In the Internet of Things (IoT) era, billions of sensors and devices collect and process data from the environment, transmit them to cloud centers, and receive feedback via the internet for connectivity and perception. However, transmitting massive amounts of heterogeneous data, perceiving complex environments from these data, and then making smart decisions in a timely manner are difficult. Artificial intelligence (AI), especially deep learning, is now a proven success in various areas including computer vision, speech recognition, and natural language processing. AI introduced into the IoT heralds the era of artificial intelligence of things (AIoT). This paper presents a comprehensive survey on AIoT to show how AI can empower the IoT to make it faster, smarter, greener, and safer. Specifically, we briefly present the AIoT architecture in the context of cloud computing, fog computing, and edge computing. Then, we present progress in AI research for IoT from four perspectives: perceiving, learning, reasoning, and behaving. Next, we summarize some promising applications of AIoT that are likely to profoundly reshape our world. Finally, we highlight the challenges facing AIoT and some potential research opportunities.

Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions. These systems, however, rely on complex handcrafted heuristics for sequential matching - which are applied on top of a pre-computed pairwise similarity matrix between reference and query image sequences of a single route - to further reduce false-positive rates compared to single-frame retrieval methods. As a result, performing multi-frame place recognition can be extremely slow for deployment on autonomous vehicles or evaluation on large datasets, and fail when using relatively short parameter values such as a sequence length of 2 frames. In this paper, we propose DeepSeqSLAM: a trainable CNN+RNN architecture for jointly learning visual and positional representations from a single monocular image sequence of a route. We demonstrate our approach on two large benchmark datasets, Nordland and Oxford RobotCar - recorded over 728 km and 10 km routes, respectively, each during 1 year with multiple seasons, weather, and lighting conditions. On Nordland, we compare our method to two state-of-the-art sequence-based methods across the entire route under summer-winter changes using a sequence length of 2 and show that our approach can get over 72% AUC compared to 27% AUC for Delta Descriptors and 2% AUC for SeqSLAM; while drastically reducing the deployment time from around 1 hour to 1 minute against both. The framework code and video are available at https://mchancan.github.io/deepseqslam

In the Internet-of-Things (IoT) systems, there are plenty of informative data provided by a massive number of IoT devices (e.g., sensors). Learning a function from such data is of great interest in machine learning tasks for IoT systems. Focusing on streaming (or sequential) data, we present a privacy-preserving distributed online learning framework with multiplekernels (named DOMKL). The proposed DOMKL is devised by leveraging the principles of an online alternating direction of multipliers (OADMM) and a distributed Hedge algorithm. We theoretically prove that DOMKL over T time slots can achieve an optimal sublinear regret, implying that every learned function achieves the performance of the best function in hindsight as in the state-of-the-art centralized online learning method. Moreover, it is ensured that the learned functions of any two neighboring learners have a negligible difference as T grows, i.e., the so-called consensus constraints hold. Via experimental tests with various real datasets, we verify the effectiveness of the proposed DOMKL on regression and time-series prediction tasks.

This paper proposes a dual-supervised uncertainty inference (DS-UI) framework for improving Bayesian estimation-based uncertainty inference (UI) in deep neural network (DNN)-based image recognition. In the DS-UI, we combine the classifier of a DNN, i.e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer. Unlike existing UI methods for DNNs, which only calculate the means or modes of the DNN outputs' distributions, the proposed MoGMM-FC layer acts as a probabilistic interpreter for the features that are inputs of the classifier to directly calculate the probability density of them for the DS-UI. In addition, we propose a dual-supervised stochastic gradient-based variational Bayes (DS-SGVB) algorithm for the MoGMM-FC layer optimization. Unlike conventional SGVB and optimization algorithms in other UI methods, the DS-SGVB not only models the samples in the specific class for each Gaussian mixture model (GMM) in the MoGMM, but also considers the negative samples from other classes for the GMM to reduce the intra-class distances and enlarge the inter-class margins simultaneously for enhancing the learning ability of the MoGMM-FC layer in the DS-UI. Experimental results show the DS-UI outperforms the state-of-the-art UI methods in misclassification detection. We further evaluate the DS-UI in open-set out-of-domain/-distribution detection and find statistically significant improvements. Visualizations of the feature spaces demonstrate the superiority of the DS-UI.

