Search results for: time delay neural network

Authors: Zhenzhen Xu, Chunfu Shao, Shengyou Wang, Chunjiao Dong

Abstract:

To improve the satisfaction of residents' travel, this paper analyzes the characteristics and influencing factors of urban residents' travel behavior. First, a Multinominal Logit Model (MNL) model is built to analyze the characteristics of residents' travel behavior, reveal the influence of individual attributes, family attributes and travel characteristics on the choice of travel mode, and identify the significant factors. Then put forward suggestions for policy improvement. Finally, Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) models are introduced to evaluate the policy effect. This paper selects Futian Street in Futian District, Shenzhen City for investigation and research. The results show that gender, age, education, income, number of cars owned, travel purpose, departure time, journey time, travel distance and times all have a significant influence on residents' choice of travel mode. Based on the above results, two policy improvement suggestions are put forward from reducing public transportation and non-motor vehicle travel time, and the policy effect is evaluated. Before the evaluation, the prediction effect of MNL, SVM and MLP models was evaluated. After parameter optimization, it was found that the prediction accuracy of the three models was 72.80%, 71.42%, and 76.42%, respectively. The MLP model with the highest prediction accuracy was selected to evaluate the effect of policy improvement. The results showed that after the implementation of the policy, the proportion of public transportation in plan 1 and plan 2 increased by 14.04% and 9.86%, respectively, while the proportion of private cars decreased by 3.47% and 2.54%, respectively. The proportion of car trips decreased obviously, while the proportion of public transport trips increased. It can be considered that the measures have a positive effect on promoting green trips and improving the satisfaction of urban residents, and can provide a reference for relevant departments to formulate transportation policies.

Keywords: neural network, travel characteristics analysis, transportation choice, travel sharing rate, traffic resource allocation

Procedia PDF Downloads 138

Authors: Jorge Rodriguez-Guerra, Carlos Calleja, Aron Pujana, Iker Elorza, Ana Maria Macarulla

Abstract:

Society demands more reliable manufacturing processes capable of producing high quality products in shorter production cycles. New control algorithms have been studied to satisfy this paradigm, in which Fault-Tolerant Control (FTC) plays a significant role. It is suitable to detect, isolate and adapt a system when a harmful or faulty situation appears. In this paper, a general overview about FTC characteristics are exposed; highlighting the properties a system must ensure to be considered faultless. In addition, a research to identify which are the main FTC techniques and a classification based on their characteristics is presented in two main groups: Active Fault-Tolerant Controllers (AFTCs) and Passive Fault-Tolerant Controllers (PFTCs). AFTC encompasses the techniques capable of re-configuring the process control algorithm after the fault has been detected, while PFTC comprehends the algorithms robust enough to bypass the fault without further modifications. The mentioned re-configuration requires two stages, one focused on detection, isolation and identification of the fault source and the other one in charge of re-designing the control algorithm by two approaches: fault accommodation and control re-design. From the algorithms studied, one has been selected and applied to a case study based on an industrial hydraulic-press. The developed model has been embedded under a real-time validation platform, which allows testing the FTC algorithms and analyse how the system will respond when a fault arises in similar conditions as a machine will have on factory. One AFTC approach has been picked up as the methodology the system will follow in the fault recovery process. In a first instance, the fault will be detected, isolated and identified by means of a neural network. In a second instance, the control algorithm will be re-configured to overcome the fault and continue working without human interaction.

Keywords: fault-tolerant control, electro-hydraulic actuator, fault detection and isolation, control re-design, real-time

Procedia PDF Downloads 177

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 63

Authors: Swapnil Singh, Sanjoy Das

Abstract:

Mobile Ad-Hoc Network (MANET) is infrastructure less networks dynamically formed by autonomous system of mobile nodes that are connected via wireless links. Mobile nodes communicate with each other on the fly. In this network each node also acts as a router. The battery power and the bandwidth are very scarce resources in this network. The network lifetime and connectivity of nodes depends on battery power. Therefore, energy is a valuable constraint which should be efficiently used. In this paper, we survey various energy efficient routing protocol. The energy efficient routing protocols are classified on the basis of approaches they use to minimize the energy consumption. The purpose of this paper is to facilitate the research work and combine the existing solution and to develop a more energy efficient routing mechanism.

