Search results for: Imbalanced dataset
301 Acceleration-Based Motion Model for Visual Simultaneous Localization and Mapping
Authors: Daohong Yang, Xiang Zhang, Lei Li, Wanting Zhou
Abstract:
Visual Simultaneous Localization and Mapping (VSLAM) is a technology that obtains information in the environment for self-positioning and mapping. It is widely used in computer vision, robotics and other fields. Many visual SLAM systems, such as OBSLAM3, employ a constant-speed motion model that provides the initial pose of the current frame to improve the speed and accuracy of feature matching. However, in actual situations, the constant velocity motion model is often difficult to be satisfied, which may lead to a large deviation between the obtained initial pose and the real value, and may lead to errors in nonlinear optimization results. Therefore, this paper proposed a motion model based on acceleration, which can be applied on most SLAM systems. In order to better describe the acceleration of the camera pose, we decoupled the pose transformation matrix, and calculated the rotation matrix and the translation vector respectively, where the rotation matrix is represented by rotation vector. We assume that, in a short period of time, the changes of rotating angular velocity and translation vector remain the same. Based on this assumption, the initial pose of the current frame is estimated. In addition, the error of constant velocity model was analyzed theoretically. Finally, we applied our proposed approach to the ORBSLAM3 system and evaluated two sets of sequences on the TUM dataset. The results showed that our proposed method had a more accurate initial pose estimation and the accuracy of ORBSLAM3 system is improved by 6.61% and 6.46% respectively on the two test sequences.Keywords: error estimation, constant acceleration motion model, pose estimation, visual SLAM
Procedia PDF Downloads 87300 Epilepsy Seizure Prediction by Effective Connectivity Estimation Using Granger Causality and Directed Transfer Function Analysis of Multi-Channel Electroencephalogram
Authors: Mona Hejazi, Ali Motie Nasrabadi
Abstract:
Epilepsy is a persistent neurological disorder that affects more than 50 million people worldwide. Hence, there is a necessity to introduce an efficient prediction model for making a correct diagnosis of the epileptic seizure and accurate prediction of its type. In this study we consider how the Effective Connectivity (EC) patterns obtained from intracranial Electroencephalographic (EEG) recordings reveal information about the dynamics of the epileptic brain and can be used to predict imminent seizures, as this will enable the patients (and caregivers) to take appropriate precautions. We use this definition because we believe that effective connectivity near seizures begin to change, so we can predict seizures according to this feature. Results are reported on the standard Freiburg EEG dataset which contains data from 21 patients suffering from medically intractable focal epilepsy. Six channels of EEG from each patients are considered and effective connectivity using Directed Transfer Function (DTF) and Granger Causality (GC) methods is estimated. We concentrate on effective connectivity standard deviation over time and feature changes in five brain frequency sub-bands (Alpha, Beta, Theta, Delta, and Gamma) are compared. The performance obtained for the proposed scheme in predicting seizures is: average prediction time is 50 minutes before seizure onset, the maximum sensitivity is approximate ~80% and the false positive rate is 0.33 FP/h. DTF method is more acceptable to predict epileptic seizures and generally we can observe that the greater results are in gamma and beta sub-bands. The research of this paper is significantly helpful for clinical applications, especially for the exploitation of online portable devices.Keywords: effective connectivity, Granger causality, directed transfer function, epilepsy seizure prediction, EEG
Procedia PDF Downloads 460299 Molecular Identification and Evolutionary Status of Lucilia bufonivora: An Obligate Parasite of Amphibians in Europe
Authors: Gerardo Arias, Richard Wall, Jamie Stevens
Abstract:
Lucilia bufonivora Moniez, is an obligate parasite of toads and frogs widely distributed in Europe. Its sister taxon Lucilia silvarum Meigen behaves mainly as a carrion breeder in Europe, however it has been reported as a facultative parasite of amphibians. These two closely related species are morphologically almost identical, which has led to misidentification, and in fact, it has been suggested that the amphibian myiasis cases by L. silvarum reported in Europe should be attributed to L. bufonivora. Both species remain poorly studied and their taxonomic relationships are still unclear. The identification of the larval specimens involved in amphibian myiasis with molecular tools and phylogenetic analysis of these two closely related species may resolve this problem. In this work seventeen unidentified larval specimens extracted from toad myiasis cases of the UK, the Netherlands and Switzerland were obtained, their COX1 (mtDNA) and EF1-α (Nuclear DNA) gene regions were amplified and then sequenced. The 17 larval samples were identified with both molecular markers as L. bufonivora. Phylogenetic analysis was carried out with 10 other blowfly species, including L. silvarum samples from the UK and USA. Bayesian Inference trees of COX1 and a combined-gene dataset suggested that L. silvarum and L. bufonivora are separate sister species. However, the nuclear gene EF1-α does not appear to resolve their relationships, suggesting that the rates of evolution of the mtDNA are much faster than those of the nuclear DNA. This work provides the molecular evidence for successful identification of L. bufonivora and a molecular analysis of the populations of this obligate parasite from different locations across Europe. The relationships with L. silvarum are discussed.Keywords: calliphoridae, molecular evolution, myiasis, obligate parasitism
Procedia PDF Downloads 233298 Investigation and Analysis of Residential Building Energy End-Use Profile in Hot and Humid Area with Reference to Zhuhai City in China
Authors: Qingqing Feng, S. Thomas Ng, Frank Xu
Abstract:
