Search results for: BP neural network model

Authors: Hoyeon Park, Yunhwan Keon, Kyoung-Jae Kim

Abstract:

Location Based Social Network services (LBSNs) is a new term that combines location based service and social network service (SNS). Unlike traditional SNS, LBSNs emphasizes empirical elements in the user's actual physical location. Point-of-Interest (POI) is the most important factor to implement LBSNs recommendation system. POI information is the most popular spot in the area. In this study, we would like to recommend POI to users in a specific area through recommendation system using collaborative filtering. The process is as follows: first, we will use different data sets based on Seoul and New York to find interesting results on human behavior. Secondly, based on the location-based activity information obtained from the personalized LBSNs, we have devised a new rating that defines the user's preference for the area. Finally, we have developed an automated rating algorithm from massive raw data using distributed systems to reduce advertising costs of LBSNs.

Keywords: location-based social network services, point-of-interest, recommender systems, business analytics

Procedia PDF Downloads 229

Authors: Rafid A. Al-Khannak, Fawzi M. Al-Naima

Abstract:

Power load is one of the most important controlling keys which decide power demands and illustrate power usage to shape power market. Hence, power load forecasting is the parameter which facilitates understanding and analyzing all these aspects. In this paper, power load forecasting is solved under MATLAB environment by constructing a neural network for the power load to find an accurate simulated solution with the minimum error. A developed algorithm to achieve load forecasting application with faster technique is the aim for this paper. The algorithm is used to enable MATLAB power application to be implemented by multi machines in the Grid computing system, and to accomplish it within much less time, cost and with high accuracy and quality. Grid Computing, the modern computational distributing technology, has been used to enhance the performance of power applications by utilizing idle and desired Grid contributor(s) by sharing computational power resources.

Keywords: DeskGrid, Grid Server, idle contributor(s), grid computing, load forecasting

Procedia PDF Downloads 476

Authors: Z. Abdollahi Biron, P. Pisu

Abstract:

Connected vehicles are one of the promising technologies for future Intelligent Transportation Systems (ITS). A connected vehicle system is essentially a set of vehicles communicating through a network to exchange their information with each other and the infrastructure. Although this interconnection of the vehicles can be potentially beneficial in creating an efficient, sustainable, and green transportation system, a set of safety and reliability challenges come out with this technology. The first challenge arises from the information loss due to unreliable communication network which affects the control/management system of the individual vehicles and the overall system. Such scenario may lead to degraded or even unsafe operation which could be potentially catastrophic. Secondly, faulty sensors and actuators can affect the individual vehicle’s safe operation and in turn will create a potentially unsafe node in the vehicular network. Further, sending that faulty sensor information to other vehicles and failure in actuators may significantly affect the safe operation of the overall vehicular network. Therefore, it is of utmost importance to take these issues into consideration while designing the control/management algorithms of the individual vehicles as a part of connected vehicle system. In this paper, we consider a connected vehicle system under Co-operative Adaptive Cruise Control (CACC) and propose a fault diagnosis scheme that deals with these aforementioned challenges. Specifically, the conventional CACC algorithm is modified by adding a Kalman filter-based estimation algorithm to suppress the effect of lost information under unreliable network. Further, a sliding mode observer-based algorithm is used to improve the sensor reliability under faults. The effectiveness of the overall diagnostic scheme is verified via simulation studies.

Keywords: fault diagnostics, communication network, connected vehicles, packet drop out, platoon

Procedia PDF Downloads 239

Authors: Taha Bensiradj, Samira Moussaoui

Abstract:

Hybrid Sensors and Vehicular Networks (HSVN), represent a hybrid network, which uses several generations of Ad-Hoc networks. It is used especially in Intelligent Transport Systems (ITS). The HSVN allows making collaboration between the Wireless Sensors Network (WSN) deployed on the border of the road and the Vehicular Network (VANET). This collaboration is defined by messages exchanged between the two networks for the purpose to inform the drivers about the state of the road, provide road safety information and more information about traffic on the road. Moreover, this collaboration created by HSVN, also allows the use of a network and the advantage of improving another network. For example, the dissemination of information between the sensors quickly decreases its energy, and therefore, we can use vehicles that do not have energy constraint to disseminate the information between sensors. On the other hand, to solve the disconnection problem in VANET, the sensors can be used as gateways that allow sending the messages received by one vehicle to another. However, because of the short communication range of the sensor and its low capacity of storage and processing of data, it is difficult to ensure the exchange of road messages between it and the vehicle, which can be moving at high speed at the time of exchange. This represents the time where the vehicle is in communication range with the sensor. This work is the proposition of a communication protocol between the sensors and the vehicle used in HSVN. The latter has as the purpose to ensure the exchange of road messages in the available time of exchange.

