Search results for: decision based artificial neural network

Authors: Maamar Ali Saud Al Tobi, Geraint Bevan, K. P. Ramachandran, Peter Wallace, David Harrison

Abstract:

Centrifugal pumps are complex machines which can experience different types of fault. Condition monitoring can be used in centrifugal pump fault detection through vibration analysis for mechanical and hydraulic forces. Vibration analysis methods have the potential to be combined with artificial intelligence systems where an automatic diagnostic method can be approached. An automatic fault diagnosis approach could be a good option to minimize human error and to provide a precise machine fault classification. This work aims to introduce an approach to centrifugal pump fault diagnosis based on artificial intelligence and genetic algorithm systems. An overview of the future works, research methodology and proposed experimental setup is presented and discussed. The expected results and outcomes based on the experimental work are illustrated.

Keywords: centrifugal pump setup, vibration analysis, artificial intelligence, genetic algorithm

Procedia PDF Downloads 410

Authors: Talal Alshammari, Nasser Alshammari, Mohamed Sedky, Chris Howard

Abstract:

With the widespread adoption of the Internet-connected devices, and with the prevalence of the Internet of Things (IoT) applications, there is an increased interest in machine learning techniques that can provide useful and interesting services in the smart home domain. The areas that machine learning techniques can help advance are varied and ever-evolving. Classifying smart home inhabitants’ Activities of Daily Living (ADLs), is one prominent example. The ability of machine learning technique to find meaningful spatio-temporal relations of high-dimensional data is an important requirement as well. This paper presents a comparative evaluation of state-of-the-art machine learning techniques to classify ADLs in the smart home domain. Forty-two synthetic datasets and two real-world datasets with multiple inhabitants are used to evaluate and compare the performance of the identified machine learning techniques. Our results show significant performance differences between the evaluated techniques. Such as AdaBoost, Cortical Learning Algorithm (CLA), Decision Trees, Hidden Markov Model (HMM), Multi-layer Perceptron (MLP), Structured Perceptron and Support Vector Machines (SVM). Overall, neural network based techniques have shown superiority over the other tested techniques.

Keywords: activities of daily living, classification, internet of things, machine learning, prediction, smart home

Procedia PDF Downloads 357

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 339

Authors: Ahmed Jedidi, Mesfer Mohammed Alshamrani, Alwi Mohammad A. Bamhdi

Abstract:

Optical performance monitoring and optical network management are essential in building a reliable, high-capacity, and service-differentiation enabled all-optical network. One of the serious problems in this network is the fact that optical crosstalk is additive, and thus the aggregate effect of crosstalk over a whole AON may be more nefarious than a single point of crosstalk. As results, we note a huge degradation of the Quality of Service (QoS) in our network. For that, it is necessary to identify and monitor the impairments in whole network. In this way, this paper presents new system to identify and monitor crosstalk in AONs in real-time fashion. particular, it proposes a new technique to manage intra-crosstalk in objective to relax QoS of the network.

Keywords: all-optical networks, optical crosstalk, optical cross-connect, crosstalk, monitoring crosstalk

Procedia PDF Downloads 463

Authors: Artur Matuck, Guilherme F. Nobre

Abstract:

Machines can be either tool, media, or social agents. Advances in technology have been delivering machines capable of autonomous expression, both through communication and art. This paper deals with models (theoretical approach) and experiments (applied approach) related to artificial agents. On one hand it traces how social sciences' scholars have worked with topics such as text automatization, man-machine writing cooperation, and communication. On the other hand it covers how computer sciences' scholars have built communicative and artistic machines, including the programming of creativity. The aim is to present a brief survey on artificially intelligent communicators and artificially creative writers, and provide the basis to understand the meta-authorship and also to new and further man-machine co-authorship.

