This disclosure relates generally to method and system to perform interval analysis in source code using functional approach. The method performs data-flow analysis using functional approach to solve infinite-height analyses and properties are validated such as array index within bounds, non-zero division, and preventing arithmetic overflow or underflow on real-life applications. The method receives source code comprising one or more functions to perform a whole program interval analysis over each function using a functional approach to identify range interval of each variable at every program point in the source code. Further, summary for each function is computed which is stored in the form of variable and its corresponding range interval at every exit point of each function. Finally, an incremental interval analysis is performed over each function having edited version change and summary is recomputed for each function impacted by change to optimize overall interval analysis.

This disclosure relates generally to a method and system for local interpolation function (LIF) based synthetic aperture radar (SAR) imaging for irregular scanning geometries. Current available methods are computationally expensive, sensitive to initialization and lacks generalization, particularly when applied across sampling schemes in continuous sampling scale scenarios which is a key characteristic of irregular scanning geometries. The present disclosure achieves enhanced SAR image across various spatial coordinates. Noisy SAR images are obtained using Non-uniform Fast Fourier Transform (NUFFT) based Range Migration Algorithm (RMA). The noisy SAR image is mapped into a LIF feature map using an encoder of a trained LIF neural network. An enhanced SAR image is further predicted based on the LIF feature map using a decoder of the LIF neural network. The disclosed method for SAR image enhancement using LIF neural network is used for supply chain management, airport security screening, medical imaging and so on.

Modified Atmosphere Packaging (MAP) extends food shelf-life but is not customized for specific commodities and supply-chain conditions, leading to sub-optimal usage. The present disclosure utilizes physics-based models to simulate the system of MAP and generate data for shelf-life of the food commodity for various designs of MAP films stored in different environmental storage conditions. Further, this data is used to develop a hybrid recurrent neural network (RNN) and deep artificial neural network (ANN) model, which learns how the changes in storage conditions of temperature and relative humidity affect the shelf-life of the food commodity for different designs of MAP. Whereas optimization of multiple ordinary differential equations is time and compute resource intensive, the developed hybrid RNN-ANN model can be used as a surrogate which makes optimization significantly less resource intensive. A surrogateassisted optimization model thus developed can be used to predict the optimum design of MAP for specific storage conditions.

This disclosure relates generally to processing of gas using packed bed column, and more particularly, a split bed packed column for processing gas. In current packed bed column configurations high pressure drop in packed column leads to increased energy consumption and puts a restriction on using high feed velocities, resulting in high cycle time. This results in increased requirement of adsorbent for processing of gas which thereby increases the operational expenses. The disclosed configuration includes multiple beds inside the same column differentiated by partitions instead of a single long bed inside the column. This configuration enables decreasing the pressure drop along the length, resulting in decreased energy consumption for the same cycle time, without compromising on other process key performance indicators. The disclosed configuration is used for gas separation via adsorption, thermal energy storage applications and so on.

Conventional payment systems require payers to select the payment instrument first and then authorize payments. The payer cannot change payment instrument post authorizing payment as authorization is specific to a value store. The system and method of the present disclosure enables a payment method to be payment instrument/value store agnostic, so that payer gets more flexibility in terms of selecting which value store(s) to use for authorization but not necessarily for honoring the payment. This gives the payer the required flexibility to swap value store(s) post initial authorization but before settlement basis better informed decision by means of recommendations. Similarly on the payee's side, the payee has limited or no visibility of value store until payer presents it for payment. The system and method of the present disclosure gives an added opportunity to the payee to influence payer's selection of value store(s) post initial authorization but before settlement.