Keywords: HSVN, ITS, VANET, WSN

Procedia PDF Downloads 362

Authors: Zhiyan Meng, Dan Liu, Jintao Meng

Abstract:

Dependable encrypted traffic classification is crucial for improving cybersecurity and handling the growing amount of data. Large language models have shown that learning from large datasets can be effective, making pre-trained methods for encrypted traffic classification popular. However, attention-based pre-trained methods face two main issues: their large neural parameters are not suitable for low-computation environments like mobile devices and real-time applications, and they often overfit by getting stuck in local minima. To address these issues, we developed a lightweight transformer model, which reduces the computational parameters through lightweight vocabulary construction and Squeeze-and-Excitation Block. We use sharpness-aware optimization to avoid local minima during pre-training and capture temporal features with relative positional embeddings. Our approach keeps the model's classification accuracy high for downstream tasks. We conducted experiments on four datasets -USTC-TFC2016, VPN 2016, Tor 2016, and CICIOT 2022. Even with fewer than 18 million parameters, our method achieves classification results similar to methods with ten times as many parameters.

Keywords: sharpness-aware optimization, encrypted traffic classification, squeeze-and-excitation block, pretrained model

Procedia PDF Downloads 30

Authors: Jurijs Salijevs, Katrina Bolocko

Abstract:

The integration of artificial intelligence and neural networks has significantly changed full-body imaging and high-resolution 3D mapping systems, and this paper reviews research in these areas. With an emphasis on their use in the early identification of melanoma and other disorders, the goal is to give a wide perspective on the current status and potential future of these medical imaging technologies. Authors also examine methodologies such as machine learning and deep learning, seeking to identify efficient procedures that enhance diagnostic capabilities through the analysis of 3D body scans. This work aims to encourage further research and technological development to harness the full potential of AI in disease diagnosis.

Keywords: artificial intelligence, neural networks, 3D scan, body scan, 3D mapping system, healthcare

Procedia PDF Downloads 103

Authors: Zouhair Haddi, Stephane Delliaux, Jean-Francois Pons, Ismail Kechaf, Jean-Claude De Haro, Mustapha Ouladsine

Abstract:

Atrial fibrillation (AF) has been considered as the most common cardiac arrhythmia, and a major public health burden associated with significant morbidity and mortality. Nowadays, telemedical approaches targeting cardiac outpatients situate AF among the most challenged medical issues. The automatic, early, and fast AF detection is still a major concern for the healthcare professional. Several algorithms based on univariate analysis have been developed to detect atrial fibrillation. However, the published results do not show satisfactory classification accuracy. This work was aimed at resolving this shortcoming by proposing multivariate data analysis methods for automatic AF detection. Four publicly-accessible sets of clinical data (AF Termination Challenge Database, MIT-BIH AF, Normal Sinus Rhythm RR Interval Database, and MIT-BIH Normal Sinus Rhythm Databases) were used for assessment. All time series were segmented in 1 min RR intervals window and then four specific features were calculated. Two pattern recognition methods, i.e., Principal Component Analysis (PCA) and Learning Vector Quantization (LVQ) neural network were used to develop classification models. PCA, as a feature reduction method, was employed to find important features to discriminate between AF and Normal Sinus Rhythm. Despite its very simple structure, the results show that the LVQ model performs better on the analyzed databases than do existing algorithms, with high sensitivity and specificity (99.19% and 99.39%, respectively). The proposed AF detection holds several interesting properties, and can be implemented with just a few arithmetical operations which make it a suitable choice for telecare applications.

Keywords: atrial fibrillation, multivariate data analysis, automatic detection, telemedicine

Procedia PDF Downloads 268

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 190

Authors: Go Bong Choi, Shin Je Lee, Sung Jin Yoo, Gibaek Lee, Jong Min Lee

Abstract:

In South Korea, it is difficult to obtain data for statistical pipe assessment. In this paper, to address these issues, we find that various statistical model presented before is how data mixed with noise and are whether apply in South Korea. Three major type of model is studied and if data is presented in the paper, we add noise to data, which affects how model response changes. Moreover, we generate data from model in paper and analyse effect of noise. From this we can find robustness and applicability in Korea of each model.