Keywords: delaunay triangulation, deployment, energy efficiency, MANET

Procedia PDF Downloads 615

Authors: María Dolores Caro, Eugenio M. Fedriani, Ángel F. Tenorio

Abstract:

The transportation of dangerous goods by lorries throughout Europe must be done by using the roads conforming the European Road Transport Network. In this network, there are several parking areas where lorry drivers can park to rest according to the regulations. According to the "European Agreement concerning the International Carriage of Dangerous Goods by Road", parking areas where lorries transporting dangerous goods can park to rest, must follow several security stipulations to keep safe the rest of road users. At this respect, these lorries must be parked in adapted areas with strict and permanent surveillance measures. Moreover, drivers must satisfy several restrictions about resting and driving time. Under these facts, one may expect that there exist enough parking areas for the transport of this type of goods in order to obey the regulations prescribed by the European Union and its member countries. However, the already-existing parking areas are not sufficient to cover all the stops required by drivers transporting dangerous goods. Our main goal is, starting from the already-existing parking areas and the loading-and-unloading location, to provide an optimal answer to the following question: how many additional parking areas must be built and where must they be located to assure that lorry drivers can transport dangerous goods following all the stipulations about security and safety for their stops? The sense of the word “optimal” is due to the fact that we give a global solution for the location of parking areas throughout the whole European Road Transport Network, adjusting the number of additional areas to be as lower as possible. To do so, we have modeled the problem using graph theory since we are working with a road network. As nodes, we have considered the locations of each already-existing parking area, each loading-and-unloading area each road bifurcation. Each road connecting two nodes is considered as an edge in the graph whose weight corresponds to the distance between both nodes in the edge. By applying a new efficient algorithm, we have found the additional nodes for the network representing the new parking areas adapted for dangerous goods, under the fact that the distance between two parking areas must be less than or equal to 400 km.

Keywords: trans-european transport network, dangerous goods, parking areas, graph-based modeling

Procedia PDF Downloads 280

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 266

Authors: Yasmina Houda Bendahma, Tewfik Bouchaour, Meriem Merad, Ulrich Maschke

Abstract:

The purpose of this work is to study retention of dye dissolved in distilled water, by an hydrophilic acrylic polymer network. The polymer network considered is Poly (2-hydroxyethyl methacrylate) (PHEMA): it is prepared by photo-polymerization under UV irradiation in the presence of a monomer (HEMA), initiator and an agent cross-linker. PHEMA polymer network obtained can be used in the retention of dye molecules present in the wastewater. The results obtained are interesting in the study of the kinetics of swelling and de-swelling of cross linked polymer networks PHEMA in colored aqueous solutions. The dyes used for retention by the PHEMA networks are eosin Y and Malachite Green, dissolved in distilled water. Theoretical conformational study by a simplified molecular model of system cross linked PHEMA / dye (eosin Y and Malachite Green), is used to simulate the retention phenomenon (or Docking) dye molecules in cavities in nano-domains included in the PHEMA polymer network.

Keywords: dye retention, molecular modeling, photochemically crosslinked polymer network, swelling deswelling, PHEMA, HEMA

Procedia PDF Downloads 365

Authors: Min Shi

Abstract:

State of the art research with Artificial Neural Networks for the downscaling of General Circulation Models (GCMs) mainly uses back-propagation algorithm as a training approach. This paper introduces another training approach of ANNs, Evolutionary Algorithm. The combined algorithm names neuroevolutionary (NE) algorithm. We investigate and evaluate the use of the NE algorithms in statistical downscaling by generating temperature estimates at interior points given information from a lattice of surrounding locations. The results of our experiments indicate that NE algorithms can be efficient alternative downscaling methods for daily temperatures.

