Life's most valuable asset is health. Continuously understanding the state of our health and modeling how it evolves is essential if we wish to improve it. Given the opportunity that people live with more data about their life today than any other time in history, the challenge rests in interweaving this data with the growing body of knowledge to compute and model the health state of an individual continually. This dissertation presents an approach to build a personal model and dynamically estimate the health state of an individual by fusing multi-modal data and domain knowledge. The system is stitched together from four essential abstraction elements: 1. the events in our life, 2. the layers of our biological systems (from molecular to an organism), 3. the functional utilities that arise from biological underpinnings, and 4. how we interact with these utilities in the reality of daily life. Connecting these four elements via graph network blocks forms the backbone by which we instantiate a digital twin of an individual. Edges and nodes in this graph structure are then regularly updated with learning techniques as data is continuously digested. Experiments demonstrate the use of dense and heterogeneous real-world data from a variety of personal and environmental sensors to monitor individual cardiovascular health state. State estimation and individual modeling is the fundamental basis to depart from disease-oriented approaches to a total health continuum paradigm. Precision in predicting health requires understanding state trajectory. By encasing this estimation within a navigational approach, a systematic guidance framework can plan actions to transition a current state towards a desired one. This work concludes by presenting this framework of combining the health state and personal graph model to perpetually plan and assist us in living life towards our goals.

"Focusing on your strengths is required for peak performance, but improving your weaknesses has the potential for the greatest gains. This is true for athletes, executives and entire companies." As parents, we get to see our kids growing, trying, falling and learning in the process. First steps, first words, first drawings leave us amazed. As our children become adults, they continue to learn, choose a career and become athletes, surgeons, plane pilots, journalists, teachers… and we're proud.

Microsoft launched on Tuesday, February 18, the first artificial intelligence laboratory at the Bucharest Academy of Economic Studies (ASE), one of the largest economic higher education institutes in Romania. In the new lab, which required an investment of EUR 50,000, the students can find more about machine learning, create and test AI algorithms, store and manage huge volumes of data, or develop applications and platforms themselves, local Republica.ro As of March 3, 11 cloud engineers from Microsoft Romania will hold courses aimed at helping students develop both technical and business innovation skills. The first course to be held in the new cloud lab will focus on the latest innovations in information technology using Azure, Microsoft's cloud computing platform. The next courses will focus on artificial intelligence, and the ASE students will be encouraged to develop their own projects.

The current methodology in tackling Acoustic Scene Classification (ASC) task can be described in two steps, preprocessing of the audio waveform into log-mel spectrogram and then using it as the input representation for Convolutional Neural Network (CNN). This paradigm shift occurs after DCASE 2016 where this framework model achieves the state-of-the-art result in ASC tasks on the (ESC-50) dataset and achieved an accuracy of 64.5%, which constitute to 20.5% improvement over the baseline model, and DCASE 2016 dataset with an accuracy of 90.0% (development) and 86.2% (evaluation), which constitute a 6.4% and 9% improvements with respect to the baseline system. In this paper, we explored the use of harmonic and percussive source separation (HPSS) to split the audio into harmonic audio and percussive audio, which has received popularity in the field of music information retrieval (MIR). Although works have been done in using HPSS as input representation for CNN model in ASC task, this paper further investigate the possibility on leveraging the separated harmonic component and percussive component by curating 2 CNNs which tries to understand harmonic audio and percussive audio in their natural form, one specialized in extracting deep features in time biased domain and another specialized in extracting deep features in frequency biased domain, respectively. The deep features extracted from these 2 CNNs will then be combined using bilinear pooling. Hence, presenting a two-stream time and frequency CNN architecture approach in classifying acoustic scene. The model is being evaluated on DCASE 2019 sub task 1a dataset and scored an average of 65% on development dataset, Kaggle Leadership Private and Public board.

In order to classify linearly non-separable data, neurons are typically organized into multi-layer neural networks that are equipped with at least one hidden layer. Inspired by some recent discoveries in neuroscience, we propose a new neuron model along with a novel activation function enabling learning of non-linear decision boundaries using a single neuron. We show that a standard neuron followed by the novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. Furthermore, we conduct experiments on three benchmark data sets from computer vision and natural language processing, i.e. Fashion-MNIST, UTKFace and MOROCO, showing that the ADA and the leaky ADA functions provide superior results to Rectified Liner Units (ReLU) and leaky ReLU, for various neural network architectures, e.g. 1-hidden layer or 2-hidden layers multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs) such as LeNet, VGG, ResNet and Character-level CNN. We also obtain further improvements when we change the standard model of the neuron with our pyramidal neuron with apical dendrite activations (PyNADA).

