Search results for: wireless networks

Authors: Sadixa Sanjel, Ahmed Sadek, Naseef Mansoor, Zelalem Denekew

Abstract:

Collegiate ice hockey (NCAA) sports analytics is different from the national level hockey (NHL). We apply and compare multiple machine learning models such as Linear Regression, Random Forest, and Neural Networks to predict the win ratio for a team based on their statistics. Data exploration helps determine which statistics are most useful in increasing the win ratio, which would be beneficial to coaches and team managers. We ran experiments to select the best model and chose Random Forest as the best performing. We conclude with how to bridge the gap between the college and national levels of sports analytics and the use of machine learning to enhance team performance despite not having a lot of metrics or budget for automatic tracking.

Keywords: NCAA, NHL, sports analytics, random forest, regression, neural networks, game predictions

Procedia PDF Downloads 113

Authors: Nafisa Mahbub, Hajo Ribberink

Abstract:

Electrification of long-haul trucks has been in discussion as a potential strategy to decarbonization. These trucks will require large batteries because of their weight and long daily driving distances. Around 245 million battery electric vehicles are predicted to be on the road by the year 2035. This huge increase in the number of electric vehicles (EVs) will require intensive mining operations for metals and other materials to manufacture millions of batteries for the EVs. These operations will add significant environmental burdens and there is a significant risk that the mining sector will not be able to meet the demand for battery materials, leading to higher prices. Since the battery is the most expensive component in the EVs, technologies that can enable electrification with smaller batteries sizes have substantial potential to reduce the material usage and associated environmental and cost burdens. One of these technologies is an ‘electrified road’ (eroad), where vehicles receive power while they are driving, for instance through an overhead catenary (OC) wire (like trolleybuses and electric trains), through wireless (inductive) chargers embedded in the road, or by connecting to an electrified rail in or on the road surface. This study assessed the total material use and associated life cycle GHG emissions of two types of eroads (overhead catenary and in-road wireless charging) for long-haul trucks in Canada and compared them to electrification using stationary plug-in fast charging. As different electrification technologies require different amounts of materials for charging infrastructure and for the truck batteries, the study included the contributions of both for the total material use. The study developed a bottom-up approach model comparing the three different charging scenarios – plug in fast chargers, overhead catenary and in-road wireless charging. The investigated materials for charging technology and batteries were copper (Cu), steel (Fe), aluminium (Al), and lithium (Li). For the plug-in fast charging technology, different charging scenarios ranging from overnight charging (350 kW) to megawatt (MW) charging (2 MW) were investigated. A 500 km of highway (1 lane of in-road charging per direction) was considered to estimate the material use for the overhead catenary and inductive charging technologies. The study considered trucks needing an 800 kWh battery under the plug-in charger scenario but only a 200 kWh battery for the OC and inductive charging scenarios. Results showed that overall the inductive charging scenario has the lowest material use followed by OC and plug-in charger scenarios respectively. The materials use for the OC and plug-in charger scenarios were 50-70% higher than for the inductive charging scenarios for the overall system including the charging infrastructure and battery. The life cycle GHG emissions from the construction and installation of the charging technology material were also investigated.

Keywords: charging technology, eroad, GHG emissions, material use, overhead catenary, plug in charger

Procedia PDF Downloads 50

Authors: Frank Kuebler, Rolf Steinhilper

Abstract:

Artificial neural networks (ANN) as well as Design of Experiments (DOE) based regression analysis (RA) are mainly used for modeling of complex systems. Both methodologies are commonly applied in process and quality control of manufacturing processes. Due to the fact that resource efficiency has become a critical concern for manufacturing companies, these models needs to be extended to predict resource-consumption of manufacturing processes. This paper describes an approach to use neural networks as well as DOE based regression analysis for predicting resource consumption of manufacturing processes and gives a comparison of the achievable results based on an industrial case study of a turning process.

