Search results for: credit network

Authors: Vinko Vidučić, Ljiljana Vidučić, Damir Boras

Abstract:

The goals of the research include the determination of the characteristics of SMEs finance in Croatia, as well as the determination of indirect growth rates of the information model of the entrepreneurs` perception of business environment. The research results show that cost of finance and access to finance are most important constraining factor in setting up and running the business of small entrepreneurs in Croatia. Furthermore, small entrepreneurs in Croatia are significantly dissatisfied with the administrative barriers although relatively to a lesser extent than was the case in the pre-crisis time. High collateral requirement represents the main characteristic of bank lending concerning SMEs followed by long credit elaboration process. Formulated information model has defined the individual impact of indirect growth rates of the remaining variables on the model’s specific variable.

Keywords: business environment, information model, indirect growth rates, SME finance

Procedia PDF Downloads 363

Authors: Hongyun Li, Zhibin Jiang

Abstract:

The travel of passengers in the urban rail transit network is influenced by changes in network structure and operational status, and the response of individual travel preferences to these changes also varies. Firstly, the influence of the suspension of urban rail transit line sections on passenger travel along the line is analyzed. Secondly, passenger travel trajectories containing multi-dimensional semantics are described based on network UD data. Next, passenger panel data based on spatio-temporal sequences is constructed to achieve frequent passenger clustering. Then, the Graph Convolutional Network (GCN) is used to model and identify the changes in travel modes of different types of frequent passengers. Finally, taking Shanghai Metro Line 11 as an example, the travel behavior patterns of frequent passengers after the Huaqiao section shutdown during the COVID-19 epidemic are analyzed. The results showed that after the section shutdown, most passengers would transfer to the nearest Anting station for boarding, while some passengers would transfer to other stations for boarding or cancel their travels directly. Among the passengers who transferred to Anting station for boarding, most of passengers maintained the original normalized travel mode, a small number of passengers waited for a few days before transferring to Anting station for boarding, and only a few number of passengers stopped traveling at Anting station or transferred to other stations after a few days of boarding on Anting station. The results can provide a basis for understanding urban rail transit passenger travel patterns and improving the accuracy of passenger flow prediction in abnormal operation scenarios.

Keywords: urban rail transit, section shutdown, frequent passenger, travel behavior pattern

Procedia PDF Downloads 84

Authors: Tianle Yang

Abstract:

As a common mental disorder, depression is a leading cause of various diseases worldwide. Early detection and treatment of depression can dramatically promote remission and prevent relapse. However, conventional ways of depression diagnosis require considerable human effort and cause economic burden, while still being prone to misdiagnosis. On the other hand, recent studies report that physical characteristics are major contributors to the diagnosis of depression, which inspires us to mine the internal relationship by neural networks instead of relying on clinical experiences. In this paper, neural networks are constructed to predict depression from physical characteristics. Two initialization methods are examined - Xaiver and Kaiming initialization. Experimental results show that a 3-layers neural network with Kaiming initialization achieves 83% accuracy.

Keywords: depression, neural network, Xavier initialization, Kaiming initialization

Procedia PDF Downloads 127

Authors: Gizelle K. Vianna, Gabriel V. Cunha, Gustavo S. Oliveira

Abstract:

Foliage diseases in plants can cause a reduction in both quality and quantity of agricultural production. Intelligent detection of plant diseases is an essential research topic as it may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. This work investigates ways to recognize the late blight disease from the analysis of tomato digital images, collected directly from the field. A pair of multilayer perceptron neural network analyzes the digital images, using data from both RGB and HSL color models, and classifies each image pixel. One neural network is responsible for the identification of healthy regions of the tomato leaf, while the other identifies the injured regions. The outputs of both networks are combined to generate the final classification of each pixel from the image and the pixel classes are used to repaint the original tomato images by using a color representation that highlights the injuries on the plant. The new images will have only green, red or black pixels, if they came from healthy or injured portions of the leaf, or from the background of the image, respectively. The system presented an accuracy of 97% in detection and estimation of the level of damage on the tomato leaves caused by late blight.

