These devices, particularly the smart mobile phones have transformed over a period of time from merely communication tools to smart and highly personal devices enabling to assist the users in their variety of day-to-day situations in their daily life. In the real word, users' interest on "Mobile Phones" is more and more than other platforms like "Desktop Computer" or "Tablet Computer" over time [36]. People use mobile phones not only for voice communication between individuals but also for various activities such as applications (mobile apps) using, Internet browsing, emailing, using online social network, instant messaging etc [28]. Recent advances in the sensing capabilities of smart mobile phones make them enable to collect the rich contextual information and users' various activity records with mobile phones through the device logs. These historical mobile phone data are simply as the collection of the past contexts and user's activities with the mobile phones for these past contexts. These are phone call logs [39] having phone call activities, app usages logs [45] having various mobile application usages, mobile phone notification logs [22] having the responses with various notifications from different applications, web logs [13] having Internet browsing activities of the mobile phone users. The main characteristic of such kind of phone log data is that it contains the actual diverse activities of the users in different contexts in their real world life. Modeling smartphone user behaviors by developing various computational machine learning methods (rule-based learning) in order to analyze different behavioral patterns in different contexts, and eventually predict the next behaviors or detect strange behaviors utilizing such mobile phone data, can be used for build- 2 Iqbal H. Sarker*

A fundamental problem in geophysical modeling is related to the identification and approximation of causal structures among physical processes. However, resolving the bidirectional mappings between physical parameters and model state variables (i.e., solving the forward and inverse problems) is challenging, especially when parameter dimensionality is high. Deep learning has opened a new door toward knowledge representation and complex pattern identification. In particular, the recently introduced generative adversarial networks (GANs) hold strong promises in learning cross-domain mappings for image translation. This study presents a state-parameter identification GAN (SPID-GAN) for simultaneously learning bidirectional mappings between a high-dimensional parameter space and the corresponding model state space. SPID-GAN is demonstrated using a series of representative problems from subsurface flow modeling. Results show that SPID-GAN achieves satisfactory performance in identifying the bidirectional state-parameter mappings, providing a new deep-learning-based, knowledge representation paradigm for a wide array of complex geophysical problems.

Many applications of machine learning and optimization operate on data streams. While these datasets are fundamental to fuel decision-making algorithms, often they contain sensitive information about individuals and their usage poses significant privacy risks. Motivated by an application in energy systems, this paper presents OPTSTREAM, a novel algorithm for releasing differentially private data streams under the w-event model of privacy. OPTSTREAM is a 4-step procedure consisting of sampling, perturbation, reconstruction, and post-processing modules. First, the sampling module selects a small set of points to access in each period of interest. Then, the perturbation module adds noise to the sampled data points to guarantee privacy. Next, the reconstruction module reassembles non-sampled data points from the perturbed sample points. Finally, the post-processing module uses convex optimization over the private output of the previous modules, as well as the private answers of additional queries on the data stream, to improve accuracy by redistributing the added noise. OPTSTREAM is evaluated on a test case involving the release of a real data stream from the largest European transmission operator. Experimental results show that OPTSTREAM may not only improve the accuracy of state-of-the-art methods by at least one order of magnitude but also supports accurate load forecasting on the private data.

Machine learning models are capable of capturing the structure-property relationship from a dataset of computationally demanding ab initio calculations. In fact, machine learning models have reached chemical accuracy on small organic molecules contained in the popular QM9 dataset. At the same time, the domain of large crystal structures remains rather unexplored. Over the past two years, the Organic Materials Database (OMDB) has hosted a growing number of electronic properties of previously synthesized organic crystal structures. The complexity of the organic crystals contained within the OMDB, which have on average 85 atoms per unit cell, makes this database a challenging platform for machine learning applications. In this paper, we focus on predicting the band gap which represents one of the basic properties of a crystalline material. With this aim, we release a consistent dataset of 12500 crystal structures and their corresponding DFT band gap freely available for download at https://omdb.diracmaterials.org/dataset. We run two recent machine learning models, kernel ridge regression with the Smooth Overlap of Atomic Positions (SOAP) kernel and the deep learning model SchNet, on this new dataset and find that an ensemble of these two models reaches mean absolute error (MAE) of 0.361 eV, which corresponds to a percentage error of 12% on the average band gap of 3.03 eV. The models also provide chemical insights into the data. For example, by visualizing the SOAP kernel similarity between the crystals, different clusters of materials can be identified, such as organic metals or semiconductors. Finally, the trained models are employed to predict the band gap for 260092 materials contained within the Crystallography Open Database (COD) and made available online so the predictions can be obtained for any arbitrary crystal structure uploaded by a user.