Keywords: temperature, downscaling, artificial neural networks, evolutionary algorithms

Procedia PDF Downloads 349

Authors: Diogo Prosdocimi, Don Ross, Matthew Townshend

Abstract:

Road authorities are mandated within limited budgets to both deliver improved access to basic services and facilitate economic growth. This responsibility is further complicated if maintenance backlogs and funding shortfalls exist, as evident in many countries including South Africa. These conditions require authorities to make difficult prioritisation decisions, with the effect that Road Asset Management Systems with a one-dimensional focus on traffic volumes may overlook the maintenance of low-volume roads that provide isolated communities with vital access to basic services. Given these challenges, this paper overlays the full South African road network with geo-referenced information for population, primary and secondary schools, and healthcare facilities to identify the network of connective roads between communities and basic service centres. This connective network is then rationalised according to the Gross Value Added and number of jobs per mesozone, administrative and functional road classifications, speed limit, and road length, location, and name to estimate the Basic Access Road Network. A two-step floating catchment area (2SFCA) method, capturing a weighted assessment of drive-time to service centres and the ratio of people within a catchment area to teachers and healthcare workers, is subsequently applied to generate a Multivariate Road Index. This Index is used to assign higher maintenance priority to roads within the Basic Access Road Network that provide more people with better access to services. The relatively limited incidence of Basic Access Roads indicates that authorities could maintain the entire estimated network without exhausting the available road budget before practical economic considerations get any purchase. Despite this fact, a final case study modelling exercise is performed for the Namakwa District Municipality to demonstrate the extent to which optimal relocation of schools and healthcare facilities could minimise the Basic Access Road Network and thereby release budget for investment in roads that best promote GDP growth.

Keywords: basic access roads, multivariate road index, road prioritisation, two-step floating catchment area method

Procedia PDF Downloads 231

Authors: Chien-Lin Wang, Cha-Ling Ko, Tainsong Chen

Abstract:

Pulse wave velocity (PWV) of blood flow provides important information of vessel property and blood pressure which can be used to assess cardiovascular disease. However, the above measurements need expensive equipment, such as Doppler ultrasound, MRI, angiography etc. The photoplethysmograph (PPG) signals are commonly utilized to detect blood volume changes. In this study, two infrared (IR) probes are designed and placed at a fixed distance from finger base and fingertip. An analog circuit with automatic gain adjustment is implemented to get the stable original PPG signals from above two IR probes. In order to obtain the time delay precisely between two PPG signals, we obtain the pulse transit time from the second derivative of the original PPG signals. To get a portable, wireless and low power consumption PWV measurement device, the low energy Bluetooth 4.0 (BLE) and the microprocessor (Cortex™-M3) are used in this study. The PWV is highly correlated with blood pressure. This portable device has potential to be used for continuous blood pressure monitoring.

Keywords: pulse wave velocity, photoplethysmography, portable device, biomedical engineering

Procedia PDF Downloads 527

Authors: Jakyoung Kim, Sungwook Jang

Abstract:

The purpose of this study is to examine the research trends of life-long education for people with disabilities using a keyword network analysis. For this purpose, 151 papers were selected from 594 papers retrieved using keywords such as 'people with disabilities' and 'life-long education' in the Korean Education and Research Information Service. The Keyword network analysis was constructed by extracting and coding the keyword used in the title of the selected papers. The frequency of the extracted keywords, the centrality of degree, and betweenness was analyzed by the keyword network. The results of the keyword network analysis are as follows. First, the main keywords that appeared frequently in the study of life-long education for people with disabilities were 'people with disabilities', 'life-long education', 'developmental disabilities', 'current situations', 'development'. The research trends of life-long education for people with disabilities are focused on the current status of the life-long education and the program development. Second, the keyword network analysis and visualization showed that the keywords with high frequency of occurrences also generally have high degree centrality and betweenness centrality. In terms of the keyword network diagram, it was confirmed that research trends of life-long education for people with disabilities are centered on six prominent keywords. Based on these results, it was discussed that life-long education for people with disabilities in the future needs to expand the subjects and the supporting areas of the life-long education, and the research needs to be further expanded into more detailed and specific areas. 

Keywords: life-long education, people with disabilities, research trends, keyword network analysis

Procedia PDF Downloads 338

Authors: Lutful Karim, Mohammed S. Al-kahtani

Abstract:

Sensors are being used in various applications such as agriculture, health monitoring, air and water pollution monitoring, traffic monitoring and control and hence, play the vital role in the growth of big data. However, sensors collect redundant data. Thus, aggregating and filtering sensors data are significantly important to design an efficient big data framework. Current researches do not focus on aggregating and filtering data at multiple layers of sensor-based big data framework. Thus, this paper introduces (i) three layers data aggregation and framework for big data and (ii) a priority-based, dynamic data aggregation scheme (PDDA) for the lowest layer at sensors. Simulation results show that the PDDA outperforms existing tree and cluster-based data aggregation scheme in terms of overall network energy consumptions and end-to-end data transmission delay.

