Biblio

This turorial offers a rich blend of theory and practice regarding dimensionality reduction methods, to address the information overload problem in recommender systems. This problem affects our everyday experience while searching for knowledge on a topic. Naive Collaborative Filtering cannot deal with challenging issues such as scalability, noise, and sparsity. We can deal with all the aforementioned challenges by applying matrix and tensor decomposition methods. These methods have been proven to be the most accurate (i.e., Netflix prize) and efficient for handling big data. For each method (SVD, SVD++, timeSVD++, HOSVD, CUR, etc.) we will provide a detailed theoretical mathematical background and a step-by-step analysis, by using an integrated toy example, which runs throughout all parts of the tutorial, helping the audience to understand clearly the differences among factorisation methods.

User modeling of individual users on the Social Web platforms such as Twitter plays a significant role in providing personalized recommendations and filtering interesting information from social streams. Recently, researchers proposed the use of concepts (e.g., DBpedia entities) for representing user interests instead of word-based approaches, since Knowledge Bases such as DBpedia provide cross-domain background knowledge about concepts, and thus can be used for extending user interest profiles. Even so, not all concepts can be covered by a Knowledge Base, especially in the case of microblogging platforms such as Twitter where new concepts/topics emerge everyday. In this short paper, instead of using concepts alone, we propose using synsets from WordNet and concepts from DBpedia for representing user interests. We evaluate our proposed user modeling strategies by comparing them with other bag-of-concepts approaches. The results show that using synsets and concepts together for representing user interests improves the quality of user modeling significantly in the context of link recommendations on Twitter.

The Wikidata platform is a crowdsourced, structured knowledgebase aiming to provide integrated, free and language-agnostic facts which are–-amongst others–-used by Wikipedias. Users who actively enter, review and revise data on Wikidata are assisted by a property suggesting system which provides users with properties that might also be applicable to a given item. We argue that evaluating and subsequently improving this recommendation mechanism and hence, assisting users, can directly contribute to an even more integrated, consistent and extensive knowledge base serving a huge variety of applications. However, the quality and usefulness of such recommendations has not been evaluated yet. In this work, we provide the first evaluation of different approaches aiming to provide users with property recommendations in the process of curating information on Wikidata. We compare the approach currently facilitated on Wikidata with two state-of-the-art recommendation approaches stemming from the field of RDF recommender systems and collaborative information systems. Further, we also evaluate hybrid recommender systems combining these approaches. Our evaluations show that the current recommendation algorithm works well in regards to recall and precision, reaching a recall@7 of 79.71% and a precision@7 of 27.97%. We also find that generally, incorporating contextual as well as classifying information into the computation of property recommendations can further improve its performance significantly.

The Netflix experience is driven by a number of recommendation algorithms: personalized ranking, page generation, similarity, ratings, search, etc. On the January 6th, 2016 we simultaneously launched Netflix in 130 new countries around the world, which brought the total to over 190 countries. Preparing for such a rapid expansion while ensuring each algorithm was ready to work seamlessly created new challenges for our recommendation and search teams. In this talk, we will highlight the four most interesting challenges we encountered in making our algorithms operate globally and how this improved our ability to connect members worldwide with stories they'll love. In particular, we will dive into the problems of uneven availability across catalogs, balancing personal and cultural tastes, handling language, and tracking quality of recommendations. Uneven catalog availability is a challenge because many recommendation algorithms assume that people could interact with any item and then use the absence of interaction implicitly or explicitly as negative information in the model. However, this assumption does not hold globally and across time where item availability differs. Running algorithms globally means needing a notion of location so that we can handle local variations in taste while also providing a good basis for personalization. Language is another challenge in recommending video content because people can typically only enjoy content that has assets (audio, subtitles) in languages they understand. The preferences for how people enjoy such content also vary between people and depend on their familiarity with a language. Also, while would like our recommendations to work well for every one of our members, tracking quality becomes difficult because with so many members in so many countries speaking so many languages, it can be hard to determine when an algorithm or system is performing sub-optimally for some subset of them. Thus, to support this global launch, we examined each and every algorithm that is part of our service and began to address these challenges.