Keywords: proportional hazard model, survival model, water main deterioration, ecological sciences

Procedia PDF Downloads 743

Authors: Amjad Khan

Abstract:

The security of Vehicular ad hoc networking is of great importance as it involves serious life threats. Thus to provide secure communication amongst Vehicles on road, the conventional security system is not enough. It is necessary to prevent the network resources from wastage and give them protection against malicious nodes so that to ensure the data bandwidth availability to the legitimate nodes of the network. This work is related to provide a non conventional security system by introducing some constraints to minimize the DoS (Denial of services) especially data and bandwidth. The data packets received by a node in the network will pass through a number of tests and if any of the test fails, the node will drop those data packets and will not forward it anymore. Also if a node claims to be the nearest node for forwarding emergency messages then the sender can effectively identify the true or false status of the claim by using these constraints. Consequently the DoS(Denial of Services) attack is minimized by the instant availability of data without wasting the network resources.

Keywords: black hole attack, grey hole attack, intransient traffic tempering, networking

Procedia PDF Downloads 285

Authors: Shiri Elisheva Decktor, Sharon Hornstein

Abstract:

Highway merges and unmarked junctions are key components in any urban road network, which can act as bottlenecks and create traffic disruption. Inefficient highway merges may trigger traffic instabilities such as stop-and-go waves, pose safety conditions and lead to longer journey times. These phenomena occur spontaneously if the average vehicle density exceeds a certain critical value. This study focuses on modeling the traffic using a microscopic traffic flow model. A hybrid traffic model, which combines human-driven and controlled vehicles is assumed. The controlled vehicles obey different driving policies when approaching the merge, or in the vicinity of other vehicles. We developed a co-simulation model in SUMO (Simulation of Urban Mobility), in which the human-driven cars are modeled using the IDM model, and the controlled cars are modeled using a dedicated controller. The scenario chosen for this study is a closed track with one merge and one exit, which could be later implemented using a scaled infrastructure on our lab setup. This will enable us to benchmark the results of this study obtained in simulation, to comparable results in similar conditions in the lab. The metrics chosen for the comparison of the performance of our algorithm on the overall traffic conditions include the average speed, wait time near the merge, and throughput after the merge, measured under different travel demand conditions (low, medium, and heavy traffic).

Keywords: highway merges, traffic modeling, SUMO, driving policy

Procedia PDF Downloads 106

Authors: Arnab Mondal, Sanjeev Kumar Sharma, Ranjit Kumar Upadhyay

Abstract:

We study the spatiotemporal dynamics of a neuronal cable. The processes of one- dimensional (1D) and 2D diffusion are considered for a single variable, which is the membrane voltage, i.e., membrane voltage diffusively interacts for spatiotemporal pattern formalism. The recovery and other variables interact through the membrane voltage. A 3D Leech-Heart (LH) model is introduced to investigate the nonlinear responses of an excitable neuronal cable. The deterministic LH model shows different types of firing properties. We explore the parameter space of the uncoupled LH model and based on the bifurcation diagram, considering v_k2_ashift as a bifurcation parameter, we analyze the 1D diffusion dynamics in three regimes: bursting, regular spiking, and a quiescent state. Depending on parameters, it is shown that the diffusive system may generate regular and irregular bursting or spiking behavior. Further, it is explored a 2D diffusion acting on the membrane voltage, where different types of patterns can be observed. The results show that the LH neurons with different firing characteristics depending on the control parameters participate in a collective behavior of an information processing system that depends on the overall network.

Keywords: bifurcation, pattern formation, spatio-temporal dynamics, stability analysis

Procedia PDF Downloads 222

Authors: Brandon Foggo, Nanpeng Yu

Abstract:

Power distribution circuits undergo frequent network topology changes that are often left undocumented. As a result, the documentation of a circuit’s connectivity becomes inaccurate with time. The lack of reliable circuit connectivity information is one of the biggest obstacles to model, monitor, and control modern distribution systems. To enhance the reliability and efficiency of electric power distribution systems, the circuit’s connectivity information must be updated periodically. This paper focuses on one critical component of a distribution circuit’s topology - the secondary transformer to phase association. This topology component describes the set of phase lines that feed power to a given secondary transformer (and therefore a given group of power consumers). Finding the documentation of this component is call Phase Identification, and is typically performed with physical measurements. These measurements can take time lengths on the order of several months, but with supervised learning, the time length can be reduced significantly. This paper compares several such methods applied to Phase Identification for a large range of real distribution circuits, describes a method of training data selection, describes preprocessing steps unique to the Phase Identification problem, and ultimately describes a method which obtains high accuracy (> 96% in most cases, > 92% in the worst case) using only 5% of the measurements typically used for Phase Identification.