Energy consumption in domestic sector has been increasing rapidly in China all along these years. Confronted with environmental challenges, the international society has made a concerted effort by setting the Paris Agreement, the Sustainable Development Goals, and the New Urban Agenda. Thus it’s very important for China to put forward reasonable countermeasures to boost building energy conservation which necessitates looking into the actuality of residential energy end-use profile and its influence factors. In this study, questionnaire surveys have been conducted in Zhuhai city in China, a typical city in hot summer warm winter climate zone. The data solicited mainly include the occupancy schedule, building’s information, residents’ information, household energy uses, the type, quantity and use patterns of appliances and occupants’ satisfaction. Over 200 valid samples have been collected through face-to-face interviews. Descriptive analysis, clustering analysis, correlation analysis and sensitivity analysis were then conducted on the dataset to understand the energy end-use profile. The findings identify: 1) several typical clusters of occupancy patterns and appliances utilization patterns; 2) the top three sensitive factors influencing energy consumption; 3) the correlations between satisfaction and energy consumption. For China with many different climates zones, it’s difficult to find a silver bullet on energy conservation. The aim of this paper is to provide a theoretical basis for multi-stakeholders including policy makers, residents, and academic communities to formulate reasonable energy saving blueprints for hot and humid urban residential buildings in China.Keywords: residential building, energy end-use profile, questionnaire survey, sustainability
Procedia PDF Downloads 124297 Current Methods for Drug Property Prediction in the Real World
Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh
Abstract:
Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning
Procedia PDF Downloads 71296 A Review of Deep Learning Methods in Computer-Aided Detection and Diagnosis Systems based on Whole Mammogram and Ultrasound Scan Classification
Authors: Ian Omung'a
Abstract:
Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision
Procedia PDF Downloads 87295 Development of Medical Intelligent Process Model Using Ontology Based Technique
Authors: Emmanuel Chibuogu Asogwa, Tochukwu Sunday Belonwu
Abstract:
An urgent demand for creative solutions has been created by the rapid expansion of medical knowledge, the complexity of patient care, and the requirement for more precise decision-making. As a solution to this problem, the creation of a Medical Intelligent Process Model (MIPM) utilizing ontology-based appears as a promising way to overcome this obstacle and unleash the full potential of healthcare systems. The development of a Medical Intelligent Process Model (MIPM) using ontology-based techniques is motivated by a lack of quick access to relevant medical information and advanced tools for treatment planning and clinical decision-making, which ontology-based techniques can provide. The aim of this work is to develop a structured and knowledge-driven framework that leverages ontology, a formal representation of domain knowledge, to enhance various aspects of healthcare. Object-Oriented Analysis and Design Methodology (OOADM) were adopted in the design of the system as we desired to build a usable and evolvable application. For effective implementation of this work, we used the following materials/methods/tools: the medical dataset for the test of our model in this work was obtained from Kaggle. The ontology-based technique was used with Confusion Matrix, MySQL, Python, Hypertext Markup Language (HTML), Hypertext Preprocessor (PHP), Cascaded Style Sheet (CSS), JavaScript, Dreamweaver, and Fireworks. According to test results on the new system using Confusion Matrix, both the accuracy and overall effectiveness of the medical intelligent process significantly improved by 20% compared to the previous system. Therefore, using the model is recommended for healthcare professionals.Keywords: ontology-based, model, database, OOADM, healthcare
Procedia PDF Downloads 70294 Integrating Molecular Approaches to Understand Diatom Assemblages in Marine Environment
Authors: Shruti Malviya, Chris Bowler
Abstract:
Environmental processes acting at multiple spatial scales control marine diatom community structure. However, the contribution of local factors (e.g., temperature, salinity, etc.) in these highly complex systems is poorly understood. We, therefore, investigated the diatom community organization as a function of environmental predictors and determined the relative contribution of various environmental factors on the structure of marine diatoms assemblages in the world’s ocean. The dataset for this study was derived from the Tara Oceans expedition, constituting 46 sampling stations from diverse oceanic provinces. The V9 hypervariable region of 18s rDNA was organized into assemblages based on their distributional co-occurrence. Using Ward’s hierarchical clustering, nine clusters were defined. The number of ribotypes and reads varied within each cluster-three clusters (II, VIII and IX) contained only a few reads whereas two of them (I and IV) were highly abundant. Of the nine clusters, seven can be divided into two categories defined by a positive correlation with phosphate and nitrate and a negative correlation with longitude and, the other by a negative correlation with salinity, temperature, latitude and positive correlation with Lyapunov exponent. All the clusters were found to be remarkably dominant in South Pacific Ocean and can be placed into three classes, namely Southern Ocean-South Pacific Ocean clusters (I, II, V, VIII, IX), South Pacific Ocean clusters (IV and VII), and cosmopolitan clusters (III and VI). Our findings showed that co-occurring ribotypes can be significantly associated into recognizable clusters which exhibit a distinct response to environmental variables. This study, thus, demonstrated distinct behavior of each recognized assemblage displaying a taxonomic and environmental signature.Keywords: assemblage, diatoms, hierarchical clustering, Tara Oceans
Procedia PDF Downloads 196293 Analyzing the Climate Change Impact and Farmer's Adaptability Strategies in Khyber Pakhtunkhwa, Pakistan
Authors: Khuram Nawaz Sadozai, Sonia
Abstract:
The agriculture sector is deemed more vulnerable to climate change as its variation can directly affect the crop’s productivity, but farmers’ adaptation strategies play a vital role in climate change-agriculture relationship. Therefore, this research has been undertaken to assess the Climate Change impact on wheat productivity and farmers’ adaptability strategies in Khyber Pakhtunkhwa province, Pakistan. The panel dataset was analyzed to gauge the impact of changing climate variables (i.e., temperature, rainfall, and humidity) on wheat productivity from 1985 to 2015. Amid the study period, the fixed effect estimates confirmed an inverse relationship of temperature and rainfall on the wheat yield. The impact of temperature is observed to be detrimental as compared to the rainfall, causing 0.07 units reduction in the production of wheat with 1C upsurge in temperature. On the flip side, humidity revealed a positive association with the wheat productivity by confirming that high humidity could be beneficial to the production of the crop over time. Thus, this study ensures significant nexus between agricultural production and climatic parameters. However, the farming community in the underlying study area has limited knowledge about the adaptation strategies to lessen the detrimental impact of changing climate on crop yield. It is recommended that farmers should be well equipped with training and advanced agricultural management practices under the realm of climate change. Moreover, innovative technologies pertinent to the agriculture system should be encouraged to handle the challenges arising due to variations in climate factors.Keywords: climate change, fixed effect model, panel data, wheat productivity
