Search results for: deep neural image models

Authors: Elina Bakhtieva

Abstract:

The variety of available digital tools, strategies and activities might confuse and disorient even an experienced marketer. This applies in particular to B2B companies, which are usually less flexible in uptaking of digital technology than B2C companies. B2B companies are lacking a framework that corresponds to the specifics of the B2B business, and which helps to evaluate a company’s capabilities and to choose an appropriate path. A B2B digital marketing maturity model helps to fill this gap. However, modern marketing offers no widely approved digital marketing maturity model, and thus, some marketing institutions provide their own tools. The purpose of this paper is building an optimized B2B digital marketing maturity model based on a SWOT (strengths, weaknesses, opportunities, and threats) analysis of existing models. The current study provides an analytical review of the existing digital marketing maturity models with open access. The results of the research are twofold. First, the provided SWOT analysis outlines the main advantages and disadvantages of existing models. Secondly, the strengths of existing digital marketing maturity models, helps to identify the main characteristics and the structure of an optimized B2B digital marketing maturity model. The research findings indicate that only one out of three analyzed models could be used as a separate tool. This study is among the first examining the use of maturity models in digital marketing. It helps businesses to choose between the existing digital marketing models, the most effective one. Moreover, it creates a base for future research on digital marketing maturity models. This study contributes to the emerging B2B digital marketing literature by providing a SWOT analysis of the existing digital marketing maturity models and suggesting a structure and main characteristics of an optimized B2B digital marketing maturity model.

Keywords: B2B digital marketing strategy, digital marketing, digital marketing maturity model, SWOT analysis

Procedia PDF Downloads 324

Authors: Jayanta Kumar Ghosh, Swastik Sunil Goriwale, Himangshu Sarkar

Abstract:

Groundwater is one of the most valuable natural resources that society consumes for its domestic, industrial, and agricultural water supply. Its bulk and indiscriminate consumption affects the groundwater resource. Often, it has been found that the groundwater recharge rate is much lower than its demand. Thus, to maintain water and food security, it is necessary to monitor and management of groundwater storage. However, it is challenging to estimate groundwater storage (GWS) by making use of existing hydrological models. To overcome the difficulties, machine learning (ML) models are being introduced for the evaluation of groundwater level (GWL). Thus, the objective of this research work is to develop an ML-based model for the prediction of GWL. This objective has been realized through the development of an artificial neural network (ANN) model based on hydro-gravimetry. The model has been developed using training samples from field observations spread over 8 months. The developed model has been tested for the prediction of GWL in an observation well. The root means square error (RMSE) for the test samples has been found to be 0.390 meters. Thus, it can be concluded that the hydro-gravimetric-based ANN model can be used for the prediction of GWL. However, to improve the accuracy, more hydro-gravimetric parameter/s may be considered and tested in future.

Keywords: machine learning, hydro-gravimetry, ground water level, predictive model

Procedia PDF Downloads 111

Authors: Majdi M. Alomari, Nafesah I. Alshdaifat, Mohammad S. Widyan

Abstract:

Different countries have introduced different schemes and policies to counter global warming. The rationale behind the proposed policies and the potential barriers to successful implementation of the policies adopted by the countries were analyzed and estimated based on different models. It is argued that these models enhance the transparency and provide a better understanding to the policy makers. However, these models are underpinned with several structural and baseline assumptions. These assumptions, modeling features and future prediction of emission reductions and other implication such as cost and benefits of a transition to a low-carbon economy and its economy wide impacts were discussed. On the other hand, there are potential barriers in the form political, financial, and cultural and many others that pose a threat to the mitigation options.

Keywords: energy models, environmental policy instruments, mitigating CO2 emission, economic wide impact

Procedia PDF Downloads 511

Authors: Murad Almadani, Khalil Abu-Hantash, Xinyu Wang, Herbert Jelinek, Kinda Khalaf

Abstract:

Gait analysis is used by healthcare professionals as a tool to gain a better understanding of the movement impairment and track progress. In most circumstances, monitoring patients in their real-life environments with low-cost equipment such as cameras and wearable sensors is more important. Inertial sensors, on the other hand, cannot provide enough information on angular dynamics. This research offers a method for tracking 2D joint coordinates using cutting-edge vision algorithms and a single RGB camera. We provide an end-to-end comprehensive deep learning pipeline for marker-less gait parameter estimation, which, to our knowledge, has never been done before. To make our pipeline function in real-time for real-world applications, we leverage the AlphaPose human posture prediction model and a deep learning transformer. We tested our approach on the well-known GPJATK dataset, which produces promising results.