Keywords: artificial communication, artificial creativity, artificial writers, meta-authorship, robotic art

Procedia PDF Downloads 292

Authors: Ian McCulloh, Andrew Placona, Darren Stewart, Daniel Gause, Kevin Kiernan, Morgan Stuart, Christopher Zinner, Laura Cartwright

Abstract:

An estimated 22-25% of viable deceased donor kidneys are discarded every year in the US, while waitlisted candidates are dying every day. As many as 85% of transplanted organs are refused at least once for a patient that scored higher on the match list. There are hundreds of clinical variables involved in making a clinical transplant decision and there is rarely an ideal match. Decision makers exhibit an optimism bias where they may refuse an organ offer assuming a better match is imminent. We propose a semi-parametric Cox proportional hazard model, augmented by an accelerated failure time model based on patient specific suitable organ supply and demand to estimate a time-to-next-offer. Performance is assessed with Cox-Snell residuals and decision curve analysis, demonstrating improved decision support for up to a 5-year outlook. Providing clinical decision makers with quantitative evidence of likely patient outcomes (e.g., time to next offer and the mortality associated with waiting) may improve decisions and reduce optimism bias, thus reducing discarded organs and matching more patients on the waitlist.

Keywords: decision science, KDPI, optimism bias, organ transplant

Procedia PDF Downloads 105

Authors: Ian A. McCulloh, Madelaine Zinser, Jesse Patsolic, Michael Ramos

Abstract:

Recommender systems are a common artificial intelligence (AI) application. For any given input, a search system will return a rank-ordered list of similar items. As users review returned items, they must decide when to halt the search and either revise search terms or conclude their requirement is novel with no similar items in the database. We present a statistically designed experiment that investigates the impact of similarity ratings on human judgement to conclude a search item is novel and halt the search. 450 participants were recruited from Amazon Mechanical Turk to render judgement across 12 decision tasks. We find the inclusion of ratings increases the human perception that items are novel. Percent similarity increases novelty discernment when compared with star-rated similarity or the absence of a rating. Ratings reduce the time to decide and improve decision confidence. This suggests the inclusion of similarity ratings can aid human decision-makers in knowledge search tasks.

Keywords: ratings, rankings, crowdsourcing, empirical studies, user studies, similarity measures, human-centered computing, novelty in information retrieval

Procedia PDF Downloads 131

Authors: Mariam Shah

Abstract:

This paper will examine the potential influence and role of unconscious cognition on judicial decision making. The theoretical underpinnings of this paper rest on phenomenological theory grounded predominantly in Schutzian phenomenology. Aspects of Husserlian and Gadamerian phenomenology will be included within the phenomenological framework put forward in this paper, in an attempt to provide a more complete and thorough account of how unconscious cognition can influence judicial decision making. This paper has far reaching implications, as the framework provides a foundation for unconscious cognitive factors which can work to influence decision making more generally.

Keywords: decision making, Gadamer, Gadamerian, Husserl, Husserlian, judicial decision making, phenomenology, Schutz, Schutzian

Procedia PDF Downloads 414

Authors: Abdelkader Mendas

Abstract:

The integration of MultiCriteria Decision Making (MCDM) approaches in a Geographical Information System (GIS) provides a powerful spatial decision support system which offers the opportunity to efficiently produce the land suitability maps for agriculture. Indeed, GIS is a powerful tool for analyzing spatial data and establishing a process for decision support. Because of their spatial aggregation functions, MCDM methods can facilitate decision making in situations where several solutions are available, various criteria have to be taken into account and decision-makers are in conflict. The parameters and the classification system used in this work are inspired from the FAO (Food and Agriculture Organization) approach dedicated to a sustainable agriculture. A spatial decision support system has been developed for establishing the land suitability map for agriculture. It incorporates the multicriteria analysis method ELECTRE Tri (ELimitation Et Choix Traduisant la REalité) in a GIS within the GIS program package environment. The main purpose of this research is to propose a conceptual and methodological framework for the combination of GIS and multicriteria methods in a single coherent system that takes into account the whole process from the acquisition of spatially referenced data to decision-making. In this context, a spatial decision support system for developing land suitability maps for agriculture has been developed. The algorithm of ELECTRE Tri is incorporated into a GIS environment and added to the other analysis functions of GIS. This approach has been tested on an area in Algeria. A land suitability map for durum wheat has been produced. Through the obtained results, it appears that ELECTRE Tri method, integrated into a GIS, is better suited to the problem of land suitability for agriculture. The coherence of the obtained maps confirms the system effectiveness.