Keywords: distribution network, machine learning, network topology, phase identification, smart grid

Procedia PDF Downloads 300

Authors: Aydin Teymourifar, Gurkan Ozturk, Ozan Bahadir

Abstract:

NSGA-II is one of the most well-known and most widely used evolutionary algorithms. In addition to its new versions, such as NSGA-III, there are several modified types of this algorithm in the literature. In this paper, a hybrid NSGA-II algorithm has been suggested for solving the multi-objective flexible job shop scheduling problem. For a better search, new neighborhood-based crossover and mutation operators are defined. To create new generations, the neighbors of the selected individuals by the tournament selection are constructed. Also, at the end of each iteration, before sorting, neighbors of a certain number of good solutions are derived, except for solutions protected by elitism. The neighbors are generated using a constraint-based neural network that uses various constructs. The non-dominated sorting and crowding distance operators are same as the classic NSGA-II. A comparison based on some multi-objective benchmarks from the literature shows the efficiency of the algorithm.

Keywords: flexible job shop scheduling problem, multi-objective optimization, NSGA-II algorithm, neighborhood structures

Procedia PDF Downloads 229

Authors: Chung-Yuan Huang, Yu-Hsiang Fu, Chuen-Tsai Sun

Abstract:

Community detection represents an important data-mining tool for analyzing and understanding real-world complex network structures and functions. We believe that at least four criteria determine the appropriateness of a community detection algorithm: (a) it produces useable normalized mutual information (NMI) and modularity results for social networks, (b) it overcomes resolution limitation problems associated with synthetic networks, (c) it produces good NMI results and performance efficiency for Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks, and (d) it produces good modularity and performance efficiency for large-scale real-world complex networks. To our knowledge, no existing community detection algorithm meets all four criteria. In this paper, we describe a simple hierarchical arc-merging (HAM) algorithm that uses network topologies and rule-based arc-merging strategies to identify community structures that satisfy the criteria. We used five well-studied social network datasets and eight sets of LFR benchmark networks to validate the ground-truth community correctness of HAM, eight large-scale real-world complex networks to measure its performance efficiency, and two synthetic networks to determine its susceptibility to resolution limitation problems. Our results indicate that the proposed HAM algorithm is capable of providing satisfactory performance efficiency and that HAM-identified communities were close to ground-truth communities in social and LFR benchmark networks while overcoming resolution limitation problems.

Keywords: complex network, social network, community detection, network hierarchy

Procedia PDF Downloads 228

Authors: Xi Liu, Fan Yuan

Abstract:

In the evolving landscape of physics-based machine learning (PBML), particularly within fluid dynamics and its applications in electromechanical engineering, robot vision, and robot learning, achieving precision and alignment with researchers' specific needs presents a formidable challenge. In response, this work proposes a methodology that integrates neural transformation with a modified smoothed particle hydrodynamics model for generating transformed 3D fluid simulations. This approach is useful for nanoscale science, where the unique and complex behaviors of viscoelastic medium demand accurate neurally-transformed simulations for materials understanding and manipulation. In electromechanical engineering, the method enhances the design and functionality of fluid-operated systems, particularly microfluidic devices, contributing to advancements in nanomaterial design, drug delivery systems, and more. The proposed approach also aligns with the principles of PBML, offering advantages such as multi-fluid stylization and consistent particle attribute transfer. This capability is valuable in various fields where the interaction of multiple fluid components is significant. Moreover, the application of neurally-transformed hydrodynamical models extends to manufacturing processes, such as the production of microelectromechanical systems, enhancing efficiency and cost-effectiveness. The system's ability to perform neural transfer on 3D fluid scenes using a deep learning algorithm alongside physical models further adds a layer of flexibility, allowing researchers to tailor simulations to specific needs across scientific and engineering disciplines.