Keywords: artificial neural networks, digital image processing, pattern recognition, phytosanitary

Procedia PDF Downloads 326

Authors: Afif Saleh Abugharsa

Abstract:

The IEEE 802.15.4 standard is designed for low-rate wireless personal area networks (LR-WPAN) with focus on enabling wireless sensor networks. It aims to give a low data rate, low power consumption, and low cost wireless networking on the device-level communication. The objective of this study is to investigate the performance of IEEE 802.15.4 based networks using simulation tool. In this project the network simulator 2 NS2 was used to several performance measures of wireless sensor networks. Three scenarios were considered, multi hop network with a single coordinator, star topology, and an ad hoc on demand distance vector AODV. Results such as packet delivery ratio, hop delay, and number of collisions are obtained from these scenarios.

Keywords: ZigBee, wireless sensor networks, IEEE 802.15.4, low power, low data rate

Procedia PDF Downloads 432

Authors: Humeyra Bolakar Tosun

Abstract:

The transport sector has an undisputed place in human life. People need transport access to continuous increase day by day with growing population. The number of rail network, urban transport planning, infrastructure improvements, transportation management and other related areas is a key factor affecting our country made it quite necessary to improve the work of transportation. In this context, it plays an important role in domestic rail freight demand planning. Alternatives that the increase in the transportation field and has made it mandatory requirements such as the demand for improving transport quality. In this study generally is known and used in studies by the definition, rail freight transport, railway line length, population, energy consumption. In this study, Iron Road Load Net Demand was modeled by multiple regression and ANN methods. In this study, model dependent variable (Output) is Iron Road Load Net demand and 6 entries variable was determined. These outcome values extracted from the model using ANN and regression model results. In the regression model, some parameters are considered as determinative parameters, and the coefficients of the determinants give meaningful results. As a result, ANN model has been shown to be more successful than traditional regression model.

Keywords: railway load carrying, neural network, modelling transport, transportation

Procedia PDF Downloads 142

Authors: John M. Lyne, K. Andrea Scott

Abstract:

In fluid dynamics, direct numerical simulations (DNS) of turbulent flows require large amounts of nodes to appropriately resolve all scales of energy transfer. Due to the size of these databases, sharing these datasets amongst the academic community is a challenge. Recent work has been done to investigate the use of super-resolution to enable database sharing, where a low-resolution flow field is super-resolved to high resolutions using a neural network. Recently, Generative Adversarial Networks (GAN) have grown in popularity with impressive results in the generation of faces, landscapes, and more. This work investigates the generation of unique high-resolution channel flow velocity fields from a low-dimensional latent space using a GAN. The training objective of the GAN is to generate samples in which the distribution of the generated samplesis ideally indistinguishable from the distribution of the training data. In this study, the network is trained using samples drawn from a statistically stationary channel flow at a Reynolds number of 560. Results show that the turbulent statistics and energy spectra of the generated flow fields are within reasonable agreement with those of the DNS data, demonstrating that GANscan produce the intricate multi-scale phenomena of turbulence.

Keywords: computational fluid dynamics, channel flow, turbulence, generative adversarial network

Procedia PDF Downloads 205

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 70

Authors: Brando Vagenende, Marie-Anne Guerry

Abstract:

For stochastic matrices of any order, the geometric description of the convex set of eigenvalues is completely known. The purpose of this study is to investigate the subset of the monotone matrices. This type of matrix appears in contexts such as intergenerational occupational mobility, equal-input modeling, and credit ratings-based systems. Monotone matrices are stochastic matrices in which each row stochastically dominates the previous row. The monotonicity property of a stochastic matrix can be expressed by a nonnegative lower-order matrix with the same eigenvalues as the original monotone matrix (except for the eigenvalue 1). Specifically, the aim of this research is to focus on the properties of eigenvalues of monotone matrices. For those matrices up to order 3, there already exists a complete description of the convex set of eigenvalues. For monotone matrices of order at least 4, this study gives, through simulations, more insight into the geometric description of their eigenvalues. Furthermore, this research treats in a geometric and algebraic way the properties of eigenvalues of monotone matrices of order at least 4.