Keywords: gait analysis, human pose estimation, deep learning, real time gait estimation, AlphaPose, transformer

Procedia PDF Downloads 104

Authors: Rodrigo S. Fonseca, Antônio C. P. Veiga

Abstract:

Aiming at helping people with some movement limitation that makes typing and communication difficult, there is a need to customize an assistive tool with a learning environment that helps the user in order to optimize text input, identifying the error and providing the correction and possibilities of choice in the Portuguese language. The work presents an Orthographic and Grammatical System that can be incorporated into writing environments, improving and facilitating the use of an alphanumeric keyboard, using a prototype built using a genetic algorithm in addition to carrying out the prediction, which can occur based on the quantity and position of the inserted letters and even placement in the sentence, ensuring the sequence of ideas using a Long Short Term Memory (LSTM) neural network. The prototype optimizes data entry, being a component of assistive technology for the textual formulation, detecting errors, seeking solutions and informing the user of accurate predictions quickly and effectively through machine learning.

Keywords: genetic algorithm, neural networks, word prediction, machine learning

Procedia PDF Downloads 176

Authors: Gaurav Sancheti

Abstract:

This study presents an impacting approach of Artificial Neural Networks (ANNs) in determining the quantity of High Tensile Steel (HTS) strands required in post-tensioned (PT) slabs. Various PT slab configurations were generated by varying the span and depth of the slab. For each of these slab configurations, quantity of required HTS strands were recorded. ANNs with backpropagation algorithm and varying architectures were developed and their performance was evaluated in terms of Mean Square Error (MSE). The recorded data for the quantity of HTS strands was used as a feeder database for training the developed ANNs. The networks were validated using various validation techniques. The results show that the proposed ANNs have a great potential with good prediction and generalization capability.

Keywords: artificial neural networks, back propagation, conceptual design, high tensile steel strands, post tensioned slabs, validation techniques

Procedia PDF Downloads 204

Authors: Mehrnaz Mostafavi

Abstract:

The assessment and categorization of incidental lung nodules present a considerable challenge in healthcare, often necessitating resource-intensive multiple computed tomography (CT) scans for growth confirmation. This research addresses this issue by introducing a distinct computational approach leveraging radiomics and deep-learning methods. However, understanding local services is essential before implementing these advancements. With diverse tracking methods in place, there is a need for efficient and accurate identification approaches, especially in the context of managing lung nodules alongside pre-existing cancer scenarios. This study explores the integration of text-based algorithms in medical data curation, indicating their efficacy in conjunction with machine learning and deep-learning models for identifying lung nodules. Combining medical images with text data has demonstrated superior data retrieval compared to using each modality independently. While deep learning and text analysis show potential in detecting previously missed nodules, challenges persist, such as increased false positives. The presented research introduces a Structured-Query-Language (SQL) algorithm designed for identifying pulmonary nodules in a tertiary cancer center, externally validated at another hospital. Leveraging natural language processing (NLP) and machine learning, the algorithm categorizes lung nodule reports based on sentence features, aiming to facilitate research and assess clinical pathways. The hypothesis posits that the algorithm can accurately identify lung nodule CT scans and predict concerning nodule features using machine-learning classifiers. Through a retrospective observational study spanning a decade, CT scan reports were collected, and an algorithm was developed to extract and classify data. Results underscore the complexity of lung nodule cohorts in cancer centers, emphasizing the importance of careful evaluation before assuming a metastatic origin. The SQL and NLP algorithms demonstrated high accuracy in identifying lung nodule sentences, indicating potential for local service evaluation and research dataset creation. Machine-learning models exhibited strong accuracy in predicting concerning changes in lung nodule scan reports. While limitations include variability in disease group attribution, the potential for correlation rather than causality in clinical findings, and the need for further external validation, the algorithm's accuracy and potential to support clinical decision-making and healthcare automation represent a significant stride in lung nodule management and research.

Keywords: lung cancer diagnosis, structured-query-language (SQL), natural language processing (NLP), machine learning, CT scans

Procedia PDF Downloads 65

Authors: Ahmed Elaksher

Abstract:

Over the last few years, significant progresses have been made and new approaches have been proposed for efficient collection of 3D spatial data from Unmanned aerial vehicles (UAVs) with reduced costs compared to imagery from satellite or manned aircraft. In these systems, a low-cost GPS unit provides the position, velocity of the vehicle, a low-quality inertial measurement unit (IMU) determines its orientation, and off-the-shelf cameras capture the images. Structure from Motion (SfM) and photogrammetry are the main tools for 3D surface reconstruction from images collected by these systems. Unlike traditional techniques, SfM allows the computation of calibration parameters using point correspondences across images without performing a rigorous laboratory or field calibration process and it is more flexible in that it does not require consistent image overlap or same rotation angles between successive photos. These benefits make SfM ideal for UAVs aerial mapping. In this paper, a direct comparison between SfM Digital Elevation Models (DEM) and those generated through traditional photogrammetric techniques was performed. Data was collected by a 3DR IRIS+ Quadcopter with a Canon PowerShot S100 digital camera. Twenty ground control points were randomly distributed on the ground and surveyed with a total station in a local coordinate system. Images were collected from an altitude of 30 meters with a ground resolution of nine mm/pixel. Data was processed with PhotoScan, VisualSFM, Imagine Photogrammetry, and a photogrammetric algorithm developed by the author. The algorithm starts with performing a laboratory camera calibration then the acquired imagery undergoes an orientation procedure to determine the cameras’ positions and orientations. After the orientation is attained, correlation based image matching is conducted to automatically generate three-dimensional surface models followed by a refining step using sub-pixel image information for high matching accuracy. Tests with different number and configurations of the control points were conducted. Camera calibration parameters estimated from commercial software and those obtained with laboratory procedures were comparable. Exposure station positions were within less than few centimeters and insignificant differences, within less than three seconds, among orientation angles were found. DEM differencing was performed between generated DEMs and few centimeters vertical shifts were found.