Procedia PDF Downloads 114292 2D Convolutional Networks for Automatic Segmentation of Knee Cartilage in 3D MRI
Authors: Ananya Ananya, Karthik Rao
Abstract:
Accurate segmentation of knee cartilage in 3-D magnetic resonance (MR) images for quantitative assessment of volume is crucial for studying and diagnosing osteoarthritis (OA) of the knee, one of the major causes of disability in elderly people. Radiologists generally perform this task in slice-by-slice manner taking 15-20 minutes per 3D image, and lead to high inter and intra observer variability. Hence automatic methods for knee cartilage segmentation are desirable and are an active field of research. This paper presents design and experimental evaluation of 2D convolutional neural networks based fully automated methods for knee cartilage segmentation in 3D MRI. The architectures are validated based on 40 test images and 60 training images from SKI10 dataset. The proposed methods segment 2D slices one by one, which are then combined to give segmentation for whole 3D images. Proposed methods are modified versions of U-net and dilated convolutions, consisting of a single step that segments the given image to 5 labels: background, femoral cartilage, tibia cartilage, femoral bone and tibia bone; cartilages being the primary components of interest. U-net consists of a contracting path and an expanding path, to capture context and localization respectively. Dilated convolutions lead to an exponential expansion of receptive field with only a linear increase in a number of parameters. A combination of modified U-net and dilated convolutions has also been explored. These architectures segment one 3D image in 8 – 10 seconds giving average volumetric Dice Score Coefficients (DSC) of 0.950 - 0.962 for femoral cartilage and 0.951 - 0.966 for tibia cartilage, reference being the manual segmentation.Keywords: convolutional neural networks, dilated convolutions, 3 dimensional, fully automated, knee cartilage, MRI, segmentation, U-net
Procedia PDF Downloads 251291 EcoMush: Mapping Sustainable Mushroom Production in Bangladesh
Authors: A. A. Sadia, A. Emdad, E. Hossain
Abstract:
The increasing importance of mushrooms as a source of nutrition, health benefits, and even potential cancer treatment has raised awareness of the impact of climate-sensitive variables on their cultivation. Factors like temperature, relative humidity, air quality, and substrate composition play pivotal roles in shaping mushroom growth, especially in Bangladesh. Oyster mushrooms, a commonly cultivated variety in this region, are particularly vulnerable to climate fluctuations. This research explores the climatic dynamics affecting oyster mushroom cultivation and, presents an approach to address these challenges and provides tangible solutions to fortify the agro-economy, ensure food security, and promote the sustainability of this crucial food source. Using climate and production data, this study evaluates the performance of three clustering algorithms -KMeans, OPTICS, and BIRCH- based on various quality metrics. While each algorithm demonstrates specific strengths, the findings provide insights into their effectiveness for this specific dataset. The results yield essential information, pinpointing the optimal temperature range of 13°C-22°C, the unfavorable temperature threshold of 28°C and above, and the ideal relative humidity range of 75-85% with the suitable production regions in three different seasons: Kharif-1, 2, and Robi. Additionally, a user-friendly web application is developed to support mushroom farmers in making well-informed decisions about their cultivation practices. This platform offers valuable insights into the most advantageous periods for oyster mushroom farming, with the overarching goal of enhancing the efficiency and profitability of mushroom farming.Keywords: climate variability, mushroom cultivation, clustering techniques, food security, sustainability, web-application
Procedia PDF Downloads 57290 Grassland Phenology in Different Eco-Geographic Regions over the Tibetan Plateau
Authors: Jiahua Zhang, Qing Chang, Fengmei Yao
Abstract:
Studying on the response of vegetation phenology to climate change at different temporal and spatial scales is important for understanding and predicting future terrestrial ecosystem dynamics andthe adaptation of ecosystems to global change. In this study, the Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) dataset and climate data were used to analyze the dynamics of grassland phenology as well as their correlation with climatic factors in different eco-geographic regions and elevation units across the Tibetan Plateau. The results showed that during 2003–2012, the start of the grassland greening season (SOS) appeared later while the end of the growing season (EOS) appeared earlier following the plateau’s precipitation and heat gradients from southeast to northwest. The multi-year mean value of SOS showed differences between various eco-geographic regions and was significantly impacted by average elevation and regional average precipitation during spring. Regional mean differences for EOS were mainly regulated by mean temperature during autumn. Changes in trends of SOS in the central and eastern eco-geographic regions were coupled to the mean temperature during spring, advancing by about 7d/°C. However, in the two southwestern eco-geographic regions, SOS was delayed significantly due to the impact of spring precipitation. The results also showed that the SOS occurred later with increasing elevation, as expected, with a delay rate of 0.66 d/100m. For 2003–2012, SOS showed an advancing trend in low-elevation areas, but a delayed trend in high-elevation areas, while EOS was delayed in low-elevation areas, but advanced in high-elevation areas. Grassland SOS and EOS changes may be influenced by a variety of other environmental factors in each eco-geographic region.Keywords: grassland, phenology, MODIS, eco-geographic regions, elevation, climatic factors, Tibetan Plateau