Keywords: artificial neural network, design of experiments, regression analysis, resource efficiency, manufacturing process

Procedia PDF Downloads 523

Authors: Paola Causin, Andrea Aspri, Alessandro Benfenati

Abstract:

Diffuse Optical Tomography (DOT) is an emergent medical imaging technique which employs NIR light to estimate the spatial distribution of optical coefficients in biological tissues for diagnostic purposes, in a noninvasive and non-ionizing manner. DOT reconstruction is a severely ill-conditioned problem due to prevalent scattering of light in the tissue. In this contribution, we present our research in adopting hybrid knowledgedriven/data-driven approaches which exploit the existence of well assessed physical models and build upon them neural networks integrating the availability of data. Namely, since in this context regularization procedures are mandatory to obtain a reasonable reconstruction [1], we explore the use of neural networks as tools to include prior information on the solution. 2. Materials and Methods The idea underlying our approach is to leverage neural networks to solve PDE-constrained inverse problems of the form 𝒒 ∗ = 𝒂𝒓𝒈 𝒎𝒊𝒏𝒒 𝐃(𝒚, 𝒚̃), (1) where D is a loss function which typically contains a discrepancy measure (or data fidelity) term plus other possible ad-hoc designed terms enforcing specific constraints. In the context of inverse problems like (1), one seeks the optimal set of physical parameters q, given the set of observations y. Moreover, 𝑦̃ is the computable approximation of y, which may be as well obtained from a neural network but also in a classic way via the resolution of a PDE with given input coefficients (forward problem, Fig.1 box ). Due to the severe ill conditioning of the reconstruction problem, we adopt a two-fold approach: i) we restrict the solutions (optical coefficients) to lie in a lower-dimensional subspace generated by auto-decoder type networks. This procedure forms priors of the solution (Fig.1 box ); ii) we use regularization procedures of type 𝒒̂ ∗ = 𝒂𝒓𝒈𝒎𝒊𝒏𝒒 𝐃(𝒚, 𝒚̃)+ 𝑹(𝒒), where 𝑹(𝒒) is a regularization functional depending on regularization parameters which can be fixed a-priori or learned via a neural network in a data-driven modality. To further improve the generalizability of the proposed framework, we also infuse physics knowledge via soft penalty constraints (Fig.1 box ) in the overall optimization procedure (Fig.1 box ). 3. Discussion and Conclusion DOT reconstruction is severely hindered by ill-conditioning. The combined use of data-driven and knowledgedriven elements is beneficial and allows to obtain improved results, especially with a restricted dataset and in presence of variable sources of noise.

Keywords: inverse problem in tomography, deep learning, diffuse optical tomography, regularization

Procedia PDF Downloads 73

Authors: Chiraz Ben Jabeur, Hassene Seddik

Abstract:

In this paper, a full approach of modeling and control of a four-rotor unmanned air vehicle (UAV), known as quad-rotor aircraft, is presented. In fact, a PD and a PD optimized Neural Networks Approaches (PD-NN) are developed to be applied to control a quad-rotor. The goal of this work is to concept a smart self-tuning PD controller based on neural networks able to supervise the quad-rotor for an optimized behavior while tracking the desired trajectory. Many challenges could arise if the quad-rotor is navigating in hostile environments presenting irregular disturbances in the form of wind added to the model on each axis. Thus, the quad-rotor is subject to three-dimensional unknown static/varying wind disturbances. The quad-rotor has to quickly perform tasks while ensuring stability and accuracy and must behave rapidly with regard to decision-making facing disturbances. This technique offers some advantages over conventional control methods such as PD controller. Simulation results are obtained with the use of Matlab/Simulink environment and are founded on a comparative study between PD and PD-NN controllers based on wind disturbances. These later are applied with several degrees of strength to test the quad-rotor behavior. These simulation results are satisfactory and have demonstrated the effectiveness of the proposed PD-NN approach. In fact, this controller has relatively smaller errors than the PD controller and has a better capability to reject disturbances. In addition, it has proven to be highly robust and efficient, facing turbulences in the form of wind disturbances.

Keywords: hostile environment, PD and PD-NN controllers, quad-rotor control, robustness against disturbance

Procedia PDF Downloads 136

Authors: Akber Oumer Abdurezak

Abstract:

Road traffic accident is a major problem in Ethiopia, resulting in the deaths of many people and potential injuries and crash every year and loss of properties. According to the Federal Transport Authority, one of the main causes of traffic accident and crash in Ethiopia is over speeding. Implementation of different technologies is used to monitor the speed of vehicles in order to minimize accidents and crashes. This research aimed at designing a speed monitoring system to monitor the speed of travelling vehicles and movements, reporting illegal speeds or overspeeding vehicles to the concerned bodies. The implementation of the system is through a wireless sensor network. The proposed system can sense and detect the movement of vehicles, process, and analysis the data obtained from the sensor and the cloud system. The data is sent to the central controlling server. The system contains accelerometer and gyroscope sensors to sense and collect the data of the vehicle. Arduino to process the data and Global System for Mobile Communication (GSM) module for communication purposes to send the data to the concerned body. When the speed of the vehicle exceeds the allowable speed limit, the system sends a message to database as “over speeding”. Both accelerometer and gyroscope sensors are used to collect acceleration data. The acceleration data then convert to speed, and the corresponding speed is checked with the speed limit, and those above the speed limit are reported to the concerned authorities to avoid frequent accidents. The proposed system decreases the occurrence of accidents and crashes due to overspeeding and can be used as an eye opener for the implementation of other intelligent transport system technologies. This system can also integrate with other technologies like GPS and Google Maps to obtain better output.

Keywords: accelerometer, IOT, GSM, gyroscope

Procedia PDF Downloads 74

Authors: M. S. Aparna, Pushparaj Shetty D.

Abstract:

Nowadays social networking sites have become so popular that the producers or the sellers look for these sites as one of the best options to target the right audience to market their products. There are several tools available to monitor or analyze the social networks. Our task is to identify the right community web pages and find out the behavior analysis of the members by using these tools and formulate an appropriate strategy to market the products or services to achieve the set goals. The advertising becomes more effective when the information of the product/ services come from a known source. The strategy explores great buying influence in the audience on referral marketing. Our methodology proceeds with critical budget analysis and promotes viral influence propagation. In this context, we encompass the vital bits of budget evaluation such as the number of optimal seed nodes or primary influential users activated onset, an estimate coverage spread of nodes and maximum influence propagating distance from an initial seed to an end node. Our proposal for Buyer Prediction mathematical model arises from the urge to perform complex analysis when the probability density estimates of reliable factors are not known or difficult to calculate. Order Statistics and Buyer Prediction mapping function guarantee the selection of optimal influential users at each level. We exercise an efficient tactics of practicing community pages and user behavior to determine the product enthusiasts on social networks. Our approach is promising and should be an elementary choice when there is little or no prior knowledge on the distribution of potential buyers on social networks. In this strategy, product news propagates to influential users on or surrounding networks. By applying the same technique, a user can search friends who are capable to advise better or give referrals, if a product interests him.

Keywords: viral marketing, social network analysis, community web pages, buyer prediction, influence propagation, budget constraints

Procedia PDF Downloads 261

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 174

Authors: Alhusein Almahjoub, Dongyu Qiu

Abstract:

This paper deals with the random access procedure in next-generation networks and presents the solution to reduce total service time (TST) which is one of the most important performance metrics in current and future internet of things (IoT) based networks. The proposed solution focuses on the calculation of optimal transmission probability which maximizes the success probability and reduces TST. It uses the information of several idle preambles in every time slot, and based on it, it estimates the number of backlogged IoT devices using Naïve Bayes estimation which is a type of supervised learning in the machine learning domain. The estimation of backlogged devices is necessary since optimal transmission probability depends on it and the eNodeB does not have information about it. The simulations are carried out in MATLAB which verify that the proposed solution gives excellent performance.

Keywords: random access, LTE/LTE-A, 5G, machine learning, Naïve Bayes estimation

Procedia PDF Downloads 145

Authors: Kadam Bhambri, Neena Gupta

Abstract:

All optical wavelength conversion is essential in present day optical networks for transparent interoperability, contention resolution, and wavelength routing. The incorporation of all optical wavelength convertors leads to better utilization of the network resources and hence improves the efficiency of optical networks. Wavelength convertors that can work with Dispersion Managed (DM) solitons are attractive due to their superior transmission capabilities. In this paper, wavelength conversion for dispersion managed soliton signals was demonstrated at 100 Gbps through semiconductor optical amplifier and an optical filter. The wavelength conversion was achieved for a 1550 nm input signal to1555nm output signal. The output signal was measured in terms of BER, Q factor and system margin.    