Recommender systems must find items that match the heterogeneous preferences of its users. Customizable recommenders allow users to directly manipulate the system's algorithm in order to help it match those preferences. However, customizing may demand a certain degree of skill and new users particularly may struggle to effectively customize the system. In user studies of two different systems, I show that there is considerable heterogeneity in the way that new users will try to customize a recommender, even within groups of users with similar underlying preferences. Furthermore, I show that this heterogeneity persists beyond the first few interactions with the recommender. System designs should consider this heterogeneity so that new users can both receive good recommendations in their early interactions as well as learn how to effectively customize the system for their preferences.

Providing a global understanding of privacy is crucial, because everything is connected. Nowadays companies are providing their customers with more services that will give them more access to their data and daily activity; electricity companies are marketing the new smart meters as a new service with great benefit to reduce the electricity usage by monitoring the electricity reading in real time. Although the users might benefit from this extra service, it will compromise the privacy of the users by having constant access to the readings. Since the smart meters will provide the users with real electricity readings, they will be able to decide and identify which devices are consuming energy in that specific moment and how much it will cost. This kind of information can be exploited by numerous types of people. Unauthorized use of this information is an invasion of privacy and may lead to much more severe consequences. This paper will propose an algorithm approach for the comparison and analysis of Smart Meter data readings, considering the time and temperature factors at each second to identify the use patterns at each house by identifying the appliances activities at each second in time complexity O(log(m)).

The paper focuses on one of the methods of designing a highly-automated hardware-software complex aimed at controlling the security of power grids and units that support both central heating and power systems of smart cities. We understand this condition as a situation when any energy consumers of smart cities will be provided with necessary for their living amounts of energy and fuel at any time, including possible periods of techno genic and natural hazards. Two main scientific principles lie in the base of the approach introduced. The first one is diversification of risks of energy security of smart cities by rational choosing the different energy generation sources ratio for fuel-energy balance of a smart city, including large fuel electric power plants and small power autonomous generators. For example, they can be wind energy machinery of sun collectors, heat pipes, etc. The second principle is energy efficiency and energy saving of smart cities. In our case this principle is realized by the high level of automation of monitoring and operation of security status of energy systems and complexes that provide the consumers of smart cities with heat, hot water and electricity, as well as by preventive alert of possible emergencies and high reliability of functioning of all energy facilities. We formulate the main principle governing the construction of a smart hardware-software complex used to maintain a highly-automated control over risks connected with functioning of both power sources and transmission grids. This principle is for open block architecture, including highly autonomous block-modules of primary registration of measuring information, data analysis and systems of automated operation. It also describes general IT-tools used to control the risks of supplying smart cities with energy and shows the structure of a highly-automated system designed to select technological and managerial solutions for a smart city's energy supply system.

Event discovery from single pictures is a challenging problem that has raised significant interest in the last decade. During this time, a number of interesting solutions have been proposed to tackle event discovery in still images. However, a large scale benchmarking image dataset for the evaluation and comparison of event discovery algorithms from single images is still lagging behind. To this aim, in this paper we provide a large-scale properly annotated and balanced dataset of 490,000 images, covering every aspect of 14 different types of social events, selected among the most shared ones in the social network. Such a large scale collection of event-related images is intended to become a powerful support tool for the research community in multimedia analysis by providing a common benchmark for training, testing, validation and comparison of existing and novel algorithms. In this paper, we provide a detailed description of how the dataset is collected, organized and how it can be beneficial for the researchers in the multimedia analysis domain. Moreover, a deep learning based approach is introduced into event discovery from single images as one of the possible applications of this dataset with a belief that deep learning can prove to be a breakthrough also in this research area. By providing this dataset, we hope to gather research community in the multimedia and signal processing domains to advance this application.

In most adaptive video streaming systems adaptation decisions rely solely on the available network resources. As the content of a video has a large influence on the perception of quality our belief is that this is not sufficient. Thus, we have proposed a support service for content-aware video adaptation on mobile devices: Video Adaptation Service (VAS). Based on the content of a streamed video, the adaptation process is improved by setting a target quality level for a session based on an objective video quality metric. In this work, we demonstrate VAS and its advantages of a reduced data traffic by only streaming the lowest video representation which is necessary to reach a desired quality. By leveraging the content properties of a video stream, the system is able to keep a stable video quality and at the same time reduce the network load.