Procedia PDF Downloads 319289 Remote Sensing through Deep Neural Networks for Satellite Image Classification
Authors: Teja Sai Puligadda
Abstract:
Satellite images in detail can serve an important role in the geographic study. Quantitative and qualitative information provided by the satellite and remote sensing images minimizes the complexity of work and time. Data/images are captured at regular intervals by satellite remote sensing systems, and the amount of data collected is often enormous, and it expands rapidly as technology develops. Interpreting remote sensing images, geographic data mining, and researching distinct vegetation types such as agricultural and forests are all part of satellite image categorization. One of the biggest challenge data scientists faces while classifying satellite images is finding the best suitable classification algorithms based on the available that could able to classify images with utmost accuracy. In order to categorize satellite images, which is difficult due to the sheer volume of data, many academics are turning to deep learning machine algorithms. As, the CNN algorithm gives high accuracy in image recognition problems and automatically detects the important features without any human supervision and the ANN algorithm stores information on the entire network (Abhishek Gupta., 2020), these two deep learning algorithms have been used for satellite image classification. This project focuses on remote sensing through Deep Neural Networks i.e., ANN and CNN with Deep Sat (SAT-4) Airborne dataset for classifying images. Thus, in this project of classifying satellite images, the algorithms ANN and CNN are implemented, evaluated & compared and the performance is analyzed through evaluation metrics such as Accuracy and Loss. Additionally, the Neural Network algorithm which gives the lowest bias and lowest variance in solving multi-class satellite image classification is analyzed.Keywords: artificial neural network, convolutional neural network, remote sensing, accuracy, loss
Procedia PDF Downloads 151288 Applications of Multivariate Statistical Methods on Geochemical Data to Evaluate the Hydrocarbons Source Rocks and Oils from Ghadames Basin, NW Libya
Authors: Mohamed Hrouda
Abstract:
The Principal Component Analysis (PCA) was performed on a dataset comprising 41 biomarker concentrations from twenty-three core source rocks samples and seven oil samples from different location, with the objective of establishing the major sources of variance within the steranes, tricyclic terpanes, hopanes, and triaromatic steroid. This type of analysis can be used as an aid when deciding which molecular biomarker maturity, source facies or depositional environment parameters should be plotted, because the principal component loadings plots tend to extract the biomarker variables related to maturity, source facies or depositional environment controls. Facies characterization of the source rock samples separate the Silurian and Devonian source rock samples into three groups. Maturity evaluation of source rock samples based on biomarker and aromatic hydrocarbon distributions indicates that not all the samples are strongly affected by maturity, the Upper Devonian samples from wells located in the northern part of the basin are immature, whereas the other samples which have been selected from the Lower Silurian are mature and have reached the main stage of the oil window, the Lower Silurian source rock strata revealed a trend of increasing maturity towards the south and southwestern part of Ghadames Basin. Most of the facies-based parameters employed in this project using biomarker distributions clearly separate the oil samples into three groups. Group I contain oil samples from wells within Al-Wafa oil field Located in the south western part of the basin, Group II contains oil samples collected from Al-Hamada oil field complex in the south and the third group contains oil samples collected from oil fields located in the northKeywords: Ghadamis basin, geochemistry, silurian, devonian
Procedia PDF Downloads 56287 Unpacking the Summarising Event in Trauma Emergencies: The Case of Pre-briefings
Authors: Professor Jo Angouri, Polina Mesinioti, Chris Turner
Abstract:
In order for a group of ad-hoc professional to perform as a team, a shared understanding of the problem at hand and an agreed action plan are necessary components. This is particularly significant in complex, time sensitive professional settings such as in trauma emergencies. In this context, team briefings prior to the patient arrival (pre-briefings) constitute a critical event for the performance of the team; they provide the necessary space for co-constructing a shared understanding of the situation through summarising information available to the team: yet the act of summarising is widely assumed in medical practice but not systematically researched. In the vast teamwork literature, terms such as ‘shared mental model’, ‘mental space’ and ‘cognate labelling’ are used extensively, and loosely, to denote the outcome of the summarising process, but how exactly this is done interactionally remains under researched. This paper reports on the forms and functions of pre-briefings in a major trauma centre in the UK. Taking an interactional approach, we draw on 30 simulated and real-life trauma emergencies (15 from each dataset) and zoom in on the use of pre-briefings, which we consider focal points in the management of trauma emergencies. We show how ad hoc teams negotiate sharedness of future orientation through summarising, synthesising information, and establishing common understanding of the situation. We illustrate the role, characteristics, and structure of pre-briefing sequences that have been evaluated as ‘efficient’ in our data and the impact (in)effective pre-briefings have on teamwork. Our work shows that the key roles in the event own the act of summarising and we problematise the implications for leadership in trauma emergencies. We close the paper with a model for pre-briefing and provide recommendations for clinical practice, arguing that effective pre-briefing practice is teachable.Keywords: summarising, medical emergencies, interaction analysis, shared/mental models
Procedia PDF Downloads 86286 3D Numerical Study of Tsunami Loading and Inundation in a Model Urban Area
Authors: A. Bahmanpour, I. Eames, C. Klettner, A. Dimakopoulos
Abstract:
