Abstract: The present disclosure is directed to a traffic light recognition system and method for advanced driver assistance systems (ADAS) and robust to variations in illumination, partial occlusion, climate, shape and angle at which traffic light is viewed. The solution performs a real time recognition of traffic light by detecting the region of interest, where extracting the region of interest is achieved by projecting the sequence of frames into a kernel space, binarizing the linearly separated sequence of frames, identifying and classifying the region of interest as a candidate representative of traffic light. With the aforesaid combination of techniques used, traffic light can be conveniently recognized from amidst closely similar appearing objects such as vehicle headlights, tail or rear lights, lamp posts, reflections, street lights etc. with enhanced accuracy in real time.

Abstract: A system and a method for creating an optimized actionable interface for data access and visualization is provided. Different types of metrics and Key Performance Indicators (KPIs) data associated with enterprise data is analyzed for determining one or more key metrics and KPIs data and identifying a causal attribution data between the key metrics and KPIs data for determining effect of change of one key metric and KPI data on another key metric and KPI data. Further, one or more widgets are generated based on the analyzed metrics and KPIs data. Further, a unified user interface (UI) is generated for visualization of the widgets. Lastly, an end-user activity on the unified UI is tracked based on one or more tags embedded in the unified UI. The tags capture the end-user clicks and actions on the unified UI.

Abstract: A computer-implemented method for automated test script generation for application testing, more particularly for testing one or more functions of Application Under Test (AUT) where, in operation, a test case flow sequence is ascertained, including a data list defining one or more methods, where each method is further representative of an automation code corresponding to a manual step of the test case, and a test class for testing a function of AUT is generated using the test case flow sequence if each of the one or more methods are available in the framework, such that the disclosure provides for generating a test class for testing the function of AUT by automatically generating the one or methods if the methods are not available in the framework.

Abstract: The present invention provides for a system and a method for translating a legacy source code to a cloud native code. The present invention provides for receiving a source code and deriving a plurality of queries from the source code and the queries comprise a plurality of tokens. The present invention provides for constructing an abstract syntax tree in the form of a data structure from the tokens. The present invention provides for traversing the abstract syntax tree, the identified pattern, the scope table and the syntax table for translation of the tokens of the abstract syntax tree into new tokens stored in the form of a cloud native abstract syntax tree. The present invention provides for concatenating the new tokens stored in the cloud native abstract syntax tree to generate a translated cloud native code to be hosted on a cloud platform.

Abstract: The present invention discloses a system and a method for providing color vision deficiency assistance by selectively recoloring pixels of an image frame including unperceivable colors with perceivable colors in real time. In particular, the present invention provides for rescaling the image frame using a first set of rules. Further, a perceivable color space is selected based on one or more parameters. Furthermore, one or more pixels associated with unperceivable colors are identified using a second set of rules. Yet further, the identified one or more pixels are recolored using the selected perceivable color space and a third set of rules. Finally, a corrected image frame comprising perceivable colors is provided.

Abstract: A system and a method for automating unit test case including generating a codebase extract by analysing an application source code, identifying one or more potential executable paths within a selected class or method based on an analysis of the codebase extract, executing one or more statements associated with each of the one or more potential paths using a symbolic execution technique and identifying one or more calls to external dependencies associated with the respective paths, and subsequently, a hint for spying and mocking respective external dependencies is generated, as a by-product of symbolic execution on identification of the external dependencies, whereby each hint is updated with respective ideal return value, and a unit test case for testing a selected class or method is generated by processing the hints with test data and an exclusion list.

Abstract: A system and method for retrieval of similar images related to query images is provided. The query images are pre-processed for noise removal by selecting filtering technique based on noise variance estimation in each query image with respect to pre-set noise variance threshold value. The pre-processed query images are pre-classified for determining class one image identifier. Image types are generated from pre-processed query images for determining class two image identifier. Features are extracted from pre-classified query images based on class one image identifier and from generated images based on class two image identifier. The images similar to query images are retrieved which have features similar to extracted features of pre-classified query images and generated images. The retrieved similar images are ranked for determining most similar images with respect to query images. Similarity between query images and retrieved similar images is analyzed for re-ranking retrieved similar images.

Abstract: A system and method for conversion of monolithic services to micro-services is provided. One or more features related to service associated with domain implemented by monolithic service source code are identified. Features are identified for creating first feature set. One or more features are determined related to dependencies and cross-dependencies amongst one or more service functions associated with service, implemented by monolithic service source code, and between service functions and entities associated with domain expressed in the monolithic service source code. One or more features related to dependencies and cross-dependencies are determined for creating second feature set. Relationship between features present in first feature set and second feature set is determined. The relationship is representative of similarity of the features present in first feature set and second feature set.

Abstract: A system and a method for adaptive information storage management is provided. One or more parameters from an incoming data stream is identified based on a set of predetermined rules. The identified parameters correspond to a set of predetermined parameters. A subset of rules is applied, from the set of predetermined rules, on the incoming data stream. The subset of rules represent a series of iterative rules associated with each identified parameter. One or more data storage allocation files are generated that represent results of application of the set of predetermined rules and the subset of rules. The results include at least a storage system type identified from the storage system as optimal for storing the incoming data stream.

Abstract: A system, a method, and a computer program product for recognizing a logo from an image is provided. The method comprises receiving and preprocessing an image that contains the logo to be recognized. The method further comprises detecting text of the logo to recognize the logo. The method furthermore comprises extracting local and global features of a region of interest associated with the logo to recognize the logo if the text is not detected in the logo. The method further comprises detecting one or more signs in proximity of the logo to recognize the logo if the logo is not recognized by extracting the local and global features of the logo. The method finally comprises identifying a region where the logo is present in the pre-processed image to recognize the logo if the logo is not recognized by detecting the one or more signs in proximity of the logo.