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document vocabulary mismatches. While neural retrieval models have recently demonstrated strong results for ad-hoc retrieval, combining them with PRF is not straightforward due to incompatibilities between existing PRF approaches and neural architectures. To bridge this gap, we propose an end-to-end neural PRF framework that can be used with existing neural IR models by embedding different neural models as building blocks. Extensive experiments on two standard test collections confirm the effectiveness of the proposed NPRF framework in improving the performance of two state-of-the-art neural IR models.

ABSTRACT The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference process, while their parallel versions are difficult to train and even more expensive computationally. Meanwhile, generative adversarial networks (GANs) have achieved impressive results in image generation and are making their way into audio applications; parallel inference is among their lucrative properties. Listening test results show that while direct waveform generation with GAN is still far behind WaveNet, a GAN-based glottal excitation model can achieve quality and voice similarity on par with a WaveNet vocoder. Index Terms-- Neural vocoding, text-to-speech, GAN, glottal excitation model 1. INTRODUCTION Recent advances in deep learning have led to text-to-speech (TTS) systems achieving near-human naturalness [1]. This is partially due to neural sequence-to-sequence mapping methods that can learn to align and map between input text and output acoustic feature sequences [2].

We approach the development of models and control strategies of susceptible-infected-susceptible (SIS) epidemic processes from the perspective of marked temporal point processes and stochastic optimal control of stochastic differential equations (SDEs) with jumps. In contrast to previous work, this novel perspective is particularly well-suited to make use of fine-grained data about disease outbreaks, and it lets us overcome the shortcomings of current control strategies. Our control strategy resorts to treatment intensities to determine who to treat and when to do so, to minimize the amount of infected individuals over time. Preliminary experiments with synthetic data show that our control strategy consistently outperforms several alternatives. Looking into the future, we believe our methodology provides a promising step towards the development of practical data-driven control strategies of epidemic processes.

Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made solely based on the observed behavior of a user during an ongoing session. Given the high practical relevance of the problem, an increased interest in this problem can be observed in recent years, leading to a number of proposals for session-based recommendation algorithms that typically aim to predict the user's immediate next actions. In this work, we present the results of an in-depth performance comparison of a number of such algorithms, using a variety of datasets and evaluation measures. Our comparison includes the most recent approaches based on recurrent neural networks like GRU4REC, factorized Markov model approaches such as FISM or FOSSIL, as well as simpler methods based, e.g., on nearest neighbor schemes. Our experiments reveal that algorithms of this latter class, despite their sometimes almost trivial nature, often perform equally well or significantly better than today's more complex approaches based on deep neural networks. Our results therefore suggest that there is substantial room for improvement regarding the development of more sophisticated session-based recommendation algorithms.

TRANSFERABLE POSITIVE/NEGATIVE SPEECH EMOTION RECOGNITION VIA CLASS-WISE ADVERSARIAL DOMAIN ADAPTATION Hao Zhou, Ke Chen School of Computer Science, The University of Manchester, Manchester, M13 9PL, U.K. ABSTRACT Speech emotion recognition plays an important role in building more intelligent and humanlike agents. Due to the difficulty of collecting speech emotional data, an increasingly popular solution is leveraging a related and rich source corpus to help address the target corpus. However, domain shift between the corpora poses a serious challenge, making domain shift adaptation difficult to function even on the recognition of positive/negative emotions. In this work, we propose class-wise adversarial domain adaptation to address this challenge by reducing the shift for all classes between different corpora. Experiments on the well-known corpora EMODB and Aibo demonstrate that our method is effective even when only a very limited number of target labeled examples are provided.

Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differing length. We propose a modification to DTW that performs individual and independent pairwise alignment of feature trajectories. The modified technique, termed feature trajectory dynamic time warping (FTDTW), is applied as a similarity measure in the agglomerative hierarchical clustering of speech segments. Experiments using MFCC and PLP parametrisations extracted from TIMIT and from the Spoken Arabic Digit Dataset (SADD) show consistent and statistically significant improvements in the quality of the resulting clusters in terms of F-measure and normalised mutual information (NMI).