Abstract: An important task in several wellness applications is detection of emotional valence from speech. Two types of features of speech signals are used to detect valence: acoustic features and text features. Acoustic features are derived from short frames of speech, while text features are derived from the text transcription. Present disclosure provides systems and methods that determine the effect of text on acoustic features. Acoustic features of speech segments carrying emotion words are to be treated differently from other segments that do not carry such words. Only specific speech segments of the input speech signal are considered based on a dictionary specific to a language to assess emotional valence. A model trained (or trained classifier) for specific language either by including the acoustic features of the emotion related words or by omitting it is used by the system for determining emotional valence in an input speech signal.

Abstract: Depth estimation of images using deep learning methods is a wide range of application in Augmented Reality, 3D graphics and robotics. Conventional methods are supervised, which requires explicit ground truth depth information for training and the conventional unsupervised methods fails to provide a generalized solution. The present disclosure estimates accurate depth information and confidence map of a given monocular image in an unsupervised manner. A depth Neural Network receives a monocular image and predicts per-pixel depth map and a confidence map. The depth NN utilizes a negative exponential of photometric loss as ground truth information. The predicted confidence-map is further used to estimate per-pixel uncertainty map. The pose NN predicts a plurality of pose vectors between a plurality of the consecutive monocular images. Finally, the Bayesian inference module is computes the fused depth information and the fused uncertainty map.

Abstract: This disclosure relates generally to estimating age of a leaf using morphological features extracted from segmented leaves. Traditionally, leaf age estimation requires a single leaf to be plucked from the plant and its image to be captured in a controlled environment. The method and system of the present disclosure obviates these needs and enables obtaining one or more full leaves from images captured in an uncontrolled environment. The method comprises segmenting the image to identify veins of the leaves that further enable obtaining the full leaves. The obtained leaves further enable identifying an associated plant species. The method also discloses some morphological features which are fed to a pre-trained multivariable linear regression model to estimate age of every leaf. The estimated leaf age finds application in estimation of multiple plant characteristics like photosynthetic rate, transpiration, nitrogen content and health of the plants.

Abstract: This disclosure relates generally to system and method for assessing insider influence on enterprise assets. Existing work focuses on the detection of insider threat and does not consider the influence of an insider on their peers and subordinates. The present disclosure aggregates and preprocesses the enterprise data specific to the individuals received from various sources, and further creates an enterprise graph between entities. Weights of every edge connected between any two entities in the enterprise graph is then calculated. Community of the individuals are detected wherein, relevant insider(s) are identified, and susceptibility of the individuals for probable influence by relevant insider(s) based on the analysis scenarios(s) is calculated. Paths taken by the relevant insider(s) is calculated for estimating probability of data loss.

Abstract: This disclosure relates generally to method and system for forecasting sales based on N-Gram model. The present disclosure provides accurate prediction of sales for optimal operations to reduce the cost. The method receives a plurality of inputs of each product comprising a sales history, and a current price bin. The categorical sale(s) for each product is discretized based on the sales history by clustering each product sales history into a one or more groups based on a maximum sales velocity range. Further, a probability table is generated for the discretized categorical sales of each product based on computing a round off weighted mean and a median using a N-Gram model. Then, a smooth probability table is computed for the generated probability table. To forecast sales multistep prediction for the smooth probability table is computed based on atleast one of a joint approach, a bootstrapped approach, and a step greedy approach.

Abstract: A system and method for monitoring behavior of voice agents in a simulated environment of voice-based call center to route a call. It includes a set of models and wearable devices to estimate and analyze cognitive load and emotional state of a voice agent which are obtained using wearable devices in the real time. It collects physiological signals from the voice agents and analyze them along with skill-set profiles of the voice agent to identify best suited voice agent based on agent-customer matching score obtained using skill-set profile analysis, cognitive load and a predicted emotive state of the voice agent. It may assist the voice agent in call if the cognitive load of the voice agent raises beyond predefined threshold using brain computer interfacing.

Abstract: A system and method for determining stress level of a person in real-time have been disclosed. In one aspect, the system captures physiological data associated to the person. In one embodiment, the physiological data may be captured by using a plurality of sensors attached at wrist or ankle or neck or waist or hip of the person, for a predetermined time interval. The plurality of sensors may include a wrist watch or a wristband or a textile material. The system further pre-processes the physiological data in order to extract one or more physiological parameters. In one aspect, the pre-processing may include performing an analysis on the physiological data. The system further determines the stress level of the person upon performing the statistical analysis on the one or more physiological parameters. According to another embodiment, a method for real time determination of stress level of the person has also been provided.

