In recent years, great progress has been made in the field of forecasting meteorological variables. Recently, deep learning architectures have made a major breakthrough in forecasting the daily average temperature over a ten-day horizon. However, advances in forecasting events related to the maximum temperature over short horizons remain a challenge for the community. A problem that is even more complex consists in making predictions of the maximum daily temperatures in the short, medium, and long term. In this work, we focus on forecasting events related to the maximum daily temperature over medium-term periods (90 days). Therefore, instead of addressing the problem from a meteorological point of view, this article tackles it from a climatological point of view. Due to the complexity of this problem, a common approach is to frame the study as a temporal classification problem with the classes: maximum temperature above normal, normal or below normal. From a practical point of view, we created a large historical dataset (from 1981 to 2018) collecting information from weather stations located in South America. In addition, we also integrated exogenous information from the Pacific, Atlantic, and Indian Ocean basins. We applied the AutoGluonTS platform to solve the above-mentioned problem. This AutoML tool shows competitive forecasting performance with respect to large operational platforms dedicated to tackling this climatological problem; but with a "relatively" low computational cost in terms of time and resources.

In this paper, we study the impact of data complexity and data quality in the overlapping community detection problem. We show that community detection algorithms are very unstable against incomplete or erroneous data, and this result is consistent with all the evaluated performance metrics. We verify it using three quality metrics (F1, NMI, and Omega) when the ground-truth community structure is known, in four very popular and representative detection algorithms: Order Statistics Local Optimization Method (OSLOM), Greedy Clique Expansion (GCE) algorithm, Speaker-listener Label Propagation Algorithm (SLPA), and Cluster Affiliation Model for Big Networks (BIG-CLAM). We evaluate it over a set of real instances that arise from detecting the courses that belong to different careers (degrees) of an engineering University, and over large benchmark sets of synthetic instances frequently used in the literature.

Word embeddings are widely used in natural language processing (NLP) to group semantically similar words but have been applied in other areas to find semantic similarity between entities. In this paper we create a vector embedding for Internet Domain Names (DNS) using a corpus of real anonymized DNS log queries from a large Internet Service Provider (ISP). We then use this embedding as a layer of a recurrent neural network (RNN) that works as a Language Model for the DNS queries generated by the users. We show that this RNN can be used to predict the next DNS query generated by a user with good accuracy (considering the size of the problem). Moreover, we show that training the same RNN without using the pre-trained vector model takes more time and is substantially less accurate. The results presented in this work can have practical applications in many engineering activities related to DNS architecture design. For example, latency reduction in address resolution, optimization of cache systems in recursive DNS servers, automatic filtering of inappropriate domains, and detecting anomalies in traffic.

Word embeddings is a well known set of techniques widely used in natural language processing (NLP), and word2vec is a computationally-efficient predictive model to learn such embeddings. This paper explores the use of word embeddings in a new scenario. We create a vector representation of Internet Domain Names (DNS) by taking the core ideas from NLP techniques and applying them to real anonymized DNS log queries from a large Internet Service Provider (ISP). Our main objective is to find semantically similar domains only using information of DNS queries without any other previous knowledge about the content of those domains. We use the word2vec unsupervised learning algorithm with a Skip-Gram model to create the embeddings. And we validate the quality of our results by expert visual inspection of similarities, and by comparing them with a third party source, namely, similar sites service offered by Alexa Internet, Inc.

Going to the cinema or watching television are social activities that generally take place in groups. In these cases, a recommender system for ephemeral groups of users is more suitable than (well-studied) recommender systems for individuals. In this paper we present a recommendation system for groups of users that go to the cinema. The system uses the Slope One algorithm for computing individual predictions and the Multiplicative Utilitarian Strategy as a model to recommend to an entire group. We show how we solved all practical aspects of the system; including its architecture and a mobile application for the service, the lack of user data (ramp-up and cold-start problems), the scaling fit of the group model strategy, and other improvements in order to reduce the response time. Finally, we validate the performance of the system with a set of experiments with 57 ephemeral groups.