We develop a new set of diagnostic tools to analyze inundation into a model district using three-dimensional CFD simulations, with a view to generating a database against which to test simpler models. A three-dimensional model of Oregon city with different-sized groups of building next to the coastline is used to run calculations of the movement of a long period wave on the shore. The initial and boundary conditions of the off-shore water are set using a nonlinear inverse method based on Eulerian spatial information matching experimental Eulerian time series measurements of water height. The water movement is followed in time, and this enables the pressure distribution on every surface of each building to be followed in a temporal manner. The three-dimensional numerical data set is validated against published experimental work. In the first instance, we use the dataset as a basis to understand the success of reduced models - including 2D shallow water model and reduced 1D models - to predict water heights, flow velocity and forces. This is because models based on the shallow water equations are known to underestimate drag forces after the initial surge of water. The second component is to identify critical flow features, such as hydraulic jumps and choked states, which are flow regions where dissipation occurs and drag forces are large. Finally, we describe how future tsunami inundation models should be modified to account for the complex effects of buildings through drag and blocking.Financial support from UCL and HR Wallingford is greatly appreciated. The authors would like to thank Professor Daniel Cox and Dr. Hyoungsu Park for providing the data on the Seaside Oregon experiment.Keywords: computational fluid dynamics, extreme events, loading, tsunami
Procedia PDF Downloads 111285 Recession Rate of Gangotri and Its Tributary Glacier, Garhwal Himalaya, India through Kinematic GPS Survey and Satellite Data
Authors: Harish Bisht, Bahadur Singh Kotlia, Kireet Kumar
Abstract:
In order to reconstruct past retreating rates, total area loss, volume change and shift in snout position were measured through multi-temporal satellite data from 1989 to 2016 and kinematic GPS survey from 2015 to 2016. The results obtained from satellite data indicate that in the last 27 years, Chaturangi glacier snout has retreated 1172.57 ± 38.3 m (average 45.07 ± 4.31 m/year) with a total area and volume loss of 0.626 ± 0.001 sq. Km and 0.139 Km³, respectively. The field measurements through differential global positioning system survey revealed that the annual retreating rate was 22.84 ± 0.05 m/year. The large variations in results derived from both the methods are probably because of higher difference in their accuracy. Snout monitoring of the Gangotri glacier during the ablation season (May to September) in the years 2005 and 2015 reveals that the retreating rate has been comparatively more declined than that shown by the earlier studies. The GPS dataset shows that the average recession rate is 10.26 ± 0.05 m/year. In order to determine the possible causes of decreased retreating rate, a relationship between debris thickness and melt rate was also established by using ablation stakes. The present study concludes that remote sensing method is suitable for large area and long term study, while kinematic GPS is more appropriate for the annual monitoring of retreating rate of glacier snout. The present study also emphasizes on mapping of all the tributary glaciers in order to assess the overall changes in the main glacier system and its health.Keywords: Chaturangi glacier, Gangotri glacier, glacier snout, kinematic global positioning system, retreat rate
Procedia PDF Downloads 132284 C-eXpress: A Web-Based Analysis Platform for Comparative Functional Genomics and Proteomics in Human Cancer Cell Line, NCI-60 as an Example
Authors: Chi-Ching Lee, Po-Jung Huang, Kuo-Yang Huang, Petrus Tang
Abstract:
Background: Recent advances in high-throughput research technologies such as new-generation sequencing and multi-dimensional liquid chromatography makes it possible to dissect the complete transcriptome and proteome in a single run for the first time. However, it is almost impossible for many laboratories to handle and analysis these “BIG” data without the support from a bioinformatics team. We aimed to provide a web-based analysis platform for users with only limited knowledge on bio-computing to study the functional genomics and proteomics. Method: We use NCI-60 as an example dataset to demonstrate the power of the web-based analysis platform and data delivering system: C-eXpress takes a simple text file that contain the standard NCBI gene or protein ID and expression levels (rpkm or fold) as input file to generate a distribution map of gene/protein expression levels in a heatmap diagram organized by color gradients. The diagram is hyper-linked to a dynamic html table that allows the users to filter the datasets based on various gene features. A dynamic summary chart is generated automatically after each filtering process. Results: We implemented an integrated database that contain pre-defined annotations such as gene/protein properties (ID, name, length, MW, pI); pathways based on KEGG and GO biological process; subcellular localization based on GO cellular component; functional classification based on GO molecular function, kinase, peptidase and transporter. Multiple ways of sorting of column and rows is also provided for comparative analysis and visualization of multiple samples.Keywords: cancer, visualization, database, functional annotation
Procedia PDF Downloads 610283 Faster Pedestrian Recognition Using Deformable Part Models
Authors: Alessandro Preziosi, Antonio Prioletti, Luca Castangia
Abstract:
Deformable part models achieve high precision in pedestrian recognition, but all publicly available implementations are too slow for real-time applications. We implemented a deformable part model algorithm fast enough for real-time use by exploiting information about the camera position and orientation. This implementation is both faster and more precise than alternative DPM implementations. These results are obtained by computing convolutions in the frequency domain and using lookup tables to speed up feature computation. This approach is almost an order of magnitude faster than the reference DPM implementation, with no loss in precision. Knowing the position of the camera with respect to horizon it is also possible prune many hypotheses based on their size and location. The range of acceptable sizes and positions is set by looking at the statistical distribution of bounding boxes in labelled images. With this approach it is not needed to compute the entire feature pyramid: for example higher resolution features are only needed near the horizon. This results in an increase in mean average precision of 5% and an increase in speed by a factor of two. Furthermore, to reduce misdetections involving small pedestrians near the horizon, input images are supersampled near the horizon. Supersampling the image at 1.5 times the original scale, results in an increase in precision of about 4%. The implementation was tested against the public KITTI dataset, obtaining an 8% improvement in mean average precision over the best performing DPM-based method. By allowing for a small loss in precision computational time can be easily brought down to our target of 100ms per image, reaching a solution that is faster and still more precise than all publicly available DPM implementations.Keywords: autonomous vehicles, deformable part model, dpm, pedestrian detection, real time