Abstract: This disclosure relates generally to field of elimination of false positives during static analysis of an application code, and, more particularly, to a method and a system for identification and elimination of false positives from delta alarms. Existing static analysis tools report/generate numerous static alarms for a version and the same static alarm also gets reported for the subsequent versions, which are referred to as repeated alarms, while static alarms remaining after the suppression of the repeated alarms, are called delta alarms. In an embodiment, the disclosed method and system for identification and elimination of false positives from delta alarms, wherein the delta alarms are post-processed to identify of a set of false positives using a version aware static analysis technique based on a set of reuse computation techniques implementing conservative or an aggressive approach based on a dynamic configuration input.

Abstract: Most current systems decompose sales volume of a product into base volume and additional volumes associated to each sales driver. Here base volume refers to sales quantity that is derived from non-promoted sales period. It leads base volume of a product with partial price effect. In addition, base volume includes volume contributed by store location, space allocated to product category and assortment etc. In the present disclosure a system and method for sales decomposition is described by computing reference base volume and sales contribution by each sales driver. Here reference base volume is the volume derived by excluding the effect of sales drivers namely, retailer price, competitor price, demographics, weather conditions, space occupied by the category to which the product belongs, number of available substitute products in assortment. Retail strategies are recommended in real time based on sales contribution of the sales driver for the product.

Abstract: State of the art food quality measurement techniques fail to determine quality of the food item once it is packed and sealed in a container. The disclosure herein generally relates to food quality prediction, and, more particularly, to a system and method for predicting food quality in a non-invasive manner. A Color Changing Indicator (CCI) in a biosensor strip forming a component of the enclosed package in which the liquid food item is packed, changes color when came in contact with the liquid food item. For different quality of the liquid food item the CCI has different color. Based on the color of the CCI, and ambient temperature and relative humidity at the time the color of the CCI is determined, a machine learning model determines rate of deterioration of the liquid food item, and then predicts remaining shelf life, which in turn provided as output to a user.

Abstract: This disclosure relates generally to generating annotations and field-names for a relational schema. Typically, most domains have relational database (RDB) system built for them instead of domain ontologies and usually linguistic information of the schema is not used to recover the domain terms. The disclosed method and system facilitate generating annotations and field-names for a relational schema, while considering the linguistic information of a schema by using a trained model, trained through a proposed training technique. The trained model comprises of at least one knowledge graph and a set of associated parameters. The trained model is further used to perform a plurality of tasks, wherein the plurality of tasks include generating a plurality of new fieldnames for a relational schema through a stochastic generative process and for generating a new annotation for a fieldname of a relational schema through a probabilistic inference technique.

Abstract: This disclosure relates generally to a system and method for real-time non-invasive estimation of food quality within enclosed package. Existing works utilize invasive methods that require direct contact of the food item with the sensors. In the present disclosure, a potential is applied over a plurality of frequencies through the food item contained the enclosed package which includes a plurality of polyethylene layers and a conducting layer arranged between two adjacent polyethylene layers using electrochemical impedance spectroscopy. Values of electrical voltages and the electrical impedances of the food item are then obtained. A plurality of features is derived from the obtained values of the electrical voltages and the electrical impedances using a trained model. The present disclosure estimates the quality of the food item in real-time by co-relating the plurality of derived features with the quality of the food item contained inside the enclosed package.

Abstract: Existing techniques in precision farming comprise supervised event detection and need labeled training data which is tedious considering the large number of crops, differences therein and even larger number of diseases and pests. The present disclosure provides an unsupervised method and uses images of any size captured in an uncontrolled environment. The methods and systems disclosed find application in automatically localizing and classifying events, including health state and growth stage and also estimating an extent of manifestation of the event. Information of spatial continuity in pixels and boundaries in a given image is used to update the feature representation and label assignment to every pixel using a fully convolutional network. Back propagation of the pixel labels modified according to the output of a graph based method helps the neural network to converge and provide a time efficient solution.