Keywords: eigenvalues of matrices, finite Markov chains, monotone matrices, nonnegative matrices, stochastic matrices

Procedia PDF Downloads 78

Authors: Lin Cheng, Zijiang Yang

Abstract:

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specification. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and node are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords: program synthesis, flow chart, specification, graph recognition, CNN

Procedia PDF Downloads 118

Authors: Moh Hanif Mubarok, Muhammad Rivai

Abstract:

The public's response to quality rice is very high. So it is necessary to set minimum standards in checking the quality of rice. Most rice quality measurements still use manual methods, which are prone to errors due to limited human vision and the subjectivity of testers. So, a gas detection system can be a solution that has high effectiveness and subjectivity for solving current problems. The use of gas sensors in testing rice quality must pay attention to several parameters. The parameters measured in this research are the percentage of rice water content, gas concentration, output voltage, and measurement time. Therefore, this research was carried out to identify carbon dioxide (CO₂), nitrous oxide (N₂O) and methane (CH₄) gases in rice quality using a series of gas sensors using the Neural Network method.

Keywords: carbon dioxide, dinitrogen oxide, methane, semiconductor gas sensor, neural network

Procedia PDF Downloads 45

Authors: Yoshimoto Kurihara, Tad Gonsalves

Abstract:

Currently, in the field of object posture estimation, there is research on estimating the position and angle of an object by storing a 3D model of the object to be estimated in advance in a computer and matching it with the model. However, in this research, we have succeeded in creating a module that is much simpler, smaller in scale, and faster in operation. Our 6D pose estimation model consists of two different networks – a classification network and a regression network. From a single RGB image, the trained model estimates the class of the object in the image, the coordinates of the object, and its rotation angle in 3D space. In addition, we compared the estimation accuracy of each camera position, i.e., the angle from which the object was captured. The highest accuracy was recorded when the camera position was 75°, the accuracy of the classification was about 87.3%, and that of regression was about 98.9%.

Keywords: 6D posture estimation, image recognition, deep learning, AlexNet

Procedia PDF Downloads 154

Authors: Noxolo Mafu

Abstract:

This study presents an overview of strategic planning in South African higher education institutions by tracing its trends and mystique in order to identify its impact. Over the democratic decades, strategic planning has become integral to institutional survival. It has been used as a potent tool by several institutions to catch up and surpass counterparts. While planning has always been part of higher education, strategic planning should be considered different. Strategic planning is primarily about development and maintenance of a strategic fitting between an institution and its dynamic opportunities. This presupposes existence of sets of stages that institutions pursue of which, can be regarded for assessment of the impact of strategic planning in an institution. The network theory serves guides the study in demystifying apparent organisational networks in strategic planning processes.

Keywords: network theory, strategy, planning, strategic planning, assessment, impact

Procedia PDF Downloads 561

Authors: Mazarine Roquet, Pierre Dewallef

Abstract:

The building sector, both residential and tertiary, accounts for a significant share of greenhouse gas emissions. In Belgium, partly due to poor insulation of the building stock, but certainly because of the massive use of fossil fuels for heating buildings, this share reaches almost 30%. To reduce carbon emissions from urban building heating, district heating networks emerge as a promising solution as they offer various assets such as improving the load factor, integrating combined heat and power systems, and enabling energy source diversification, including renewable sources and waste heat recovery. However, mainly for sake of simple operation, most existing district heating networks still operate at high or medium temperatures ranging between 120°C and 60°C (the socalled second and third-generations district heating networks). Although these district heating networks offer energy savings in comparison with individual boilers, such temperature levels generally require the use of fossil fuels (mainly natural gas) with combined heat and power. The fourth-generation district heating networks improve the transport and energy conversion efficiency by decreasing the operating temperature between 50°C and 30°C. Yet, to decarbonise the building heating one must increase the waste heat recovery and use mainly wind, solar or geothermal sources for the remaining heat supply. Fifth-generation networks operating between 35°C and 15°C offer the possibility to decrease even more the transport losses, to increase the share of waste heat recovery and to use electricity from renewable resources through the use of heat pumps to generate low temperature heat. The main objective of this contribution is to exhibit on a real-life test case the benefits of replacing an existing third-generation network by a fifth-generation one and to decarbonise the heat supply of the building stock. The second objective of the study is to highlight the difficulties resulting from the use of a fifth-generation, low-temperature, district heating network. To do so, a simulation model of the district heating network including its regulation is implemented in the modelling language Modelica. This model is applied to the test case of the heating network on the University of Liège's Sart Tilman campus, consisting of around sixty buildings. This model is validated with monitoring data and then adapted for low-temperature networks. A comparison of primary energy consumptions as well as CO2 emissions is done between the two cases to underline the benefits in term of energy independency and GHG emissions. To highlight the complexity of operating a lowtemperature network, the difficulty of adapting the mass flow rate to the heat demand is considered. This shows the difficult balance between the thermal comfort and the electrical consumption of the circulation pumps. Several control strategies are considered and compared to the global energy savings. The developed model can be used to assess the potential for energy and CO2 emissions savings retrofitting an existing network or when designing a new one.

Keywords: building simulation, fifth-generation district heating network, low-temperature district heating network, urban building heating

Procedia PDF Downloads 81

Authors: Lee Jeong Min, Lee Mi Hee, Eo Yang Dam

Abstract:

Geospatial feature extraction is a very important issue in the remote sensing research. In the meantime, the image classification based on statistical techniques, but, in recent years, data mining and machine learning techniques for automated image processing technology is being applied to remote sensing it has focused on improved results generated possibility. In this study, artificial neural network and decision tree technique is applied to classify the high-resolution satellite images, as compared to the MLC processing result is a statistical technique and an analysis of the pros and cons between each of the techniques.

Keywords: remote sensing, artificial neural network, decision tree, maximum likelihood classification

Procedia PDF Downloads 345

Authors: Ayse Ozbil, Gorsev Argin, Demet Yesiltepe

Abstract:

Data for this cross-sectional study were drawn from questionnaires conducted in 10 elementary schools (1000 students, ages 12-14) located in Istanbul, Turkey. School environments (1600 meter buffers around the school) were evaluated through GIS-based land-use data (parcel level land use density) and street-level topography. Street networks within the same buffers were evaluated by using angular segment analysis (Integration and Choice) implemented in Depthmap as well as two segment-based connectivity measures, namely Metric and Directional Reach implemented in GIS. Segment Angular Integration measures how accessible each space from all the others within the radius using the least angle measure of distance. Segment Angular Choice which measures how many times a space is selected on journeys between all pairs of origins and destinations. Metric Reach captures the density of streets and street connections accessible from each individual road segment. Directional Reach measures the extent to which the entire street network is accessible with few direction changes. In addition, socio-economic characteristics (annual income, car ownership, education-level) of parents, obtained from parental questionnaires, were also included in the analysis. It is shown that surrounding street network configuration is strongly associated with both walk-mode shares and average walking distances to/from schools when controlling for parental socio-demographic attributes as well as land-use compositions and topographic features in school environments. More specifically, findings suggest that the scale at which urban form has an impact on pedestrian travel is considerably larger than a few blocks around the school.