Keywords: UAV, photogrammetry, SfM, DEM

Procedia PDF Downloads 272

Authors: S. Teksin, S. Yayla

Abstract:

The aim of the present study was to investigate details of flow structure in downstream of a circular cylinder base mounted on a flat surface in a rectangular duct with the dimensions of 8000 x 1000 x 750 mm in deep water flow for the Reynolds number 2500, 5000 and 7500. A flexible strip was attached to behind the cylinder and compared the bare body. Also, it was analyzed that how boundary layer affects the structure of flow around the cylinder. Diameter of the cylinder was 60 mm and the length of the flexible splitter plate which had a certain modulus of elasticity was 150 mm (L/D=2.5). Time-averaged velocity vectors, vortex contours, streamwise and transverse velocity components were investigated via Particle Image Velocimetry (PIV). Velocity vectors and vortex contours were displayed through the sections in which boundary layer effect was not present. On the other hand, streamwise and transverse velocity components were monitored for both cases, i.e. with and without boundary layer effect. Experiment results showed that the vortex formation occured in a larger area for L/D=2.5 and the point where the vortex was maximum from the base of the cylinder was shifted. Streamwise and transverse velocity component contours were symmetrical with reference to the center of the cylinder for all cases. All Froud numbers based on the Reynolds numbers were quite smaller than 1. The flow characteristics of velocity component values of attached circular cylinder arrangement decreased approximately twenty five percent comparing to bare cylinder case.

Keywords: partical image velocimetry, elastic plate, cylinder, flow structure

Procedia PDF Downloads 302

Authors: Dongxu Chen, Yipeng Li

Abstract:

This paper presents an information geometry NonlocalMeans(NLM) algorithm for Poisson denoising. NLM estimates a noise-free pixel as a weighted average of image pixels, where each pixel is weighted according to the similarity between image patches in Euclidean space. In this work, every pixel is a Poisson distribution locally estimated by Maximum Likelihood (ML), all distributions consist of a statistical manifold. A NLM denoising algorithm is conducted on the statistical manifold where Fisher information matrix can be used for computing distribution geodesics referenced as the similarity between patches. This approach was demonstrated to be competitive with related state-of-the-art methods.

Keywords: image denoising, Poisson noise, information geometry, nonlocal-means

Procedia PDF Downloads 272

Authors: Chia-Yu Lin, Yu-Hsiang Shen, Cing-Ciao Ke, Chia-Hao Chang, Fan-Pin Tseng, Yu-Ching Ni, Sheng-Pin Tseng

Abstract:

Tomosynthesis is an imaging system that generates a 3D image by scanning in a limited angular range. It could provide more depth information than traditional 2D X-ray single projection. Radiation dose in tomosynthesis is less than computed tomography (CT). Because of limited angular range scanning, there are many properties depending on scanning direction. Therefore, non-coplanar imaging technique was developed to improve image quality in traditional tomosynthesis. The purpose of this study was to establish the non-coplanar imaging technique of tomosynthesis system and evaluate this technique by the reconstructed image. INER prototype tomosynthesis system contains an X-ray tube, a flat panel detector, and a motion machine. This system could move X-ray tube in multiple directions during the acquisition. In this study, we investigated three different imaging techniques that were 2D X-ray single projection, traditional tomosynthesis, and non-coplanar tomosynthesis. An anthropopathic chest phantom was used to evaluate the image quality. It contained three different size lesions (3 mm, 5 mm and, 8 mm diameter). The traditional tomosynthesis acquired 61 projections over a 30 degrees angular range in one scanning direction. The non-coplanar tomosynthesis acquired 62 projections over 30 degrees angular range in two scanning directions. A 3D image was reconstructed by iterative image reconstruction algorithm (ML-EM). Our qualitative method was to evaluate artifacts in tomosynthesis reconstructed image. The quantitative method was used to calculate a peak-to-valley ratio (PVR) that means the intensity ratio of the lesion to the background. We used PVRs to evaluate the contrast of lesions. The qualitative results showed that in the reconstructed image of non-coplanar scanning, anatomic structures of chest and lesions could be identified clearly and no significant artifacts of scanning direction dependent could be discovered. In 2D X-ray single projection, anatomic structures overlapped and lesions could not be discovered. In traditional tomosynthesis image, anatomic structures and lesions could be identified clearly, but there were many artifacts of scanning direction dependent. The quantitative results of PVRs show that there were no significant differences between non-coplanar tomosynthesis and traditional tomosynthesis. The PVRs of the non-coplanar technique were slightly higher than traditional technique in 5 mm and 8 mm lesions. In non-coplanar tomosynthesis, artifacts of scanning direction dependent could be reduced and PVRs of lesions were not decreased. The reconstructed image was more isotropic uniformity in non-coplanar tomosynthesis than in traditional tomosynthesis. In the future, scan strategy and scan time will be the challenges of non-coplanar imaging technique.