Keywords: multicriteria decision analysis, decision support system, geographical information system, land suitability for agriculture

Procedia PDF Downloads 638

Authors: Heming Yao

Abstract:

Graphene-based percolative strain gauges could find applications in many places such as touch panels, artificial skins or human motion detection because of its advantages over conventional strain gauges such as flexibility and transparency. These strain gauges rely on a novel sensing mechanism that depends on strain-induced morphology changes. Once a compression or tension strain is applied to Graphene-based percolative strain gauges, the overlap area between neighboring flakes becomes smaller or larger, which is reflected by the considerable change of resistance. Tiny strain change on graphene-based percolative strain sensor can act as an important leverage to tremendously increase resistance of strain sensor, which equipped graphene-based percolative strain gauges with higher gauge factor. Despite ongoing research in the underlying sensing mechanism and the limits of sensitivity, neither suitable understanding has been obtained of what intrinsic factors play the key role in adjust gauge factor, nor explanation on how the strain gauge sensitivity can be enhanced, which is undoubtedly considerably meaningful and provides guideline to design novel and easy-produced strain sensor with high gauge factor. We here simulated the strain process by modeling graphene flakes and its percolative networks. We constructed the 3D resistance network by simulating overlapping process of graphene flakes and interconnecting tremendous number of resistance elements which were obtained by fractionizing each piece of graphene. With strain increasing, the overlapping graphenes was dislocated on new stretched simulation graphene flake simulation film and a new simulation resistance network was formed with smaller flake number density. By solving the resistance network, we can get the resistance of simulation film under different strain. Furthermore, by simulation on possible variable parameters, such as out-of-plane resistance, in-plane resistance, flake size, we obtained the changing tendency of gauge factor with all these variable parameters. Compared with the experimental data, we verified the feasibility of our model and analysis. The increase of out-of-plane resistance of graphene flake and the initial resistance of sensor, based on flake network, both improved gauge factor of sensor, while the smaller graphene flake size gave greater gauge factor. This work can not only serve as a guideline to improve the sensitivity and applicability of graphene-based strain sensors in the future, but also provides method to find the limitation of gauge factor for strain sensor based on graphene flake. Besides, our method can be easily transferred to predict gauge factor of strain sensor based on other nano-structured transparent optical conductors, such as nanowire and carbon nanotube, or of their hybrid with graphene flakes.

Keywords: graphene, gauge factor, percolative transport, strain sensor

Procedia PDF Downloads 416

Authors: Ricardo Merlo, María González, Zully Rivero, Laura González

Abstract:

This exploratory work was to know the perception of the use of artificial intelligence (AI) that university students have during their passage through the classroom. The significance of using AI in education, the degree of interest, knowledge acquisition, and how it would influence an interactive resource for acquiring skills were explored. Within this framework, a test with 30 items was designed and administered to 800 volunteer first-year university students of natural and exact sciences. Based on a randomized pilot test, it was validated with Cronbach's Alpha coefficient. Subsequently, the descriptive statistics of the sample used allowed us to observe the preponderance of the dimensions that constitute the attitude construct. Then, the factorial analysis by dimensions contributed to discern about the students' habits according to the knowledge acquired and the emotions put into play in the topics developed in the classroom.

Keywords: attitude, artificial intelligence, didactics, teaching

Procedia PDF Downloads 35

Authors: Jingling Li, Yi Zhang, Wei Liang, Tao Cui, Jun Li

Abstract:

Compared with terrestrial network, the traffic of spatial information network has both self-similarity and short correlation characteristics. By studying its traffic prediction method, the resource utilization of spatial information network can be improved, and the method can provide an important basis for traffic planning of a spatial information network. In this paper, considering the accuracy and complexity of the algorithm, the spatial information network traffic is decomposed into approximate component with long correlation and detail component with short correlation, and a time series hybrid prediction model based on wavelet decomposition is proposed to predict the spatial network traffic. Firstly, the original traffic data are decomposed to approximate components and detail components by using wavelet decomposition algorithm. According to the autocorrelation and partial correlation smearing and truncation characteristics of each component, the corresponding model (AR/MA/ARMA) of each detail component can be directly established, while the type of approximate component modeling can be established by ARIMA model after smoothing. Finally, the prediction results of the multiple models are fitted to obtain the prediction results of the original data. The method not only considers the self-similarity of a spatial information network, but also takes into account the short correlation caused by network burst information, which is verified by using the measured data of a certain back bone network released by the MAWI working group in 2018. Compared with the typical time series model, the predicted data of hybrid model is closer to the real traffic data and has a smaller relative root means square error, which is more suitable for a spatial information network.