Keywords: physics-based machine learning, robot vision, robot learning, hydrodynamics

Procedia PDF Downloads 66

Authors: O. I. Nkwonta, B. Dzwairo, J. Adeyemo, A. Jaiyola, N. Sawyerr, F. Otieno

Abstract:

The effective management of water resources is of great importance to ensure the supply of water resources to support changing water requirements over a selected planning horizon and in a sustainable and cost-effective way. Essentially, the purpose of the water resources planning process is to balance the available water resources in a system with the water requirements and losses to which the system is subjected. In such situations, Water resources yield and planning model can be used to solve those difficulties. It has an advantage over other models by managing model runs, developing a representative system network, modelling incremental sub-catchments, creating a variety of standard system features, special modelling features, and run result output options.

Keywords: complex, water resources, planning, cost effective and management

Procedia PDF Downloads 573

Authors: Babesse Saad, Ameddah Djemeleddine

Abstract:

In this paper, a learning algorithm using neuronal networks to improve the roll stability and prevent the rollover in a single unit heavy vehicle is proposed. First, LQR control to keep balanced normalized rollovers, between front and rear axles, below the unity, then a data collected from this controller is used as a training basis of a neuronal regulator. The ANN controller is thereafter applied for the nonlinear side force model, and gives satisfactory results than the LQR one.

Keywords: rollover, single unit heavy vehicle, neural networks, nonlinear side force

Procedia PDF Downloads 475

Authors: Louise Moles, Steve Riley, Sarah D. Lichenstein, Marzieh Babaeianjelodar, Robert Kohler, Annie Cheng, Corey Horien Abigail Greene, Wenjing Luo, Jonathan Ahern, Bohan Xu, Yize Zhao, Chun Chieh Fan, R. Todd Constable, Sarah W. Yip

Abstract:

Background: Risks for depression are myriad and include both genetic and brain-based factors. However, relationships between these systems are poorly understood, limiting understanding of disease etiology, particularly at the developmental level. Methods: We use a data-driven machine learning approach connectome-based predictive modeling (CPM) to identify functional connectivity signatures associated with polygenic risk scores for depression (DEP-PRS) among youth from the Adolescent Brain and Cognitive Development (ABCD) study across diverse brain states, i.e., during resting state, during affective working memory, during response inhibition, during reward processing. Results: Using 10-fold cross-validation with 100 iterations and permutation testing, CPM identified connectivity signatures of DEP-PRS across all examined brain states (rho’s=0.20-0.27, p’s<.001). Across brain states, DEP-PRS was positively predicted by increased connectivity between frontoparietal and salience networks, increased motor-sensory network connectivity, decreased salience to subcortical connectivity, and decreased subcortical to motor-sensory connectivity. Subsampling analyses demonstrated that model accuracies were robust across random subsamples of N’s=1,000, N’s=500, and N’s=250 but became unstable at N’s=100. Conclusions: These data, for the first time, identify neural networks of polygenic depression risk in a large sample of youth before the onset of significant clinical impairment. Identified networks may be considered potential treatment targets or vulnerability markers for depression risk.

Keywords: genetics, functional connectivity, pre-adolescents, depression

Procedia PDF Downloads 58

Authors: Xiping Wang，Shuran Yao, Liqin Dai

Abstract:

Many studies report the winter is getting warmer and the minimum air temperature is obviously rising as the important climate warming evidences. The exacerbated air temperature fluctuation tending to bring more severe weather variation is another important consequence of recent climate change which induced more disasters to crop growth in quite a certain regions. Hebei Province is an important winter wheat growing province in North of China that recently endures more winter freezing injury influencing the local winter wheat crop management. A winter wheat freezing injury assessment Bayesian Network framework was established for the objectives of estimating, assessing and predicting winter wheat freezing disasters in Hebei Province. In this framework, the freezing disasters was classified as three severity degrees (SI) among all the three types of freezing, i.e., freezing caused by severe cold in anytime in the winter, long extremely cold duration in the winter and freeze-after-thaw in early season after winter. The factors influencing winter wheat freezing SI include time of freezing occurrence, growth status of seedlings, soil moisture, winter wheat variety, the longitude of target region and, the most variable climate factors. The climate factors included in this framework are daily mean and range of air temperature, extreme minimum temperature and number of days during a severe cold weather process, the number of days with the temperature lower than the critical temperature values, accumulated negative temperature in a potential freezing event. The Bayesian Network model was evaluated using actual weather data and crop records at selected sites in Hebei Province using real data. With the multi-stage influences from the various factors, the forecast and assessment of the event-based target variables, freezing injury occurrence and its damage to winter wheat production, were shown better scoped by Bayesian Network model.