Keywords: image reconstruction, non-coplanar imaging technique, tomosynthesis, X-ray imaging

Procedia PDF Downloads 353

Authors: Marcos Valdez Alexander Junior, Igor Aguilar-Alonso

Abstract:

Malnutrition is the root of different diseases that universally affect everyone, diseases such as obesity and malnutrition. The objective of this research is to predict the calories of the food to be eaten, developing a smart mobile application to show the user if a meal is balanced. Due to the large percentage of obesity and malnutrition in Peru, the present work is carried out. The development of the intelligent application is proposed with a three-layer architecture, and for the prediction of the nutritional value of the food, the use of pre-trained models based on convolutional neural networks is proposed.

Keywords: volume estimation, calorie estimation, artificial vision, food nutrition

Procedia PDF Downloads 82

Authors: Diana G. Ramirez-Wong, Marius Ramirez, Regina Sanchez-Leija, Adriana Rugerio, R. Araceli Mauricio-Sanchez, Martin A. Hernandez-Landaverde, Arturo Carranza, John A. Pojman, Josue D. Mota-Morales, Gabriel Luna-Barcenas

Abstract:

Chitin films were prepared using alpha-chitin from shrimp shells as raw material and a simple method of precipitation-evaporation. Choline chloride: urea Deep Eutectic Solvent (DES) was used to disperse chitin and compared against hexafluoroisopropanol (HFIP). A careful analysis of the chemical and crystalline structure was followed along the synthesis of the films, revealing crystalline-phase transitions. The full conversion of alpha- to beta-, or alpha- to gamma-chitin structure were detected by XRD and NMR on the films. The synthesis of highly crystalline monophasic gamma-chitin films was achieved using a DES; whereas HFIP helps to promote the beta-phase. These results are encouraging to continue in the study of DES as good processing media to control the final properties of chitin based materials.

Keywords: chitin, deep eutectic solvent, polymorph, phase transformation

Procedia PDF Downloads 521

Authors: Dražen Cvitanić, Biljana Maljković

Abstract:

This paper presents models for predicting operating speeds on tangent sections of two-lane rural roads developed on continuous speed data. The data corresponds to 20 drivers of different ages and driving experiences, driving their own cars along an 18 km long section of a state road. The data were first used for determination of maximum operating speeds on tangents and their comparison with speeds in the middle of tangents i.e. speed data used in most of operating speed studies. Analysis of continuous speed data indicated that the spot speed data are not reliable indicators of relevant speeds. After that, operating speed models for tangent sections were developed. There was no significant difference between models developed using speed data in the middle of tangent sections and models developed using maximum operating speeds on tangent sections. All developed models have higher coefficient of determination then models developed on spot speed data. Thus, it can be concluded that the method of measuring has more significant impact on the quality of operating speed model than the location of measurement.

Keywords: operating speed, continuous speed data, tangent sections, spot speed, consistency

Procedia PDF Downloads 441

Authors: Fanqiang Kong, Chending Bian

Abstract:

Sparse unmixing is a promising approach in a semisupervised fashion by assuming that the observed pixels of a hyperspectral image can be expressed in the form of linear combination of only a few pure spectral signatures (end members) in an available spectral library. However, the sparse unmixing problem still remains a great challenge at finding the optimal subset of endmembers for the observed data from a large standard spectral library, without considering the spatial information. Under such circumstances, a sparse unmixing algorithm termed as non-local simultaneous sparse unmixing (NLSSU) is presented. In NLSSU, the non-local simultaneous sparse representation method for endmember selection of sparse unmixing, is used to finding the optimal subset of endmembers for the similar image patch set in the hyperspectral image. And then, the non-local means method, as a regularizer for abundance estimation of sparse unmixing, is used to exploit the abundance image non-local self-similarity. Experimental results on both simulated and real data demonstrate that NLSSU outperforms the other algorithms, with a better spectral unmixing accuracy.