Keywords: spatial information network, traffic prediction, wavelet decomposition, time series model

Procedia PDF Downloads 147

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 420

Authors: Jin Xu

Abstract:

5G network developers need to satisfy the necessary requirements of additional capacity from massive users and spectrally efficient wireless technologies. Therefore, the significant amount of underutilized spectrum in network is motivating operators to combine long-term evolution (LTE) with intelligent spectrum management technology. This new LTE intelligent spectrum management in unlicensed band (LTE-U) has the physical layer topology to access spectrum, specifically the 5-GHz band. We proposed a new intelligent cloud RAN for 5G.

Keywords: cloud radio access network, wireless network, cloud computing, multi-agent

Procedia PDF Downloads 424

Authors: Yonatan Sverdlov, Shimon Ullman

Abstract:

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to be adjusted to suit the objectives of new tasks, resulting in a phenomenon called catastrophic forgetting. Most approaches to this problem seek a balance between maximizing performance on the new tasks and minimizing the forgetting of previous tasks. In contrast, our approach attempts to maximize the performance of the new task, while ensuring zero forgetting. This is accomplished through the introduction of task-specific modulation parameters for each task, and only these parameters are learned for the new task, after a set of initial tasks have been learned. Through comprehensive experimental evaluations, our model demonstrates superior performance in acquiring and retaining novel tasks that pose difficulties for other multi-task models. This emphasizes the efficacy of our approach in preventing catastrophic forgetting while accommodating the acquisition of new tasks.

Keywords: continual learning, life-long learning, neural analogies, adaptive modulation

Procedia PDF Downloads 70

Authors: Ali Vaezi, Jyotirmoy Dalal, Manish Verma

Abstract:

The railroad is one of the primary transportation modes for hazardous materials (hazmat) shipments in North America. Installing an emergency response network capable of providing a commensurate response is one of the primary levers to contain (or mitigate) the adverse consequences from rail hazmat incidents. To this end, we propose a two-stage stochastic program to determine the location of and equipment packages to be stockpiled at each response facility. The raw input data collected from publicly available reports were processed, fed into the proposed optimization program, and then tested on a realistic railroad network in Ontario (Canada). From the resulting analyses, we conclude that the decisions based only on empirical datasets would undermine the effectiveness of the resulting network; coverage can be improved by redistributing equipment in the network, purchasing equipment with higher containment capacity, and making use of a disutility multiplier factor.

Keywords: hazmat, rail network, stochastic programming, emergency response

Procedia PDF Downloads 182

Authors: Sheng Fu, Yinbo Gao, Hao Lin

Abstract:

In the current mine air compressors monitoring system, there are some difficulties in the installation and maintenance because of the wired connection. To solve the problem, this paper introduces a new air compressors monitoring system based on ZigBee in which the monitoring parameters are transmitted wirelessly. The collecting devices are designed to form a cluster network to collect vibration, temperature, and pressure of air cylinders and other parameters. All these devices are battery-powered. Besides, the monitoring software in PC is developed using MFC. Experiments show that the designed wireless sensor network works well in the site environmental condition and the system is very convenient to be installed since the wireless connection. This monitoring system will have a wide application prospect in the upgrade of the old monitoring system of the air compressors.

