The complete blood count (CBC) performed by automated hematology analyzers is one of the most ordered laboratory tests. It is a first-line tool for assessing a patient's general health status, or diagnosing and monitoring disease progression. When the analysis does not fit an expected setting, technologists manually review a blood smear using a microscope. The International Consensus Group for Hematology Review published in 2005 a set of criteria for reviewing CBCs. Commonly, adjustments are locally needed to account for laboratory resources and populations characteristics. Our objective is to provide a decision support tool to identify which CBC variables are associated with higher risks of abnormal smear and at which cutoff values. We propose a cost-sensitive Lasso-penalized additive logistic regression combined with stability selection. Using simulated and real CBC data, we demonstrate that our tool correctly identify the true cutoff values, provided that there is enough available data in their neighbourhood.

Inspired by the success of deep learning, recent industrial Click-Through Rate (CTR) prediction models have made the transition from traditional shallow approaches to deep approaches. Deep Neural Networks (DNNs) are known for its ability to learn non-linear interactions from raw feature automatically, however, the non-linear feature interaction is learned in an implicit manner. The non-linear interaction may be hard to capture and explicitly model the \textit{co-action} of raw feature is beneficial for CTR prediction. \textit{Co-action} refers to the collective effects of features toward final prediction. In this paper, we argue that current CTR models do not fully explore the potential of feature co-action. We conduct experiments and show that the effect of feature co-action is underestimated seriously. Motivated by our observation, we propose feature Co-Action Network (CAN) to explore the potential of feature co-action. The proposed model can efficiently and effectively capture the feature co-action, which improves the model performance while reduce the storage and computation consumption. Experiment results on public and industrial datasets show that CAN outperforms state-of-the-art CTR models by a large margin. Up to now, CAN has been deployed in the Alibaba display advertisement system, obtaining averaging 12\% improvement on CTR and 8\% on RPM.

In this work, we present an ensemble of descriptors for the classification of transmission electron microscopy images of viruses. We propose to combine handcrafted and deep learning approaches for virus image classification. The set of handcrafted is mainly based on Local Binary Pattern variants, for each descriptor a different Support Vector Machine is trained, then the set of classifiers is combined by sum rule. The deep learning approach is a densenet201 pretrained on ImageNet and then tuned in the virus dataset, the net is used as features extractor for feeding another Support Vector Machine, in particular the last average pooling layer is used as feature extractor. Finally, classifiers trained on handcrafted features and classifier trained on deep learning features are combined by sum rule. The proposed fusion strongly boosts the performance obtained by each stand-alone approach, obtaining state of the art performance.

In tis paper we consider approaches for time series forecasting based on deep neural networks and neuro-fuzzy nets. Also, we make short review of researches in forecasting based on various models of ANFIS models. Deep Learning has proven to be an effective method for making highly accurate predictions from complex data sources. Also, we propose our models of DL and Neuro-Fuzzy Networks for this task. Finally, we show possibility of using these models for data science tasks. This paper presents also an overview of approaches for incorporating rule-based methodology into deep learning neural networks.

A team of scientists built a tentacle-like robot gripper that they say is more sensitive than a conventional claw or hand-shaped machine -- because it wraps around and delicately constricts objects like a python or an elephant's trunk. Modeling an elephant's complex musculature allows it to snugly grip delicate or hard-to-reach objects, according to a press release, in a new, gentler paradigm for robotic arms. Thanks to a network of sensors that tell the robot snake how hard it's gripping, the University of New South Wales (UNSW) scientists that designed it say it can grab and hold delicate objects far more safely than conventional robots, according to research published last week in the journal Advanced Materials Technologies. In a short lab video, the robot can be seen automatically winding around and grabbing objects ranging from a hammer to cucumber. The scientists say it can hold a grip on objects 220 times heavier than itself.

Chris Johnston, Executive Director for Paerata Rise says "Our goal is to be one of the most desirable places to live in Auckland and becoming a Smart Village is an extension of this. It means we are able to offer the utmost connection to our residents through a private network, and the most cutting-edge technologies." "We are proud to be able to support the unique, first class community being built at Paerata Rise with the latest concepts in mobile network technology. While everyone has experienced the frustration of bad coverage, ultimately an excellent network should go unnoticed – instead allowing users' mobile applications, services, and other benefits to come to the fore," adds Ross Spearman, General Manager of Dense Air New Zealand. "The realities of smart villages and connected neighbourhoods are starting to emerge in the world around us, however the real'smarts' need to be built into the foundations of communities which is why we are executing this project at this stage of our development," says Johnston.

Developers and business leaders can learn about the latest trends in artificial intelligence (AI) at IBM's free Data & AI digital conference on Nov. 10 starting at 2 pm GMT. The sessions will focus on operations, ethics, and cloud computing. IBM is running the conference again on Nov. 24 for India and the Asia Pacific region. People who register for the conference get $300 in credits to spend on any services in the IBM Cloud Catalog. Attendees who completes the course in Track 3 earn an AI and Data Essentials badge.

Australian water infrastructure is more than a hundred years old, thus has begun to show its age through water main failures. Our work concerns approximately half a million pipelines across major Australian cities that deliver water to houses and businesses, serving over five million customers. Failures on these buried assets cause damage to properties and water supply disruptions. We applied Machine Learning techniques to find a cost-effective solution to the pipe failure problem in these Australian cities, where on average 1500 of water main failures occur each year. To achieve this objective, we construct a detailed picture and understanding of the behaviour of the water pipe network by developing a Machine Learning model to assess and predict the failure likelihood of water main breaking using historical failure records, descriptors of pipes and other environmental factors. Our results indicate that our system incorporating a nonparametric survival analysis technique called "Random Survival Forest" outperforms several popular algorithms and expert heuristics in long-term prediction. In addition, we construct a statistical inference technique to quantify the uncertainty associated with the long-term predictions.

In this paper, the process of forecasting household energy consumption is studied within the framework of the nonparametric Gaussian Process (GP), using multiple short time series data. As we begin to use smart meter data to paint a clearer picture of residential electricity use, it becomes increasingly apparent that we must also construct a detailed picture and understanding of consumer's complex relationship with gas consumption. Both electricity and gas consumption patterns are highly dependent on various factors, and the intricate interplay of these factors is sophisticated. Moreover, since typical gas consumption data is low granularity with very few time points, naive application of conventional time-series forecasting techniques can lead to severe over-fitting. Given these considerations, we construct a stacked GP method where the predictive posteriors of each GP applied to each task are used in the prior and likelihood of the next level GP. We apply our model to a real-world dataset to forecast energy consumption in Australian households across several states. We compare intuitively appealing results against other commonly used machine learning techniques. Overall, the results indicate that the proposed stacked GP model outperforms other forecasting techniques that we tested, especially when we have a multiple short time-series instances.

In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatiotemporal tube of the target person from an untrimmed video based on a given textural description. This task is useful, especially for healthcare and security-related applications, where the surveillance videos can be extremely long but only a specific person during a specific period of time is concerned. HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization. Unfortunately, the existing grounding methods cannot handle this task well. We tackle this task by proposing an effective baseline method named Spatio-Temporal Grounding with Visual Transformers (STGVT), which utilizes Visual Transformers to extract cross-modal representations for video-sentence matching and temporal localization. To facilitate this task, we also contribute an HC-STVG dataset consisting of 5,660 video-sentence pairs on complex multi-person scenes. Specifically, each video lasts for 20 seconds, pairing with a natural query sentence with an average of 17.25 words. Extensive experiments are conducted on this dataset, demonstrating the newly-proposed method outperforms the existing baseline methods.