Keywords: big data, clustering, tree topology, data aggregation, sensor networks

Procedia PDF Downloads 346

Authors: Ather Saeed, Arif Khan, Jeffrey Gosper

Abstract:

Sensor devices are prone to errors and sudden node failures, which are difficult to detect in a timely manner when deployed in real-time, hazardous, large-scale harsh environments and in medical emergencies. Therefore, the loss of data can be life-threatening when the sensed phenomenon is not disseminated due to sudden node failure, battery depletion or temporary malfunctioning. We introduce a set of partial differential equations for localizing faults, similar to Green’s and Maxwell’s equations used in Electrostatics and Electromagnetism. We introduce a node organization and clustering scheme for self-stabilizing sensor networks. Green’s theorem is applied to regions where the curve is closed and continuously differentiable to ensure network connectivity. Experimental results show that the proposed GTFD (Green’s Theorem fault-detection and Self-stabilization) protocol not only detects faulty nodes but also accurately generates network stability graphs where urgent intervention is required for dynamically self-stabilizing the network.

Keywords: Green’s Theorem, self-stabilization, fault-localization, RSSI, WSN, clustering

Procedia PDF Downloads 75

Authors: Chaghoub Soraya, Zhang Xiaoyan

Abstract:

This research presents the first constant approximation algorithm to the p-median network design problem with multiple cable types. This problem was addressed with a single cable type and there is a bifactor approximation algorithm for the problem. To the best of our knowledge, the algorithm proposed in this paper is the first constant approximation algorithm for the p-median network design with multiple cable types. The addressed problem is a combination of two well studied problems which are p-median problem and network design problem. The introduced algorithm is a random sampling approximation algorithm of constant factor which is conceived by using some random sampling techniques form the literature. It is based on a redistribution Lemma from the literature and a steiner tree problem as a subproblem. This algorithm is simple, and it relies on the notions of random sampling and probability. The proposed approach gives an approximation solution with one constant ratio without violating any of the constraints, in contrast to the one proposed in the literature. This paper provides a (21 + 2)-approximation algorithm for the p-median network design problem with multiple cable types using random sampling techniques.

Keywords: approximation algorithms, buy-at-bulk, combinatorial optimization, network design, p-median

Procedia PDF Downloads 203

Authors: S. B. Kumbalavati, J. D. Mallapur, K. Y. Bendigeri

Abstract:

A mobile Ad-hoc network (MANET) is a multihop wireless network where nodes communicate each other without any pre-deployed infrastructure. There is no central administrating unit. Hence, MANET is generally prone to many of the attacks. These attacks may alter, release or deny data. These attacks are nothing but intrusions. Intrusion is a set of actions that attempts to compromise integrity, confidentiality and availability of resources. A major issue in the design and operation of ad-hoc network is sharing the common spectrum or common channel bandwidth among all the nodes. We are performing intrusion detection using game theory approach. Game theory is a mathematical tool for analysing problems of competition and negotiation among the players in any field like marketing, e-commerce and networking. In this paper mathematical model is developed using game theory approach and intruders are detected and removed. Bandwidth utilization is estimated and comparison is made between bandwidth utilization with intrusion detection technique and without intrusion detection technique. Percentage of intruders and efficiency of the network is analysed.

Keywords: ad-hoc network, IDS, game theory, sensor networks

Procedia PDF Downloads 387

Authors: Mohamed Adnan Landolsi, Ali F. Almutairi

Abstract:

The paper addresses the problem of line-of-sight (LOS) vs. non-line-of-sight (NLOS) propagation link identification in ultra-wideband (UWB) wireless networks, which is necessary for improving the accuracy of radiolocation and positioning applications. A LOS/NLOS likelihood hypothesis testing approach is applied based on exploiting distinctive statistical features of the channel impulse response (CIR) using parameters related to the “skewness” of the CIR and its root mean square (RMS) delay spread. A log-normal fit is presented for the probability densities of the CIR parameters. Simulation results show that different environments (residential, office, outdoor, etc.) have measurable differences in their CIR parameters’ statistics, which is then exploited in determining the nature of the propagation channels. Correct LOS/NLOS channel identification rates exceeding 90% are shown to be achievable for most types of environments. Additional improvement is also obtained by combining both CIR skewness and RMS delay statistics.

