Abstract: There is a need for design and implementation of interfaces for providing user-friendly feedback while creating and updating compliant passwords. This disclosure relates to a method of creating compliant password by in-place feedback to a password composition policy (PCP). A policy-enabled-virtual keyboard (PKBD) receives input from a user and is processed based on parameters associated with the PCP to identify accessible and inaccessible keys on the PKBD with in-place feedback. The in-place feedback is provided to highlight accessible keys of the PKBD for the user, if class associated with character, or mandated number of characters by the PCP are received are covered. Alternatively, the keys of the PKBD are disabled for access to the user by validating if class associated with character received are not covered, and a deviation of the parameters. A compliant password is created based on the PCP by providing in-place feedback for a resultant validation.

Abstract: This disclosure relates generally to method of modernizing a legacy batch based on at least one functional context. The method includes at least one of: preprocessing, a plurality of metadata associated with a plurality of batches to obtain a plurality of derived data; generating, the functional context based on the plurality of derived data; determining, an average elapsed time for at least one application from the at least one functional context; parsing, log of the at least one consistent long running job to identify step and associated file referenced in the at least one long running job; determining, a hotspot based on at least program; and recommending, at least one batch design associated with at least one batch job in a future state. The hotspot corresponds to long running job on a batch stream, high volume files, and program with an increased millions of instructions per second (MIPS) usage.

Abstract: Automation is the key to build efficient workflows with minimum effort consumption. However, there is a large gap in workflow synthesis for automated AI application development. Computer vision workflow synthesis largely rely on domain expert due to lack of generalization over solution search space for given goal. This search space for creating suitable solution(s) using available algorithms is quite vast, which makes exploratory work of solution building a time-, effort- and intellect intensive endeavor. Embodiments of the present disclosure provide system and method for goal-driven algorithm selection approach for building computer vision workflows on the fly. The system generates one or more task workflows with associated success probability depending on initial conditions and input natural language goal query by combining various image processing algorithms. Symbolic AI planning is aided by Reinforcement Learning to recommend optimal workflows that are robust and adaptive to changes in the environment.

Abstract: State of the art milk quality estimation techniques fail to determine quality of the milk non-invasively. This disclosure relates generally to a system and method for non-invasive estimation of milk quality within targeted packaging. A voltage signal is applied at a first capacitor plate amongst a plurality of capacitor plates placed on either side of a targeted packaging containing milk, wherein the targeted packaging is placed inside an electrode receptacle. The resulting voltage signal is measured at a second capacitor plate of the plurality of capacitor plates. A capacitance value is calculated from the measured voltage signal and a value of pH corresponding to the calculated capacitance value is then determined using a regression-based model. A correlation of the determined value of pH with one or more pre-defined quality indices is performed and the quality of milk within the targeted packaging estimated based on the correlation.

Abstract: The present disclosure provides a dynamic functional adaptation of software systems based on real time need, which is unaddressed by the conventional methods. Initially, the system receives an output generated by a software system under execution corresponding to a given input. Further, a deviation in the generated output is identified based on a comparison between the generated output and a corresponding expected output. Further, an optimal policy is identified based on the generated output and the identified deviation using a reward based Reinforcement Learning (RL) model. Further, an adaptation specification is generated based on the identified optimal policy using an Adaptation Specification Generation (ASG) technique, Further, a software code is generated dynamically for the identified optimal policy using an ASG based code generation technique.

Abstract: This disclosure relates generally to method and system to track and monitor human using an array of radars. Human tracking is necessarily important in security, especially with the growth of threats and incidents. Conventional systems and method lack in tracking target subject being authenticated to move around the monitoring environment. The present invention provides a method of detect human continually based on radar signals from an array of radars to track the presence of one or more target subjects associated within the monitoring environment. Further, a height surface plot of each target subject present in a radar range is constructed for identification. Then, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map. The characteristics of each target subject helps in detecting the target subject accurately.

Abstract: The disclosure generally relates to methods and systems for graph assisted unsupervised domain adaptation for machine fault diagnosis. The present disclosure solves the technical problems in the art using a Graph Assisted Unsupervised Domain Adaptation (GA-UDA) technique for the machine fault diagnosis. The GA-UDA technique carries out the domain adaptation in two stages. In the first stage, a Class-wise maximum mean discrepancy (CMMD) loss is minimized to transform the data from both source and target domains to a shared feature space. In the second stage, the augmented transformed (projected) data from both the source and the target domains are utilized to construct a joint graph. Subsequently, the labels of target domain data are estimated through label propagation over the joint graph. The GA-UDA technique of the present disclosure helps in addressing significant distribution shift between the two domains.

