Textual case based reasoning (TCBR) is a challenging problem because a single case may consist of different topics and complex linguistic terms. Many efforts have been made to enhance retrieval process in TCBR using c...
详细信息
ISBN:
(纸本)9783030311292;9783030311285
Textual case based reasoning (TCBR) is a challenging problem because a single case may consist of different topics and complex linguistic terms. Many efforts have been made to enhance retrieval process in TCBR using clustering methods. This paper proposes an enhanced clustering approach called GloSOPHIA (GloVe SOPHIA). It is based on extending SOPHIA by integrating word embeddings technique to enhance knowledge discovery in TCBR. To evaluate the quality of the proposed method, we will apply the GloSOPHIA to an Arabic newspaper corpus called watan-2004 and will compare the results with SOPHIA (SOPHisticated Information Analysis), K-means, and Self-Organizing Map (SOM) with different types of evaluation criteria. The results show that GloSOPHIA outperforms the 3 other clustering methods in most of the evaluation criteria.
This article aims to describe methods determining the intensity of movement activity while using a smart orthosis for the upper limbs. The methods proposed can be applied both in clinical practice and the home environ...
详细信息
ISBN:
(纸本)9783030299934;9783030299927
This article aims to describe methods determining the intensity of movement activity while using a smart orthosis for the upper limbs. The methods proposed can be applied both in clinical practice and the home environment. Kinematics data was quantified by evaluation methods of time domain data. These can determine the integral of the absolute value of total acceleration, kinetic energy of the segment in translational motion, mechanical power during a segment motion, and a geometric sum of three partial accelerations of three-dimensional motion. The method's applicability was tested by a comparison of the forearm and upper arm movement while the subjects performed various activities. Following on from the goal of method tested, the team applied it to a set of cyclic and non-cyclic movements commonly performed in a home environment. The study was conducted on twenty healthy participants. Four gyro-accelerometers to record the upper limb movement were attached to the subject's forearms and upper arms. The results of the calculated values for the proposed parameters revealed statistically significant differences depending on the physical activities monitored. The results also showed that the calculated values for the forearm and upper arm parameters correlate significantly. This is due to the concurrent similar movement of the segments with accelerometers during a particular physical activity. The proposed methods have proven their applicability for monitoring the intensity of motion during rehabilitation.
The paper presents an innovative model for consumer participation in electricity market based on IoT. The goal is to develop a new business model and the underlying IoT infrastructure to enable the participation of in...
详细信息
ISBN:
(纸本)9783030456870;9783030456887
The paper presents an innovative model for consumer participation in electricity market based on IoT. The goal is to develop a new business model and the underlying IoT infrastructure to enable the participation of individual household devices in smart grid services. The purpose of the proposed model is to allow for higher inclusion of renewable energy sources by providing cheap and flexible balancing services. The approach is based on the premise that consumers' attitudes towards green energy and environmental protection are important incentives for acceptance of the proposed model, and as such should be closely monitored during its development. The proposed model has been evaluated through the study of consumer' attitudes in the context of a smart grid in Serbia. The results show that consumers are interested in environmental conservation and are willing to participate in these new smart grid services.
Time Series (TS) clustering is one of the most effervescent research fields due to the Big Data and the IoT explosion. The problem gets more challenging if we consider the multivariate TS. In the field of Business and...
详细信息
ISBN:
(纸本)9783030200558;9783030200541
Time Series (TS) clustering is one of the most effervescent research fields due to the Big Data and the IoT explosion. The problem gets more challenging if we consider the multivariate TS. In the field of Business and Management, multivariate TS are becoming more and more interesting as they allow to match events the co-occur in time but that is hardly noticeable. In this study, Recurrent Neural Networks and transfer learning have been used to analyze each example, measuring similarities between variables. All the results are finally aggregated to create an adjacency matrix that allows extracting the groups. Proof-of-concept experimentation has been included, showing that the solution might be valid after several improvements.
The paper deals with the designing and implementation of a computer-aided system capable to detect seizures by classification of EEG records. The system is based on deep learning method using a recurrent long short-te...
详细信息
ISBN:
(纸本)9783030298852;9783030298845
The paper deals with the designing and implementation of a computer-aided system capable to detect seizures by classification of EEG records. The system is based on deep learning method using a recurrent long short-term memory neural network. The main purpose of the system is to help neurologists in detecting seizures fast and reliably. The research was carried out using real EEG recordings of epileptic patients as well as healthy subjects prepared with the cooperation of the medical staff of the Clinical Ward of Neurology of the University Hospital of Zielona Gora, Poland.