TCP congestion control has been known for its crucial role in stabilizing the Internet and preventing congestion collapses. However, with the rapid advancement in networking technologies, resulting in the emergence of challenging network environments such as data center networks (DCNs), the traditional TCP algorithm leads to several impairments. The shortcomings of TCP when deployed in DCNs have motivated the development of multiple new variants, including DCTCP, ICTCP, IA-TCP, and D2TCP, but all of these algorithms exhibit their advantages at the cost of a number of drawbacks in the Global Internet. Motivated by the belief that new innovations need to be established on top of a solid foundation with a thorough understanding of the existing, well-established algorithms, we have been working towards a comprehensive analysis of various conventional TCP algorithms in DCNs and other modern networks. This paper presents our first milestone towards the completion of our comparative study in which we present the results obtained by simulating multiple TCP variants: NewReno, Vegas, HighSpeed, Scalable, Westwood+, BIC, CUBIC, and YeAH using a fat tree architecture. Each protocol is evaluated in terms of queue length, number of dropped packets, average packet delay, and aggregate bandwidth as a percentage of the channel bandwidth.

We address the problem of stabilizing control for complex queueing systems with known parameters but unobservable Markovian random environment. In such systems, the controller needs to assign servers to queues without having full information about the servers' states. A control challenge is to devise a policy that matches servers to queues in a way that takes state estimates into account. Maximally attainable stability regions are non-trivial. To handle these situations, we model the system under given decision rules. The model is using Quasi-Birth-and-Death (QBD) structure to find a matrix analytic expression for the stability bound. We use this formulation to illustrate how the stability region grows as the number of controller belief states increases.

IP tracking and cloaking are practices for identifying users which are used legitimately by websites to provide services and content tailored to particular users. However, it is believed that these practices are also used by malicious websites to avoid detection by anti-virus companies crawling the web to find malware. In addition, malicious websites are also believed to use IP tracking in order to deliver targeted malware based upon a history of previous visits by users. In this paper we empirically investigate these beliefs and collect a large dataset of suspicious URLs in order to identify at what level IP tracking takes place that is at the level of an individual address or at the level of their network provider or organisation (Network tracking). Our results illustrate that IP tracking is used in a small subset of domains within our dataset while no strong indication of network tracking was observed.

Large scale sensor networks are ubiquitous nowadays. An important objective of deploying sensors is to detect anomalies in the monitored system or infrastructure, which allows remedial measures to be taken to prevent failures, inefficiencies, and security breaches. Most existing sensor anomaly detection methods are local, i.e., they do not capture the global dependency structure of the sensors, nor do they perform well in the presence of missing or erroneous data. In this paper, we propose an anomaly detection technique for large scale sensor data that leverages relationships between sensors to improve robustness even when data is missing or erroneous. We develop a probabilistic graphical model-based global outlier detection technique that represents a sensor network as a pairwise Markov Random Field and uses graphical model inference to detect anomalies. We show our model is more robust than local models, and detects anomalies with 90% accuracy even when 50% of sensors are erroneous. We also build a synthetic graphical model generator that preserves statistical properties of a real data set to test our outlier detection technique at scale.

The speech emotion recognition accuracy of prosody feature and voice quality feature declines with the decrease of SNR (Signal to Noise Ratio) of speech signals. In this paper, we propose novel sub-band spectral centroid weighted wavelet packet cepstral coefficients (W-WPCC) for robust speech emotion recognition. The W-WPCC feature is computed by combining the sub-band energies with sub-band spectral centroids via a weighting scheme to generate noise-robust acoustic features. And Deep Belief Networks (DBNs) are artificial neural networks having more than one hidden layer, which are first pre-trained layer by layer and then fine-tuned using back propagation algorithm. The well-trained deep neural networks are capable of modeling complex and non-linear features of input training data and can better predict the probability distribution over classification labels. We extracted prosody feature, voice quality features and wavelet packet cepstral coefficients (WPCC) from the speech signals to combine with W-WPCC and fused them by Deep Belief Networks (DBNs). Experimental results on Berlin emotional speech database show that the proposed fused feature with W-WPCC is more suitable in speech emotion recognition under noisy conditions than other acoustics features and proposed DBNs feature learning structure combined with W-WPCC improve emotion recognition performance over the conventional emotion recognition method.

Heart rate monitoring has become increasingly popular in the industry through mobile phones and wearable devices. However, current determination of heart rate through mobile applications suffers from high corruption of signals during intensive physical exercise. In this paper, we present a novel technique for accurately determining heart rate during intensive motion by classifying PPG signals obtained from smartphones or wearable devices combined with motion data obtained from accelerometer sensors. Our approach utilizes the Internet of Things (IoT) cloud connectivity of smartphones for selection of PPG signals using deep learning. The technique is validated using the TROIKA dataset and is accurately able to predict heart rate with a 10-fold cross validation error margin of 4.88%.