Keywords: condition monitoring, wireless sensor network, air compressor, zigbee, data collecting

Procedia PDF Downloads 505

Authors: Bashaiar Alsanaa

Abstract:

The process of decision making requires environment surveillance and public opinion monitoring, both of which can be attained through effective use of social media. This study aims to investigate the extent to which new media influence the decision making process by the Kuwaiti government. The research explores how unprecedented access to information as well as dynamic user-interaction made possible by new technologies play a significant role in all aspects of decision making whether on the end of the public or decision makers themselves. The research analyzes two case studies where public opinion was forceful on social media in order to explore how such media create interactive and liberal environments for individuals to participate in the process of taking action with regards to political, economic and social issues. The findings of this descriptive study indicate the overwhelming extent to which social media are being used in Kuwait to create new social reform by the government based on citizen interaction with current topics.

Keywords: communication, descriptive, new media technologies, social media.

Procedia PDF Downloads 118

Authors: Alexander Vandesompele, Joni Dambre

Abstract:

The diversity in dendritic arborization, as first illustrated by Santiago Ramon y Cajal, has always suggested a role for dendrites in the functionality of neurons. In the past decades, thanks to new recording techniques and optical stimulation methods, it has become clear that dendrites are not merely passive electrical components. They are observed to integrate inputs in a non-linear fashion and actively participate in computations. Regardless, in simulations of neural networks dendritic structure and functionality are often overlooked. Especially in a machine learning context, when designing artificial neural networks, point neuron models such as the leaky-integrate-and-fire (LIF) model are dominant. These models mimic the integration of inputs at the neuron soma, and ignore the existence of dendrites. In this work, the LIF point neuron model is extended with a simple form of dendritic computation. This gives the LIF neuron increased capacity to discriminate spatiotemporal input sequences, a dendritic functionality as observed in another study. Simulations of the spiking neurons are performed using the Bindsnet framework. In the common LIF model, incoming synapses are independent. Here, we introduce a dependency between incoming synapses such that the post-synaptic impact of a spike is not only determined by the weight of the synapse, but also by the activity of other synapses. This is a form of short term plasticity where synapses are potentiated or depressed by the preceding activity of neighbouring synapses. This is a straightforward way to prevent inputs from simply summing linearly at the soma. To implement this, each pair of synapses on a neuron is assigned a variable,representing the synaptic relation. This variable determines the magnitude ofthe short term plasticity. These variables can be chosen randomly or, more interestingly, can be learned using a form of Hebbian learning. We use Spike-Time-Dependent-Plasticity (STDP), commonly used to learn synaptic strength magnitudes. If all neurons in a layer receive the same input, they tend to learn the same through STDP. Adding inhibitory connections between the neurons creates a winner-take-all (WTA) network. This causes the different neurons to learn different input sequences. To illustrate the impact of the proposed dendritic mechanism, even without learning, we attach five input neurons to two output neurons. One output neuron isa regular LIF neuron, the other output neuron is a LIF neuron with dendritic relationships. Then, the five input neurons are allowed to fire in a particular order. The membrane potentials are reset and subsequently the five input neurons are fired in the reversed order. As the regular LIF neuron linearly integrates its inputs at the soma, the membrane potential response to both sequences is similar in magnitude. In the other output neuron, due to the dendritic mechanism, the membrane potential response is different for both sequences. Hence, the dendritic mechanism improves the neuron’s capacity for discriminating spa-tiotemporal sequences. Dendritic computations improve LIF neurons even if the relationships between synapses are established randomly. Ideally however, a learning rule is used to improve the dendritic relationships based on input data. It is possible to learn synaptic strength with STDP, to make a neuron more sensitive to its input. Similarly, it is possible to learn dendritic relationships with STDP, to make the neuron more sensitive to spatiotemporal input sequences. Feeding structured data to a WTA network with dendritic computation leads to a significantly higher number of discriminated input patterns. Without the dendritic computation, output neurons are less specific and may, for instance, be activated by a sequence in reverse order.

Keywords: dendritic computation, spiking neural networks, point neuron model

Procedia PDF Downloads 133

Authors: I. Teotónio, C.O. Cruz, C.M. Silva, M. Manso

Abstract:

Diverse stakeholders show different concerns when choosing green roof systems. Also, green roof solutions vary in their cost and performance. Therefore, decision-makers continually face the difficult task of balancing benefits against green roofs costs. Decision analysis methods, as multicriteria analysis, can be used when the decision‑making process includes different perspectives, multiple objectives, and uncertainty. The present study adopts a multicriteria decision model to evaluate the installation of green roofs in buildings, determining the solution with the best trade-off between costs and benefits in agreement with the preferences of the users/investors. This methodology was applied to a real decision problem, assessing the preferences between different green roof systems in an existing building in Lisbon. This approach supports the decision-making process on green roofs and enables robust and informed decisions on urban planning while optimizing buildings retrofitting.

