Search results for: forecasting accuracy

Authors: Rita Magdalena, N. K. Caecar Pratiwi, Yunendah Nur Fuadah, Sofia Saidah, Bima Sakti

Abstract:

Vessel segmentation of retinal fundus is important for biomedical sciences in diagnosing ailments related to the eye. Segmentation can simplify medical experts in diagnosing retinal fundus image state. Therefore, in this study, we designed a software using MATLAB which enables the segmentation of the retinal blood vessels on retinal fundus images. There are two main steps in the process of segmentation. The first step is image preprocessing that aims to improve the quality of the image to be optimum segmented. The second step is the image segmentation in order to perform the extraction process to retrieve the retina’s blood vessel from the eye fundus image. The image segmentation methods that will be analyzed in this study are Morphology Operation, Discrete Wavelet Transform and combination of both. The amount of data that used in this project is 40 for the retinal image and 40 for manually segmentation image. After doing some testing scenarios, the average accuracy for Morphology Operation method is 88.46 % while for Discrete Wavelet Transform is 89.28 %. By combining the two methods mentioned in later, the average accuracy was increased to 89.53 %. The result of this study is an image processing system that can segment the blood vessels in retinal fundus with high accuracy and low computation time.

Keywords: discrete wavelet transform, fundus retina, morphology operation, segmentation, vessel

Procedia PDF Downloads 173

Authors: Veronica Sorgato, Jeremy Belhassen, Philippe Chartier, Roddy Sihanath, Nicolas Docquiere, Jean-Yves Giraud

Abstract:

We analyzed the image-guided radiotherapy method used by the TomoTherapy® System (Accuray Corp.) for patient repositioning in clinical routine. The TomoTherapy® System computes X, Y, Z and roll displacements to match the reference CT, on which the dosimetry has been performed, with the pre-treatment MV CT. The accuracy of the repositioning method has been studied according to the treatment localization. For this, a database of 18774 treatment sessions, performed during 2 consecutive years (2016-2017 period) has been used. The database includes the X, Y, Z and roll displacements proposed by TomoTherapy® System as well as the manual correction of these proposals applied by the radiation therapist. This manual correction aims to further improve the repositioning based on the clinical situation and depends on the structures surrounding the target tumor tissue. The statistical analysis performed on the database aims to define repositioning limits to be used as security and guiding tool for the manual adjustment implemented by the radiation therapist. This tool will participate not only to notify potential repositioning errors but also to further improve patient positioning for optimal treatment.

Keywords: accuracy, IGRT MVCT, image-guided radiotherapy megavoltage computed tomography, statistical analysis, tomotherapy, localization

Procedia PDF Downloads 204

Authors: C. Mayr, J. Periya, A. Kariminezhad

Abstract:

In this paper, we developed a learning framework for the classification of vulnerable road users (VRU) by their range-Doppler signatures. The frequency-modulated continuous-wave (FMCW) radar raw data is first pre-processed to obtain robust object range-Doppler maps per coherent time interval. The complex-valued range-Doppler maps captured from our outdoor measurements are further fed into a convolutional neural network (CNN) to learn the classification. This CNN has gone through a hyperparameter optimization process for improved learning. By learning VRU range-Doppler signatures, the three classes 'pedestrian', 'dog', and 'noise' are classified with an average accuracy of almost 95%. Interestingly, this classification accuracy holds for a combined longitudinal and lateral object trajectories.

Keywords: machine learning, radar, signal processing, autonomous driving

Procedia PDF Downloads 214

Authors: Youtao Gao, Bingyu Jin, Tanran Zhao, Bo Xu

Abstract:

The history of satellite navigation can be dated back to the 1960s. From the U.S. Transit system and the Russian Tsikada system to the modern Global Positioning System (GPS) and the Globalnaya Navigatsionnaya Sputnikovaya Sistema (GLONASS), performance of satellite navigation has been greatly improved. Nowadays, the navigation accuracy and coverage of these existing systems have already fully fulfilled the requirement of near-Earth users, but these systems are still beyond the reach of deep space targets. Due to the renewed interest in space exploration, a novel high-precision satellite navigation system is becoming even more important. The increasing demand for such a deep space navigation system has contributed to the emergence of a variety of new constellation architectures, such as the Lunar Global Positioning System. Apart from a Walker constellation which is similar to the one adopted by GPS on Earth, a novel constellation architecture which consists of libration point satellites in the Earth-Moon system is also available to construct the lunar navigation system, which can be called accordingly, the libration point satellite navigation system. The concept of using Earth-Moon libration point satellites for lunar navigation was first proposed by Farquhar and then followed by many other researchers. Moreover, due to the special characteristics of Libration point orbits, an autonomous orbit determination technique, which is called ‘Liaison navigation’, can be adopted by the libration point satellites. Using only scalar satellite-to-satellite tracking data, both the orbits of the user and libration point satellites can be determined autonomously. In this way, the extensive Earth-based tracking measurement can be eliminated, and an autonomous satellite navigation system can be developed for future space exploration missions. The method of state estimate is an unnegligible factor which impacts on the orbit determination accuracy besides type of orbit, initial state accuracy and measurement accuracy. We apply the extended Kalman filter(EKF) and the unscented Kalman filter(UKF) to determinate the orbits of Lagrangian navigation satellites. The autonomous orbit determination errors are compared. The simulation results illustrate that UKF can improve the accuracy and z-axis convergence to some extent.

Keywords: extended Kalman filter, autonomous orbit determination, unscented Kalman filter, navigation constellation

Procedia PDF Downloads 262

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.

Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model

Procedia PDF Downloads 71

Authors: Norhashidah Hj Mohd Ali, Teng Wai Ping

Abstract:

In this paper, the formulation of a new group explicit method with a fourth order accuracy is described in solving the two-dimensional Helmholtz equation. The formulation is based on the nine-point fourth-order compact finite difference approximation formula. The complexity analysis of the developed scheme is also presented. Several numerical experiments were conducted to test the feasibility of the developed scheme. Comparisons with other existing schemes will be reported and discussed. Preliminary results indicate that this method is a viable alternative high accuracy solver to the Helmholtz equation.

Keywords: explicit group method, finite difference, Helmholtz equation, five-point formula, nine-point formula

Procedia PDF Downloads 472

Authors: Wenhao Lan, Ning Li, Qiang Tong

Abstract:

To improve the registration accuracy of a source point cloud and template point cloud when the initial relative deflection angle is too large, a PointNetLK algorithm combined with an oriented bounding box (PointNetLK-OBB) is proposed. In this algorithm, the OBB of a 3D point cloud is used to represent the macro feature of source and template point clouds. Under the guidance of the iterative closest point algorithm, the OBB of the source and template point clouds is aligned, and a mirror symmetry effect is produced between them. According to the fitting degree of the source and template point clouds, the mirror symmetry plane is detected, and the optimal rotation and translation of the source point cloud is obtained to complete the 3D point cloud registration task. To verify the effectiveness of the proposed algorithm, a comparative experiment was performed using the publicly available ModelNet40 dataset. The experimental results demonstrate that, compared with PointNetLK, PointNetLK-OBB improves the registration accuracy of the source and template point clouds when the initial relative deflection angle is too large, and the sensitivity of the initial relative position between the source point cloud and template point cloud is reduced. The primary contribution of this paper is the use of PointNetLK to avoid the non-convex problem of traditional point cloud registration and leveraging the regularity of the OBB to avoid the local optimization problem in the PointNetLK context.

Keywords: mirror symmetry, oriented bounding box, point cloud registration, PointNetLK-OBB

Procedia PDF Downloads 124

Authors: Amel Oueslati, Olfa Benouda

Abstract:

New Value at Risk (VaR) estimation is proposed and investigated. The well-known two stages Garch-EVT approach uses conditional volatility to generate one step ahead forecasts of VaR. With daily data for twelve stocks that decompose the Dow Jones Industrial Average (DJIA) index, this paper incorporates the volume in the first stage volatility estimation. Afterwards, the forecasting ability of this conditional volatility concerning the VaR estimation is compared to that of a basic volatility model without considering any trading component. The results are significant and bring out the importance of the trading volume in the VaR measure.