Keywords: UWB, propagation, LOS, NLOS, identification

Procedia PDF Downloads 249

Authors: Dalin Si, Azizan Aziz, Bertrand Lasternas

Abstract:

To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.

Keywords: building energy prediction, data mining, demand response, electricity market

Procedia PDF Downloads 316

Authors: P. L. Cheng, I. N. Umar

Abstract:

Online discussion forum is a popular e-learning technique that allows participants to interact and construct knowledge. This study aims to examine the levels of participation, categories of participants and the structure of their interactions in a forum. A convenience sampling of one course coordinator and 23 graduate students was selected in this study. The forums’ log file and the Social Network Analysis software were used in this study. The analysis reveals 610 activities (including viewing forum’s topic, viewing discussion thread, posting a new thread, replying to other participants’ post, updating an existing thread and deleting a post) performed by them in this forum, with an average of 3.83 threads posted. Also, this forum consists of five at-risk participants, six bridging participants, four isolated participants and five leaders of information. In addition, the network density value is 0.15 and there exist five reciprocal interactions in this forum. The closeness value varied between 28 and 68 while the eigen vector centrality value varied between 0.008 and 0.39. The finding indicates that the participants tend to listen more rather than express their opinions in the forum. It was also revealed that those who actively provide supports in the discussion forum were not the same people who received the most responses from their peers. This study found that cliques do not exist in the forum and the participants are not selective to whom they response to, rather, it was based on the content of the posts made by their peers. Based upon the findings, further analysis with different method and population, larger sample size and a longer time frame are recommended.

Keywords: e-learning, learning management system, online forum, social network analysis

Procedia PDF Downloads 390

Authors: Djamel Fawzi Hadj Sadok, Marrone Silvério Melo Dantas Pedro Henrique Dreyer, Gabriel Fonseca Reis de Souza, Daniel Bezerra, Ricardo Souza, Silvia Lins, Judith Kelner

Abstract:

A radio base station (RBS), part of the radio access network, is a particular type of equipment that supports the connection between a wide range of cellular user devices and an operator network access infrastructure. Nowadays, most of the RBS maintenance is carried out manually, resulting in a time consuming and costly task. A suitable candidate for RBS maintenance automation is repairing faulty links between devices caused by missing or unplugged connectors. A suitable candidate for RBS maintenance automation is repairing faulty links between devices caused by missing or unplugged connectors. This paper proposes and compares two deep learning solutions to identify attached RJ45 connectors on network ports. We named connector detection, the solution based on object detection, and connector classification, the one based on object classification. With the connector detection, we get an accuracy of 0:934, mean average precision 0:903. Connector classification, get a maximum accuracy of 0:981 and an AUC of 0:989. Although connector detection was outperformed in this study, this should not be viewed as an overall result as connector detection is more flexible for scenarios where there is no precise information about the environment and the possible devices. At the same time, the connector classification requires that information to be well-defined.

Keywords: radio base station, maintenance, classification, detection, deep learning, automation

Procedia PDF Downloads 201

Authors: Sophia Shi

Abstract:

Acute kidney injury (AKI) is the sudden onset of kidney damage in which the kidneys cannot filter waste from the blood, requiring emergency hospitalization. AKI patient mortality rate is high in the ICU and is virtually impossible for doctors to predict because it is so unexpected. Currently, there is no hybrid model predicting AKI that takes advantage of two types of data. De-identified patient data from the MIMIC-III database and de-identified kidney images and corresponding patient records from the Beijing Hospital of the Ministry of Health were collected. Using data features including serum creatinine among others, two numeric models using MIMIC and Beijing Hospital data were built, and with the hospital ultrasounds, an image-only model was built. Convolutional neural networks (CNN) were used, VGG and Resnet for numeric data and Resnet for image data, and they were combined into a hybrid model by concatenating feature maps of both types of models to create a new input. This input enters another CNN block and then two fully connected layers, ending in a binary output after running through Softmax and additional code. The hybrid model successfully predicted AKI and the highest AUROC of the model was 0.953, achieving an accuracy of 90% and F1-score of 0.91. This model can be implemented into urgent clinical settings such as the ICU and aid doctors by assessing the risk of AKI shortly after the patient’s admission to the ICU, so that doctors can take preventative measures and diminish mortality risks and severe kidney damage.