Abstract: A system and a method for providing service virtualization in a distributed computing architecture without a central server is disclosed. The present invention provides one or more service pods implementable on one or more workstations. Each of the one or more service pods is configured to host one or more virtual services. Each of the one or more service pods interface with one or more live services to generate virtual service data to emulate said live services. The one or more service pods interface with each other via a network fabric technique and interact with one or more client applications to be tested. Each of the one or more service pods are configured to receive and process requests from one or more client applications using various modes of service pods. The present invention provides complete abstraction of the one or more workstations from the one or more service pods.

Abstract: A system and method for automated resolution of events in a computing environment is provided. Problem types are identified from the events which are associated with configuration items (CIs) at issue. Further, domains of the CIs at issue are identified. Domains represent types of the CIs at issue. Existence of diagnosis and resolution sequences is checked which is based on identified problem types and domain associated with the CI types. Thereafter, diagnosis and resolution sequences are fetched, where sequences fetched at a first instance are at least in part updated with one or more new sequences. Fetched sequences are executed iteratively such that a next step of the executed diagnosis and resolution sequence is based on an output of a first step of the executed diagnosis and resolution sequence.

Abstract: A system and computer-implemented method for efficiently monitoring hand hygiene is provided. The system comprises one or more sensors configured to determine presence of one or more individuals in vicinity. The system further comprises one or more controllers configured to ascertain identity of the one or more individuals. The one or more controllers are further configured to send one or more alerts to the one or more identified individuals to wash their hands. Furthermore, the one or more controllers are configured to monitor one or more handwashing instances by the one or more identified individuals and generate one or more compliance results for each of the one or more monitored handwashing instances. The one or more controllers are also configured to initiate one or more actions corresponding to each of the one or more monitored handwashing instances based on the generated one or more compliance results.

Abstract: A system and computer-implemented method for detecting retinopathy is provided. The system comprises an image input module configured to receive one or more fundus images. Further, the system comprises a pre-processing module configured to apply one or more transformations to the one or more received fundus images. Furthermore, the system comprises a feature extraction module configured to extract one or more features from the one or more transformed images using one or more Convolutional Neural Networks (CNNs). Also, the system comprises a prediction module configured to determine stage of retinopathy by classifying the one or more extracted features using pre-stored features, wherein the pre-stored features are extracted from one or more training fundus images by the one or more CNNs and further wherein each pre-stored feature corresponds to a class which is associated with a predetermined stage of retinopathy.

Abstract: A system and computer-implemented method for managing a smart devices network using fog computing is provided. The system comprises an application manager configured to receive service requests from devices in a smart devices network and collect data related to fog computing nodes and intermediate computing nodes and a resource utilization predictor configured to predict availability of the fog computing nodes and the intermediate computing nodes. Furthermore, the system comprises a resource manager configured to dynamically allocate at least one of: a specific fog computing node and a specific intermediate computing node, schedule triggering of fog applications based on the predicted availability, trigger, at the specific fog computing node and the specific intermediate computing node, the fog applications for executing the received service requests corresponding to the devices and perform actions corresponding to the executed one or more service requests.

Abstract: A system for improving software code quality using artificial intelligence is provided. The system comprises a training data extraction module to extract learning data files from a source control management system and an integrated development environment for preparing training data. The system further comprises a machine learning model trainer that conducts training of an artificial neural network. The system further comprises a machine learning recommendation module that queries the trained artificial neural network to check for recommendations for improving quality of one or more new software codes and one or more modified software codes. The system also comprises a remediation module that determines one or more coding standard violations in the one or more new software codes and one or more modified software codes. The quality of the one or more new software codes and one or more modified software codes is improved by applying the recommendations.

Abstract: Method and system for identifying and analysing hidden relationships in application databases is provided. During a database session database query language statements (DQLS) are retrieved from log tables in application databases to analyze and identify join indicators. Join indicators represent data fields from two or more tables which are joined using values common to each data field. Based on identified join indicators, data definition language (DDL) file is generated including relationship between two or more tables. Above steps are repeated until all DQLS in log tables are analyzed. Thereafter it is ascertained if content of created DDL file is defined in database schema (DS). DS is represented in physical data models of application databases. If it is not defined in the database schema, a logical data definition language file is generated based on generated DDL file to update logical data model, which represents hidden relationships between tables in application databases.

Abstract: A system and method for handling one or more dependency services hosted by one or more dependency servers for an upstream service hosted by an administrative server in a distributed computer architecture is provided. The present invention provides for identifying any abnormality in the behavior of the dependency services on the basis of metric values associated with service-parameters of said dependency services. Further, the resiliency services are enabled in order to handle one or more faltering dependency services based on the faulty metric values associated with the service-parameters. Yet further, the one or more faltering dependency services are continuously monitored, and one or more resiliency services are withdrawn once the fault in said dependency services is resolved. Yet further, the present invention provides a conversational bot interface for managing the administrative server and associated dependency services.

Abstract: A system and a method for detecting fraudulent transactions at a transaction site by analyzing pattern of events associated with one or more transactions are provided. The present invention provides for forming a collection of most probable fraudulent patterns and true patterns associated with one or more transactions, selecting a pattern classification technique, generating a data input from an ongoing transaction that is interpretable by the selected pattern classification technique, and effectively and efficiently categorising ongoing transaction into fraudulent and genuine transactions using selected pattern classification technique. The present invention may be utilized in a variety of applications where discrete time-ordered visual events are associated with a transaction, for example: vehicles detected in relation to a transit point, badge or card swipes from an automated door lock etc., which indicate trespassing, theft and unauthorized access to restricted areas etc.