We propose a mathematical model to minimize the expected download time of cloud assisted Peer-to-Peer video on demand services. First, we define a simple fluid model that quantifies the evolution of peers, which are grouped into different classes regarding the number of concurrent video downloads. Then, analytical expressions for the expected download time are obtained under steady state, via Little's law. The goal is to minimize the expected download time with limited storage capacity in cache nodes of the network, called super-peers. The nature of this combinatorial problem is similar to the Multi-Knapsack Problem (MKP): the number of copies must be chosen for each video stream, with storage capacity constraints. We resolve the problem with a greedy randomized technique. The performance of this co-operative system is compared with a traditional content delivery network. Finally, the new caching policy is tested in a real scenario. The results confirm that the swarm assisted peer-to-peer service is both more economical and suitable to address massive scenarios, whereas the performance of both systems is similar in small scale instances.

This paper presents the GoalBit Starter platform. GoalBit is an open source peer-to-peer distribution system of real-time video streams over Internet. The main advantage of a P2P architecture is the possibility of using available upload bandwidth in the hosts connected. The main difficulty is that these hosts are typically highly dynamic, they continuously enter and leave the network. To deal with this problem a mesh connectivity approach is used (Bittorrent-like) where the stream is decomposed into several pieces and shared between different peers. Nowadays, the GoalBit platform is used by operators and by final users to broadcast their live contents. To illustrate its potential, we present some empirical results measured in an emulation of a GoalBit P2P streaming, with more than 300 peers concurrently connected.

In this paper, we present an algorithm based on the GRASP meta-heuristic for solving a dynamic assignment problem in a P2P network designed for sending real-time video over the Internet. In a highly dynamic P2P topology, the frequent connections and disconnections of nodes are the main obstacle we face when trying to offer a high Quality-of-Experience (QoE) to clients. We first introduce the P2P network architecture where this node dynamics occurs. This architecture employs a multi-source streaming approach where the stream is decomposed into several flows sent by different peers to each client, including some level of redundancy, in order to cope with the fluctuations in network connectivity. Then, we present the GRASP-based algorithm developed in order to tackle the problem of maintaining connectivity in presence of node dynamics by periodically reassigning network connections; these assignments are performed so as to maximize the global expected QoE, calculated using the recently proposed PSQA methodology. Additionally, we provide a variation of the GRASP-based algorithm, based on the Random Neural Network model. Finally, we show the results obtained when these algorithms are applied to a case study based on real life data.

We consider the design of a P2P network for the distribution of real-time video streams through the Internet. We follow a multi-source approach where the stream is decomposed into several flows sent by different peers to each client. The goal is to resist to the frequent moves of the peers entering and leaving the network. We analyze our approach using the recently proposed PSQA technology which allows to obtain an accurate (and automatic) numerical evaluation of the quality as perceived by each client. Our transmission technique includes the use of an arbitrary amount of redundancy in the signal, whose specification is a part of the dimensioning process, and it works with very low signaling overhead. We illustrate with real data how the overall system allows to compensate efficiently the possible losses of frames due to peers leaving the network.

This paper explores a key aspect of the problem of sending real-time video over the Internet using a P2P architecture. The main difficulty with such a system is the high dynamics of the P2P topology, because of the frequent moves of the nodes leaving and entering the network. We consider a multi-source approach where the stream is decomposed into several flows sent by different peers to each client. Using the recently proposed PSQA technology for evaluating automatically and accurately the perceived quality at the client side, the paper focuses on the consequences of the way the stream is decomposed on the resulting quality. Our main contribution is to provide a global methodology that can be used to design such a system, illustrated by looking at three extreme cases. Our approach allows to do the design by addressing the ultimate target, the perceived quality (or Quality of Experience), instead of the standard but indirect metrics such as loss rates, delays, reliability, etc. We also propose an improved version of PSQA obtained by considering the video sequences at frame-level, instead of the packet-level approach of previous works.