Keywords: Acute kidney injury, Convolutional neural network, Hybrid deep learning, Patient record data, ResNet, Ultrasound kidney images, VGG

Procedia PDF Downloads 131

Authors: Pranav Gunhal., Krish Jhurani

Abstract:

This study tackles the significant computational challenge of predicting excited state dynamics in organic photovoltaic (OPV) materials—a pivotal factor in the performance of solar energy solutions. Time-dependent density functional theory (TDDFT), though effective, is computationally prohibitive for larger and more complex molecules. As a solution, the research explores the application of transformer neural networks, a type of artificial intelligence (AI) model known for its superior performance in natural language processing, to predict excited state dynamics in OPV materials. The methodology involves a two-fold process. First, the transformer model is trained on an extensive dataset comprising over 10,000 TDDFT calculations of excited state dynamics from a diverse set of OPV materials. Each training example includes a molecular structure and the corresponding TDDFT-calculated excited state lifetimes and key electronic transitions. Second, the trained model is tested on a separate set of molecules, and its predictions are rigorously compared to independent TDDFT calculations. The results indicate a remarkable degree of predictive accuracy. Specifically, for a test set of 1,000 OPV materials, the transformer model predicted excited state lifetimes with a mean absolute error of 0.15 picoseconds, a negligible deviation from TDDFT-calculated values. The model also correctly identified key electronic transitions contributing to the excited state dynamics in 92% of the test cases, signifying a substantial concordance with the results obtained via conventional quantum chemistry calculations. The practical integration of the transformer model with existing quantum chemistry software was also realized, demonstrating its potential as a powerful tool in the arsenal of materials scientists and chemists. The implementation of this AI model is estimated to reduce the computational cost of predicting excited state dynamics by two orders of magnitude compared to conventional TDDFT calculations. The successful utilization of transformer neural networks to accurately predict excited state dynamics provides an efficient computational pathway for the accelerated discovery and design of new OPV materials, potentially catalyzing advancements in the realm of sustainable energy solutions.

Keywords: transformer neural networks, organic photovoltaic materials, excited state dynamics, time-dependent density functional theory, predictive modeling

Procedia PDF Downloads 118

Authors: Akeel A. Shah, Tong Zhang

Abstract:

Computational approaches to learning the properties of materials are commonplace, motivated by the need to screen or design materials for a given application, e.g., semiconductors and energy storage. Experimental approaches can be both time consuming and costly. Unfortunately, computational approaches such as ab-initio electronic structure calculations and classical or ab-initio molecular dynamics are themselves can be too slow for the rapid evaluation of materials, often involving thousands to hundreds of thousands of candidates. Machine learning assisted approaches have been developed to overcome the time limitations of purely physics-based approaches. These approaches, on the other hand, require large volumes of data for training (hundreds of thousands on many standard data sets such as QM7b). This means that they are limited by how quickly such a large data set of physics-based simulations can be established. At high fidelity, such as configuration interaction, composite methods such as G4, and coupled cluster theory, gathering such a large data set can become infeasible, which can compromise the accuracy of the predictions - many applications require high accuracy, for example band structures and energy levels in semiconductor materials and the energetics of charge transfer in energy storage materials. In order to circumvent this problem, multi-fidelity approaches can be adopted, for example the Δ-ML method, which learns a high-fidelity output from a low-fidelity result such as Hartree-Fock or density functional theory (DFT). The general strategy is to learn a map between the low and high fidelity outputs, so that the high-fidelity output is obtained a simple sum of the physics-based low-fidelity and correction, Although this requires a low-fidelity calculation, it typically requires far fewer high-fidelity results to learn the correction map, and furthermore, the low-fidelity result, such as Hartree-Fock or semi-empirical ZINDO, is typically quick to obtain, For high-fidelity outputs the result can be an order of magnitude or more in speed up. In this work, a new multi-fidelity approach is developed, based on a graph convolutional network (GCN) combined with semi-supervised learning. The GCN allows for the material or molecule to be represented as a graph, which is known to improve accuracy, for example SchNet and MEGNET. The graph incorporates information regarding the numbers of, types and properties of atoms; the types of bonds; and bond angles. They key to the accuracy in multi-fidelity methods, however, is the incorporation of low-fidelity output to learn the high-fidelity equivalent, in this case by learning their difference. Semi-supervised learning is employed to allow for different numbers of low and high-fidelity training points, by using an additional GCN-based low-fidelity map to predict high fidelity outputs. It is shown on 4 different data sets that a significant (at least one order of magnitude) increase in accuracy is obtained, using one to two orders of magnitude fewer low and high fidelity training points. One of the data sets is developed in this work, pertaining to 1000 simulations of quinone molecules (up to 24 atoms) at 5 different levels of fidelity, furnishing the energy, dipole moment and HOMO/LUMO.