In this paper, we propose a deep learning approach for smartphone user identification based on analyzing motion signals recorded by the accelerometer and the gyroscope, during a single tap gesture performed by the user on the screen. We transform the discrete 3-axis signals from the motion sensors into a gray-scale image representation which is provided as input to a convolutional neural network (CNN) that is pre-trained for multi-class user classification. In the pre-training stage, we benefit from different users and multiple samples per user. After pre-training, we use our CNN as feature extractor, generating an embedding associated to each single tap on the screen. The resulting embeddings are used to train a Support Vector Machines (SVM) model in a few-shot user identification setting, i.e. requiring only 20 taps on the screen during the registration phase. We compare our identification system based on CNN features with two baseline systems, one that employs handcrafted features and another that employs recurrent neural network (RNN) features. All systems are based on the same classifier, namely SVM. To pre-train the CNN and the RNN models for multi-class user classification, we use a different set of users than the set used for few-shot user identification, ensuring a realistic scenario. The empirical results demonstrate that our CNN model yields a top accuracy of 89.75% in multi-class user classification and a top accuracy of 96.72% in few-shot user identification. In conclusion, we believe that our system is ready for practical use, having a better generalization capacity than both baselines.

In late September, Beijing unveiled to the world Daxing, a glimmering $11 billion airport showcasing technologies such as robots and facial recognition scanners that many other airports worldwide are either adopting or are now considering. Daxing fits the description of what experts hail as a "smart airport." Just as a smart home is where internet-connected devices control functions like security and thermostats, smart airports use cloud-based technologies to simplify and improve services. Of course, many of the nearly 4,000 scheduled service airports across the world are still embarrassingly antiquated. The good news for aviation is that more facilities are investing, finally, to better serve airlines, suppliers, and travelers. This year, airports worldwide will spend $11.8 billion -- 68 percent more than the level three years ago -- on information technology, according to an estimate published this month by SITA (Société Internationale de Telecommunications Aeronautiques, an airline-owned tech provider). A few trends are driving the rise of smart airports. Flight volumes are increasing, so airports need better ways to process flyers. Airports need better ways to make money, too, by encouraging passengers to spend more in their shops and restaurants. Data is growing in importance. Everything happening at an airport, from where passengers are flowing to which items are selling in stores, generates data. Airports can analyze this data to spot opportunities for eking out fatter profits. They can sell the data to third-parties as well.

The goal of query performance prediction (QPP) is to automatically estimate the effectiveness of a search result for any given query, without relevance judgements. Post-retrieval features have been shown to be more effective for this task while being more expensive to compute than pre-retrieval features. Combining multiple post-retrieval features is even more effective, but state-of-the-art QPP methods are impossible to interpret because of the black-box nature of the employed machine learning models. However, interpretation is useful for understanding the predictive model and providing more answers about its behavior. Moreover, combining many post-retrieval features is not applicable to real-world cases, since the query running time is of utter importance. In this paper, we investigate a new framework for feature selection in which the trained model explains well the prediction. We introduce a step-wise (forward and backward) model selection approach where different subsets of query features are used to fit different models from which the system selects the best one. We evaluate our approach on four TREC collections using standard QPP features. We also develop two QPP features to address the issue of query-drift in the query feedback setting. We found that: (1) our model based on a limited number of selected features is as good as more complex models for QPP and better than non-selective models; (2) our model is more efficient than complex models during inference time since it requires fewer features; (3) the predictive model is readable and understandable; and (4) one of our new QPP features is consistently selected across different collections, proving its usefulness.

It is an open directory of AI ecosystem activities, stakeholder information and more that shall foster collaboration between AI practitioners worldwide, provide access to those interested in becoming active in the field of AI, and drive local and global AI agenda development via the necessary input from the grassroots AI community. As of now, we're having 26 cities from already 6 continents unlocked, roughly 500 upcoming events to join, over 1,000 active community groups to engage with, tens of local AI influencers to follow and almost 1,000 startups to discover. The past year, we've seen various ambassadors using the information to bring together local AI stakeholders such as Meetup organizers and other community actors, AI startup founders, data scientists and machine learning engineers from various organziations, AI-related initiative founders and governmental/municipality representatives discussing to develop (a) their local AI ecosystem further and (b) an aligned AI agenda. Our new director Valentina Colombo joined us to facilitate ambassadors and the AI community leveraging the AI Ecosystem Wiki in even more ways. Expect regular newsletters on the global AI ecosystem, progress benchmarks and reports, local AI ecosystem regulars, AI Council support and much more.

Safe Cities conference is happening now, in #Bucharest. Here are three ideas from this insightful event: "Gen Z could represent 20% of the workforce by 2020." City admistrators need to think out of the box in order to attract and retain Gen Z. KEY POINT: Data is the main FUEL for the cities of the future. This was such a great opportunity to have Romania on the map of #Dell #Safe Cities world tour.