Analyses of human action forces is a standard function of current digital human models. However, research has been indicating that this feature needs to be improved as it lacks accuracy. Muscle-torque based modeling c...
详细信息
ISBN:
(纸本)9783030202163;9783030202156
Analyses of human action forces is a standard function of current digital human models. However, research has been indicating that this feature needs to be improved as it lacks accuracy. Muscle-torque based modeling can be used to calculate action forces. Because it is not efficient to measure torques in all spatial directions, different calculating approaches have been developed. The question is which one is the best to calculate action forces? In this paper, we will therefor explain four different calculations - a spherical, linear, independent and fluid approach. To compare their quality, a study based on 366 measurements of maximum torques has been conducted. Results show that the spherical approach predicts maximum muscle torques to about 1.7% accuracy. The fluid approach increases the accuracy significantly (R-2 0.9), but needs more input data. Hence, a mix using both approaches is proposed as the best solution to calculate action forces in digital human models.
In this paper, we propose a complete framework, namely Mercury, that combines Computer Vision and Deep Learning algorithms to continuously monitor the driver during the driving activity. The proposed solution complies...
详细信息
ISBN:
(纸本)9783030395124;9783030395117
In this paper, we propose a complete framework, namely Mercury, that combines Computer Vision and Deep Learning algorithms to continuously monitor the driver during the driving activity. The proposed solution complies to the requirements imposed by the challenging automotive context: the light invariance, in order to have a system able to work regardless of the time of day and the weather conditions. Therefore, infrared-based images, i.e. depth maps (in which each pixel corresponds to the distance between the sensor and that point in the scene), have been exploited in conjunction with traditional intensity images. Second, the non-invasivity of the system is required, since driver's movements must not be impeded during the driving activity: in this context, the use of cameras and vision-based algorithms is one of the best solutions. Finally, real-time performance is needed since a monitoring system must immediately react as soon as a situation of potential danger is detected.
This paper analyzes financial ratios of 27 consumer discretionary firms listed on the S&P 500 over an eleven-year period from 2006-2016. It adopts a two-step approach wherein first a confirmatory factor analysis (...
详细信息
ISBN:
(纸本)9783030196417;9783030196424
This paper analyzes financial ratios of 27 consumer discretionary firms listed on the S&P 500 over an eleven-year period from 2006-2016. It adopts a two-step approach wherein first a confirmatory factor analysis (CFA) on the financial time-series is conducted and the resulting constructs' scores are then used to perform a cluster analysis using self-organizing maps (SOMs). The consumer discretionary sector is considered an economic and stock market predictor. It consists of non-essential goods and services which in an economic slump are more likely to be foregone. The suggested approach is expected to be a useful reference guide to help understand the past performance of inter- and intra-sector companies. It also enriches the body of literature on the application of machine learning techniques to the analysis of firm- and sectoral-level performance.
We propose a one-dimensional blood flow model taking into account muscle pump, external contraction and autoregulation. This model is used to study two effects: blood flow during running and the impact of enhanced ext...
详细信息
ISBN:
(纸本)9783030350482;9783030350475
We propose a one-dimensional blood flow model taking into account muscle pump, external contraction and autoregulation. This model is used to study two effects: blood flow during running and the impact of enhanced external counterpulsation on the coronary blood flow on the basis of patient-specific data. On the basis of mathematical modelling we observe optimal stride frequency, which maximizes venous return.
This article presents the mechanisms for processing fuzzy expert estimates in network models for project management. The distribution of the probability function of the execution time is proposed. This function allows...
详细信息
ISBN:
(纸本)9783030264741
This article presents the mechanisms for processing fuzzy expert estimates in network models for project management. The distribution of the probability function of the execution time is proposed. This function allows us to build a beta-distribution of a random variable over the entire domain of its definition for a combination of approximate points and interval expert estimates. This article describes also the approximation of linguistic estimates by using fuzzy triangular and trapezoidal numbers. It is based on the construction of the membership function of a fuzzy triangular number, accounting for its scale. The proposed approach makes it possible to obtain more accurate prediction estimates for making informed decisions during informational uncertainty.
暂无评论