Keywords: Garch-EVT, value at risk, volume, volatility

Procedia PDF Downloads 260

Authors: Philipp Sommer, Amgad Agoub

Abstract:

The construction sector significantly impacts global CO₂ emissions, particularly through the energy usage of residential buildings. To address this, various governments, including Germany's, are focusing on reducing emissions via sustainable refurbishment initiatives. This study examines the application of machine learning (ML) to estimate energy demands dynamically in residential buildings and enhance the potential for large-scale sustainable refurbishment. A major challenge in Germany is the lack of extensive publicly labeled datasets for energy performance, as energy performance certificates, which provide critical data on building-specific energy requirements and consumption, are not available for all buildings or require on-site inspections. Conversely, England and other countries in the European Union (EU) have rich public datasets, providing a viable alternative for analysis. This research adapts insights from these English datasets to the German context by developing a comprehensive data schema and calibration dataset capable of predicting building energy demand effectively. The study proposes a minimal feature set, determined through feature importance analysis, to optimize the ML model. Findings indicate that ML significantly improves the scalability and accuracy of energy demand forecasts, supporting more effective emissions reduction strategies in the construction industry. Integrating energy performance certificates into municipal heat planning in Germany highlights the transformative impact of data-driven approaches on environmental sustainability. The goal is to identify and utilize key features from open data sources that significantly influence energy demand, creating an efficient forecasting model. Using Extreme Gradient Boosting (XGB) and data from energy performance certificates, effective features such as building type, year of construction, living space, insulation level, and building materials were incorporated. These were supplemented by data derived from descriptions of roofs, walls, windows, and floors, integrated into three datasets. The emphasis was on features accessible via remote sensing, which, along with other correlated characteristics, greatly improved the model's accuracy. The model was further validated using SHapley Additive exPlanations (SHAP) values and aggregated feature importance, which quantified the effects of individual features on the predictions. The refined model using remote sensing data showed a coefficient of determination (R²) of 0.64 and a mean absolute error (MAE) of 4.12, indicating predictions based on efficiency class 1-100 (G-A) may deviate by 4.12 points. This R² increased to 0.84 with the inclusion of more samples, with wall type emerging as the most predictive feature. After optimizing and incorporating related features like estimated primary energy consumption, the R² score for the training and test set reached 0.94, demonstrating good generalization. The study concludes that ML models significantly improve prediction accuracy over traditional methods, illustrating the potential of ML in enhancing energy efficiency analysis and planning. This supports better decision-making for energy optimization and highlights the benefits of developing and refining data schemas using open data to bolster sustainability in the building sector. The study underscores the importance of supporting open data initiatives to collect similar features and support the creation of comparable models in Germany, enhancing the outlook for environmental sustainability.

Keywords: machine learning, remote sensing, residential building, energy performance certificates, data-driven, heat planning

Procedia PDF Downloads 22

Authors: Steffy Maria Joseph, Abdu Rahiman V, Abdul Hameed K. M.

Abstract:

Online handwritten character recognition is a challenging field in Artificial Intelligence. The classification success rate of current techniques decreases when the dataset involves similarity and complexity in stroke styles, number of strokes and stroke characteristics variations. Malayalam is a complex south indian language spoken by about 35 million people especially in Kerala and Lakshadweep islands. In this paper, we consider the significant feature extraction for the similar stroke styles of Malayalam. This extracted feature set are suitable for the recognition of other handwritten south indian languages like Tamil, Telugu and Kannada. A classification scheme based on support vector machines (SVM) is proposed to improve the accuracy in classification and recognition of online malayalam handwritten characters. SVM Classifiers are the best for real world applications. The contribution of various features towards the accuracy in recognition is analysed. Performance for different kernels of SVM are also studied. A graphical user interface has developed for reading and displaying the character. Different writing styles are taken for each of the 44 alphabets. Various features are extracted and used for classification after the preprocessing of input data samples. Highest recognition accuracy of 97% is obtained experimentally at the best feature combination with polynomial kernel in SVM.

Keywords: SVM, matlab, malayalam, South Indian scripts, onlinehandwritten character recognition

Procedia PDF Downloads 552

Authors: Miroslav H. Hristov, Velizar A. Vassilev, Georgi K. Dukendjiev

Abstract:

Due to the constant development of measurement systems and the aim for computerization, unavoidable improvements are made for the main disadvantages of air gauges. With the appearance of the air-electronic measuring devices, some of their disadvantages are solved. The output electrical signal allows them to be included in the modern systems for measuring information processing and process management. Producer efforts are aimed at reducing the influence of supply pressure and measurement system setup errors. Increased accuracy requirements and preventive error measures are due to the main uses of air electronic systems - measurement of geometric dimensions in the automotive industry where they are applied as modules in measuring systems to measure geometric parameters, form, orientation and location of the elements.