Keywords: .materials screening, computational materials, machine learning, multi-fidelity, graph convolutional network, semi-supervised learning

Procedia PDF Downloads 41

Authors: Semih Demir, Anil Celebi

Abstract:

Circuit switched networks widely used until the end of the 20^th century have been transformed into packages switched networks. Time Division Multiplexing over Internet Protocol (TDMoIP) is a system that enables Time Division Multiplexing (TDM) traffic to be carried over packet switched networks (PSN). In TDMoIP systems, devices that send TDM data to the PSN and receive it from the network must operate with the same clock frequency. In this study, it was aimed to implement clock synchronization process in Field Programmable Gate Array (FPGA) chips using time information attached to the packages received from PSN. The designed hardware is verified using the datasets obtained for the different carrier types and comparing the results with the software model. Field tests are also performed by using the real time TDMoIP system.

Keywords: clock recovery on TDMoIP, FPGA, MATLAB reference model, clock synchronization

Procedia PDF Downloads 278

Authors: R. Rajabpour, N. Talebbeydokhti, M. H. Ahmadi

Abstract:

Carefully scheduling the operations of pumps can be resulted to significant energy savings. Schedules can be defined either implicit, in terms of other elements of the network such as tank levels, or explicit by specifying the time during which each pump is on/off. In this study, two new explicit representations based on time-controlled triggers were analyzed, where the maximum number of pump switches was established beforehand, and the schedule may contain fewer switches than the maximum. The optimal operation of pumping stations was determined using a Jumping Particle Swarm Optimization (JPSO) algorithm to achieve the minimum energy cost. The model integrates JPSO optimizer and EPANET hydraulic network solver. The optimal pump operation schedule of VanZyl water distribution system was determined using the proposed model and compared with those from Genetic and Ant Colony algorithms. The results indicate that the proposed model utilizing the JPSP algorithm outperformed the others and is a versatile management model for the operation of real-world water distribution system.

Keywords: JPSO, operation, optimization, water distribution system

Procedia PDF Downloads 245

Authors: Anton V. Bourdine, Vladimir A. Burdin, Oleg R. Delmukhametov

Abstract:

This work presents a fast and simple method for the design of large core silica optical fibers with differential mode delay (DMD) management. Some results are reported concerned with refractive index profile optimization for 42 µm core 16-LP-mode optical fiber for next-generation optical networks. Here special refractive index profile form provides total DMD reducing over all mode staff under desired enhanced mode effective area. Method for the simulation of 'real manufactured' few-mode optical fiber (FMF) core geometry differing from the desired optimized structure by core non-symmetrical ellipticity and refractive index profile deviation including local fluctuations is proposed. Results of the following analysis of optimized FMF with inserted geometry distortions performed by earlier on developed modification of rigorous mixed finite-element method showed strong DMD degradation that requires additional higher-order mode management. In addition, this work also presents a method for design mode division multiplexer channel precision spatial positioning scheme at FMF core end that provides one of the potentiality solutions of described DMD degradation problem concerned with 'distorted' core geometry due to features of optical fiber manufacturing techniques.