Keywords: Istanbul, street network layout, urban form, walking to/from school

Procedia PDF Downloads 408

Authors: Ali Reza Tahavvor, Saeed Hosseini, Nazli Jowkar, Afshin Karimzadeh Fard

Abstract:

Experimental & numeral study of temperature distribution during milling process, is important in milling quality and tools life aspects. In the present study the milling cross-section temperature is determined by using Artificial Neural Networks (ANN) according to the temperature of certain points of the work piece and the points specifications and the milling rotational speed of the blade. In the present work, at first three-dimensional model of the work piece is provided and then by using the Computational Heat Transfer (CHT) simulations, temperature in different nods of the work piece are specified in steady-state conditions. Results obtained from CHT are used for training and testing the ANN approach. Using reverse engineering and setting the desired x, y, z and the milling rotational speed of the blade as input data to the network, the milling surface temperature determined by neural network is presented as output data. The desired points temperature for different milling blade rotational speed are obtained experimentally and by extrapolation method for the milling surface temperature is obtained and a comparison is performed among the soft programming ANN, CHT results and experimental data and it is observed that ANN soft programming code can be used more efficiently to determine the temperature in a milling process.

Keywords: artificial neural networks, milling process, rotational speed, temperature

Procedia PDF Downloads 404

Authors: Stefan K. Behfar

Abstract:

The rapid growth of the Ethereum network has brought forth the urgent need for scalable analysis methods to handle the increasing volume of blockchain data. In this research, we propose efficient methodologies for making Ethereum network analysis scalable. Our approach leverages a combination of graph-based data representation, probabilistic sampling, and parallel processing techniques to achieve unprecedented scalability while preserving critical network insights. Data Representation: We develop a graph-based data representation that captures the underlying structure of the Ethereum network. Each block transaction is represented as a node in the graph, while the edges signify temporal relationships. This representation ensures efficient querying and traversal of the blockchain data. Probabilistic Sampling: To cope with the vastness of the Ethereum blockchain, we introduce a probabilistic sampling technique. This method strategically selects a representative subset of transactions and blocks, allowing for concise yet statistically significant analysis. The sampling approach maintains the integrity of the network properties while significantly reducing the computational burden. Graph Convolutional Networks (GCNs): We incorporate GCNs to process the graph-based data representation efficiently. The GCN architecture enables the extraction of complex spatial and temporal patterns from the sampled data. This combination of graph representation and GCNs facilitates parallel processing and scalable analysis. Distributed Computing: To further enhance scalability, we adopt distributed computing frameworks such as Apache Hadoop and Apache Spark. By distributing computation across multiple nodes, we achieve a significant reduction in processing time and enhanced memory utilization. Our methodology harnesses the power of parallelism, making it well-suited for large-scale Ethereum network analysis. Evaluation and Results: We extensively evaluate our methodology on real-world Ethereum datasets covering diverse time periods and transaction volumes. The results demonstrate its superior scalability, outperforming traditional analysis methods. Our approach successfully handles the ever-growing Ethereum data, empowering researchers and developers with actionable insights from the blockchain. Case Studies: We apply our methodology to real-world Ethereum use cases, including detecting transaction patterns, analyzing smart contract interactions, and predicting network congestion. The results showcase the accuracy and efficiency of our approach, emphasizing its practical applicability in real-world scenarios. Security and Robustness: To ensure the reliability of our methodology, we conduct thorough security and robustness evaluations. Our approach demonstrates high resilience against adversarial attacks and perturbations, reaffirming its suitability for security-critical blockchain applications. Conclusion: By integrating graph-based data representation, GCNs, probabilistic sampling, and distributed computing, we achieve network scalability without compromising analytical precision. This approach addresses the pressing challenges posed by the expanding Ethereum network, opening new avenues for research and enabling real-time insights into decentralized ecosystems. Our work contributes to the development of scalable blockchain analytics, laying the foundation for sustainable growth and advancement in the domain of blockchain research and application.

Keywords: Ethereum, scalable network, GCN, probabilistic sampling, distributed computing

Procedia PDF Downloads 75

Authors: A. Graa, I. Ziane, F. Benhamida, S. Souag

Abstract:

This paper presents a comparative analysis study of an efficient and reliable quadratic programming (QP) to solve economic load dispatch (ELD) problem with considering transmission losses in a power system. The proposed QP method takes care of different unit and system constraints to find optimal solution. To validate the effectiveness of the proposed QP solution, simulations have been performed using Algerian test system. Results obtained with the QP method have been compared with other existing relevant approaches available in literatures. Experimental results show a proficiency of the QP method over other existing techniques in terms of robustness and its optimal search.