Keywords: air-electronic, geometrical parameters, improvement, measurement systems

Procedia PDF Downloads 208

Authors: Miao Sabrina Wang

Abstract:

This paper examines the impact of grammatical differences on simultaneous interpreting from English into Mandarin Chinese by drawing upon an empirical study of professional and student interpreters. The research focuses on the effects of three grammatical categories including passives, adverbial components and noun phrases on simultaneous interpreting. For each category, interpretations of instances in which the grammatical structures are the same across the two languages are compared with interpretations of instances in which the grammatical structures differ across the two languages in terms of content accuracy and delivery appropriateness. The results indicate that grammatical differences have a significant impact on the interpreting performance of both professionals and students.

Keywords: content accuracy, delivery appropriateness, grammatical differences, simultaneous interpreting

Procedia PDF Downloads 509

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 99

Authors: Elena Collino, Dario A. Ronzio, Goffredo Decimi, Maurizio Riva

Abstract:

The rapid increase of renewable energy in Italy is led by wind and solar installations. The 2017 Italian energy strategy foresees a further development of these sustainable technologies, especially solar. This fact has resulted in new opportunities, challenges, and different problems to deal with. The growth of renewables allows to meet the European requirements regarding energy and environmental policy, but these types of sources are difficult to manage because they are intermittent and non-programmable. Operationally, these characteristics can lead to instability on the voltage profile and increasing uncertainty on energy reserve scheduling. The increasing renewable production must be considered with more and more attention especially by the Transmission System Operator (TSO). The TSO, in fact, every day provides orders on energy dispatch, once the market outcome has been determined, on extended areas, defined mainly on the basis of power transmission limitations. In Italy, six market zone are defined: Northern-Italy, Central-Northern Italy, Central-Southern Italy, Southern Italy, Sardinia, and Sicily. An accurate hourly renewable power forecasting for the day-ahead on these extended areas brings an improvement both in terms of dispatching and reserve management. In this study, an operational forecasting tool of the hourly solar output for the six Italian market zones is presented, and the performance is analysed. The implementation is carried out by means of a numerical weather prediction model, coupled with a statistical post-processing in order to derive the power forecast on the basis of the meteorological projection. The weather forecast is obtained from the limited area model RAMS on the Italian territory, initialized with IFS-ECMWF boundary conditions. The post-processing calculates the solar power production with the Analog Ensemble technique (AN). This statistical approach forecasts the production using a probability distribution of the measured production registered in the past when the weather scenario looked very similar to the forecasted one. The similarity is evaluated for the components of the solar radiation: global (GHI), diffuse (DIF) and direct normal (DNI) irradiation, together with the corresponding azimuth and zenith solar angles. These are, in fact, the main factors that affect the solar production. Considering that the AN performance is strictly related to the length and quality of the historical data a training period of more than one year has been used. The training set is made by historical Numerical Weather Prediction (NWP) forecasts at 12 UTC for the GHI, DIF and DNI variables over the Italian territory together with corresponding hourly measured production for each of the six zones. The AN technique makes it possible to estimate the aggregate solar production in the area, without information about the technologic characteristics of the all solar parks present in each area. Besides, this information is often only partially available. Every day, the hourly solar power forecast for the six Italian market zones is made publicly available through a website.

Keywords: analog ensemble, electricity market, PV forecast, solar energy

Procedia PDF Downloads 127

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 123

Authors: James Ladzekpo

Abstract:

Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.

