Abstract: Noise estimation is essential in today wireless systems
for power control, adaptive modulation, interference suppression and
quality of service. Deep learning (DL) has already been applied in the
physical layer for modulation and signal classifications. Unacceptably
low accuracy of less than 50% is found to undermine traditional
application of DL classification for SNR prediction. In this paper,
we use divide-and-conquer algorithm and classifier fusion method
to simplify SNR classification and therefore enhances DL learning
and prediction. Specifically, multiple CNNs are used for classification
rather than a single CNN. Each CNN performs a binary classification
of a single SNR with two labels: less than, greater than or equal.
Together, multiple CNNs are combined to effectively classify over a
range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained
CNNs to predict SNR over a wide range of joint channel parameters
including multiple Doppler shifts (0, 60, 120 Hz), power-delay
profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The
approach achieves individual SNR prediction accuracy of 92%,
composite accuracy of 70% and prediction convergence one order
of magnitude faster than that of traditional estimation.
Abstract: Cold-start is a notoriously difficult problem which
can occur in recommendation systems, and arises when there is
insufficient information to draw inferences for users or items. To
address this challenge, a contextual bandit algorithm – the Fast
Approximate Bayesian Contextual Cold Start Learning algorithm
(FAB-COST) – is proposed, which is designed to provide improved
accuracy compared to the traditionally used Laplace approximation
in the logistic contextual bandit, while controlling both algorithmic
complexity and computational cost. To this end, FAB-COST uses
a combination of two moment projection variational methods:
Expectation Propagation (EP), which performs well at the cold
start, but becomes slow as the amount of data increases; and
Assumed Density Filtering (ADF), which has slower growth of
computational cost with data size but requires more data to obtain an
acceptable level of accuracy. By switching from EP to ADF when
the dataset becomes large, it is able to exploit their complementary
strengths. The empirical justification for FAB-COST is presented, and
systematically compared to other approaches on simulated data. In a
benchmark against the Laplace approximation on real data consisting
of over 670, 000 impressions from autotrader.co.uk, FAB-COST
demonstrates at one point increase of over 16% in user clicks. On
the basis of these results, it is argued that FAB-COST is likely to
be an attractive approach to cold-start recommendation systems in a
variety of contexts.
Abstract: The management of COVID-19 patients based on chest imaging is emerging as an essential tool for evaluating the spread of the pandemic which has gripped the global community. It has already been used to monitor the situation of COVID-19 patients who have issues in respiratory status. There has been increase to use chest imaging for medical triage of patients who are showing moderate-severe clinical COVID-19 features, this is due to the fast dispersal of the pandemic to all continents and communities. This article demonstrates the development of machine learning techniques for the test of COVID-19 patients using Chest X-Ray (CXR) images in nearly real-time, to distinguish the COVID-19 infection with a significantly high level of accuracy. The testing performance has covered a combination of different datasets of CXR images of positive COVID-19 patients, patients with viral and bacterial infections, also, people with a clear chest. The proposed AI scheme successfully distinguishes CXR scans of COVID-19 infected patients from CXR scans of viral and bacterial based pneumonia as well as normal cases with an average accuracy of 94.43%, sensitivity 95%, and specificity 93.86%. Predicted decisions would be supported by visual evidence to help clinicians speed up the initial assessment process of new suspected cases, especially in a resource-constrained environment.
Abstract: In order to electronically exchange information between network users in the web of data, different software such as outlook is presented. So, the traffic of users on a site or even the floors of a building can be decreased as a result of applying a secure and reliable data sharing software. It is essential to provide a fast, secure and reliable network system in the data sharing webs to create an advanced communication systems in the users of network. In the present research work, different encoding methods and algorithms in data sharing systems is studied in order to increase security of data sharing systems by preventing the access of hackers to the transferred data. To increase security in the networks, the possibility of textual conversation between customers of a local network is studied. Application of the encryption and decryption algorithms is studied in order to increase security in networks by preventing hackers from infiltrating. As a result, a reliable and secure communication system between members of a network can be provided by preventing additional traffic in the website environment in order to increase speed, accuracy and security in the network and web systems of data sharing.