A model involving Gaussian processes (GPs) is introduced to simultaneously handle multi-task learning, clustering, and prediction for multiple functional data. This procedure acts as a model-based clustering method for functional data as well as a learning step for subsequent predictions for new tasks. The model is instantiated as a mixture of multi-task GPs with common mean processes. A variational EM algorithm is derived for dealing with the optimisation of the hyper-parameters along with the hyper-posteriors' estimation of latent variables and processes. We establish explicit formulas for integrating the mean processes and the latent clustering variables within a predictive distribution, accounting for uncertainty on both aspects. This distribution is defined as a mixture of cluster-specific GP predictions, which enhances the performances when dealing with group-structured data. The model handles irregular grid of observations and offers different hypotheses on the covariance structure for sharing additional information across tasks. The performances on both clustering and prediction tasks are assessed through various simulated scenarios and real datasets. The overall algorithm, called MagmaClust, is publicly available as an R package.

Ride Vision, an Israeli startup that is building an AI-driven safety system to prevent motorcycle collisions, today announced that it has raised a $7 million Series A round led by crowdsourcing platform OurCrowd. YL Ventures, which typically specializes in cybersecurity startups but also led the company's $2.5 million seed round in 2018, Mobilion VC and motorcycle mirror manufacturer Metagal also participated in this round. The company has now raised a total of $10 million. In addition to this new funding round, Ride Vision also today announced a new partnership with automotive parts manufacturer Continental . "As motorcycle enthusiasts, we at Ride Vision are excited at the prospect of our international launch and our partnership with Continental," Uri Lavi, CEO and co-founder of Ride Vision, said in today's announcement.

Playing video games could have a positive impact on a person's wellbeing, scientists at the University of Oxford have claimed. Researchers at the Oxford Internet Institute accessed the data of two games, Plants vs Zombies: Battle for Neighborville and Animal Crossing: New Horizons, in order to investigate the relationship between game play behaviour and mental health. The scientists, who worked with Electronic Arts and Nintendo of America, found that players experiencing genuine enjoyment from the games saw an improvement in their mental health. Professor Andrew Przybylski, lead author of the study and director of research at the Oxford Internet Institute, said the findings show'video games aren't necessarily bad for your health' and there are other psychological factors which have a significant effect on a person's wellbeing. Scientists at the University of Oxford found that the players experiencing genuine enjoyment from the games experienced a more positive wellbeing.

From a well-timed recyclable PPE glove to a wheel-based device to cut "invisible" pollution from tyres, 20 groundbreaking designs by students across the world are in the running to be named on Thursday as the international winner of the annual James Dyson award. The prestigious accolade brings with it a £30,000 cash prize – and gives winners a chance to turn their innovation into a commercial product with real-world impact. One in five previous winners have gone on to commercialise a wide range of exotic inventions, including bionic arms, origami-style clothing and bio-reactive food labels. For this year's award, a record 1,798 entries have been submitted – two-thirds more than last year – with a majority addressing urgent global issues such as climate change, sustainability, medicine and healthcare. This year's entries opened in March amid the deepening coronavirus pandemic.

Recent advances in commonsense reasoning depend on large-scale human-annotated training data to achieve peak performance. However, manual curation of training examples is expensive and has been shown to introduce annotation artifacts that neural models can readily exploit and overfit on. We investigate G-DAUG^C, a novel generative data augmentation method that aims to achieve more accurate and robust learning in the low-resource setting. Our approach generates synthetic examples using pretrained language models, and selects the most informative and diverse set of examples for data augmentation. In experiments with multiple commonsense reasoning benchmarks, G-DAUG^C consistently outperforms existing data augmentation methods based on back-translation, and establishes a new state-of-the-art on WinoGrande, CODAH, and CommonsenseQA. Further, in addition to improvements in in-distribution accuracy, G-DAUG^C-augmented training also enhances out-of-distribution generalization, showing greater robustness against adversarial or perturbed examples. Our analysis demonstrates that G-DAUG^C produces a diverse set of fluent training examples, and that its selection and training approaches are important for performance. Our findings encourage future research toward generative data augmentation to enhance both in-distribution learning and out-of-distribution generalization.

In this paper, we propose a rule-based engine composed of high quality and interpretable regular expressions for medical text classification. The regular expressions are auto generated by a constructive heuristic method and optimized using a Pool-based Simulated Annealing (PSA) approach. Although existing Deep Neural Network (DNN) methods present high quality performance in most Natural Language Processing (NLP) applications, the solutions are regarded as uninterpretable black boxes to humans. Therefore, rule-based methods are often introduced when interpretable solutions are needed, especially in the medical field. However, the construction of regular expressions can be extremely labor-intensive for large data sets. This research aims to reduce the manual efforts while maintaining high-quality solutions