Keywords: diabetes, machine learning, prediction, biomarkers

Procedia PDF Downloads 30

Authors: Muhammad Nouman, Fahad Tiwana, Muhammad Irfan, Mohsin Tiwana

Abstract:

Traffic congestion has been increasing significantly in major metropolitan areas as a result of increased motorization, urbanization, population growth and changes in the urban density. Traffic congestion compromises efficiency of transport infrastructure and causes multiple traffic concerns; including but not limited to increase of travel time, safety hazards, air pollution, and fuel consumption. Traffic management has become a serious challenge for federal and provincial governments, as well as exasperated commuters. Effective, flexible, efficient and user-friendly traffic information/database management systems characterize traffic conditions by making use of traffic counts for storage, processing, and visualization. While, the emerging data collection technologies continue to proliferate, its accuracy can be guaranteed through the comparison of observed data with the manual handheld counters. This paper presents the design of tablet based manual traffic counting application and framework for development of traffic database management system for Pakistan. The database management system comprises of three components including traffic counting android application; establishing online database and its visualization using Google maps. Oracle relational database was chosen to develop the data structure whereas structured query language (SQL) was adopted to program the system architecture. The GIS application links the data from the database and projects it onto a dynamic map for traffic conditions visualization. The traffic counting device and example of a database application in the real-world problem provided a creative outlet to visualize the uses and advantages of a database management system in real time. Also, traffic data counts by means of handheld tablet/ mobile application can be used for transportation planning and forecasting.

Keywords: manual count, emerging data sources, traffic information quality, traffic surveillance, traffic counting device, android; data visualization, traffic management

Procedia PDF Downloads 172

Authors: Yeon-Jong Jeong, Jun-Hong Park, Hyuk Choi

Abstract:

In this study, we have studied the design of intermediate die in multipass drawing. Research has been continuously studied because of the advantage of better dimensional accuracy, smooth surface and improved mechanical properties in the case of drawing. Among them, multipass drawing, which is a method to realize complicated shape by drawing, was discussed in this study. The most important factor in the multipass drawing is the dimensional accuracy and simplify the process. To accomplish this, a multistage shape drawing was performed using various intermediate die shape designs, and finite element analysis was performed.

Keywords: FEM (Finite Element Method), multipass drawing, intermediate die, hollow pipe

Procedia PDF Downloads 298

Authors: Eiman Kattan, Hong Wei

Abstract:

In using Convolutional Neural Network (CNN) for classification, there is a set of hyperparameters available for the configuration purpose. This study aims to evaluate the impact of a range of parameters in CNN architecture i.e. AlexNet on land cover classification based on four remotely sensed datasets. The evaluation tests the influence of a set of hyperparameters on the classification performance. The parameters concerned are epoch values, batch size, and convolutional filter size against input image size. Thus, a set of experiments were conducted to specify the effectiveness of the selected parameters using two implementing approaches, named pertained and fine-tuned. We first explore the number of epochs under several selected batch size values (32, 64, 128 and 200). The impact of kernel size of convolutional filters (1, 3, 5, 7, 10, 15, 20, 25 and 30) was evaluated against the image size under testing (64, 96, 128, 180 and 224), which gave us insight of the relationship between the size of convolutional filters and image size. To generalise the validation, four remote sensing datasets, AID, RSD, UCMerced and RSCCN, which have different land covers and are publicly available, were used in the experiments. These datasets have a wide diversity of input data, such as number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in both training and testing. The results have shown that increasing the number of epochs leads to a higher accuracy rate, as expected. However, the convergence state is highly related to datasets. For the batch size evaluation, it has shown that a larger batch size slightly decreases the classification accuracy compared to a small batch size. For example, selecting the value 32 as the batch size on the RSCCN dataset achieves the accuracy rate of 90.34 % at the 11th epoch while decreasing the epoch value to one makes the accuracy rate drop to 74%. On the other extreme, setting an increased value of batch size to 200 decreases the accuracy rate at the 11th epoch is 86.5%, and 63% when using one epoch only. On the other hand, selecting the kernel size is loosely related to data set. From a practical point of view, the filter size 20 produces 70.4286%. The last performed image size experiment shows a dependency in the accuracy improvement. However, an expensive performance gain had been noticed. The represented conclusion opens the opportunities toward a better classification performance in various applications such as planetary remote sensing.

