information fusion


TDWI Checklist Report Solving Modern Data Integration Challenges with an Enterprise Integration Fabric Transforming Data with Intelligence

#artificialintelligence

Ever since the early days of reporting, data warehousing, and analytics, there has been a need for data integration for many reasons. However, if you fast forward 30 years to today, you will see the traditional extract/transform/load (ETL) approach is insufficient to enable real-time predictive and prescriptive analytics. This checklist explores ideas for determining where traditional approaches to data integration are impeding modern analytics and will guide the reader in ways to modernize. Your e-mail address is used to communicate with you about your registration, related products and services, and offers from select vendors.


Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise

Neural Information Processing Systems

Modern machine learning-based approaches to computer vision require very large databases of labeled images. Some contemporary vision systems already require on the order of millions of images for training (e.g., Omron face detector). While the collection of these large databases is becoming a bottleneck, new Internet-based services that allow labelers from around the world to be easily hired and managed provide a promising solution. However, using these services to label large databases brings with it new theoretical and practical challenges: (1) The labelers may have wide ranging levels of expertise which are unknown a priori, and in some cases may be adversarial; (2) images may vary in their level of difficulty; and (3) multiple labels for the same image must be combined to provide an estimate of the actual label of the image. Probabilistic approaches provide a principled way to approach these problems.


Kalman Filter, Sensor Fusion, and Constrained Regression: Equivalences and Insights

Neural Information Processing Systems

The Kalman filter (KF) is one of the most widely used tools for data assimilation and sequential estimation. In this work, we show that the state estimates from the KF in a standard linear dynamical system setting are equivalent to those given by the KF in a transformed system, with infinite process noise (i.e., a flat prior'') and an augmented measurement space. This reformulation---which we refer to as augmented measurement sensor fusion (SF)---is conceptually interesting, because the transformed system here is seemingly static (as there is effectively no process model), but we can still capture the state dynamics inherent to the KF by folding the process model into the measurement space. Further, this reformulation of the KF turns out to be useful in settings in which past states are observed eventually (at some lag). Here, when the measurement noise covariance is estimated by the empirical covariance, we show that the state predictions from SF are equivalent to those from a regression of past states on past measurements, subject to particular linear constraints (reflecting the relationships encoded in the measurement map).


Optimal integration of visual speed across different spatiotemporal frequency channels

Neural Information Processing Systems

How does the human visual system compute the speed of a coherent motion stimulus that contains motion energy in different spatiotemporal frequency bands? Here we propose that perceived speed is the result of optimal integration of speed information from independent spatiotemporal frequency tuned channels. We formalize this hypothesis with a Bayesian observer model that treats the channel activity as independent cues, which are optimally combined with a prior expectation for slow speeds. We test the model against behavioral data from a 2AFC speed discrimination task with which we measured subjects' perceived speed of drifting sinusoidal gratings with different contrasts and spatial frequencies, and of various combinations of these single gratings. We find that perceived speed of the combined stimuli is independent of the relative phase of the underlying grating components, and that the perceptual biases and discrimination thresholds are always smaller for the combined stimuli, supporting the cue combination hypothesis.


Localized Data Fusion for Kernel k-Means Clustering with Application to Cancer Biology

Neural Information Processing Systems

In many modern applications from, for example, bioinformatics and computer vision, samples have multiple feature representations coming from different data sources. Multiview learning algorithms try to exploit all these available information to obtain a better learner in such scenarios. In this paper, we propose a novel multiple kernel learning algorithm that extends kernel k-means clustering to the multiview setting, which combines kernels calculated on the views in a localized way to better capture sample-specific characteristics of the data. We demonstrate the better performance of our localized data fusion approach on a human colon and rectal cancer data set by clustering patients. Our method finds more relevant prognostic patient groups than global data fusion methods when we evaluate the results with respect to three commonly used clinical biomarkers.


Reciprocally Coupled Local Estimators Implement Bayesian Information Integration Distributively

Neural Information Processing Systems

Psychophysical experiments have demonstrated that the brain integrates information from multiple sensory cues in a near Bayesian optimal manner. The present study proposes a novel mechanism to achieve this. We consider two reciprocally connected networks, mimicking the integration of heading direction information between the dorsal medial superior temporal (MSTd) and the ventral intraparietal (VIP) areas. Each network serves as a local estimator and receives an independent cue, either the visual or the vestibular, as direct input for the external stimulus. We find that positive reciprocal interactions can improve the decoding accuracy of each individual network as if it implements Bayesian inference from two cues.


On Single Source Robustness in Deep Fusion Models

Neural Information Processing Systems

Algorithms that fuse multiple input sources benefit from both complementary and shared information. Shared information may provide robustness against faulty or noisy inputs, which is indispensable for safety-critical applications like self-driving cars. We investigate learning fusion algorithms that are robust against noise added to a single source. We first demonstrate that robustness against single source noise is not guaranteed in a linear fusion model. Motivated by this discovery, two possible approaches are proposed to increase robustness: a carefully designed loss with corresponding training algorithms for deep fusion models, and a simple convolutional fusion layer that has a structural advantage in dealing with noise.


Speech Analytics Market Share Size, Global Snapshot Analysis and Growth Opportunities by 2025 – Food & Beverage Herald

#artificialintelligence

Rising number of contact centers and necessity for compliance and risk management across several verticals have led the companies to invent solutions in speech analytics which will aid companies to comprehend the changing necessities of customers. Several organizations functioning in diverse industrial domains have been evolving interests for the transcription and analyzing of customers and structural media and uptake rational decisions for the management of business and consumers with the help of speech and text intelligence. This is the main factor that is responsible for the growth of the speech analytics market and a protuberant driving factor in the growing demands for speech analytics in several industrial applications. This rising demand can also be accredited to the burdens on businesses for safeguarding their rational assets for improving agility and competence in business operations via the all-embracing insights quarried in the Voice of Customer (VoC). Speech analytics is used in sectors such as customer experience management, agent performance, business processes, compliance and risk management, and market intelligence.


Speech Analytics Market Drivers, End User, Key Players and Challenges by 2025 – Market Research Sheets

#artificialintelligence

Rising number of contact centers and necessity for compliance and risk management across several verticals have led the companies to invent solutions in speech analytics which will aid companies to comprehend the changing necessities of customers. Several organizations functioning in diverse industrial domains have been evolving interests for the transcription and analyzing of customers and structural media and uptake rational decisions for the management of business and consumers with the help of speech and text intelligence. This is the main factor that is responsible for the growth of the speech analytics market and a protuberant driving factor in the growing demands for speech analytics in several industrial applications. This rising demand can also be accredited to the burdens on businesses for safeguarding their rational assets for improving agility and competence in business operations via the all-embracing insights quarried in the Voice of Customer (VoC). Speech analytics is used in sectors such as customer experience management, agent performance, business processes, compliance and risk management, and market intelligence.


Senior Data Engineer - IoT BigData Jobs

#artificialintelligence

Description The Data Engineering team at Intuit's Small Business Group (SBG) is looking for a Senior Data Engineer – QE with a winning track record in Big Data, Data Warehousing, Visualization and Data Web Services. Responsibilities: Work with Data Engineers, Product Managers and Data Scientists to identify datasets needed for deep customer insights and for building operational propensity models. Work with data ingestion engineers to bring required source datasets into the data warehouse. Test ETL code to populate the dimensional model. Work with BI developers to ensure that the data warehouse is providing the required data and the required performance.