Keywords: decision making, green roofs, investors preferences, multicriteria analysis, sustainable development

Procedia PDF Downloads 184

Authors: Edgar Santoyo, Daniel Perez-Zarate, Agustin Acevedo, Lorena Diaz-Gonzalez, Mirna Guevara

Abstract:

Four new gas geothermometers have been derived from a multivariate geo chemometric analysis of a geothermal fluid chemistry database, two of which use the natural logarithm of CO₂ and H2S concentrations (mmol/mol), respectively, and the other two use the natural logarithm of the H₂S/H₂ and CO₂/H₂ ratios. As a strict compilation criterion, the database was created with gas-phase composition of fluids and bottomhole temperatures (BHTM) measured in producing wells. The calibration of the geothermometers was based on the geochemical relationship existing between the gas-phase composition of well discharges and the equilibrium temperatures measured at bottomhole conditions. Multivariate statistical analysis together with the use of artificial neural networks (ANN) was successfully applied for correlating the gas-phase compositions and the BHTM. The predicted or simulated bottomhole temperatures (BHTANN), defined as output neurons or simulation targets, were statistically compared with measured temperatures (BHTM). The coefficients of the new geothermometers were obtained from an optimized self-adjusting training algorithm applied to approximately 2,080 ANN architectures with 15,000 simulation iterations each one. The self-adjusting training algorithm used the well-known Levenberg-Marquardt model, which was used to calculate: (i) the number of neurons of the hidden layer; (ii) the training factor and the training patterns of the ANN; (iii) the linear correlation coefficient, R; (iv) the synaptic weighting coefficients; and (v) the statistical parameter, Root Mean Squared Error (RMSE) to evaluate the prediction performance between the BHTM and the simulated BHTANN. The prediction performance of the new gas geothermometers together with those predictions inferred from sixteen well-known gas geothermometers (previously developed) was statistically evaluated by using an external database for avoiding a bias problem. Statistical evaluation was performed through the analysis of the lowest RMSE values computed among the predictions of all the gas geothermometers. The new gas geothermometers developed in this work have been successfully used for predicting subsurface temperatures in high-temperature geothermal systems of Mexico (e.g., Los Azufres, Mich., Los Humeros, Pue., and Cerro Prieto, B.C.) as well as in a blind geothermal system (known as Acoculco, Puebla). The last results of the gas geothermometers (inferred from gas-phase compositions of soil-gas bubble emissions) compare well with the temperature measured in two wells of the blind geothermal system of Acoculco, Puebla (México). Details of this new development are outlined in the present research work. Acknowledgements: The authors acknowledge the funding received from CeMIE-Geo P09 project (SENER-CONACyT).

Keywords: artificial intelligence, gas geochemistry, geochemometrics, geothermal energy

Procedia PDF Downloads 351

Authors: Abdulaziz Afandi

Abstract:

Minimizing the inventory cost, optimizing the inventory quantities, and increasing system operational availability are the main motivations to enhance forecasting demand of spare parts in a major power utility company in Medina. This paper reports in an effort made to optimize the orders quantities of spare parts by improving the method of forecasting the demand. The study focuses on equipment that has frequent spare parts purchase orders with uncertain demand. The pattern of the demand considers a lumpy pattern which makes conventional forecasting methods less effective. A comparison was made by benchmarking various methods of forecasting based on experts’ criteria to select the most suitable method for the case study. Three actual data sets were used to make the forecast in this case study. Two neural networks (NN) approaches were utilized and compared, namely long short-term memory (LSTM) and multilayer perceptron (MLP). The results as expected, showed that the NN models gave better results than traditional forecasting method (judgmental method). In addition, the LSTM model had a higher predictive accuracy than the MLP model.