Keywords: bayesian networks, climatic change, freezing Injury, winter wheat

Procedia PDF Downloads 408

Authors: Mamouni Mohammed Dhiya Eddine

Abstract:

This work aims at studying the exploitation of high-speed networks of clusters for distributed storage. Parallel applications running on clusters require both high-performance communications between nodes and efficient access to the storage system. Many studies on network technologies led to the design of dedicated architectures for clusters with very fast communications between computing nodes. Efficient distributed storage in clusters has been essentially developed by adding parallelization mechanisms so that the server(s) may sustain an increased workload. In this work, we propose to improve the performance of distributed storage systems in clusters by efficiently using the underlying high-performance network to access distant storage systems. The main question we are addressing is: do high-speed networks of clusters fit the requirements of a transparent, efficient and high-performance access to remote storage? We show that storage requirements are very different from those of parallel computation. High-speed networks of clusters were designed to optimize communications between different nodes of a parallel application. We study their utilization in a very different context, storage in clusters, where client-server models are generally used to access remote storage (for instance NFS, PVFS or LUSTRE). Our experimental study based on the usage of the GM programming interface of MYRINET high-speed networks for distributed storage raised several interesting problems. Firstly, the specific memory utilization in the storage access system layers does not easily fit the traditional memory model of high-speed networks. Secondly, client-server models that are used for distributed storage have specific requirements on message control and event processing, which are not handled by existing interfaces. We propose different solutions to solve communication control problems at the filesystem level. We show that a modification of the network programming interface is required. Data transfer issues need an adaptation of the operating system. We detail several propositions for network programming interfaces which make their utilization easier in the context of distributed storage. The integration of a flexible processing of data transfer in the new programming interface MYRINET/MX is finally presented. Performance evaluations show that its usage in the context of both storage and other types of applications is easy and efficient.

Keywords: distributed storage, remote file access, cluster, high-speed network, MYRINET, zero-copy, memory registration, communication control, event notification, application programming interface

Procedia PDF Downloads 220

Authors: Leah Wright, Trevor Townsend

Abstract:

Mode choice models are crucial instruments in the analysis of travel behaviour. These models show the relationship between an individual’s choice of transportation mode for a given O-D pair and the individual’s socioeconomic characteristics such as household size and income level, age and/or gender, and the features of the transportation system. The most popular functional forms of these models are based on Utility-Based Choice Theory, which addresses the uncertainty in the decision-making process with the use of an error term. However, with the development of artificial intelligence, many researchers have started to take a different approach to travel demand modelling. In recent times, researchers have looked at using neural networks, fuzzy logic and rough set theory to develop improved mode choice formulas. The concept of cloud theory has recently been introduced to model decision-making under uncertainty. Unlike the previously mentioned theories, cloud theory recognises a relationship between randomness and fuzziness, two of the most common types of uncertainty. This research aims to investigate the use of cloud theory in mode choice models. This paper highlights the conceptual framework of the mode choice model using cloud theory. Merging decision-making under uncertainty and mode choice models is state of the art. The cloud theory model is expected to address the issues and concerns with the nested logit and improve the design of mode choice models and their use in travel demand.

Keywords: Cloud theory, decision-making, mode choice models, travel behaviour, uncertainty

Procedia PDF Downloads 388

Authors: Martin K. Steiger, Lukas Heisler, Hans-Georg Brachtendorf

Abstract:

Deep neural networks and their variants form the backbone of many AI applications. Based on the so-called residual networks, a continuous formulation of such models as ordinary differential equations (ODEs) has proven advantageous since different techniques may be applied that significantly increase the learning speed and enable controlled trade-offs with the resulting error at the same time. For the evaluation of such models, high-performance numerical differential equation solvers are used, which also provide the gradients required for training. However, whether classical gradient-based methods are even applicable or which one yields the best results has not been discussed yet. This paper aims to redeem this situation by providing empirical results for different applications.