Abstract: Dependency on limited availability of subject matter experts (SMEs) who are well versed in Model-Driven Engineering (MDE) technology is a significant barrier to MDE utilized for generating conceptual models. In the present disclosure, MDE and generative Artificial Intelligence (AI) operate in a symbiotic relationship complimenting respective strengths and overcoming limitations. The generative AI techniques lower the knowledge barrier and enable domain SMEs to construct purposive models by operating at natural language level instead of at MDE technology level, thereby simplifying the method of generating conceptual models that are purposive. When operating at natural language level, the method and system of the present disclosure ensures that the generative AI receives focused and well directed prompts to optimize the number of interactions and reduce computing power utilized.

Abstract: This disclosure relates generally to the field of program slicing, and, more particularly, to a method and system for function call and variable access based relaxed backward slicing. The method discloses a slicing criterion which focuses only on functions called from an entry function. The slicing criteria uses control and data flow information to slice the given entry function with respect to functions called from the body of the entry function and eventually remove all functions not called directly or indirectly from the entry function. The variables modified by calls in the entry function are considered through side-effect while identifying control and data dependence chain within body of entry function. The proposed technique identifies partitions of functions based on the variables accessible in and functions called from the entry function. Thus, unrelated sets of functions with respect to the entry function are computed and divided into different partitions.

Abstract: There is no mechanism for vehicle utilization and optimization through continuous and incremental planning which ensures that transportation plans are based on real-time conditions. The present invention discloses systems and methods for vehicle utilization and optimization based on self-learning mechanism. A machine learning model for dynamic association of users to vehicles is provided that learns previously clubbed patterns of users with their corresponding locations. The learnt previously clubbed patterns are utilized for determining association between previously clubbed locations which is further utilized to obtain an optimal set of locations. The users are dynamically associated to vehicles allocated for the obtained optimal set of locations by honoring one or more social and vehicle constraints. The proposed system has self-learning capability which ensures effective vehicle utilization and optimization in real time.

Abstract: Conventionally, deep learning-based methods have shown some success in ligand-based drug design. However, these methods face data scarcity problems while designing drugs against novel targets. Embodiments of the present disclosure provide systems and methods that leverage the potential of deep learning and molecular modeling approaches to develop a drug design pipeline, which can be useful for cases where there is limited or no availability of target-specific ligand datasets. Inhibitors of other proteins, structurally similar to the target protein are screened at the active site of the target protein to create an initial target-specific dataset. Transfer learning is implemented to learn features of target-specific dataset and design new chemical entities/molecules using a deep generative model. A deep predictive model is used predict docking scores of newly designed/identified molecules.

Abstract: This disclosure relates generally to method and system for providing data privacy in service operations. Identifying risk arising from processing of user request in service operations is time consuming and monitoring insider threats is a difficult task. The method includes receiving a user request for a service comprising a plurality of sensitive attributes and further a vulnerability rating is assigned to each sensitive attribute. To mitigate the risk, the method estimates a disclosure proportion for the plurality of sensitive attributes and a masking operation is performed. Further, a sensitivity score is computed to allocate the user request to an agent associated with an agent registry with enabled data privacy and minimal data exposure. The agent is monitored by computing an agent mis-usability score to assess an insider threat risk. Additionally, a feedback alert is notified to autotune the plurality of privacy settings.

Abstract: Graphene metasurface based linear to circular polarization converters in THz band plays a crucial role in beyond 5G/THz wireless systems. However, conventional converters suffer a trade-off between “high bandwidth”, “compact size” and “high field confinement”. The present disclosure provides a graphene metasurface based tunable linear to circular polarization converter to minimize the trade-off by operating at a large bandwidth of 800 GHz with considerable compact size and high field confinement. The linear to circular polarization converter of the present disclosure includes a metasurface comprising two-dimensional periodic array of unit cells along x-axis and y-axis, wherein each unit cell is a three-layered stacked structure with a predefined periodicity. The three-layered stacked structure includes a top layer, a middle layer and a bottom layer. The top layer is a single layer graphene. The middle layer is a dielectric substrate, and the bottom layer comprises thin layer of gold.