Keywords: economic dispatch, quadratic programming, Algerian network, dynamic load

Procedia PDF Downloads 563

Authors: Nonlapun Meenil, Pisitpong Intarapong, Thitima Wongsheree, Pranchalee Samanpiboon

Abstract:

In Thailand, once pineapples are harvested, they must be classified into two classes based on their sweetness: sweet and unsweet. This paper has studied and developed the assessment of internal quality of pineapples using a low-cost compact spectroscopy sensor according to the Spectroscopy approach and Neural Network (NN). During the experiments, Batavia pineapples were utilized, generating 100 samples. The extracted pineapple juice of each sample was used to determine the Soluble Solid Content (SSC) labeling into sweet and unsweet classes. In terms of experimental equipment, the sensor cover was specifically designed to install the sensor and light source to read the reflectance at a five mm depth from pineapple flesh. By using a spectroscopy sensor, data on visible and near-infrared reflectance (Vis-NIR) were collected. The NN was used to classify the pineapple classes. Before the classification step, the preprocessing methods, which are Class balancing, Data shuffling, and Standardization were applied. The 510 nm and 900 nm reflectance values of the middle parts of pineapples were used as features of the NN. With the Sequential model and Relu activation function, 100% accuracy of the training set and 76.67% accuracy of the test set were achieved. According to the abovementioned information, using a low-cost compact spectroscopy sensor has achieved favorable results in classifying the sweetness of the two classes of pineapples.

Keywords: neural network, pineapple, soluble solid content, spectroscopy

Procedia PDF Downloads 70

Authors: Ahmad Mansoor Stanikzai, Yoshitaka Kajita

Abstract:

This research is a very essential towards transportation planning of Kabul New City. In this research, the travel demand of Kabul metropolitan area (Existing and Kabul New City) are evaluated for three different target years (2015, current, 2025, mid-term, 2040, long-term). The outcome of this study indicates that, though currently the vehicle volume is less the capacity of existing road networks, Kabul city is suffering from daily traffic congestions. This is mainly due to lack of transportation management, the absence of proper policies, improper public transportation system and violation of traffic rules and regulations by inhabitants. On the other hand, the observed result indicates that the current vehicle to capacity ratio (VCR) which is the most used index to judge traffic status in the city is around 0.79. This indicates the inappropriate traffic condition of the city. Moreover, by the growth of population in mid-term (2025) and long-term (2040) and in the case of no development in the road network and transportation system, the VCR value will dramatically increase to 1.40 (2025) and 2.5 (2040). This can be a critical situation for an urban area from an urban transportation perspective. Thus, by introducing high-capacity public transportation system and the development of road network in Kabul New City and integrating these links with the existing city road network, significant improvements were observed in the value of VCR.

Keywords: Afghanistan, Kabul new city, planning, policy, urban transportation

Procedia PDF Downloads 330

Authors: Zixian Zhang, Shanliang Yao, Zile Huang, Zhaodong Wu, Xiaohui Zhu, Yong Yue, Jieming Ma

Abstract:

Unmanned Surface Vehicles (USVs) are valuable due to their ability to perform dangerous and time-consuming tasks on the water. Object detection tasks are significant in these applications. However, inherent challenges, such as the complex distribution of obstacles, reflections from shore structures, water surface fog, etc., hinder the performance of object detection of USVs. To address these problems, this paper provides a fusion method for USVs to effectively detect objects in the inland surface environment, utilizing vision sensors and 3+1D Millimeter-wave radar. MMW radar is complementary to vision sensors, providing robust environmental information. The radar 3D point cloud is transferred to 2D radar pseudo image to unify radar and vision information format by utilizing the point transformer. We propose a multi-source object detection network (RV-YOLOX )based on radar-vision fusion for inland waterways environment. The performance is evaluated on our self-recording waterways dataset. Compared with the YOLOX network, our fusion network significantly improves detection accuracy, especially for objects with bad light conditions.