Keywords: all optical wavelength conversion, dispersion managed solitons, semiconductor optical amplifier, cross gain modultation

Procedia PDF Downloads 452

Authors: Mohamed Othmani, Yassine Khlifi

Abstract:

This paper presents a technique for compact three dimensional (3D) object model reconstruction using wavelet networks. It consists to transform an input surface vertices into signals,and uses wavelet network parameters for signal approximations. To prove this, we use a wavelet network architecture founded on several mother wavelet families. POLYnomials WindOwed with Gaussians (POLYWOG) wavelet families are used to maximize the probability to select the best wavelets which ensure the good generalization of the network. To achieve a better reconstruction, the network is trained several iterations to optimize the wavelet network parameters until the error criterion is small enough. Experimental results will shown that our proposed technique can effectively reconstruct an irregular 3D object models when using the optimized wavelet network parameters. We will prove that an accurateness reconstruction depends on the best choice of the mother wavelets.

Keywords: 3d object, optimization, parametrization, polywog wavelets, reconstruction, wavelet networks

Procedia PDF Downloads 283

Authors: Stylianos Kampakis

Abstract:

This paper presents a new algorithm for neural networks called “Input Dropout with Aggressive Re-weighting” (IDAR) aimed specifically at datasets with many useless features. IDAR combines two techniques (dropout of input neurons and aggressive re weighting) in order to eliminate the influence of noisy features. The technique can be seen as a generalization of dropout. The algorithm is tested on two different benchmark data sets: a noisy version of the iris dataset and the MADELON data set. Its performance is compared against three other popular techniques for dealing with useless features: L2 regularization, LASSO and random forests. The results demonstrate that IDAR can be an effective technique for handling data sets with many useless features.

Keywords: neural networks, feature selection, regularization, aggressive reweighting

Procedia PDF Downloads 454

Authors: Sumitra Nuanmeesri

Abstract:

The research focus on study, analyze and design the model of the infrastructure and computer networks for distance education, online learning via new media, e-learning and blended learning. The collected information from study and analyze process that information was evaluated by the index of item objective congruence (IOC) by 9 specialists to design model. The results of evaluate the model with the mean and standard deviation by the sample of 9 specialists value is 3.85. The results showed that the infrastructure and computer networks are designed to be appropriate to a great extent appropriate to a great extent.

Keywords: blended learning, new media, infrastructure and computer network, tele-education, online learning

Procedia PDF Downloads 402

Authors: Tatiana A. Dolenko, Sergey A. Burikov, Alexander O. Efitorov, Sergey A. Dolenko

Abstract:

In this study, a comparative analysis of the approaches associated with the use of neural network algorithms for effective solution of a complex inverse problem – the problem of identifying and determining the individual concentrations of inorganic salts in multicomponent aqueous solutions by the spectra of Raman scattering of light – is performed. It is shown that application of artificial neural networks provides the average accuracy of determination of concentration of each salt no worse than 0.025 M. The results of comparative analysis of input data compression methods are presented. It is demonstrated that use of uniform aggregation of input features allows decreasing the error of determination of individual concentrations of components by 16-18% on the average.

Keywords: inverse problems, multi-component solutions, neural networks, Raman spectroscopy

Procedia PDF Downloads 527

Authors: Kahlil Fredrick Cui, Marissa Pastor

Abstract:

Earthquakes are complex phenomena, exhibiting complex correlations in space, time, and magnitude. Recently, the concept of complex networks has been used to shed light on the statistical and dynamical characteristics of regional seismicity. In this work, we study the relationships and interactions of seismic regions in Chile, Japan, and the Philippines through weighted and directed complex network analysis. Geographical areas are digitized into cells of fixed dimensions which in turn become the nodes of the network when an earthquake has occurred therein. Nodes are linked if a correlation exists between them as determined and measured by a correlation metric. The networks are found to be scale-free, exhibiting power-law behavior in the distributions of their different centrality measures: the in- and out-degree and the in- and out-strength. The evidence is also found of preferential interaction between seismically active regions through their degree-degree correlations suggesting that seismicity is dictated by the activity of a few active regions. The importance of a seismic region to the overall seismicity is measured using a generalized centrality metric taken to be an indicator of its activity or passivity. The spatial distribution of earthquake activity indicates the areas where strong earthquakes have occurred in the past while the passivity distribution points toward the likely locations an earthquake would occur whenever another one happens elsewhere. Finally, we propose a method that would project the location of the next possible earthquake using the generalized centralities coupled with correlations calculated between the latest earthquakes and a geographical point in the future.