Keywords: CNNs, hyperparamters, remote sensing, land cover, land use

Procedia PDF Downloads 147

Authors: P. Nafisi Poor, P. Javid

Abstract:

Over the past few years, the idea of adaptive buildings and specifically, adaptive building energy management systems (ABEMS) has become popular. Well-performed management in terms of energy is to create a balance between energy consumption and user comfort; therefore, in new energy management models, efficient energy consumption is not the sole factor and the user's comfortability is also considered in the calculations. One of the main ways of measuring this factor is by analyzing user feedback on the conditions to understand whether they are satisfied with conditions or not. This paper provides a comprehensive review of recent approaches towards energy management systems based on users' feedbacks and subsequently performs a comparison between them premised upon their efficiency and accuracy to understand which approaches were more accurate and which ones resulted in a more efficient way of minimizing energy consumption while maintaining users' comfortability. It was concluded that the highest accuracy rate among the presented works was 95% accuracy in determining satisfaction and up to 51.08% energy savings can be achieved without disturbing user’s comfort. Considering the growing interest in designing and developing adaptive buildings, these studies can support diverse inquiries about this subject and can be used as a resource to support studies and researches towards efficient energy consumption while maintaining the comfortability of users.

Keywords: adaptive buildings, energy efficiency, intelligent buildings, user comfortability

Procedia PDF Downloads 112

Authors: Xudong Guan, Ainong Li, Gaohuan Liu, Chong Huang, Wei Zhao

Abstract:

Due to the low spatial resolution of MODIS data, the accuracy of small-area plaque extraction with a high degree of landscape fragmentation is greatly limited. To this end, the study combines Landsat data with higher spatial resolution and MODIS data with higher temporal resolution for decision-level fusion. Considering the importance of the land heterogeneity factor in the fusion process, it is superimposed with the weighting factor, which is to linearly weight the Landsat classification result and the MOIDS classification result. Three levels were used to complete the process of data fusion, that is the pixel of MODIS data, the pixel of Landsat data, and objects level that connect between these two levels. The multilevel decision fusion scheme was tested in two sites of the lower Mekong basin. We put forth a comparison test, and it was proved that the classification accuracy was improved compared with the single data source classification results in terms of the overall accuracy. The method was also compared with the two-level combination results and a weighted sum decision rule-based approach. The decision fusion scheme is extensible to other multi-resolution data decision fusion applications.

Keywords: image classification, decision fusion, multi-temporal, remote sensing

Procedia PDF Downloads 101

Authors: Engy S. El-Kayal, Mohamed M. S. Arafa

Abstract:

There are various causes of ankle pain including traumatic and non-traumatic causes. Various imaging techniques are available for assessment of AP. MRI is considered to be the imaging modality of choice for ankle joint evaluation with an advantage of its high spatial resolution, multiplanar capability, hence its ability to visualize small complex anatomical structures around the ankle. However, the high costs and the relatively limited availability of MRI systems, as well as the relatively long duration of the examination all are considered disadvantages of MRI examination. Therefore there is a need for a more rapid and less expensive examination modality with good diagnostic accuracy to fulfill this gap. HRU has become increasingly important in the assessment of ankle disorders, with advantages of being fast, reliable, of low cost and readily available. US can visualize detailed anatomical structures and assess tendinous and ligamentous integrity. The aim of this study was to compare the diagnostic accuracy of HRU with MRI in the assessment of patients with AP. We included forty patients complaining of AP. All patients were subjected to real-time HRU and MRI of the affected ankle. Results of both techniques were compared to surgical and arthroscopic findings. All patients were examined according to a defined protocol that includes imaging the tendon tears or tendinitis, muscle tears, masses, or fluid collection, ligament sprain or tears, inflammation or fluid effusion within the joint or bursa, bone and cartilage lesions, erosions and osteophytes. Analysis of the results showed that the mean age of patients was 38 years. The study comprised of 24 women (60%) and 16 men (40%). The accuracy of HRU in detecting causes of AP was 85%, while the accuracy of MRI in the detection of causes of AP was 87.5%. In conclusions: HRU and MRI are two complementary tools of investigation with the former will be used as a primary tool of investigation and the latter will be used to confirm the diagnosis and the extent of the lesion especially when surgical interference is planned.

Keywords: ankle pain (AP), high-resolution ultrasound (HRU), magnetic resonance imaging (MRI) ultrasonography (US)

Procedia PDF Downloads 172

Authors: Irtaza M. Syed, Kaamran Raahemifar

Abstract:

This paper presents modeling of a Alternating Current (AC) Photovoltaic (PV) module using Matlab/Simulink. The proposed AC-PV module model is simple, realistic, and application oriented. The model is derived on module level as compared to cell level directly from the information provided by the manufacturer data sheet. DC-PV module, MPPT control, BC, VSI and LC filter, all were treated as a single unit. The model accounts for changes in variations of both irradiance and temperature. The AC-PV module proposed model is simulated and the results are compared with the datasheet projected numbers to validate model’s accuracy and effectiveness. Implementation and results demonstrate simplicity and accuracy, as well as reliability of the model.