Keywords: deep neural networks, gradient-based learning, image processing, ordinary differential equation networks

Procedia PDF Downloads 168

Authors: Chen Jun-Hong, He Pu, Tao Wen-Quan

Abstract:

Proton exchange membrane fuel cell (PEMFC) is the most promising future energy source owing to its low operating temperature, high energy efficiency, high power density, and environmental friendliness. In this paper, a comprehensive PEMFC system control-oriented model is developed in the Matlab/Simulink environment, which includes the hydrogen supply subsystem, air supply subsystem, and thermal management subsystem. Besides, Improved Artificial Bee Colony (IABC) is used in the parameter identification of PEMFC semi-empirical equations, making the maximum relative error between simulation data and the experimental data less than 0.4%. Operation temperature is essential for PEMFC, both high and low temperatures are disadvantageous. In the thermal management subsystem, water pump and fan are both controlled with the PID controller to maintain the appreciate operation temperature of PEMFC for the requirements of safe and efficient operation. To improve the control effect further, fuzzy control is introduced to optimize the PID controller of the pump, and the Radial Basis Function (RBF) neural network is introduced to optimize the PID controller of the fan. The results demonstrate that Fuzzy-PID and RBF-PID can achieve a better control effect with 22.66% decrease in Integral Absolute Error Criterion (IAE) of T_st (Temperature of PEMFC) and 77.56% decrease in IAE of T_in (Temperature of inlet cooling water) compared with traditional PID. In the end, a novel thermal management structure is proposed, which uses the cooling air passing through the main radiator to continue cooling the secondary radiator. In this thermal management structure, the parasitic power dissipation can be reduced by 69.94%, and the control effect can be improved with a 52.88% decrease in IAE of T_in under the same controller.

Keywords: PEMFC system, parameter identification, temperature control, Fuzzy-PID, RBF-PID, parasitic power

Procedia PDF Downloads 85

Authors: Wennan Long, Yuhao Nie, Yunan Li, Adam Brandt

Abstract:

To fight against climate change, California government issued the Senate Bill No. 100 (SB-100) in 2018 September, which aims at achieving a target of 100% renewable electricity by the end of 2045. A capacity expansion problem is solved in this case study using a binary quadratic programming model. The optimal locations and capacities of the potential renewable power plants (i.e., solar, wind, biomass, geothermal and hydropower), the phase-out schedule of existing fossil-based (nature gas) power plants and the transmission of electricity across the entire network are determined with the minimal total annualized cost measured by net present value (NPV). The results show that the renewable electricity contribution could increase to 85.9% by 2030 and reach 100% by 2035. Fossil-based power plants will be totally phased out around 2035 and solar and wind will finally become the most dominant renewable energy resource in California electricity mix.

Keywords: 100% renewable electricity, California, capacity expansion, mixed integer non-linear programming

Procedia PDF Downloads 171

Authors: Natascha C. D'Amico, Enzo Grossi, Giovanni Valbusa, Ala Malasevschi, Gianpiero Cardone, Sergio Papa

Abstract:

Purpose: To characterize, through a radiomic approach, the nature of areas classified PI-RADS (Prostate Imaging Reporting and Data System) 3/5, recognized in multiparametric prostate magnetic resonance with T2-weighted (T2w), diffusion and perfusion sequences with paramagnetic contrast. Methods and Materials: 24 cases undergoing multiparametric prostate MR and biopsy were admitted to this pilot study. Clinical outcome of the PI-RADS 3/5 was found through biopsy, finding 8 malignant tumours. The analysed images were acquired with a Philips achieva 1.5T machine with a CE- T2-weighted sequence in the axial plane. Semi-automatic tumour segmentation was carried out on MR images using 3DSlicer image analysis software. 45 shape-based, intensity-based and texture-based features were extracted and represented the input for preprocessing. An evolutionary algorithm (a TWIST system based on KNN algorithm) was used to subdivide the dataset into training and testing set and select features yielding the maximal amount of information. After this pre-processing 20 input variables were selected and different machine learning systems were used to develop a predictive model based on a training testing crossover procedure. Results: The best machine learning system (three-layers feed-forward neural network) obtained a global accuracy of 90% ( 80 % sensitivity and 100% specificity ) with a ROC of 0.82. Conclusion: Machine learning systems coupled with radiomics show a promising potential in distinguishing benign from malign tumours in PI-RADS 3/5 areas.