This paper proposes a method for segmentation of nuclei of single/isolated and overlapping/touching immature white blood cells from microscopic images of B-Lineage acute lymphoblastic leukemia (ALL) prepared from peripheral blood and bone marrow aspirate. We propose deep belief network approach for the segmentation of these nuclei. Simulation results and comparison with some of the existing methods demonstrate the efficacy of the proposed method.

Abnormality detection is useful in reducing the amount of data to be processed manually by directing attention to the specific portion of data. However, selections of suitable features are important for the success of an abnormality detection system. Designing and selecting appropriate features are time-consuming, requires expensive domain knowledge and human labor. Further, it is very challenging to represent high-level concepts of abnormality in terms of raw input. Most of the existing abnormality detection system use handcrafted feature detector and are based on shallow architecture. In this work, we explore Deep Belief Network for abnormality detection and simultaneously, compared the performance of classic neural network in terms of features learned and accuracy of detecting the abnormality. Further, we explore the set of features learn by each layer of the deep architecture. We also provide a simple and fast mechanism to visualize the feature at the higher layer. Further, the effect of different activation function on abnormality detection is also compared. We observed that deep learning based approach can be used for detecting an abnormality. It has better performance compare to classical neural network in separating distinct as well as almost similar data.

In ad-hoc networks, data messages are transmitted from a source wireless node to a destination one along a wireless multihop transmission route consisting of a sequence of intermediate wireless nodes. Each intermediate wireless node forwards data messages to its next-hop wireless node. Here, a wireless signal carrying the data message is broadcasted by using an omni antenna and it is not difficult for a eavesdropper wireless node to overhear the wireless signal to get the data message. Some researches show that it is useful to transmit noise wireless signal which collide to the data message wireless signal in order for interfering the overhearing. However, some special devices such as directional antennas and/or high computation power for complicated signal processing are required. For wireless multihop networks with huge number of wireless nodes, small and cheap wireless nodes are mandatory for construction of the network. This paper proposes the method for interfering the overhearing by the eavesdropper wireless nodes where routing protocol and data message transmission protocol with cooperative noise signal transmissions by 1-hop and 2-hop neighbor wireless nodes of each intermediate wireless node.

With the rising interest of expedient, safe, and high-efficient transportation, vehicular ad hoc networks (VANETs) have turned into a critical technology in smart transportation systems. Because of the high mobility of nodes, VANETs are vulnerable to security attacks. In this paper, we propose a novel framework of software-defined VANETs with trust management. Specifically, we separate the forwarding plane in VANETs from the control plane, which is responsible for the control functionality, such as routing protocols and trust management in VANETs. Using the on-demand distance vector routing (TAODV) protocol as an example, we present a routing protocol named software-defined trust based ad hoc on-demand distance vector routing (SD-TAODV). Simulation results are presented to show the effectiveness of the proposed software-defined VANETs with trust management.

Drones have quickly become ubiquitous for both recreational and serious use. As is frequently the case with new technology in general, their rapid adoption already far exceeds our legal, policy, and social ability to cope with such issues as privacy and interference with well-established commercial and military air space. While the FAA has issued rulings, they will almost certainly be challenged in court as disputes arise, for example, when property owners shoot drones down. It is clear that drones will provide a critical role in smart cities and be connected to, if not directly a part of the IoT (Internet of Things). Drones will provide an essential role in providing network relay connectivity and situational awareness, particularly in disaster assessment and recovery scenarios. As is typical for new network technologies, the deployment of the drone hardware far exceeds our research in protocols – extending our previous understanding of MANETs (mobile ad hoc networks) and DTNs (disruption tolerant networks) – and more importantly, management, control, resilience, security, and privacy concerns. This keynote address will discuss these challenges and consider future research directions.

We propose a distributed and adaptive trust evaluation algorithm (DATEA) to calculate the trust between nodes. First, calculate the communication trust by using the number of data packets between nodes, and predict the trust based on the trend of this value, calculate the comprehensive trust by combining the history trust with the predict value; calculate the energy trust based on the residual energy of nodes; calculate the direct trust by using the communication trust and energy trust. Second, calculate the recommendation trust based on the recommendation reliability and the recommendation familiarity; put forward the adaptively weighting method, and calculate the integrate direct trust by combining the direct trust with recommendation trust. Third, according to the integrate direct trust, considering the factor of trust propagation distance, the indirect trust between nodes is calculated. Simulation experiments show that the proposed algorithm can effectively avoid the attacks of malicious nodes, besides, the calculated direct trust and indirect trust about normal nodes are more conformable to the actual situation.