Abstract: Monitoring and analysis of plurality of operations in mining and mineral processing is critical to achieve optimized performance. Existing tools are specific to one or other individual operations and this individuality introduces limitations for end to end monitoring of entire mining to mineral processing operations. Method and system for online monitoring and optimization of mining and mineral processing operations providing an integrated approach utilizing short-term mining plan data, information generated using established drill and blast design software, simulation models of fragmentation, crushing, screening, grinding and flotation to arrive at an optimized charge plan and set points for controllers is disclosed. The proposed method and system improves key performance indicators such as cost of mining operations, specific energy consumption in comminution circuit, maximizes yield of desired particle size, and maximizes grade and recovery of mineral of interest while considering operational constraints.

Abstract: Systems and methods for detecting an anomaly in a cardiovascular signal using hierarchical extremas and repetitions. The traditional systems and methods provide for some anomaly detection in the cardiovascular signal but do not consider the discrete nature and strict rising and falling patterns of the cardiovascular signal and frequency in terms of hierarchical maxima points and minima points. Embodiments of the present disclosure provide for detecting the anomaly in the cardiovascular signal using hierarchical extremas and repetitions by smoothening the cardiovascular signal, deriving sets of hierarchical extremas using window detection, identifying signal patterns based upon the sets of hierarchical extremas, identifying repetitions in the signal patterns based upon occurrences and randomness of occurrences of the signal patterns and classifying the cardiovascular signal as anomalous and non-anomalous for detecting the anomaly in the cardiovascular signal.

Abstract: In computing, an unresolved problem of high manual effort required for mapping data attributes between the source and the target systems involved in process of the data transformation. This disclosure relates to method of auto-mapping of a plurality of source data attributes and a plurality of target data attributes associated with one or more applications based on similarity of a metadata information is provided. The processor implemented method include processing, a corresponding source table to a target table based on similarity associated with a table name; determining, a candidate source data attributes for at least one target data attribute based on similarity associated with a data attribute name; computing, a weighted score of each of the candidate source data attributes for corresponding at least one target data attribute; and mapping, the weighted score to determine an association of a final data attribute.

Abstract: The disclosure generally relates to methods and systems for ensuring the on-time delivery (OTD) of a product by a manufacturing company. According to the present disclosure, a part persona for each part is generated using a data model, by placing the part as an central entity and the one or more influencing factors of each part that affect the OTD of the product are captured in the part persona. A trained intent and OTD prediction model is built and used to predict an initial intent and an initial OTD for each part, based on the corresponding part persona. Further, the trained intent and OTD prediction model is used to predict a successive intent and a successive OTD for each part, based on the conversations and the events. Hence the OTD of the product is accurately predicted and which is useful to ensuring the OTD of the product.

Abstract: The fine-grained variations in product images are usually due to slight variations in text, size, and color of the package. Both marginal variations in image content and illumination poses an important challenge in product classification. This disclosure relates to a system and method for fine-grained classification of similar-looking products utilizing object-level and part-level information. The system simultaneously captures an object-level and part-level information of the product. The object-level classification score of the product is estimated with the trained RC-Net, a deep supervised convolutional autoencoder. For annotation-free modelling of part-level information of the product the discriminative part-proposal of the product is identified around the BRISK key points. An ordered sequence of the discriminative part-proposals and the product image, encoded using stacked convolutional LSTM network, estimates the part-level classification score.

Abstract: This disclosure relates generally to relates to the field of estimation of remaining useful life (RUL) in lithium based batteries, and, more particularly, to estimation of remaining useful life in lithium based batteries based on coupled estimation of a state of charge (SOC) and a state of health (SOH) during charging/discharging in constant current (CC) and constant voltage (CV) modes. The disclosed RUL estimation technique considers the inter-dependency of SOC-SOH and influence of internal-external parameters/factors during the coupled estimation of SOC-SOH. The coupled estimation of SOC and SOH is based on a reduced order physics based modelling technique and considers the influence real time environment obtained using real-time dynamic data obtained by several sensors during the coupled estimation of SOC-SOH.

Abstract: This disclosure relates generally to systems and methods for masking and unmasking of sensitive data. The present systems and methods solve the problems of consistency of the data masking, by using a random index and a masked index with use of regular expression concept. An additional random key produce different masked data versions, however the original form of the sensitive data is achieved with any masked data version. Plurality of masked data versions are generated by masking the sensitive input dataset, where the plurality of masked data versions comprises same format of the sensitive input dataset. The generated masked data versions are secured and hard to predict the original form of the sensitive input dataset by authorized or unauthorized environments. Also, the present method consume less processing time, as the masking process and the unmasking process make operations on the indexes rather than with the original dataset.