Keywords: PV modeling, AC PV Module, datasheet, VI curves irradiance, temperature, MPPT, Matlab/Simulink

Procedia PDF Downloads 545

Authors: Xiaoqi Jia, Qing Zhu, Hao Zhang, Su Yang

Abstract:

A gender recognition system is able to tell the gender of the given person through a few of frontal facial images. An effective gender recognition approach enables to improve the performance of many other applications, including security monitoring, human-computer interaction, image or video retrieval and so on. In this paper, we present an effective method for gender classification task in frontal facial images based on deep belief networks (DBNs), which can pre-train model and improve accuracy a little bit. Our experiments have shown that the pre-training method with DBNs for gender classification task is feasible and achieves a little improvement of accuracy on FERET and CAS-PEAL-R1 facial datasets.

Keywords: gender recognition, beep belief net-works, semi-supervised learning, greedy-layer wise RBMs

Procedia PDF Downloads 425

Authors: Muhammad Ahnaf Zahin, Yaw Adu-Gyamfi

Abstract:

Bus transit is a crucial component of transportation networks, especially in urban areas. Any intelligent transportation system must have accurate real-time information on bus travel times since it minimizes waiting times for passengers at different stations along a route, improves service reliability, and significantly optimizes travel patterns. Bus agencies must enhance the quality of their information service to serve their passengers better and draw in more travelers since people waiting at bus stops are frequently anxious about when the bus will arrive at their starting point and when it will reach their destination. For solving this issue, different models have been developed for predicting bus travel times recently, but most of them are focused on smaller road networks due to their relatively subpar performance in high-density urban areas on a vast network. This paper develops a deep learning-based architecture using a single-step multi-station forecasting approach to predict average bus travel times for numerous routes, stops, and trips on a large-scale network using heterogeneous bus transit data collected from the GTFS database. Over one week, data was gathered from multiple bus routes in Saint Louis, Missouri. In this study, Gated Recurrent Unit (GRU) neural network was followed to predict the mean vehicle travel times for different hours of the day for multiple stations along multiple routes. Historical time steps and prediction horizon were set up to 5 and 1, respectively, which means that five hours of historical average travel time data were used to predict average travel time for the following hour. The spatial and temporal information and the historical average travel times were captured from the dataset for model input parameters. As adjacency matrices for the spatial input parameters, the station distances and sequence numbers were used, and the time of day (hour) was considered for the temporal inputs. Other inputs, including volatility information such as standard deviation and variance of journey durations, were also included in the model to make it more robust. The model's performance was evaluated based on a metric called mean absolute percentage error (MAPE). The observed prediction errors for various routes, trips, and stations remained consistent throughout the day. The results showed that the developed model could predict travel times more accurately during peak traffic hours, having a MAPE of around 14%, and performed less accurately during the latter part of the day. In the context of a complicated transportation network in high-density urban areas, the model showed its applicability for real-time travel time prediction of public transportation and ensured the high quality of the predictions generated by the model.

Keywords: gated recurrent unit, mean absolute percentage error, single-step forecasting, travel time prediction.

Procedia PDF Downloads 49

Authors: R. Premasiri, W. A. H. A. Abeygunasekara, S. M. Hewavidana, T. Jananthan, R. M. S. Madawala, K. Vaheeshan

Abstract:

Forecasting the potential for disastrous events such as landslides has become one of the major necessities in the current world. Most of all, the landslides occurred in Sri Lanka are found to be triggered mostly by intense rainfall events. The study area is the landslide near Gerandiella waterfall which is located by the 41st kilometer post on Nuwara Eliya-Gampala main road in Kotmale Division in Sri Lanka. The landslide endangers the entire Kotmale town beneath the slope. Geographic Information System (GIS) platform is very much useful when it comes to the need of emulating the real-world processes. The models are used in a wide array of applications ranging from simple evaluations to the levels of forecast future events. This project investigates the possibility of developing a dynamic model to map the spatial distribution of the slope stability. The model incorporates several theoretical models including the infinite slope model, Green Ampt infiltration model and Perched ground water flow model. A series of rainfall values can be fed to the model as the main input to simulate the dynamics of slope stability. Hydrological model developed using GIS is used to quantify the perched water table height, which is one of the most critical parameters affecting the slope stability. Infinite slope stability model is used to quantify the degree of slope stability in terms of factor of safety. DEM was built with the use of digitized contour data. Stratigraphy was modeled in Surfer using borehole data and resistivity images. Data available from rainfall gauges and piezometers were used in calibrating the model. During the calibration, the parameters were adjusted until a good fit between the simulated ground water levels and the piezometer readings was obtained. This model equipped with the predicted rainfall values can be used to forecast of the slope dynamics of the area of interest. Therefore it can be investigated the slope stability of rainfall induced landslides by adjusting temporal dimensions.

Keywords: factor of safety, geographic information system, hydrological model, slope stability

Procedia PDF Downloads 396

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 24

Authors: Xiaolin Zeng, Lei Cheng, Zhirong Li, Xueping Liu

Abstract:

Aiming at the problem of low accuracy and susceptibility to cultural relic diseases in the generation of high-resolution archaeology drawings by current image generation algorithms, an archaeology drawings generation algorithm based on a conditional generative adversarial network is proposed. An attention mechanism is added into the high-resolution image generation network as the backbone network, which enhances the line feature extraction capability and improves the accuracy of line drawing generation. A dual-branch parallel architecture consisting of two backbone networks is implemented, where the semantic translation branch extracts semantic features from orthophotographs of cultural relics, and the gradient screening branch extracts effective gradient features. Finally, the fusion fine-tuning module combines these two types of features to achieve the generation of high-quality and high-resolution archaeology drawings. Experimental results on the self-constructed archaeology drawings dataset of grotto temple statues show that the proposed algorithm outperforms current mainstream image generation algorithms in terms of pixel accuracy (PA), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR) and can be used to assist in drawing archaeology drawings.

Keywords: archaeology drawings, digital heritage, image generation, deep learning

Procedia PDF Downloads 24

Authors: Balarabe Nkom, Adam P. R. Taylor, Craig Baguley

Abstract:

Power Line Communications (PLC) is being employed in existing power systems, despite the infrastructure not being designed with PLC considerations in mind. Given that power transformers can last for decades, the distribution transformer in particular exists as a relic of un-optimized technology. To determine issues that may need to be addressed in subsequent designs of such transformers, it is essential to have a highly accurate transformer model for simulations and subsequent optimization for the PLC environment, with a view to increase data speed, throughput, and efficiency, while improving overall system stability and reliability. This paper reviews various methods currently available for creating transformer models and provides insights into the requirements of each for obtaining high accuracy. The review indicates that a combination of traditional analytical methods using a hybrid approach gives good accuracy at reasonable costs.

Keywords: distribution transformer, modelling, optimization, power line communications

Procedia PDF Downloads 481

Authors: Zhang Shuqi, Liu Dan

Abstract:

For the problems in intelligent network anomaly traffic detection models, such as low detection accuracy caused by the lack of training samples, poor effect with small sample attack detection, a classification model enhancement method, F-ACGAN(Flow Auxiliary Classifier Generative Adversarial Network) which introduces generative adversarial network and adversarial training, is proposed to solve these problems. Generating adversarial data with category labels could enhance the training effect and improve classification accuracy and model robustness. FACGAN consists of three steps: feature preprocess, which includes data type conversion, dimensionality reduction and normalization, etc.; A generative adversarial network model with feature learning ability is designed, and the sample generation effect of the model is improved through adversarial iterations between generator and discriminator. The adversarial disturbance factor of the gradient direction of the classification model is added to improve the diversity and antagonism of generated data and to promote the model to learn from adversarial classification features. The experiment of constructing a classification model with the UNSW-NB15 dataset shows that with the enhancement of FACGAN on the basic model, the classification accuracy has improved by 8.09%, and the score of F1 has improved by 6.94%.

Keywords: data imbalance, GAN, ACGAN, anomaly detection, adversarial training, data augmentation

Procedia PDF Downloads 80