Abstract: Current approaches for identifying accretion in rotary kiln lack access to information regarding the internal condition of the rotary kiln such as temperatures of the wall, gas or solid bed and specific methodology that is required to calculate accretion and hence forecast. Present disclosure provides method and system for forecasting and diagnosing accretion in rotary kiln. The system first takes historical data associated with rotary kiln, real-time data, and a future time horizon information. Then, system predicts accretion scores for future time horizon based on received data using a pretrained accretion forecasting model which are further utilized to estimate a rate of accretion. Thereafter, the system identifies high accretion (HA) operating regime and low accretion (LA) operating regime over predefined time period. Further, system identifies one or more accretion variables responsible for causing each of the HA operating regime and the LA operating regime using an accretion diagnostic model.

Abstract: As discussed earlier, accretion happens to be the most critical problem faced by users of the rotary kiln as it leads to shutdown of the rotary kiln which ultimately leads to reduction in production. Currently available accretion monitoring systems require expensive equipment and sensors which increases the production cost. Present disclosure provides method and system for monitoring accretion happening inside the rotary kiln. The system first takes real-time data associated with a rotary kiln as input. The system then localizes accretion clusters present in the rotary kiln using an accretion localization model. Thereafter, the system estimates the accretion probability score based on the HTM statistics calculated based on the accretion cluster information and real-time data using an accretion scoring model. Further, the system compute accretion score representative of real-time accretion condition of the rotary kiln based on the accretion probability score and the inputs.

Abstract: With the growing use of large-scale datasets containing participant's genomics and clinical data for research and studies purposes, it is important to ensure the privacy of the participant by generating a secure representation of genome data observation. Embodiments herein provide a system and method to perform DNA analysis on an encrypted genome without the need for decryption and ensure user's genome privacy. Herein, a stream of input genome is divided into chunks called as the sketched, where each k-mer in the sketch is hashed to get a sampling level and a counter value for the k-mer in a sketch. A privacy enhancing technique is designed over the representations using a Fully Homomorphic Encryption (FHE). Genomic data is analyzed with identified efficient algorithms for real world deployment in encrypted domain.

Abstract: Existing Magnetic Resonance (MR) analysis approaches are either manual, which is time consuming and error prone, or automatic yet fail to identify correct landmarks. The disclosure herein generally relates method and system for MR image analysis. The system trains and uses a Generative adversarial network (GAN) for the MR image analysis. A generator network of the GAN generates a heatmap of a plurality of landmarks, by processing input data. Further, a discriminator network of the GAN, which has gradients updated based on a Modified Discriminator Loss (MDL) calculated based on a foreground pixel loss function and a standard discriminator loss, predicts each of a plurality of patches in a second input data as one of real and fake, based on presence of the one or more foreground pixel regions in the landmark heatmap in the ground-truth heatmap identified based on the foreground pixel loss function.

Abstract: For performing analysis of enterprise application, code analysis tools may be used. But currently available analysis tools lack support for analyzing database processing statements, such as structured query language (SQL) statements and inter-service communication statements that may be present along with the programming language statements in the computer program. Present disclosure provides method and system for performing program transformations for precise analysis of enterprise applications. The system transform each database processing statement present in a computer program associated with the enterprise application into host programming language statement and each service call into function call statements. In particular, the system replaces syntax of embedded language with equivalent host programming language syntax. The system then uses existing code analyzers for performing analysis of the computer program to get data flow information of the computer program.

Abstract: The embodiments of present disclosure herein address unresolved problem of cognitive navigation strategies for a telepresence robotic system. This includes giving instruction remotely over network to go to a point in an indoor space, to go an area, to go to an object. Also, human robot interaction to give and understand interaction is not integrated in a common telepresence framework. The embodiments herein provide a telepresence robotic system empowered with a smart navigation which is based on in situ intelligent visual semantic mapping of the live scene captured by a robot. It further presents an edge-centric software architecture of a teledrive comprising a speech recognition based HRI, a navigation module and a real-time WebRTC based communication framework that holds the entire telepresence robotic system together. Additionally, the disclosure provides a robot independent API calls via device driver ROS, making the offering hardware independent and capable of running in any robot.

Abstract: Works in the literature fail to leverage embedding access patterns and memory units' access/storage capabilities, which when combined can yield high-speed heterogeneous systems by dynamically re-organizing embedding tables partitions across hardware during inference. A method and system for optimal deployment of embeddings tables across heterogeneous memory architecture for high-speed recommendations inference is disclosed, which dynamically partitions and organizes embedding tables across fast memory architectures to reduce access time. Partitions are chosen to take advantage of the past access patterns of those tables to ensure that frequently accessed data is available in the fast memory most of the time. Partition and replication is used to co-optimize memory access time and resources.