Keywords: differential mode delay, few-mode optical fibers, nonlinear Shannon limit, optical fiber non-circularity, ‘real manufactured’ optical fiber core geometry simulation, refractive index profile optimization

Procedia PDF Downloads 157

Authors: M. Kamel, A. Hoayek, M. Batton-Hubert

Abstract:

With the increase of network virtualization and the disparity of vendors, the continuous monitoring and detection of anomalies cannot rely on static rules. An advanced analytical methodology is needed to discriminate between ordinary events and unusual anomalies. In this paper, we focus on log data (textual data), which is a crucial source of information for network performance. Then, we introduce an algorithm used as a pipeline to help with the pretreatment of such data, group it into patterns, and dynamically label each pattern as an anomaly or not. Such tools will provide users and experts with continuous real-time logs monitoring capability to detect anomalies and failures in the underlying system that can affect performance. An application of real-world data illustrates the algorithm.

Keywords: logs, anomaly detection, ML, scoring, NLP

Procedia PDF Downloads 94

Authors: M. Hussain, Aqsa Farooq

Abstract:

Let G = (V,E) be a connected graph and distance between any two vertices a and b in G is a−b geodesic and is denoted by d(a, b). A set of vertices W resolves a graph G if each vertex is uniquely determined by its vector of distances to the vertices in W. A metric dimension of G is the minimum cardinality of a resolving set of G. In this paper line graph of honeycomb network has been derived and then we calculated the metric dimension on line graph of honeycomb network.

Keywords: Resolving set, Metric dimension, Honeycomb network, Line graph

Procedia PDF Downloads 200

Authors: Olamide Shittu, Olayinka Akanle

Abstract:

Value Chain Analysis is a common method of examining the stages involved in the production of a product, mostly agricultural produce, from the input to the consumption stage including the actors involved in each stage. However, the Functional Institutional Analysis is the most common method in literature employed to analyze the value chain of products. Apart from studying the relatively neglected phenomenon of recycled polymer products in Lagos Metropolis, this paper adopted the use of social network analysis to attempt a grounded theory of the nature of social network that exists among the value chain actors of the subject matter. The study adopted a grounded theory approach by conducting in-depth interviews, administering questionnaires and conducting observations among the identified value chain actors of recycled polymer products in Lagos Metropolis, Nigeria. The thematic analysis of the collected data gave the researchers the needed background to formulate a truly representative network of the social relationships among the value chain actors of recycled polymer products in Lagos Metropolis. The paper introduced concepts such as Transient and Perennial Social Ties to explain the observed social relations among the actors. Some actors have more social capital than others as a result of the structural holes that exist in their triad network. Households and resource recoverers are at disadvantaged position in the network as they have high constraints in their relationships with other actors. The study attempted to provide a new perspective in the study of the environmental value chain by analyzing the network of actors to bring about policy action points and improve recycling in Nigeria. Government and social entrepreneurs can exploit the structural holes that exist in the network for the socio-economic and sustainable development of the state.

Keywords: recycled polymer products, social network analysis, social ties, value chain analysis

Procedia PDF Downloads 410

Authors: E. Sobhani-Tehrani, K. Khorasani, N. Meskin

Abstract:

This paper presents a novel integrated hybrid approach for fault diagnosis (FD) of nonlinear systems. Unlike most FD techniques, the proposed solution simultaneously accomplishes fault detection, isolation, and identification (FDII) within a unified diagnostic module. At the core of this solution is a bank of adaptive neural parameter estimators (NPE) associated with a set of single-parameter fault models. The NPEs continuously estimate unknown fault parameters (FP) that are indicators of faults in the system. Two NPE structures including series-parallel and parallel are developed with their exclusive set of desirable attributes. The parallel scheme is extremely robust to measurement noise and possesses a simpler, yet more solid, fault isolation logic. On the contrary, the series-parallel scheme displays short FD delays and is robust to closed-loop system transients due to changes in control commands. Finally, a fault tolerant observer (FTO) is designed to extend the capability of the NPEs to systems with partial-state measurement.

Keywords: hybrid fault diagnosis, dynamic neural networks, nonlinear systems, fault tolerant observer

Procedia PDF Downloads 401

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 161