Keywords: hyperspectral unmixing, simultaneous sparse representation, sparse regression, non-local means

Procedia PDF Downloads 233

Authors: Razieh Arian, Hadi Adibi-Asl

Abstract:

This paper investigates an efficient combustion modeling for cycle simulation of internal combustion engine (ICE) studies. The term “efficient model” means that the models must generate desired simulation results while having fast simulation time. In other words, the efficient model is defined based on the application of the model. The objective of this study is to develop math-based models for control applications or shortly control-oriented models. This study compares different modeling approaches used to model the ICEs such as mean-value models, zero dimensional, quasi-dimensional, and multi-dimensional models for control applications. Mean-value models have been widely used for model-based control applications, but recently by developing advanced simulation tools (e.g. Maple/MapleSim) the higher order models (more complex) could be considered as control-oriented models. This paper presents the enhanced zero-dimensional cycle-by-cycle modeling and simulation of a spark ignition engine with a two-zone combustion model. The simulation results are cross-validated against the simulation results from GT-Power package and show a good agreement in terms of trends and values.

Keywords: Two-zone combustion, control-oriented model, wiebe function, internal combustion engine

Procedia PDF Downloads 323

Authors: Andrew R. Willis, Kevin Brink, Kathleen Dipple

Abstract:

This article describes a software package called ROS-georegistration intended for use with the robot operating system (ROS) and the Gazebo 3D simulation environment. ROSgeoregistration provides tools for the simulation, test, and deployment of aerial georegistration algorithms and is available at github.com/uncc-visionlab/rosgeoregistration. A model creation package is provided which downloads multi-spectral images from the Google Earth Engine database and, if necessary, incorporates these images into a single, possibly very large, reference image. Additionally a Gazebo plugin which uses the real-time sensor pose and image formation model to generate simulated imagery using the specified reference image is provided along with related plugins for UAV relevant data. The novelty of this work is threefold: (1) this is the first system to link the massive multi-spectral imaging database of Google’s Earth Engine to the Gazebo simulator, (2) this is the first example of a system that can simulate geospatially and radiometrically accurate imagery from multiple sensor views of the same terrain region, and (3) integration with other UAS tools creates a new holistic UAS simulation environment to support UAS system and subsystem development where real-world testing would generally be prohibitive. Sensed imagery and ground truth registration information is published to client applications which can receive imagery synchronously with telemetry from other payload sensors, e.g., IMU, GPS/GNSS, barometer, and windspeed sensor data. To highlight functionality, we demonstrate ROSgeoregistration for simulating Electro-Optical (EO) and Synthetic Aperture Radar (SAR) image sensors and an example use case for developing and evaluating image-based UAS position feedback, i.e., pose for image-based Guidance Navigation and Control (GNC) applications.

Keywords: EO-to-EO, EO-to-SAR, flight simulation, georegistration, image generation, robot operating system, vision-based navigation

Procedia PDF Downloads 90

Authors: Mostafa Mjahed

Abstract:

Tilt Rotor UAVs (Unmanned Aerial Vehicles) are naturally unstable and difficult to maneuver. The purpose of this paper is to design controllers for the stabilization and trajectory tracking of this type of UAV. To this end, artificial intelligence methods have been exploited. First, the dynamics of this UAV was modeled using the Lagrange-Euler method. The conventional method based on Proportional, Integral and Derivative (PID) control was applied by decoupling the different flight modes. To improve stability and trajectory tracking of the Tilt Rotor, the fuzzy approach and the technique of multilayer neural networks (NN) has been used. Thus, Fuzzy Proportional Integral and Derivative (FPID) and Neural Network-based Proportional Integral and Derivative controllers (NNPID) have been developed. The meta-heuristic approach based on Particle Swarm Optimization (PSO) method allowed adjusting the setting parameters of NNPID controller, giving us an improved NNPID-PSO controller. Simulation results under the Matlab environment show the efficiency of the approaches adopted. Besides, the Tilt Rotor UAV has become stable and follows different types of trajectories with acceptable precision. The Fuzzy, NN and NN-PSO-based approaches demonstrated their robustness because the presence of the disturbances did not alter the stability or the trajectory tracking of the Tilt Rotor UAV.

Keywords: neural network, fuzzy logic, PSO, PID, trajectory tracking, tilt-rotor UAV

Procedia PDF Downloads 105

Authors: Philip Symonds, Jon Taylor, Zaid Chalabi, Michael Davies

Abstract:

With the world climate projected to warm and major cities in developing countries becoming increasingly populated and polluted, governments are tasked with the problem of overheating and air quality in residential buildings. This paper presents the development of an adaptable model of these risks. Simulations are performed using the EnergyPlus building physics software. An accurate metamodel is formed by randomly sampling building input parameters and training on the outputs of EnergyPlus simulations. Metamodels are used to vastly reduce the amount of computation time required when performing optimisation and sensitivity analyses. Neural Networks (NNs) are compared to a Radial Basis Function (RBF) algorithm when forming a metamodel. These techniques were implemented using the PyBrain and scikit-learn python libraries, respectively. NNs are shown to perform around 15% better than RBFs when estimating overheating and air pollution metrics modelled by EnergyPlus.