Procedia PDF Downloads 272282 Performance Comparison of Deep Convolutional Neural Networks for Binary Classification of Fine-Grained Leaf Images
Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu
Abstract:
Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning
Procedia PDF Downloads 180281 Medical Diagnosis of Retinal Diseases Using Artificial Intelligence Deep Learning Models
Authors: Ethan James
Abstract:
Over one billion people worldwide suffer from some level of vision loss or blindness as a result of progressive retinal diseases. Many patients, particularly in developing areas, are incorrectly diagnosed or undiagnosed whatsoever due to unconventional diagnostic tools and screening methods. Artificial intelligence (AI) based on deep learning (DL) convolutional neural networks (CNN) have recently gained a high interest in ophthalmology for its computer-imaging diagnosis, disease prognosis, and risk assessment. Optical coherence tomography (OCT) is a popular imaging technique used to capture high-resolution cross-sections of retinas. In ophthalmology, DL has been applied to fundus photographs, optical coherence tomography, and visual fields, achieving robust classification performance in the detection of various retinal diseases including macular degeneration, diabetic retinopathy, and retinitis pigmentosa. However, there is no complete diagnostic model to analyze these retinal images that provide a diagnostic accuracy above 90%. Thus, the purpose of this project was to develop an AI model that utilizes machine learning techniques to automatically diagnose specific retinal diseases from OCT scans. The algorithm consists of neural network architecture that was trained from a dataset of over 20,000 real-world OCT images to train the robust model to utilize residual neural networks with cyclic pooling. This DL model can ultimately aid ophthalmologists in diagnosing patients with these retinal diseases more quickly and more accurately, therefore facilitating earlier treatment, which results in improved post-treatment outcomes.Keywords: artificial intelligence, deep learning, imaging, medical devices, ophthalmic devices, ophthalmology, retina
Procedia PDF Downloads 177280 Graph Neural Network-Based Classification for Disease Prediction in Health Care Heterogeneous Data Structures of Electronic Health Record
Authors: Raghavi C. Janaswamy
Abstract:
In the healthcare sector, heterogenous data elements such as patients, diagnosis, symptoms, conditions, observation text from physician notes, and prescriptions form the essentials of the Electronic Health Record (EHR). The data in the form of clear text and images are stored or processed in a relational format in most systems. However, the intrinsic structure restrictions and complex joins of relational databases limit the widespread utility. In this regard, the design and development of realistic mapping and deep connections as real-time objects offer unparallel advantages. Herein, a graph neural network-based classification of EHR data has been developed. The patient conditions have been predicted as a node classification task using a graph-based open source EHR data, Synthea Database, stored in Tigergraph. The Synthea DB dataset is leveraged due to its closer representation of the real-time data and being voluminous. The graph model is built from the EHR heterogeneous data using python modules, namely, pyTigerGraph to get nodes and edges from the Tigergraph database, PyTorch to tensorize the nodes and edges, PyTorch-Geometric (PyG) to train the Graph Neural Network (GNN) and adopt the self-supervised learning techniques with the AutoEncoders to generate the node embeddings and eventually perform the node classifications using the node embeddings. The model predicts patient conditions ranging from common to rare situations. The outcome is deemed to open up opportunities for data querying toward better predictions and accuracy.Keywords: electronic health record, graph neural network, heterogeneous data, prediction
Procedia PDF Downloads 81279 Remaining Useful Life Estimation of Bearings Based on Nonlinear Dimensional Reduction Combined with Timing Signals
Authors: Zhongmin Wang, Wudong Fan, Hengshan Zhang, Yimin Zhou
Abstract:
In data-driven prognostic methods, the prediction accuracy of the estimation for remaining useful life of bearings mainly depends on the performance of health indicators, which are usually fused some statistical features extracted from vibrating signals. However, the existing health indicators have the following two drawbacks: (1) The differnet ranges of the statistical features have the different contributions to construct the health indicators, the expert knowledge is required to extract the features. (2) When convolutional neural networks are utilized to tackle time-frequency features of signals, the time-series of signals are not considered. To overcome these drawbacks, in this study, the method combining convolutional neural network with gated recurrent unit is proposed to extract the time-frequency image features. The extracted features are utilized to construct health indicator and predict remaining useful life of bearings. First, original signals are converted into time-frequency images by using continuous wavelet transform so as to form the original feature sets. Second, with convolutional and pooling layers of convolutional neural networks, the most sensitive features of time-frequency images are selected from the original feature sets. Finally, these selected features are fed into the gated recurrent unit to construct the health indicator. The results state that the proposed method shows the enhance performance than the related studies which have used the same bearing dataset provided by PRONOSTIA.Keywords: continuous wavelet transform, convolution neural net-work, gated recurrent unit, health indicators, remaining useful life
Procedia PDF Downloads 128278 Human-Centred Data Analysis Method for Future Design of Residential Spaces: Coliving Case Study
Authors: Alicia Regodon Puyalto, Alfonso Garcia-Santos
Abstract:
This article presents a method to analyze the use of indoor spaces based on data analytics obtained from inbuilt digital devices. The study uses the data generated by the in-place devices, such as smart locks, Wi-Fi routers, and electrical sensors, to gain additional insights on space occupancy, user behaviour, and comfort. Those devices, originally installed to facilitate remote operations, report data through the internet that the research uses to analyze information on human real-time use of spaces. Using an in-place Internet of Things (IoT) network enables a faster, more affordable, seamless, and scalable solution to analyze building interior spaces without incorporating external data collection systems such as sensors. The methodology is applied to a real case study of coliving, a residential building of 3000m², 7 floors, and 80 users in the centre of Madrid. The case study applies the method to classify IoT devices, assess, clean, and analyze collected data based on the analysis framework. The information is collected remotely, through the different platforms devices' platforms; the first step is to curate the data, understand what insights can be provided from each device according to the objectives of the study, this generates an analysis framework to be escalated for future building assessment even beyond the residential sector. The method will adjust the parameters to be analyzed tailored to the dataset available in the IoT of each building. The research demonstrates how human-centered data analytics can improve the future spatial design of indoor spaces.Keywords: in-place devices, IoT, human-centred data-analytics, spatial design
Procedia PDF Downloads 189277 Adjusting Electricity Demand Data to Account for the Impact of Loadshedding in Forecasting Models
Authors: Migael van Zyl, Stefanie Visser, Awelani Phaswana
Abstract:
The electricity landscape in South Africa is characterized by frequent occurrences of loadshedding, a measure implemented by Eskom to manage electricity generation shortages by curtailing demand. Loadshedding, classified into stages ranging from 1 to 8 based on severity, involves the systematic rotation of power cuts across municipalities according to predefined schedules. However, this practice introduces distortions in recorded electricity demand, posing challenges to accurate forecasting essential for budgeting, network planning, and generation scheduling. Addressing this challenge requires the development of a methodology to quantify the impact of loadshedding and integrate it back into metered electricity demand data. Fortunately, comprehensive records of loadshedding impacts are maintained in a database, enabling the alignment of Loadshedding effects with hourly demand data. This adjustment ensures that forecasts accurately reflect true demand patterns, independent of loadshedding's influence, thereby enhancing the reliability of electricity supply management in South Africa. This paper presents a methodology for determining the hourly impact of load scheduling and subsequently adjusting historical demand data to account for it. Furthermore, two forecasting models are developed: one utilizing the original dataset and the other using the adjusted data. A comparative analysis is conducted to evaluate forecast accuracy improvements resulting from the adjustment process. By implementing this methodology, stakeholders can make more informed decisions regarding electricity infrastructure investments, resource allocation, and operational planning, contributing to the overall stability and efficiency of South Africa's electricity supply system.Keywords: electricity demand forecasting, load shedding, demand side management, data science
Procedia PDF Downloads 53276 A Comparative Analysis of (De)legitimation Strategies in Selected African Inaugural Speeches
Authors: Lily Chimuanya, Ehioghae Esther
Abstract:
Language, a versatile and sophisticated tool, is fundamentally sacrosanct to mankind especially within the realm of politics. In this dynamic world, political leaders adroitly use language to engage in a strategic show aimed at manipulating or mechanising the opinion of discerning people. This nuanced synergy is marked by different rhetorical strategies, meticulously synced with contextual factors ranging from cultural, ideological, and political to achieve multifaceted persuasive objectives. This study investigates the (de)legitimation strategies inherent in African presidential inaugural speeches, as African leaders not only state their policy agenda through inaugural speeches but also subtly indulge in a dance of legitimation and delegitimation, performing a twofold objective of strengthening the credibility of their administration and, at times, undermining the performance of the past administration. Drawing insights from two different legitimation models and a dataset of 4 African presidential inaugural speeches obtained from authentic websites, the study describes the roles of authorisation, rationalisation, moral evaluation, altruism, and mythopoesis in unmasking the structure of political discourse. The analysis takes a mixed-method approach to unpack the (de)legitimation strategy embedded in the carefully chosen speeches. The focus extends beyond a superficial exploration and delves into the linguistic elements that form the basis of presidential discourse. In conclusion, this examination goes beyond the nuanced landscape of language as a potent tool in politics, with each strategy contributing to the overall rhetorical impact and shaping the narrative. From this perspective, the study argues that presidential inaugural speeches are not only linguistic exercises but also viable weapons that influence perceptions and legitimise authority.Keywords: CDA, legitimation, inaugural speeches, delegitmation
Procedia PDF Downloads 58275 Scalable and Accurate Detection of Pathogens from Whole-Genome Shotgun Sequencing
Authors: Janos Juhasz, Sandor Pongor, Balazs Ligeti
Abstract:
Next-generation sequencing, especially whole genome shotgun sequencing, is becoming a common approach to gain insight into the microbiomes in a culture-independent way, even in clinical practice. It does not only give us information about the species composition of an environmental sample but opens the possibility to detect antimicrobial resistance and novel, or currently unknown, pathogens. Accurately and reliably detecting the microbial strains is a challenging task. Here we present a sensitive approach for detecting pathogens in metagenomics samples with special regard to detecting novel variants of known pathogens. We have developed a pipeline that uses fast, short read aligner programs (i.e., Bowtie2/BWA) and comprehensive nucleotide databases. Taxonomic binning is based on the lowest common ancestor (LCA) principle; each read is assigned to a taxon, covering the most significantly hit taxa. This approach helps in balancing between sensitivity and running time. The program was tested both on experimental and synthetic data. The results implicate that our method performs as good as the state-of-the-art BLAST-based ones, furthermore, in some cases, it even proves to be better, while running two orders magnitude faster. It is sensitive and capable of identifying taxa being present only in small abundance. Moreover, it needs two orders of magnitude less reads to complete the identification than MetaPhLan2 does. We analyzed an experimental anthrax dataset (B. anthracis strain BA104). The majority of the reads (96.50%) was classified as Bacillus anthracis, a small portion, 1.2%, was classified as other species from the Bacillus genus. We demonstrate that the evaluation of high-throughput sequencing data is feasible in a reasonable time with good classification accuracy.Keywords: metagenomics, taxonomy binning, pathogens, microbiome, B. anthracis
