Search results for: multimodal bio metrics

Authors: Bylhah Mugotitsa, Jim Todd, Agnes Kiragga, Jay Greenfield, Evans Omondi, Lukoye Atwoli, Reinpeter Momanyi

Abstract:

The INSPIRE network aims to build an open, ethical, sustainable, and FAIR (Findable, Accessible, Interoperable, Reusable) data science platform, particularly for longitudinal mental health (MH) data. While studies have been done at the clinical and population level, there still exists limitations in data and research in LMICs, which pose a risk of underrepresentation of mental disorders. It is vital to examine the existing longitudinal MH data, focusing on how FAIR datasets are. This landscape analysis aimed to provide both overall level of evidence of availability of longitudinal datasets and degree of consistency in longitudinal studies conducted. Utilizing prompters proved instrumental in streamlining the analysis process, facilitating access, crafting code snippets, categorization, and analysis of extensive data repositories related to depression, anxiety, and psychosis in Africa. While leveraging artificial intelligence (AI), we filtered through over 18,000 scientific papers spanning from 1970 to 2023. This AI-driven approach enabled the identification of 228 longitudinal research papers meeting inclusion criteria. Quality assurance revealed 10% incorrectly identified articles and 2 duplicates, underscoring the prevalence of longitudinal MH research in South Africa, focusing on depression. From the analysis, evaluating data and metadata adherence to FAIR principles remains crucial for enhancing accessibility and quality of MH research in Africa. While AI has the potential to enhance research processes, challenges such as privacy concerns and data security risks must be addressed. Ethical and equity considerations in data sharing and reuse are also vital. There’s need for collaborative efforts across disciplinary and national boundaries to improve the Findability and Accessibility of data. Current efforts should also focus on creating integrated data resources and tools to improve Interoperability and Reusability of MH data. Practical steps for researchers include careful study planning, data preservation, machine-actionable metadata, and promoting data reuse to advance science and improve equity. Metrics and recognition should be established to incentivize adherence to FAIR principles in MH research

Keywords: longitudinal mental health research, data sharing, fair data principles, Africa, landscape analysis

Procedia PDF Downloads 30

Authors: Retno A. Vinarti, Lucy M. Hederman

Abstract:

This research describes a knowledge model for a system which give personalized alert to users about infectious disease risks in the context of weather, location and time. The knowledge model is based on established epidemiological concepts augmented by information gleaned from infection-related data repositories. The existing disease risk prediction research has more focuses on utilizing raw historical data and yield seasonal patterns of infectious disease risk emergence. This research incorporates both data and epidemiological concepts gathered from Atlas of Human Infectious Disease (AHID) and Centre of Disease Control (CDC) as basic reasoning of infectious disease risk prediction. Using CommonKADS methodology, the disease risk prediction task is an assignment synthetic task, starting from knowledge identification through specification, refinement to implementation. First, knowledge is gathered from AHID primarily from the epidemiology and risk group chapters for each infectious disease. The result of this stage is five major elements (Person, Infectious Disease, Weather, Location and Time) and their properties. At the knowledge specification stage, the initial tree model of each element and detailed relationships are produced. This research also includes a validation step as part of knowledge refinement: on the basis that the best model is formed using the most common features, Frequency-based Selection (FBS) is applied. The portion of the Infectious Disease risk model relating to Person comes out strongest, with Location next, and Weather weaker. For Person attribute, Age is the strongest, Activity and Habits are moderate, and Blood type is weakest. At the Location attribute, General category (e.g. continents, region, country, and island) results much stronger than Specific category (i.e. terrain feature). For Weather attribute, Less Precise category (i.e. season) comes out stronger than Precise category (i.e. exact temperature or humidity interval). However, given that some infectious diseases are significantly more serious than others, a frequency based metric may not be appropriate. Future work will incorporate epidemiological measurements of disease seriousness (e.g. odds ratio, hazard ratio and fatality rate) into the validation metrics. This research is limited to modelling existing knowledge about epidemiology and chain of infection concepts. Further step, verification in knowledge refinement stage, might cause some minor changes on the shape of tree.

Keywords: epidemiology, knowledge modelling, infectious disease, prediction, risk

Procedia PDF Downloads 210

Authors: Suleyman Ogul Ertugrul, Mustafa Turgut, Serkan Inandı, Mustafa Gorkem Coban, Mustafa Kıgılı, Ali Mert, Oguzhan Kesmez, Murat Ozancı, Caglar Uyulan

Abstract:

In high-performance automotive engineering, the realistic simulation of suspension systems is crucial for enhancing vehicle dynamics and handling. This study focuses on the double wishbone suspension system, prevalent in racing vehicles due to its superior control and stability characteristics. Utilizing MATLAB and Adams Car simulation software, we conduct a comprehensive analysis of displacement behaviors and damper sizing under various dynamic conditions. The initial phase involves using MATLAB to simulate the entire suspension system, allowing for the preliminary determination of damper size based on the system's response under simulated conditions. Following this, manual calculations of wheel loads are performed to assess the forces acting on the front and rear suspensions during scenarios such as braking, cornering, maximum vertical loads, and acceleration. Further dynamic force analysis is carried out using MATLAB Simulink, focusing on the interactions between suspension components during key movements such as bumps and rebounds. This simulation helps in formulating precise force equations and in calculating the stiffness of the suspension springs. To enhance the accuracy of our findings, we focus on a detailed kinematic and dynamic analysis. This includes the creation of kinematic loops, derivation of relevant equations, and computation of Jacobian matrices to accurately determine damper travel and compression metrics. The calculated spring stiffness is crucial in selecting appropriate springs to ensure optimal suspension performance. To validate and refine our results, we replicate the analyses using the Adams Car software, renowned for its detailed handling of vehicular dynamics. The goal is to achieve a robust, reliable suspension setup that maximizes performance under the extreme conditions encountered in racing scenarios. This study exemplifies the integration of theoretical mechanics with advanced simulation tools to achieve a high-performance suspension setup that can significantly improve race car performance, providing a methodology that can be adapted for different types of racing vehicles.