Keywords: machine learning, MR prostate, PI-Rads 3, radiomics

Procedia PDF Downloads 188

Authors: Hailyie Tekleselase

Abstract:

Deep learning is increasingly used as a building block of security systems. However, neural networks are hard to interpret and typically solid to the practitioner. This paper presents a detail survey of computing methods in cyber security, and analyzes the prospects of enhancing the cyber security capabilities by suggests that of accelerating the intelligence of the security systems. There are many AI-based applications used in industrial scenarios such as Internet of Things (IoT), smart grids, and edge computing. Machine learning technologies require a training process which introduces the protection problems in the training data and algorithms. We present machine learning techniques currently applied to the detection of intrusion, malware, and spam. Our conclusions are based on an extensive review of the literature as well as on experiments performed on real enterprise systems and network traffic. We conclude that problems can be solved successfully only when methods of artificial intelligence are being used besides human experts or operators.

Keywords: artificial intelligence, machine learning, deep learning, cyber security, big data

Procedia PDF Downloads 126

Authors: Gałka Aleksandra, Jelińska Justyna, Masiak Albert, Walentukiewicz Krzysztof

Abstract:

An offline signature is well-known however not the safest way to verify identity. Nowadays, to ensure proper authentication, i.e. in banking systems, multimodal verification is more widely used. In this paper the online signature analysis based on dynamic time warping (DTW) coupled with machine learning approaches has been presented. In our research signatures made with biometric pens were gathered. Signature features as well as their forgeries have been described. For verification of authenticity various methods were used including convolutional neural networks using DTW matrix and multilayer perceptron using sums of DTW matrix paths. System efficiency has been evaluated on signatures and signature forgeries collected on the same day. Results are presented and discussed in this paper.

Keywords: dynamic time warping, handwritten signature verification, feature-based recognition, online signature

Procedia PDF Downloads 176

Authors: Mayada Mazher, Ahmed Moustafa, Ahmed Abdellatif

Abstract:

Background: Autophagy is a eukaryotic, highly conserved catabolic process implicated in many pathophysiologies such as wound healing. Autophagy-associated genes serve as a scaffolding platform for signal transduction of macrophage polarization during the inflammatory phase of wound healing and tissue repair process. In the current study, we report a model for the interplay between autophagy-associated genes and macrophages polarization associated genes. Methods: In silico analysis was performed on 249 autophagy-related genes retrieved from the public autophagy database and gene expression data retrieved from Gene Expression Omnibus (GEO); GSE81922 and GSE69607 microarray data macrophages polarization 199 DEGS. An integrated protein-protein interaction network was constructed for autophagy and macrophage gene sets. The gene sets were then used for GO terms pathway enrichment analysis. Common transcription factors for autophagy and macrophages' polarization were identified. Finally, microRNAs enriched in both autophagy and macrophages were predicated. Results: In silico prediction of common transcription factors in DEGs macrophages and autophagy gene sets revealed a new role for the transcription factors, HOMEZ, GABPA, ELK1 and REL, that commonly regulate macrophages associated genes: IL6,IL1M, IL1B, NOS1, SOC3 and autophagy-related genes: Atg12, Rictor, Rb1cc1, Gaparab1, Atg16l1. Conclusions: Autophagy and macrophages' polarization are interdependent cellular processes, and both autophagy-related proteins and macrophages' polarization related proteins coordinate in tissue remodelling via transcription factors and microRNAs regulatory network. The current work highlights a potential new role for transcription factors HOMEZ, GABPA, ELK1 and REL in wound healing.

Keywords: autophagy related proteins, integrated network analysis, macrophages polarization M1 and M2, tissue remodelling

Procedia PDF Downloads 152

Authors: Cristian F.T. Montenegro, Luís F. N. Lourenço, Maurício B. C. Salles, Renato M. Monaro

Abstract:

More PV systems have been connected to the electrical network each year. As the number of PV systems increases, some issues affecting grid operations have been identified. This paper studied the impacts related to changes in solar irradiance on a distribution/sub-transmission network, considering variations due to moving clouds and daily cycles. Using MATLAB/Simulink software, a solar farm of 30 MWp was built and then implemented to a test network. From simulations, it has been determined that irradiance changes can have a significant impact on the grid by causing voltage fluctuations outside the allowable thresholds. This work discussed some local control strategies and grid reinforcements to mitigate the negative effects of the irradiance changes on the grid.

Keywords: reactive power control, solar irradiance, utility-scale PV systems, voltage fluctuations

Procedia PDF Downloads 460