Personality traits are increasingly being incorporated in systems to provide a personalized experience to the user. Current work focusing on identifying the relationship between personality and behavior, preferences, ...
详细信息
Paraphrase evaluation is used to determine whether two input sentences share a same meaning. The automatic analysis for paraphrase evaluation technology has a potential use in the area of information retrieval technol...
详细信息
Learning the influence structure of multiple time series data is of great interest to many disciplines. This paper studies the problem of recovering the causal structure in network of multivariate linear Hawkes proces...
详细信息
ISBN:
(纸本)9781510827806
Learning the influence structure of multiple time series data is of great interest to many disciplines. This paper studies the problem of recovering the causal structure in network of multivariate linear Hawkes processes. In such processes, the occurrence of an event in one process affects the probability of occurrence of new events in some other processes. Thus, a natural notion of causality exists between such processes captured by the support of the excitation matrix. We show that the resulting causal influence network is equivalent to the Directed Information graph (DIG) of the processes, which encodes the causal factorization of the joint distribution of the processes. Furthermore, we present an algorithm for learning the support of excitation matrix of a class of multivariate Hawkes processes with exponential exciting functions (or equivalently the DIG). The performance of the algorithm is evaluated on synthesized multivariate Hawkes networks as well as a stock market and MemeTracker real-world dataset.
SNOLA is a Thematic Network of Excellence recognized by the Spanish Ministry of Economy and Competitiveness composed of the main Spanish researchers in the field of learning analytics. This network emerged in 2013 foc...
详细信息
Nano devices have great potential to play a vital role in future medical diagnostics and treatment technologies because of its non-invasive nature and ability to reach delicate body sites easily as compared to convent...
详细信息
In this paper, an approach to detect stator winding short-circuit faults in squirrel-cage induction motors based on Random Forest and Park's Vector is proposed. This is accomplished by scoring the unbalance in the...
详细信息
ISBN:
(纸本)9781509042821
In this paper, an approach to detect stator winding short-circuit faults in squirrel-cage induction motors based on Random Forest and Park's Vector is proposed. This is accomplished by scoring the unbalance in the current and voltage waveforms as well as in Park's Vector, both for current and voltage. To score the unbalance in the d-q space, a Principal Component Analysis is applied to Park's Vector and with the first two principal components the eccentricity is calculated, while the first principal component is used to determine the phase in short-circuit. The proposed strategy has been experimentally tested on a special 400-V, 50-Hz, 4-pole, 2.2-kW induction motor with reconfigurable stator windings in which it was possible to emulate different types of inter-turn short-circuits. The results are quite promising, even only using 1-kHz sampling frequency to acquire the current and voltage waveforms in the three phases, and the use of the Fast Fourier Transform is avoided. The developed solution may be used for tele-monitoring of the motor condition and to implement advanced predictive maintenance strategies.
Interoperability is one of crucial Internet-related research domains. Today, there is a shift in the architecture of the Internet and the traditional communication model; the human part in machine communication is blu...
详细信息
Interoperability is one of crucial Internet-related research domains. Today, there is a shift in the architecture of the Internet and the traditional communication model; the human part in machine communication is blurring into a more sophisticated thing-to-thing communication model. In this model things search for other things and provide collaboration-base services, this way leading to more complex interaction issues. Especially, interoperability must transcend the use of protocols and include semantic to make the different building blocks of the Internet of Things (IoT) work together and exploit the maximum of it. Hence, we present our vision and concept of a multilayer model for IoT infrastructure to: abstract the data sources infrastructure, define filtering and formatting mechanisms, and to present pertinent data in the form of simple unitary or aggregation of multiple services.
Privacy, trust and confidentiality are the main issues of sensor layer in Internet of Things (IOT). In sensor layer, the sensing information must be transmitted from sensor node to gather node by multiple hopping. Eve...
详细信息
ISBN:
(纸本)9781509024629
Privacy, trust and confidentiality are the main issues of sensor layer in Internet of Things (IOT). In sensor layer, the sensing information must be transmitted from sensor node to gather node by multiple hopping. Every sensor node will be the sender and the relay node to forward the sensing information sent by other nodes. In this paper, BS embeds S+1 secret into the keys that are derived from the real identity of sensor node, to be as the private secret keys for every sensor node. One of the secret is the common secret that is owned by all sensor nodes, the rest S secretes are the random secret used for making mutual trust. Based on the secret index set and private secret keys, we propose a mutual trust method to explore the trust types and the pairing value among the sensor nodes without any negotiating process. To deny the right of malicious nodes to make trust with other nodes, we involve a group key to hash the secret index set to do making trust and pairing value mutually. Based on the trust types and the pairing values, the sensor nodes can set a secure path to deliver the sensing information to base station.
Indoor positioning often requires detecting and recognizing ad-hoc landmarks or anchor points with known coordinates and/or a given orientation within a given reference frame. Typically, the available kind of sensors ...
详细信息
ISBN:
(纸本)9781509024261
Indoor positioning often requires detecting and recognizing ad-hoc landmarks or anchor points with known coordinates and/or a given orientation within a given reference frame. Typically, the available kind of sensors and their detection area determine the landmark features and position. Of course, an excessive use of landmarks pose serious scalability and cost issues, whereas, on the other hand, a too-low amount of dep.oyed landmarks may create areas where agent's position is hard to track or localization accuracy drops. In addition, often sensors are not omni-directional. In this paper, the optimal placement problem of landmarks detected by sensors with a limited detection area is addressed in the general case of wide-open, ideally unbounded, rooms. First, landmarks placement optimization is performed numerically. Then, a closed-form expression of the optimal distance between landmarks on a regular pattern is determined as a function of both the reading range and the directional properties of the sensor considered. Finally, the performances of the chosen placement strategy in more realistic indoor environments (i.e. consisting of multiple rooms with obstacles therein) are evaluated through simulations assuming, without loss of generality, that a wheeled robot equipped with a front camera adjusts its own position by detecting suitable visual landmarks.
暂无评论