Abstract: Syringe pumps are commonly used for drug delivery in hospitals and clinical environments. These instruments are critical in neonatology and oncology, where any variation in the flow rate and drug dosing quantity can lead to severe incidents and even death of the patient. Therefore it is very important to determine the accuracy and precision of these devices using the suitable calibration methods. The Volume Laboratory of the Portuguese Institute for Quality (LVC/IPQ) uses two different methods to calibrate syringe pumps from 16 nL/min up to 20 mL/min. The Interferometric method uses an interferometer to monitor the distance travelled by a pusher block of the syringe pump in order to determine the flow rate. Therefore, knowing the internal diameter of the syringe with very high precision, the travelled distance, and the time needed for that travelled distance, it was possible to calculate the flow rate of the fluid inside the syringe and its uncertainty. As an alternative to the gravimetric and the interferometric method, a methodology based on the application of optical technology was also developed to measure flow rates. Mainly this method relies on measuring the increase of volume of a drop over time. The objective of this work is to compare the results of the calibration of two syringe pumps using the different methodologies described above. The obtained results were consistent for the three methods used. The uncertainties values were very similar for all the three methods, being higher for the optical drop method due to setup limitations.
Abstract: Nowadays, data center industry faces strong challenges for increasing the speed and data processing capacities while at the same time is trying to keep their devices a suitable working temperature without penalizing that capacity. Consequently, the cooling systems of this kind of facilities use a large amount of energy to dissipate the heat generated inside the servers, and developing new cooling techniques or perfecting those already existing would be a great advance in this type of industry. The installation of a temperature sensor matrix distributed in the structure of each server would provide the necessary information for collecting the required data for obtaining a temperature profile instantly inside them. However, the number of temperature probes required to obtain the temperature profiles with sufficient accuracy is very high and expensive. Therefore, other less intrusive techniques are employed where each point that characterizes the server temperature profile is obtained by solving differential equations through simulation methods, simplifying data collection techniques but increasing the time to obtain results. In order to reduce these calculation times, complicated and slow computational fluid dynamics simulations are replaced by simpler and faster finite element method simulations which solve the Burgers‘ equations by backward, forward and central discretization techniques after simplifying the energy and enthalpy conservation differential equations. The discretization methods employed for solving the first and second order derivatives of the obtained Burgers‘ equation after these simplifications are the key for obtaining results with greater or lesser accuracy regardless of the characteristic truncation error.
Abstract: In this paper, we describe how to achieve knowledge understanding and prediction (Situation Awareness (SA)) for multiple-agents conducting searching activity using Bayesian inferential reasoning and learning. Bayesian Belief Network was used to monitor agents' knowledge about their environment, and cases are recorded for the network training using expectation-maximisation or gradient descent algorithm. The well trained network will be used for decision making and environmental situation prediction. Forest fire searching by multiple UAVs was the use case. UAVs are tasked to explore a forest and find a fire for urgent actions by the fire wardens. The paper focused on two problems: (i) effective agents’ path planning strategy and (ii) knowledge understanding and prediction (SA). The path planning problem by inspiring animal mode of foraging using Lévy distribution augmented with Bayesian reasoning was fully described in this paper. Results proof that the Lévy flight strategy performs better than the previous fixed-pattern (e.g., parallel sweeps) approaches in terms of energy and time utilisation. We also introduced a waypoint assessment strategy called k-previous waypoints assessment. It improves the performance of the ordinary levy flight by saving agent’s resources and mission time through redundant search avoidance. The agents (UAVs) are to report their mission knowledge at the central server for interpretation and prediction purposes. Bayesian reasoning and learning were used for the SA and results proof effectiveness in different environments scenario in terms of prediction and effective knowledge representation. The prediction accuracy was measured using learning error rate, logarithm loss, and Brier score and the result proves that little agents mission that can be used for prediction within the same or different environment. Finally, we described a situation-based knowledge visualization and prediction technique for heterogeneous multi-UAV mission. While this paper proves linkage of Bayesian reasoning and learning with SA and effective searching strategy, future works is focusing on simplifying the architecture.
Abstract: In this study, a multivariate analysis of potato spectroscopic data was presented to detect the presence of brown rot disease or not. Near-Infrared (NIR) spectroscopy (1,350-2,500 nm) combined with multivariate analysis was used as a rapid, non-destructive technique for the detection of brown rot disease in potatoes. Spectral measurements were performed in 565 samples, which were chosen randomly at the infection place in the potato slice. In this study, 254 infected and 311 uninfected (brown rot-free) samples were analyzed using different advanced statistical analysis techniques. The discrimination performance of different multivariate analysis techniques, including classification, pre-processing, and dimension reduction, were compared. Applying a random forest algorithm classifier with different pre-processing techniques to raw spectra had the best performance as the total classification accuracy of 98.7% was achieved in discriminating infected potatoes from control.