Keywords: inland waterways, YOLO, sensor fusion, self-attention

Procedia PDF Downloads 117

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 209

Authors: Adeniyi Onasanya, Maher Elshakankiri

Abstract:

In recent years, the Internet of Things (IoT) has constituted a driving force of modern technological advancement, and it has become increasingly common as its impacts are seen in a variety of application domains, including healthcare. IoT is characterized by the interconnectivity of smart sensors, objects, devices, data, and applications. With the unprecedented use of IoT in industrial, commercial and domestic, it becomes very imperative to harness the benefits and functionalities associated with the IoT technology in (re)assessing the provision and positioning of healthcare to ensure efficient and improved healthcare delivery. In this research, we are focusing on two important services in healthcare systems, which are cancer care services and business analytics/cloud services. These services incorporate the implementation of an IoT that provides solution and framework for analyzing health data gathered from IoT through various sensor networks and other smart devices in order to improve healthcare delivery and to help health care providers in their decision-making process for enhanced and efficient cancer treatment. In addition, we discuss the wireless sensor network (WSN), WSN routing and data transmission in the healthcare environment. Finally, some operational challenges and security issues with IoT-based healthcare system are discussed.

Keywords: IoT, smart health care system, business analytics, (wireless) sensor network, cancer care services, cloud services

Procedia PDF Downloads 177

Authors: Russell Rosen

Abstract:

American Sign Language (ASL) has been developed and used by signing deaf and hard of hearing (DHH) individuals in the American Deaf community since early nineteenth century. In the last two decades, secondary schools in the US offered ASL for foreign language credit to secondary school learners. The learners who learn ASL as a foreign language are largely American native speakers of English. They not only learn ASL in US schools but also create spaces under certain interactional and social conditions in their home communities outside of classrooms and use ASL with each other instead of their native English. This phenomenon is a transmigration of language from a native social group to a non-native, non-kin social group. This study looks at the transmigration of ASL from signing Deaf community to the general speaking and hearing American society. Theoretical implications of this study are discussed.

Keywords: American Sign Language, Foreign Language, Language transmission, United States

Procedia PDF Downloads 418

Authors: I. Erins, J. Erina

Abstract:

The aim of the present article is to determine the impact of the external and internal factors of bank performance on the profitability indicators of the CEE countries banks in the period from 2006 to 2012. On the basis of research conducted abroad on bank and macroeconomic profitability indicators, in order to obtain research results, the authors evaluated return on average assets (ROAA) and return on average equity (ROAE) indicators of the CEE countries banks. The authors analyzed profitability indicators of banks using descriptive methods, SPSS data analysis methods as well as data correlation and linear regression analysis. The authors concluded that most internal and external indicators of bank performance have no direct effect on the profitability of the banks in the CEE countries. The only exceptions are credit risk and bank size which affect one of the measures of bank profitability–return on average equity.

Keywords: banks, CEE countries, profitability ROAA, ROAE

Procedia PDF Downloads 365

Authors: Jiaqi Dong, Qing-Hua Qin, Yi Xiao

Abstract:

Some of the most fundamental challenges of elastic metamaterials (EMMs) optimization can be attributed to the high consumption of computational power resulted from finite element analysis (FEA) simulations that render the optimization process inefficient. Furthermore, due to the inherent mesh dependence of FEA, minuscule geometry features, which often emerge during the later stages of optimization, induce very fine elements, resulting in enormously high time consumption, particularly when repetitive solutions are needed for computing the objective function. In this study, a surrogate modelling algorithm is developed to reduce computational time in structural optimization of EMMs. The surrogate model is constructed based on a multilayer feedforward artificial neural network (ANN) architecture, trained with prepopulated eigenfrequency data prepopulated from FEA simulation and optimized through regime selection with genetic algorithm (GA) to improve its accuracy in predicting the location and width of the primary elastic band gap. With the optimized ANN surrogate at the core, a Nelder-Mead (NM) algorithm is established and its performance inspected in comparison to the FEA solution. The ANNNM model shows remarkable accuracy in predicting the band gap width and a reduction of time consumption by 47%.