Keywords: complex networks, correlations, earthquake, hazard assessment

Procedia PDF Downloads 212

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 88

Authors: Ng Liang Shen, Ngahzaifa Abdul Ghani

Abstract:

This research aimed at developing an early warning system for pre-diabetic and diabetics by analyzing simple and easily determinable signs and symptoms of diabetes among the people living in Malaysia using Particle Swarm Optimized Artificial. With the skyrocketing prevalence of Type 2 diabetes in Malaysia, the system can be used to encourage affected people to seek further medical attention to prevent the onset of diabetes or start managing it early enough to avoid the associated complications. The study sought to find out the best predictive variables of Type 2 Diabetes Mellitus, developed a system to diagnose diabetes from the variables using Artificial Neural Networks and tested the system on accuracy to find out the patent generated from diabetes diagnosis result in machine learning algorithms even at primary or advanced stages.

Keywords: diabetes diagnosis, Artificial Neural Networks, artificial intelligence, soft computing, medical diagnosis

Procedia PDF Downloads 335

Authors: Svitov David, Alyamkin Sergey

Abstract:

The usage of convolutional neural networks (CNNs) in conjunction with the margin-based softmax approach demonstrates the state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and face embeddings predicted by the teacher network.

Keywords: ArcFace, distillation, face recognition, margin-based softmax

Procedia PDF Downloads 146

Authors: Berkay Buluş, Aytekin İşman, Kübra Yüzüncüyıl

Abstract:

Developments in media and communication technologies have changed the way we use media. The importance of convergence culture has been increasing day by day within the framework of these developments. With new media, it is possible to say that social networks are the most powerful platforms that are integrated to this digitalization process. Although social networks seem like the place that people can socialize, they can also be utilized as places of production. On the other hand, audience has become users within the framework of transformation from national to global broadcasting. User generated contents make conventional media and new media collide. In this study, these communication platforms will be examined not as platforms that replace one another but mediums that unify each other. In the light of this information, information that is produced by users regarding new media platforms and all new media use practices are called convergence culture. In other words, convergence culture means intersections of conventional and new media. In this study, examples of convergence culture will be analyzed in detail.

Keywords: new media, convergence culture, convergence, use of new media, user generated content

Procedia PDF Downloads 270

Authors: Georgios Samaras

Abstract:

New media such as Facebook, YouTube and Twitter introduced the world to a new era of instant communication. An era where online interactions could replace a lot of offline actions. Technology can create a mediated environment in which participants can communicate (one-to-one, one-to-many, and many-to-many) both synchronously and asynchronously and participate in reciprocal message exchanges. Currently, social networks are attracting similar academic attention to that of the internet after its mainstream implementation into public life. Websites and platforms are seen as the forefront of a new political change. There is a significant backdrop of previous methodologies employed to research the effects of social networks. New approaches are being developed to be able to adapt to the growth of social networks and the invention of new platforms. Golden Dawn was the first openly neo-Nazi party post World War II to win seats in the parliament of a European country. Its racist rhetoric and violent tactics on social networks were rewarded by their supporters, who in the face of Golden Dawn’s leaders saw a ‘new dawn’ in Greek politics. Mainstream media banned its leaders and members of the party indefinitely after Ilias Kasidiaris attacked Liana Kanelli, a member of the Greek Communist Party, on live television. This media ban was seen as a treasonous move by a significant percentage of voters, who believed that the system was desperately trying to censor Golden Dawn to favor mainstream parties. The shocking attack on live television received international coverage and while European countries were condemning this newly emerged neo-Nazi rhetoric, almost 7 percent of the Greek population rewarded Golden Dawn with 18 seats in the Greek parliament. Many seem to think that Golden Dawn mobilised its voters online and this approach played a significant role in spreading their message and appealing to wider audiences. No strict online censorship existed back in 2012 and although Golden Dawn was openly used neo-Nazi symbolism, it was allowed to use social networks without serious restrictions until 2017. This paper used qualitative methods to investigate Golden Dawn’s rise in social networks from 2012 to 2019. The focus of the content analysis was set on three social networking platforms: Facebook, Twitter and YouTube, while the existence of Golden Dawn’s website, which was used as a news sharing hub, was also taken into account. The content analysis included text and visual analyses that sampled content from their social networking pages to translate their political messaging through an ideological lens focused on extreme-right populism. The absence of hate speech regulations on social network platforms in 2012 allowed the free expression of those heavily ultranationalist and populist views, as they were employed by Golden Dawn in the Greek political scene. On YouTube, Facebook and Twitter, the influence of their rhetoric was particularly strong. Official channels and MPs profiles were investigated to explore the messaging in-depth and understand its ideological elements.