Procedia PDF Downloads 129274 Adaptive Energy-Aware Routing (AEAR) for Optimized Performance in Resource-Constrained Wireless Sensor Networks
Authors: Innocent Uzougbo Onwuegbuzie
Abstract:
Wireless Sensor Networks (WSNs) are crucial for numerous applications, yet they face significant challenges due to resource constraints such as limited power and memory. Traditional routing algorithms like Dijkstra, Ad hoc On-Demand Distance Vector (AODV), and Bellman-Ford, while effective in path establishment and discovery, are not optimized for the unique demands of WSNs due to their large memory footprint and power consumption. This paper introduces the Adaptive Energy-Aware Routing (AEAR) model, a solution designed to address these limitations. AEAR integrates reactive route discovery, localized decision-making using geographic information, energy-aware metrics, and dynamic adaptation to provide a robust and efficient routing strategy. We present a detailed comparative analysis using a dataset of 50 sensor nodes, evaluating power consumption, memory footprint, and path cost across AEAR, Dijkstra, AODV, and Bellman-Ford algorithms. Our results demonstrate that AEAR significantly reduces power consumption and memory usage while optimizing path weight. This improvement is achieved through adaptive mechanisms that balance energy efficiency and link quality, ensuring prolonged network lifespan and reliable communication. The AEAR model's superior performance underlines its potential as a viable routing solution for energy-constrained WSN environments, paving the way for more sustainable and resilient sensor network deployments.Keywords: wireless sensor networks (WSNs), adaptive energy-aware routing (AEAR), routing algorithms, energy, efficiency, network lifespan
Procedia PDF Downloads 28273 Generalized Additive Model for Estimating Propensity Score
Authors: Tahmidul Islam
Abstract:
Propensity Score Matching (PSM) technique has been widely used for estimating causal effect of treatment in observational studies. One major step of implementing PSM is estimating the propensity score (PS). Logistic regression model with additive linear terms of covariates is most used technique in many studies. Logistics regression model is also used with cubic splines for retaining flexibility in the model. However, choosing the functional form of the logistic regression model has been a question since the effectiveness of PSM depends on how accurately the PS been estimated. In many situations, the linearity assumption of linear logistic regression may not hold and non-linear relation between the logit and the covariates may be appropriate. One can estimate PS using machine learning techniques such as random forest, neural network etc for more accuracy in non-linear situation. In this study, an attempt has been made to compare the efficacy of Generalized Additive Model (GAM) in various linear and non-linear settings and compare its performance with usual logistic regression. GAM is a non-parametric technique where functional form of the covariates can be unspecified and a flexible regression model can be fitted. In this study various simple and complex models have been considered for treatment under several situations (small/large sample, low/high number of treatment units) and examined which method leads to more covariate balance in the matched dataset. It is found that logistic regression model is impressively robust against inclusion quadratic and interaction terms and reduces mean difference in treatment and control set equally efficiently as GAM does. GAM provided no significantly better covariate balance than logistic regression in both simple and complex models. The analysis also suggests that larger proportion of controls than treatment units leads to better balance for both of the methods.Keywords: accuracy, covariate balances, generalized additive model, logistic regression, non-linearity, propensity score matching
Procedia PDF Downloads 362272 In-Depth Analysis on Sequence Evolution and Molecular Interaction of Influenza Receptors (Hemagglutinin and Neuraminidase)
Authors: Dong Tran, Thanh Dac Van, Ly Le
Abstract:
Hemagglutinin (HA) and Neuraminidase (NA) play an important role in host immune evasion across influenza virus evolution process. The correlation between HA and NA evolution in respect to epitopic evolution and drug interaction has yet to be investigated. In this study, combining of sequence to structure evolution and statistical analysis on epitopic/binding site specificity, we identified potential therapeutic features of HA and NA that show specific antibody binding site of HA and specific binding distribution within NA active site of current inhibitors. Our approach introduces the use of sequence variation and molecular interaction to provide an effective strategy in establishing experimental based distributed representations of protein-protein/ligand complexes. The most important advantage of our method is that it does not require complete dataset of complexes but rather directly inferring feature interaction from sequence variation and molecular interaction. Using correlated sequence analysis, we additionally identified co-evolved mutations associated with maintaining HA/NA structural and functional variability toward immunity and therapeutic treatment. Our investigation on the HA binding specificity revealed unique conserved stalk domain interacts with unique loop domain of universal antibodies (CR9114, CT149, CR8043, CR8020, F16v3, CR6261, F10). On the other hand, NA inhibitors (Oseltamivir, Zaninamivir, Laninamivir) showed specific conserved residue contribution and similar to that of NA substrate (sialic acid) which can be exploited for drug design. Our study provides an important insight into rational design and identification of novel therapeutics targeting universally recognized feature of influenza HA/NA.Keywords: influenza virus, hemagglutinin (HA), neuraminidase (NA), sequence evolution
Procedia PDF Downloads 152