Abstract: With rapid development of urbanization and improvement of living standards in the world, energy consumption and carbon emissions of the building sector are expected to increase in the near future; because of that, energy-saving issues have become more important among the engineers. Besides, the building sector is a major contributor to energy consumption and carbon emissions. The concept of efficient building appeared as a response to the need for reducing energy demand in this sector which has the main purpose of shifting from standard buildings to low-energy buildings. Although energy-saving should happen in all steps of a building during the life cycle (material production, construction, demolition), the main concept of efficient energy building is saving energy during the life expectancy of a building by using passive and active systems, and should not sacrifice comfort and quality to reach these goals. The main aim of this study is to investigate passive strategies (do not need energy consumption or use renewable energy) to achieve energy-efficient buildings. Energy retrofit measures were explored by eQuest software using a case study as a base model. The study investigates predictive accuracy for the major factors like thermal transmittance (U-value) of the material, windows, shading devices, thermal insulation, rate of the exposed envelope, window/wall ration, lighting system in the energy consumption of the building. The base model was located in Istanbul, Turkey. The impact of eight passive parameters on energy consumption had been indicated. After analyzing the base model by eQuest, a final scenario was suggested which had a good energy performance. The results showed a decrease in the U-values of materials, the rate of exposing buildings, and windows had a significant effect on energy consumption. Finally, savings in electric consumption of about 10.5%, and gas consumption by about 8.37% in the suggested model were achieved annually.
Abstract: Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.
Abstract: With the development of optical communication, optical performance monitoring (OPM) has received more and more attentions. Since optical signal-to-noise ratio (OSNR) is directly related to bit error rate (BER), it is one of the important parameters in optical networks. Recently, artificial neural network (ANN) has been greatly developed. ANN has strong learning and generalization ability. In this paper, a method of OSNR monitoring based on delay-tap sampling (DTS) and ANN has been proposed. DTS technique is used to extract the eigenvalues of the signal. Then, the eigenvalues are input into the ANN to realize the OSNR monitoring. The experiments of 10 Gb/s non-return-to-zero (NRZ) on–off keying (OOK), 20 Gb/s pulse amplitude modulation (PAM4) and 20 Gb/s return-to-zero (RZ) differential phase-shift keying (DPSK) systems are demonstrated for the OSNR monitoring based on the proposed method. The experimental results show that the range of OSNR monitoring is from 15 to 30 dB and the root-mean-square errors (RMSEs) for 10 Gb/s NRZ-OOK, 20 Gb/s PAM4 and 20 Gb/s RZ-DPSK systems are 0.36 dB, 0.45 dB and 0.48 dB respectively. The impact of chromatic dispersion (CD) on the accuracy of OSNR monitoring is also investigated in the three experimental systems mentioned above.
Abstract: The objective of this study was to determine the effects of environmental stressors on the performance of lactating dairy cows and discuss some future trends. There exists a relationship between the meteorological data and milk yield prediction accuracy in pasture-based dairy systems. New precision technologies are available and are being developed to improve the sustainability of the dairy industry. Some of these technologies focus on welfare of individual animals on dairy farms. These technologies allow the automatic identification of animal behaviour and health events, greatly increasing overall herd health and yield while reducing animal health inspection demands and long-term animal healthcare costs. The data set consisted of records from 489 dairy cows at two dairy farms and temperature measured from the nearest meteorological weather station in 2018. The effects of temperature on milk production and behaviour of animals were analyzed. The statistical results indicate different effects of temperature on milk yield and behaviour. The “comfort zone” for animals is in the range 10 °C to 20 °C. Dairy cows out of this zone had to decrease or increase their metabolic heat production, and it affected their milk production and behaviour.