Mobile Ad Hoc Network (MANET) is a multi-hop temporary and autonomic network comprised of a set of mobile nodes. MANETs have the features of non-center, dynamically changing topology, multi-hop routing, mobile nodes, limited resources and so on, which make it face more threats. Trust evaluation is used to support nodes to cooperate in a secure and trustworthy way through evaluating the trust of participating nodes in MANETs. However, many trust evaluation models proposed for MANETs still have many problems and shortcomings. In this paper, we review the existing researches, then analyze and compare the proposed trust evaluation models by presenting and applying uniform criteria in order to point out a number of open issues and challenges and suggest future research trends.

In this paper, we investigate the impact of information-theoretic secrecy constraint on the capacity and delay of mobile ad hoc networks (MANETs) with mobile legitimate nodes and static eavesdroppers whose location and channel state information (CSI) are both unknown. We assume n legitimate nodes move according to the fast i.i.d. mobility pattern and each desires to communicate with one randomly selected destination node. There are also nv static eavesdroppers located uniformly in the network and we assume the number of eavesdroppers is much larger than that of legitimate nodes, i.e., v textgreater 1. We propose a novel simple secure communication model, i.e., the secure protocol model, and prove its equivalence to the widely accepted secure physical model under a few technical assumptions. Based on the proposed model, a framework of analyzing the secrecy capacity and delay in MANETs is established. Given a delay constraint D, we find that the optimal secrecy throughput capacity is [EQUATION](W((D/n))(2/3), where W is the data rate of each link. We observe that: 1) the capacity-delay tradeoff is independent of the number of eavesdroppers, which indicates that adding more eavesdroppers will not degenerate the performance of the legitimate network as long as v textgreater 1; 2) the capacity-delay tradeoff of our paper outperforms the previous result Θ((1/nψe)) in [11], where ψe = nv–1 = ω(1) is the density of the eavesdroppers. Throughout this paper, for functions f(n) and G(n), we denote f(n) = o(g(n)) if limn→∞ (f(n)/g(n)) = 0; f(n) = ω(g(n)) if g(n) = o(f(n)); f(n) = O(g(n)) if there is a positive constant c such that f(n) ≤ cg(n) for sufficiently large n; f(n) = Ω(g(n))if g(n) = O(f(n)); f(n) = Θ(g(n) if both f(n) = O(g(n)) and f(n) = Omega;(g(n)) hold. Besides, the order notation [EQUATION] omits the polylogarithmic factors for better readability.

A Mobile Ad hoc Network (MANET) is a spontaneous network consisting of wireless nodes which are mobile and self-configuring in nature. Devices in MANET can move freely in any direction independently and change its link frequently to other devices. MANET does not have centralized infrastructure and its characteristics makes this network vulnerable to various kinds of attacks. Data transfer is a major problem due to its nature of unreliable wireless medium. Commonly used technique for secure transmission in wireless network is cryptography. Use of cryptography key is often involved in most of cryptographic techniques. Key management is main component in security issues of MANET and various schemes have been proposed for it. In this paper, a study on various kinds of key management techniques in MANET is presented.

We propose a formalism to model database-driven systems, called database manipulating systems (DMS). The actions of a (DMS) modify the current instance of a relational database by adding new elements into the database, deleting tuples from the relations and adding tuples to the relations. The elements which are modified by an action are chosen by (full) first-order queries. (DMS) is a highly expressive model and can be thought of as a succinct representation of an infinite state relational transition system, in line with similar models proposed in the literature. We propose monadic second order logic (MSO-FO) to reason about sequences of database instances appearing along a run. Unsurprisingly, the linear-time model checking problem of (DMS) against (MSO-FO) is undecidable. Towards decidability, we propose under-approximate model checking of (DMS), where the under-approximation parameter is the "bound on recency". In a k-recency-bounded run, only the most recent k elements in the current active domain may be modified by an action. More runs can be verified by increasing the bound on recency. Our main result shows that recency-bounded model checking of (DMS) against (MSO-FO) is decidable, by a reduction to the satisfiability problem of MSO over nested words.