Keywords: neural networks, radial basis functions, metamodelling, python machine learning libraries

Procedia PDF Downloads 430

Authors: L. Cesari, D. Alonso, F. Mutelet

Abstract:

The interest in cold production has been on the increase in absorption chillers for many years. In fact, the absorption cycles replace the compressor and thus reduce electrical consumption. The devices also allow waste heat generated through industrial activities to be recovered and cooled to a moderate temperature in accordance with regulatory guidelines. Many working fluids were investigated but could not compete with the commonly used {H2O + LiBr} and {H2O + NH3} to author’s best knowledge. Yet, the corrosion, toxicity and crystallization phenomena of these mixtures prevent the development of the absorption technology. This work investigates the possible use of a glyceline deep eutectic solvent (DES) and CO2 as working fluid in an absorption chiller. To do so, good knowledge of the mixtures is required. Experimental measurements (vapor-liquid equilibria, density, and heat capacity) were performed to complete the data lacking in the literature. The performance of the mixtures was quantified by the calculation of the coefficient of performance (COP). The results show that working fluids containing DES + CO2 are an interesting alternative and lead to different trails of working mixtures for absorption and chiller.

Keywords: absorption devices, deep eutectic solvent, energy valorization, experimental data, simulation

Procedia PDF Downloads 100

Authors: Moquan Gong

Abstract:

In recent years, with the rapid development of deep learning, pre-training technology for natural language processing has made great progress. The early field of natural language processing has long used word vector methods such as Word2Vec to encode text. These word vector methods can also be regarded as static pre-training techniques. However, this context-free text representation brings very limited improvement to subsequent natural language processing tasks and cannot solve the problem of word polysemy. ELMo proposes a context-sensitive text representation method that can effectively handle polysemy problems. Since then, pre-training language models such as GPT and BERT have been proposed one after another. Among them, the BERT model has significantly improved its performance on many typical downstream tasks, greatly promoting the technological development in the field of natural language processing, and has since entered the field of natural language processing. The era of dynamic pre-training technology. Since then, a large number of pre-trained language models based on BERT and XLNet have continued to emerge, and pre-training technology has become an indispensable mainstream technology in the field of natural language processing. This article first gives an overview of pre-training technology and its development history, and introduces in detail the classic pre-training technology in the field of natural language processing, including early static pre-training technology and classic dynamic pre-training technology; and then briefly sorts out a series of enlightening technologies. Pre-training technology, including improved models based on BERT and XLNet; on this basis, analyze the problems faced by current pre-training technology research; finally, look forward to the future development trend of pre-training technology.

Keywords: natural language processing, pre-training, language model, word vectors

Procedia PDF Downloads 33

Authors: Anjalika Fernando, Banuka Athuraliya

Abstract:

This paper presents a comprehensive approach for converting Sinhala Sign Language (SSL) into grammatically correct sentences using Natural Language Processing (NLP) techniques in real-time. While previous studies have explored various aspects of SSL translation, the research gap lies in the absence of grammar checking for SSL. This work aims to bridge this gap by proposing a two-stage methodology that leverages deep learning models to detect signs and translate them into coherent sentences, ensuring grammatical accuracy. The first stage of the approach involves the utilization of a Long Short-Term Memory (LSTM) deep learning model to recognize and interpret SSL signs. By training the LSTM model on a dataset of SSL gestures, it learns to accurately classify and translate these signs into textual representations. The LSTM model achieves a commendable accuracy rate of 94%, demonstrating its effectiveness in accurately recognizing and translating SSL gestures. Building upon the successful recognition and translation of SSL signs, the second stage of the methodology focuses on improving the grammatical correctness of the translated sentences. The project employs a Neural Machine Translation (NMT) architecture, consisting of an encoder and decoder with LSTM components, to enhance the syntactical structure of the generated sentences. By training the NMT model on a parallel corpus of Sinhala wrong sentences and their corresponding grammatically correct translations, it learns to generate coherent and grammatically accurate sentences. The NMT model achieves an impressive accuracy rate of 98%, affirming its capability to produce linguistically sound translations. The proposed approach offers significant contributions to the field of SSL translation and grammar correction. Addressing the critical issue of grammar checking, it enhances the usability and reliability of SSL translation systems, facilitating effective communication between hearing-impaired and non-sign language users. Furthermore, the integration of deep learning techniques, such as LSTM and NMT, ensures the accuracy and robustness of the translation process. This research holds great potential for practical applications, including educational platforms, accessibility tools, and communication aids for the hearing-impaired. Furthermore, it lays the foundation for future advancements in SSL translation systems, fostering inclusive and equal opportunities for the deaf community. Future work includes expanding the existing datasets to further improve the accuracy and generalization of the SSL translation system. Additionally, the development of a dedicated mobile application would enhance the accessibility and convenience of SSL translation on handheld devices. Furthermore, efforts will be made to enhance the current application for educational purposes, enabling individuals to learn and practice SSL more effectively. Another area of future exploration involves enabling two-way communication, allowing seamless interaction between sign-language users and non-sign-language users.In conclusion, this paper presents a novel approach for converting Sinhala Sign Language gestures into grammatically correct sentences using NLP techniques in real time. The two-stage methodology, comprising an LSTM model for sign detection and translation and an NMT model for grammar correction, achieves high accuracy rates of 94% and 98%, respectively. By addressing the lack of grammar checking in existing SSL translation research, this work contributes significantly to the development of more accurate and reliable SSL translation systems, thereby fostering effective communication and inclusivity for the hearing-impaired community