Keywords: populism, far-right, social media, Greece, golden dawn

Procedia PDF Downloads 147

Authors: Soheila Sadeghi

Abstract:

Construction projects are complex and often subject to significant cost overruns due to the multifaceted nature of the activities involved. Accurate cost estimation is crucial for effective budget planning and resource allocation. Traditional methods for predicting overruns often rely on expert judgment or analysis of historical data, which can be time-consuming, subjective, and may fail to consider important factors. However, with the increasing availability of data from construction projects, machine learning techniques can be leveraged to improve the accuracy of overrun predictions. This study applied machine learning algorithms to enhance the prediction of cost overruns in a case study of a construction project. The methodology involved the development and evaluation of two machine learning models: Random Forest and Neural Networks. Random Forest can handle high-dimensional data, capture complex relationships, and provide feature importance estimates. Neural Networks, particularly Deep Neural Networks (DNNs), are capable of automatically learning and modeling complex, non-linear relationships between input features and the target variable. These models can adapt to new data, reduce human bias, and uncover hidden patterns in the dataset. The findings of this study demonstrate that both Random Forest and Neural Networks can significantly improve the accuracy of cost overrun predictions compared to traditional methods. The Random Forest model also identified key cost drivers and risk factors, such as changes in the scope of work and delays in material delivery, which can inform better project risk management. However, the study acknowledges several limitations. First, the findings are based on a single construction project, which may limit the generalizability of the results to other projects or contexts. Second, the dataset, although comprehensive, may not capture all relevant factors influencing cost overruns, such as external economic conditions or political factors. Third, the study focuses primarily on cost overruns, while schedule overruns are not explicitly addressed. Future research should explore the application of machine learning techniques to a broader range of projects, incorporate additional data sources, and investigate the prediction of both cost and schedule overruns simultaneously.

Keywords: cost prediction, machine learning, project management, random forest, neural networks

Procedia PDF Downloads 50

Authors: Hasan G. Elmazoghi, Aisha I. Alzayani, Lubna S. Bentaher

Abstract:

Rainfall is a highly non-linear phenomena, which requires application of powerful supervised data mining techniques for its accurate prediction. In this study the Artificial Neural Network (ANN) technique is used to predict the mean monthly historical rainfall data collected from BENINA station in Benghazi for 31 years, the period of “1977-2006” and the results are compared against the observed values. The specific objective to achieve this goal was to determine the best combination of weather variables to be used as inputs for the ANN model. Several statistical parameters were calculated and an uncertainty analysis for the results is also presented. The best ANN model is then applied to the data of one year (2007) as a case study in order to evaluate the performance of the model. Simulation results reveal that application of ANN technique is promising and can provide reliable estimates of rainfall.

Keywords: neural networks, rainfall, prediction, climatic variables

Procedia PDF Downloads 487

Authors: Namrata Mishra

Abstract:

Health of a person plays a vital role in the collective health of his community and hence the well-being of the society as a whole. But, in today’s fast paced technology driven world, health issues are increasingly being associated with human behaviors – their lifestyle. Social networks have tremendous impact on the health behavior of individuals. Many researchers have used social network analysis to understand human behavior that implicates their social and economic environments. It would be interesting to use a similar analysis to understand human behaviors that have health implications. This paper focuses on concepts of those behavioural analyses that have health implications using social networks analysis and provides possible algorithmic approaches. The results of these approaches can be used by the governing authorities for rolling out health plans, benefits and take preventive measures, while the pharmaceutical companies can target specific markets, helping health insurance companies to better model their insurance plans.