Keywords: neural network, LSTM, MLP, forecasting demand, inventory management

Procedia PDF Downloads 127

Authors: V. Andal Priyadharshini, Anumalasetty Yashwanth Nath

Abstract:

Network automation has evolved into a solution that ensures efficiency in all areas. The age-old technique to configure common software-defined networking protocols is inefficient as it requires a box-by-box approach that needs to be repeated often and is prone to manual errors. Network automation assists network administrators in automating and verifying the protocol configuration to ensure consistent configurations. This paper implemented network automation using Python and Ansible to configure different protocols and configurations in the container lab virtual environment. Ansible can help network administrators minimize human mistakes, reduce time consumption, and enable device visibility across the network environment.

Keywords: Python network automation, Ansible configuration, container lab deployment, software-defined networking, networking lab

Procedia PDF Downloads 164

Authors: Ji-Hoon Hong, Dong-Hee Kim, Nam-Uk Kim, Tai-Myoung Chung

Abstract:

Smartphone users are increasing rapidly. Accordingly, many companies are running BYOD (Bring Your Own Device: Policies to bring private-smartphones to the company) policy to increase work efficiency. However, smartphones are always under the threat of malware, thus the company network that is connected smartphone is exposed to serious risks. Most smartphone malware detection techniques are to perform an independent detection (perform the detection of a single target application). In this paper, we analyzed a variety of intrusion detection techniques. Based on the results of analysis propose an agent using the network IDS.

Keywords: android malware detection, software-defined network, interaction environment, android malware detection, software-defined network, interaction environment

Procedia PDF Downloads 433

Authors: Skiker Kaoutar, Mounir Maouene

Abstract:

Neuroimaging studies have shown that animal and tool concepts rely on distinct networks of brain areas. Animal concepts depend predominantly on temporal areas while tool concepts rely on fronto-temporo-parietal areas. However, the origin of this neurofunctional distinction for processing animal and tool concepts remains still unclear. Here, we address this question from a network perspective suggesting that the neural distinction between animals and tools might reflect the differences in their structural semantic networks. We build semantic networks for animal and tool concepts derived from Mc Rae and colleagues’s behavioral study conducted on a large number of participants. These two networks are thus analyzed through a large number of graph theoretical measures for small-worldness: centrality, clustering coefficient, average shortest path length, as well as resistance to random and targeted attacks. The results indicate that both animal and tool networks have small-world properties. More importantly, the animal network is more vulnerable to targeted attacks compared to the tool network a result that correlates with brain lesions studies.

Keywords: animals, tools, network, semantics, small-world, resilience to damage

Procedia PDF Downloads 547

Authors: Benjamin Bobbia, Matthias Picard

Abstract:

In recent years active learning methodologies based on the representativity of the data seems more promising to limit overfitting. The presented query methodology for regression using the Wasserstein distance measuring the representativity of our labelled dataset compared to the global distribution. In this work a crucial use of GroupSort Neural Networks is made therewith to draw a double advantage. The Wasserstein distance can be exactly expressed in terms of such neural networks. Moreover, one can provide explicit bounds for their size and depth together with rates of convergence. However, heterogeneity of the dataset is also considered by weighting the Wasserstein distance with the error of approximation at the previous step of active learning. Such an approach leads to a reduction of overfitting and high prediction performance after few steps of query. After having detailed the methodology and algorithm, an empirical study is presented in order to investigate the range of our hyperparameters. The performances of this method are compared, in terms of numbers of query needed, with other classical and recent query methods on several UCI datasets.

Keywords: active learning, Lipschitz regularization, neural networks, optimal transport, regression

Procedia PDF Downloads 80

Authors: Mahmoud Almasri, Xavier Marjou, Fanny Parzysz

Abstract:

The demand for services provided by Unmanned Aerial Vehicles (UAVs) is increasing pervasively across several sectors including potential public safety, economic, and delivery services. As the number of applications using UAVs grows rapidly, more and more powerful, quality of service, and power efficient computing units are necessary. Recently, cellular technology draws more attention to connectivity that can ensure reliable and flexible communications services for UAVs. In cellular technology, flying with a high speed and altitude is subject to several key challenges, such as frequent handovers (HOs), high interference levels, connectivity coverage holes, etc. Additional HOs may lead to “ping-pong” between the UAVs and the serving cells resulting in a decrease of the quality of service and energy consumption. In order to optimize the number of HOs, we develop in this paper a Q-learning-based algorithm. While existing works focus on adjusting the number of HOs in a static network topology, we take into account the impact of cells deployment for three different simulation scenarios (Rural, Semi-rural and Urban areas). We also consider the impact of the decision distance, where the drone has the choice to make a switching decision on the number of HOs. Our results show that a Q-learning-based algorithm allows to significantly reduce the average number of HOs compared to a baseline case where the drone always selects the cell with the highest received signal. Moreover, we also propose which hyper-parameters have the largest impact on the number of HOs in the three tested environments, i.e. Rural, Semi-rural, or Urban.

Keywords: drones connectivity, reinforcement learning, handovers optimization, decision distance

Procedia PDF Downloads 108

Authors: Philipp Ruf, Massiwa Chabbi, Christoph Reich, Djaffar Ould-Abdeslam

Abstract:

In recent years, convolutional neural networks (CNN) have demonstrated high performance in image analysis, but oftentimes, there is only structured data available regarding a specific problem. By interpreting structured data as images, CNNs can effectively learn and extract valuable insights from tabular data, leading to improved predictive accuracy and uncovering hidden patterns that may not be apparent in traditional structured data analysis. In applying a single neural network for analyzing multimodal data, e.g., both structured and unstructured information, significant advantages in terms of time complexity and energy efficiency can be achieved. Converting structured data into images and merging them with existing visual material offers a promising solution for applying CNN in multimodal datasets, as they often occur in a medical context. By employing suitable preprocessing techniques, structured data is transformed into image representations, where the respective features are expressed as different formations of colors and shapes. In an additional step, these representations are fused with existing images to incorporate both types of information. This final image is finally analyzed using a CNN.

Keywords: CNN, image processing, tabular data, mixed dataset, data transformation, multimodal fusion

Procedia PDF Downloads 123

Authors: Patricia Heredia, Isabel Saz, Marta Fernández

Abstract:

This article proposes that the decision regarding exporting and the choice of export channel are nested and non-independent decisions. We assume that firms make two sequential decisions before arriving at their final choice: the decision to access foreign markets and the decision about the type of channel. This hierarchical perspective of the choices involved in the process is appealing for two reasons. First, it supports the idea that people have a limited analytical capacity. Managers often break down a complex decision into a hierarchical process because this makes it more manageable. Secondly, it recognizes that important differences exist between entry modes. In light of the above, the objective of this study is to test different entry mode choice processes: independent decisions and nested and non-independent decisions. To do this, the methodology estimates and compares the following two models: (i) a simultaneous single-stage model with three entry mode choices (using a multinomial logit model); ii) a two-stage model with the export decision preceding the channel decision using a sequential logit model. The study uses resource-based factors in determining these decision processes concerning internationalization and the study carries out empirical analysis using a DOC Rioja sample of 177 firms.Using the Akaike and Schwarz Information Criteria, the empirical evidence supports the existence of a nested structure, where the decision about exporting precedes the export mode decision. The implications and contributions of the findings are discussed.

Keywords: sequential logit model, two-stage choice process, export mode, wine industry

Procedia PDF Downloads 29

Authors: Asma Ben Yaghlane, Mohamed Naceur Azaiez, Mehdi Mrad

Abstract:

We investigate the large scale of networks in the context of network survivability under attack. We use appropriate techniques to evaluate and the attacker-based- and the defender-based-network survivability. The attacker is unaware of the operated links by the defender. Each attacked link has some pre-specified probability to be disconnected. The defender choice is so that to maximize the chance of successfully sending the flow to the destination node. The attacker however will select the cut-set with the highest chance to be disabled in order to partition the network. Moreover, we extend the problem to the case of selecting the best p paths to operate by the defender and the best k cut-sets to target by the attacker, for arbitrary integers p,k > 1. We investigate some variations of the problem and suggest polynomial-time solutions.

Keywords: defense/attack strategies, large scale, networks, partitioning a network

Procedia PDF Downloads 283