Keywords: Sinhala sign language, sign Language, NLP, LSTM, NMT

Procedia PDF Downloads 83

Authors: Arej Alhemimah

Abstract:

This study investigates the influence of tourists’ perceptions of destination image on their intention to use a tourism app. It examines the roles played by tourists’ perceptions of app/website usability, information quality, and risk in shaping tourism destination image and, subsequently, their app use intention. Using an online questionnaire, the study surveyed 194 international tourists in Saudi Arabia. Results were analysed using PLS-SEM. All the proposed hypotheses were supported and significant. Perceived risk had the strongest influence, followed by the influence of tourists’ perceptions of information quality, then app usability. Additionally, perceived risk was found to have a strong effect on the application use intention. The study makes a significant contribution to the tourism website/application literature; its implications provide practical insights and recommendations for destination marketers and managers to improve their online and social media presence in terms of enhancing e-platform usability, quality of provided information, and most importantly, to create a destination strategy to manage tourists’ risk perceptions.

Keywords: destination image, perceived risk, use intention, tourism app, information quality

Procedia PDF Downloads 57

Authors: Morten Stigaard Laursen, Rasmus Nyholm Jørgensen, Mads Dyrmann, Robert Poulsen

Abstract:

For the past three years, the Danish project, RoboWeedSupport, has sought to bridge the gap between the potential herbicide savings using a decision support system and the required weed inspections. In order to automate the weed inspections it is desired to generate a map of the weed species present within the field, to generate the map images must be captured with samples covering the field. This paper investigates the economical cost of performing this data collection based on a camera system mounted on a all-terain vehicle (ATV) able to drive and collect data at up to 50 km/h while still maintaining a image quality sufficient for identifying newly emerged grass weeds. The economical estimates are based on approximately 100 hectares recorded at three different locations in Denmark. With an average image density of 99 images per hectare the ATV had an capacity of 28 ha per hour, which is estimated to cost 6.6 EUR/ha. Alternatively relying on a boom solution for an existing tracktor it was estimated that a cost of 2.4 EUR/ha is obtainable under equal conditions.

Keywords: weed mapping, integrated weed management, weed recognition, image acquisition

Procedia PDF Downloads 217

Authors: F. Allag, S. Bouharati, M. Belmahdi, R. Zegadi

Abstract:

The rapid expansion of deserts in recent decades as a result of human actions combined with climatic changes has highlighted the necessity to understand biological processes in arid environments. Whereas physical processes and the biology of flora and fauna have been relatively well studied in marginally used arid areas, knowledge of desert soil micro-organisms remains fragmentary. The objective of this study is to conduct a diversity analysis of bacterial communities in unvegetated arid soils. Several biological phenomena in hot deserts related to microbial populations and the potential use of micro-organisms for restoring hot desert environments. Dry land ecosystems have a highly heterogeneous distribution of resources, with greater nutrient concentrations and microbial densities occurring in vegetated than in bare soils. In this work, we found it useful to use techniques of artificial intelligence in their treatment especially artificial neural networks (ANN). The use of the ANN model, demonstrate his capability for addressing the complex problems of uncertainty data.

Keywords: desert soil, climatic changes, bacteria, vegetation, artificial neural networks

Procedia PDF Downloads 380

Authors: Rania Jradi, Christophe Marvillet, Mohamed Razak Jeday

Abstract:

One of the most frequently encountered problems in industrial heat exchangers is fouling, which degrades the thermal and hydraulic performances of these types of equipment, leading thus to failure if undetected. And it occurs due to the accumulation of undesired material on the heat transfer surface. So, it is necessary to know about the heat exchanger fouling dynamics to plan mitigation strategies, ensuring a sustainable and safe operation. This paper proposes an Artificial Neural Network (ANN) approach to estimate the fouling resistance in a cross-flow heat exchanger by the collection of the operating data of the phosphoric acid concentration loop. The operating data of 361 was used to validate the proposed model. The ANN attains AARD= 0.048%, MSE= 1.811x10⁻¹¹, RMSE= 4.256x 10⁻⁶ and r²=99.5 % of accuracy which confirms that it is a credible and valuable approach for industrialists and technologists who are faced with the drawbacks of fouling in heat exchangers.