Keywords: artificial neural network, machine learning, mechanical metamaterials, Nelder-Mead optimization

Procedia PDF Downloads 126

Authors: Thrivikraman Aswathi, S. Advaith

Abstract:

As there can be cases where the use of real data is somehow limited, such as when it is hard to get access to a large volume of real data, we need to go for synthetic data generation. This produces high-quality synthetic data while maintaining the statistical properties of a specific dataset. In the present work, a generative adversarial network (GAN) is trained to produce multivariate time series (MTS) data since the MTS is now being gathered more often in various real-world systems. Furthermore, the GAN-generated MTS data is fed into a transformer-based deep learning architecture that carries out the data categorization into predefined classes. Further, the model is evaluated across various distinct domains by generating corresponding MTS data.

Keywords: GAN, transformer, classification, multivariate time series

Procedia PDF Downloads 128

Authors: Xupin Zhang, Maria Caterina Bramati, Enrest Fokoue

Abstract:

Understanding the career placement of graduates from the university is crucial for both the qualities of education and ultimate satisfaction of students. In this research, we adapt the capabilities of dynamic Bayesian networks to characterize and predict students’ job placement using data from various universities. We also provide elements of the estimation of the indicator (score) of the strength of the network. The research focuses on overall findings as well as specific student groups including international and STEM students and their insight on the career path and what changes need to be made. The derived Bayesian network has the potential to be used as a tool for simulating the career path for students and ultimately helps universities in both academic advising and career counseling.

Keywords: dynamic bayesian networks, indicator estimation, job placement, social networks

Procedia PDF Downloads 378

Authors: Preetham Shankapal, Jill King, Kori Murray, Corby Martin, Paula Giselman, Jason Hicks, Owen Carmicheal

Abstract:

Activation of reward and satiety networks in the brain while processing palatable food cues, as well as functional connectivity during rest has been studied using functional Magnetic Resonance Imaging of the brain in various obesity phenotypes. However, functional connectivity within the reward and satiety network during food cue processing is understudied. 14 obese individuals underwent two fMRI scans during viewing of Macronutrient Picture System images. Each scan included two blocks of images of High Sugar/High Fat (HSHF), High Carbohydrate/High Fat (HCHF), Low Sugar/Low Fat (LSLF) and also non-food images. Seed voxels within seven food reward relevant ROIs: Insula, putamen and cingulate, precentral, parahippocampal, medial frontal and superior temporal gyri were isolated based on a prior meta-analysis. Beta series correlation for task-related functional connectivity between these seed voxels and the rest of the brain was computed. Voxel-level differences in functional connectivity were calculated between: first and the second scan; individuals who saw novel (N=7) vs. Repeated (N=7) images in the second scan; and between the HC/HF, HSHF blocks vs LSLF and non-food blocks. Computations and analysis showed that during food image viewing, reward network ROIs showed significant functional connectivity with each other and with other regions responsible for attentional and motor control, including inferior parietal lobe and precentral gyrus. These functional connectivity values were heightened among individuals who viewed novel HS/HF images in the second scan. In the second scan session, functional connectivity was reduced within the reward network but increased within attention, memory and recognition regions, suggesting habituation to reward properties and increased recollection of previously viewed images. In conclusion it can be inferred that Functional Connectivity within reward network and between reward and other brain regions, varies by important experimental conditions during food photography viewing, including habituation to shown foods.

Keywords: fMRI, functional connectivity, task-based, beta series correlation

Procedia PDF Downloads 269