Abstract: This paper presents and benchmarks a number of
end-to-end Deep Learning based models for metaphor detection in
Greek. We combine Convolutional Neural Networks and Recurrent
Neural Networks with representation learning to bear on the metaphor
detection problem for the Greek language. The models presented
achieve exceptional accuracy scores, significantly improving the
previous state-of-the-art results, which had already achieved accuracy
0.82. Furthermore, no special preprocessing, feature engineering or
linguistic knowledge is used in this work. The methods presented
achieve accuracy of 0.92 and F-score 0.92 with Convolutional
Neural Networks (CNNs) and bidirectional Long Short Term Memory
networks (LSTMs). Comparable results of 0.91 accuracy and 0.91
F-score are also achieved with bidirectional Gated Recurrent Units
(GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The
models are trained and evaluated only on the basis of training tuples,
the related sentences and their labels. The outcome is a state-of-the-art
collection of metaphor detection models, trained on limited labelled
resources, which can be extended to other languages and similar
tasks.
Abstract: Machine learning (ML) can be implemented in Wireless Sensor Networks (WSNs) as a central solution or distributed solution where the ML is embedded in the nodes. Embedding improves privacy and may reduce prediction delay. In addition, the number of transmissions is reduced. However, quality factors such as prediction accuracy, fault detection efficiency and coordinated control of the overall system suffer. Here, we discuss and highlight the trade-offs that should be considered when choosing between embedding and centralized ML, especially for multihop networks. In addition, we present estimations that demonstrate the energy trade-offs between embedded and centralized ML. Although the total network energy consumption is lower with central prediction, it makes the network more prone for partitioning due to the high forwarding load on the one-hop nodes. Moreover, the continuous improvements in the number of operations per joule for embedded devices will move the energy balance toward embedded prediction.
Abstract: To improve the satisfaction of residents' travel, this paper analyzes the characteristics and influencing factors of urban residents' travel behavior. First, a Multinominal Logit Model (MNL) model is built to analyze the characteristics of residents' travel behavior, reveal the influence of individual attributes, family attributes and travel characteristics on the choice of travel mode, and identify the significant factors. Then put forward suggestions for policy improvement. Finally, Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) models are introduced to evaluate the policy effect. This paper selects Futian Street in Futian District, Shenzhen City for investigation and research. The results show that gender, age, education, income, number of cars owned, travel purpose, departure time, journey time, travel distance and times all have a significant influence on residents' choice of travel mode. Based on the above results, two policy improvement suggestions are put forward from reducing public transportation and non-motor vehicle travel time, and the policy effect is evaluated. Before the evaluation, the prediction effect of MNL, SVM and MLP models was evaluated. After parameter optimization, it was found that the prediction accuracy of the three models was 72.80%, 71.42%, and 76.42%, respectively. The MLP model with the highest prediction accuracy was selected to evaluate the effect of policy improvement. The results showed that after the implementation of the policy, the proportion of public transportation in plan 1 and plan 2 increased by 14.04% and 9.86%, respectively, while the proportion of private cars decreased by 3.47% and 2.54%, respectively. The proportion of car trips decreased obviously, while the proportion of public transport trips increased. It can be considered that the measures have a positive effect on promoting green trips and improving the satisfaction of urban residents, and can provide a reference for relevant departments to formulate transportation policies.
Abstract: Customer relationship analysis is vital for retail stores, especially for supermarkets. The point of sale (POS) systems make it possible to record the daily purchasing behaviors of customers as an identification point of sale (ID-POS) database, which can be used to analyze customer behaviors of a supermarket. The customer value is an indicator based on ID-POS database for detecting the customer loyalty of a store. In general, there are many supermarkets in a city, and other nearby competitor supermarkets significantly affect the customer value of customers of a supermarket. However, it is impossible to get detailed ID-POS databases of competitor supermarkets. This study firstly focused on the customer value and distance between a customer's home and supermarkets in a city, and then constructed the models based on logistic regression analysis to analyze correlations between distance and purchasing behaviors only from a POS database of a supermarket chain. During the modeling process, there are three primary problems existed, including the incomparable problem of customer values, the multicollinearity problem among customer value and distance data, and the number of valid partial regression coefficients. The improved customer value, Huff’s gravity model, and inverse attractiveness frequency are considered to solve these problems. This paper presents three types of models based on these three methods for loyal customer classification and competitors’ influence analysis. In numerical experiments, all types of models are useful for loyal customer classification. The type of model, including all three methods, is the most superior one for evaluating the influence of the other nearby supermarkets on customers' purchasing of a supermarket chain from the viewpoint of valid partial regression coefficients and accuracy.