Keywords: cross-flow heat exchanger, fouling, estimation, phosphoric acid concentration loop, artificial neural network approach

Procedia PDF Downloads 187

Authors: Wang Zhenzhen, Wang Xu, Hong Liangping

Abstract:

The construction of thematic commercial streets has been on the hotspot with the rapid development of cities. In order to improve the image and competitiveness of cities, many cities are building or rebuilding thematic commercial streets. However, many contradictions and problems have emerged during this process. Therefore, it is significant, for both the practice and the research, to analyse the development of thematic commercial streets and provide some useful suggestions. Through the deep research and comparative study of the eight typical thematic commercial streets in Harbin, this paper summarize the current situations, laws and influencing factors of the development of these streets, and then put forward some suggestions about the plan, constructions and developments of the thematic commercial streets.

Keywords: thematic commercial streets, laws of the development, influence factors, the constructions and developments, degrees of aggregation

Procedia PDF Downloads 357

Authors: Agustinus Rudatyo Himamunanto, Anastasia Rita Widiarti

Abstract:

Transliteration using Javanese manuscripts is one of methods to preserve and legate the wealth of literature in the past for the present generation in Indonesia. The transliteration manual process commonly requires philologists and takes a relatively long time. The automatic transliteration process is expected to shorten the time so as to help the works of philologists. The preprocessing and segmentation stage firstly done is used to manage the document images, thus obtaining image script units that will compile input document images free from noise and have the similarity in properties in the thickness, size, and slope. The next stage of characteristic extraction is used to find unique characteristics that will distinguish each Javanese script image. One of characteristics that is used in this research is the number of black pixels in each image units. Each image of Java scripts contained in the data training will undergo the same process similar to the input characters. The system testing was performed with the data of the book Hamong Tani. The book Hamong Tani was selected due to its content, age and number of pages. Those were considered sufficient as a model experimental input. Based on the results of random page automatic transliteration process testing, it was determined that the maximum percentage correctness obtained was 81.53%. The percentage of success was obtained in 32x32 pixel input image size with the 5x5 image window. With regard to the results, it can be concluded that the automatic transliteration model offered is relatively good.

Keywords: Javanese script, character recognition, statistical, automatic transliteration

Procedia PDF Downloads 328

Authors: Colin Smith, Linsey S Passarella

Abstract:

Due to the proliferation and decentralized nature of academic publication, no widely accepted scheme exists for organizing papers by their scientific field of study (FoS) to the author’s best knowledge. While many academic journals require author provided keywords for papers, these keywords range wildly in scope and are not consistent across papers, journals, or field domains, necessitating alternative approaches to paper classification. Past attempts to perform field-of-study (FoS) classification on scientific texts have largely used a-hierarchical FoS schemas or ignored the schema’s inherently hierarchical structure, e.g. by compressing the structure into a single layer for multi-label classification. In this paper, we introduce an application of a Layered Neural Network (LNN) to the problem of performing supervised hierarchical classification of scientific fields of study (FoS) on research papers. In this approach, paper embeddings from a pretrained language model are fed into a top-down LNN. Beginning with a single neural network (NN) for the highest layer of the class hierarchy, each node uses a separate local NN to classify the subsequent subfield child node(s) for an input embedding of concatenated paper titles and abstracts. We compare our LNN-FOS method to other recent machine learning methods using the Microsoft Academic Graph (MAG) FoS hierarchy and find that the LNN-FOS offers increased classification accuracy at each FoS hierarchical level.

Keywords: hierarchical classification, layer neural network, scientific field of study, scientific taxonomy

Procedia PDF Downloads 118

Authors: Marek Maruszczak

Abstract:

Gamified applications have been used successfully in education for years. The rapid development of technologies such as augmented reality and image recognition increases their availability and reduces their prices. Thus, there is an increasing possibility and need for a wide use of such applications in education. The main purpose of this article is to present the effects of work on a mobile application with augmented reality, the aim of which is to motivate tourists to pay more attention to the attractions and increase the likelihood of moving from one attraction to the next while visiting the Palácio Nacional de Sintra in Portugal. Work on the application was carried out together with the employees of Parques de Sintra from 2019 to 2021. Their effect was the preparation of a mobile application using augmented reality and image recognition. The application was tested on the palace premises by both Parques de Sintra employees and tourists visiting Palácio Nacional de Sintra. The collected conclusions allowed for the formulation of good practices and guidelines that can be used when designing gamified apps for the purpose of cultural education.

Keywords: augmented reality, cultural education, gamification, image recognition, mobile games

Procedia PDF Downloads 175