Keywords: breadth first search, directed graph, health behaviors, social network analysis

Procedia PDF Downloads 471

Authors: Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula

Abstract:

Factors affecting construction unit cost vary depending on a country’s political, economic, social and technological inclinations. Factors affecting construction costs have been studied from various perspectives. Analysis of cost factors requires an appreciation of a country’s practices. Identified cost factors provide an indication of a country’s construction economic strata. The purpose of this paper is to identify the essential factors that affect unit cost estimation and their breakdown using artificial neural networks. Twenty-five (25) identified cost factors in road construction were subjected to a questionnaire survey and employing SPSS factor analysis the factors were reduced to eight. The 8 factors were analysed using the neural network (NN) to determine the proportionate breakdown of the cost factors in a given construction unit rate. NN predicted that political environment accounted 44% of the unit rate followed by contractor capacity at 22% and financial delays, project feasibility, overhead and profit each at 11%. Project location, material availability and corruption perception index had minimal impact on the unit cost from the training data provided. Quantified cost factors can be incorporated in unit cost estimation models (UCEM) to produce more accurate estimates. This can create improvements in the cost estimation of infrastructure projects and establish a benchmark standard to assist the process of alignment of work practises and training of new staff, permitting the on-going development of best practises in cost estimation to become more effective.

Keywords: construction cost factors, neural networks, roadworks, Zambian construction industry

Procedia PDF Downloads 361

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feed-forward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on self organizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: classification, SOFM algorithm, neural network, neighborhood, RGB image

Procedia PDF Downloads 476

Authors: Tugce Talay, Kadir Erkan

Abstract:

In this study, the necessary steps for the design of axial flow permanent magnet motors are shown. The design and analysis of the engine were carried out based on ANSYS Maxwell program. The design parameters of the ANSYS Maxwell program and the artificial neural network system were established in MATLAB and the most efficient design parameters were found with the trained neural network. The results of the Maxwell program and the results of the artificial neural networks are compared and optimal working design parameters are found. The most efficient design parameters were submitted to the ANSYS Maxwell 3D design and the cogging torque was examined and design studies were carried out to reduce the cogging torque.

Keywords: AFPM, ANSYS Maxwell, cogging torque, design optimisation, efficiency, NNTOOL

Procedia PDF Downloads 217

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 271

Authors: Zeina Merabi, Arij Dao

Abstract:

The temporal order of information processing in the brain is an important code in many acoustic signals, including speech, music, and animal vocalizations. Despite its significance, surprisingly little is known about its underlying cellular mechanisms and network manifestations. In the songbird telencephalic nucleus HVC, a subset of neurons shows temporal combination sensitivity (TCS). These neurons show a high temporal specificity, responding differently to distinct patterns of spectral elements and their combinations. HVC neuron types include basal-ganglia-projecting HVCX, forebrain-projecting HVCRA, and interneurons (HVC¬INT), each exhibiting distinct cellular, electrophysiological and functional properties. In this work, we develop conductance-based neural network models connecting the different classes of HVC neurons via different wiring scenarios, aiming to explore possible neural mechanisms that orchestrate the combination sensitivity property exhibited by HVCX, as well as replicating in vivo firing patterns observed when TCS neurons are presented with various auditory stimuli. The ionic and synaptic currents for each class of neurons that are presented in our networks and are based on pharmacological studies, rendering our networks biologically plausible. We present for the first time several realistic scenarios in which the different types of HVC neurons can interact to produce this behavior. The different networks highlight neural mechanisms that could potentially help to explain some aspects of combination sensitivity, including 1) interplay between inhibitory interneurons’ activity and the post inhibitory firing of the HVCX neurons enabled by T-type Ca2+ and H currents, 2) temporal summation of synaptic inputs at the TCS site of opposing signals that are time-and frequency- dependent, and 3) reciprocal inhibitory and excitatory loops as a potent mechanism to encode information over many milliseconds. The result is a plausible network model characterizing auditory processing in HVC. Our next step is to test the predictions of the model.

Keywords: combination sensitivity, songbirds, neural networks, spatiotemporal integration

Procedia PDF Downloads 64

Authors: Noha M. Rashad, W. Swelam, M. H. Abd ElAzeem

Abstract:

A simple design of array antenna is presented in this paper, supporting millimeter wave applications which can be used in short range wireless communications such as 5G applications. This design enhances the use of V-band, according to IEEE standards, as the antenna works in the 70 GHz band with bandwidth more than 11 GHz and peak gain more than 13 dBi. The design is simulated using different numerical techniques achieving a very good agreement.

Keywords: 5G technology, array antenna, microstrip, millimeter wave

Procedia PDF Downloads 304

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 219