Abstract: This paper discusses the idea of capturing an expert’s knowledge in the form of human understandable rules and then inserting these rules into a dynamic cell structure (DCS) neural network. The DCS is a form of self-organizing map that can be used for many purposes, including classification and prediction. This particular neural network is considered to be a topology preserving network that starts with no pre-structure, but assumes a structure once trained. The DCS has been used in mission and safety-critical applications, including adaptive flight control and health-monitoring in aerial vehicles. The approach is to insert expert knowledge into the DCS before training. Rules are translated into a pre-structure and then training data are presented. This idea has been demonstrated using the well-known Iris data set and it has been shown that inserting the pre-structure results in better accuracy with the same training.
Abstract: Currently, extensive signal analysis is performed in order to evaluate structural health of turbomachinery blades. This approach is affected by constraints of time and the availability of qualified personnel. Thus, new approaches to blade dynamics identification that provide faster and more accurate results are sought after. Generally, modal analysis is employed in acquiring dynamic properties of a vibrating turbomachinery blade and is widely adopted in condition monitoring of blades. The analysis provides useful information on the different modes of vibration and natural frequencies by exploring different shapes that can be taken up during vibration since all mode shapes have their corresponding natural frequencies. Experimental modal testing and finite element analysis are the traditional methods used to evaluate mode shapes with limited application to real live scenario to facilitate a robust condition monitoring scheme. For a real time mode shape evaluation, rapid evaluation and low computational cost is required and traditional techniques are unsuitable. In this study, artificial neural network is developed to evaluate the mode shape of a lab scale rotating blade assembly by using result from finite element modal analysis as training data. The network performance evaluation shows that artificial neural network (ANN) is capable of mapping the correlation between natural frequencies and mode shapes. This is achieved without the need of extensive signal analysis. The approach offers advantage from the perspective that the network is able to classify mode shapes and can be employed in real time including simplicity in implementation and accuracy of the prediction. The work paves the way for further development of robust condition monitoring system that incorporates real time mode shape evaluation.
Abstract: Acoustic Emission (AE) is one of the most effective non-destructive tests that can be used to detect the defect process as it is occurring. AE techniques can be used to monitor a wide range of structures and materials such as metals, non-metals and combinations of these when load is applied. The current work investigates the effectiveness and accuracy of TOA method in AE tests involving reinforced composite concrete-mortar structures. A series of experimental tests were performed using the Hsu-Neilson (H-N) source to study 2-D location accuracy using this method on concrete-mortar (400×400 mm) specimens. Four AE sensors (R3I – resonant frequency 30 kHz) were mounted to the mortar surface and six sources were performed at each point of preselected locations on the upper surface of the mortar. Results show that the TOA method can be used effectively to locate signals on composite concrete/mortar specimen and has high accuracy.
Abstract: Modeling dam-break flows over non-flat beds requires
an accurate representation of the topography which is the main
source of uncertainty in the model. Therefore, developing robust
and accurate techniques for reconstructing topography in this class
of problems would reduce the uncertainty in the flow system. In
many hydraulic applications, experimental techniques have been
widely used to measure the bed topography. In practice, experimental
work in hydraulics may be very demanding in both time and cost.
Meanwhile, computational hydraulics have served as an alternative
for laboratory and field experiments. Unlike the forward problem,
the inverse problem is used to identify the bed parameters from the
given experimental data. In this case, the shallow water equations
used for modeling the hydraulics need to be rearranged in a way
that the model parameters can be evaluated from measured data.
However, this approach is not always possible and it suffers from
stability restrictions. In the present work, we propose an adaptive
optimal control technique to numerically identify the underlying bed
topography from a given set of free-surface observation data. In this
approach, a minimization function is defined to iteratively determine
the model parameters. The proposed technique can be interpreted
as a fractional-stage scheme. In the first stage, the forward problem
is solved to determine the measurable parameters from known data.
In the second stage, the adaptive control Ensemble Kalman Filter is
implemented to combine the optimality of observation data in order to
obtain the accurate estimation of the topography. The main features
of this method are on one hand, the ability to solve for different
complex geometries with no need for any rearrangements in the
original model to rewrite it in an explicit form. On the other hand, its
achievement of strong stability for simulations of flows in different
regimes containing shocks or discontinuities over any geometry.
Numerical results are presented for a dam-break flow problem over
non-flat bed using different solvers for the shallow water equations.
The robustness of the proposed method is investigated using different
numbers of loops, sensitivity parameters, initial samples and location
of observations. The obtained results demonstrate high reliability and
accuracy of the proposed techniques.