Keywords: FSAE, suspension system, Adams Car, kinematic

Procedia PDF Downloads 20

Authors: Jenee Gooden, Kevin Vasquez-monterroso, Lady Paula Dejesus, Sandra Wainwright, Daniel Kim, Mackenzie Walker

Abstract:

Introduction: Pyoderma gangrenosum (PG) is a rare, rapidly progressive, neutrophilic ulcerative colitis condition with an incidence of 3 to 10 cases per year ¹ ². Due to the similar appearance, PG is often misdiagnosed as a diabetic ulcer in diabetic patients. Though they may clinically appear similar in appearance, the treatment protocol and diagnostic criteria differ. Also, end-stage renal disease (ESRD) is often a condition seen in diabetic patients, which can have a significant impact on wound healing due to the wide range of uremic toxins³. This case study demonstrates a multidisciplinary team and multimodal treatment approach by podiatric surgery, general surgery, rheumatology, infectious disease, interventional cardiology, wound care and hyperbaric medicine for an uncontrolled diabetic with pyoderma gangrenosum of a significant circumferential wound, covering almost the entire right lower extremity. Methods:56 y.o male presents with multiple PG ulcerations, including the chest, right posterior lower extremity and sacrum. All ulcerations were previously managed by the same wound care specialist. His chief complaint was worsening PG ulcerations accompanied by a fever of 103 °F . This case study focuses on the wound to his RLE. Past medical history significant for diabetes mellitus type 2 with hemoglobin A1c of 10% and end stage renal disease (ESRD) on hemodialysis. A multidisciplinary team approach by podiatric surgery, general surgery, rheumatology, infectious disease, interventional cardiology, wound care and hyperbaric medicine was successfully used to perform right lower extremity limb salvage. The patient was managed by rheumatology for the continuation of prior medication, as well as the mutual agreement with wound care for the addition of dapsone. A coronary CT angiogram was performed by interventional cardiology, but no significant disease was noted, and no further vascular workup was necessary. Multiple surgical sharp wide excisional debridements with application of allografts and split thickness skin grafts for the circumferential ulceration that encompassed almost the entire right lower extremity were performed by both podiatric surgery and general surgery. Wound cultures and soft tissue biopsies were performed, and infectious disease managed antibiotic therapy. Hyperbaric oxygen therapy and wound vac therapy by wound care were also completed as adjunct management. Results: Prevention of leg amputation by limb salvage of the RLE was accomplished by a multidisciplinary team approach, with the wound size decreasing over a total of 29 weeks from 600 cm² to 12.0 x 3.5 x 0.2 cm. Our multidisciplinary team included podiatric surgery, general surgery, rheumatology, infectious disease, interventional cardiology, wound care and hyperbaric medicine. Discussion: Wound healing, in general, can have its challenges, and those challenges are only magnified when accompanied by multiple systemic illnesses. Though the negative impact of diabetes on wound healing is well known, the compound impact of being a diabetic with ESRD and having pyoderma gangrenosum is not. This case demonstrates the necessity for a multidisciplinary team approach with a wide array of treatment modalities to optimize wound healing and perform limb salvage with prevention of lower extremity amputation.

Keywords: diabetes, podiatry, pyoderma gangrenosum, end stage renal disease

Procedia PDF Downloads 43

Authors: Evelyn Asante Yeboah, Kwabena O. Asubonteng, Justice Camillus Mensah, Christine Furst

Abstract:

Smallholder-dominated mosaic landscapes in rural Africa are relevant for food production, biodiversity conservation, and climate regulation. Land-use transitions threaten the multifunctionality of such landscapes, especially the production capacity of arable lands resulting in food security challenges. Using land-cover maps derived from maximum likelihood classification of Landsat satellite images for the years 2002, 2015, and 2020, post-classification change detection, landscape metrics, and key informant interviews, the study assessed the implications of rubber plantation expansion and oil business development on the food production capacity of Ahanta West District, Ghana. The analysis reveals that settlement and rubber areas expanded by 5.82% and 10.33% of the landscape area, respectively, between 2002 and 2020. This increase translates into over twice their initial sizes (144% in settlement change and 101% in rubber change). Rubber plantation spread dominates the north and southwestern areas, whereas settlement is widespread in the eastern parts of the landscape. Rubber and settlement expanded at the expense of cropland, palm, and shrublands. Land-use transitions between cropland, palm, and shrubland were targeting each other, but the net loss in shrubland was higher (-17.27%). Isolation, subdivision, connectedness, and patch adjacency indices showed patch consolidation in the landscape configuration from 2002 to 2015 and patch fragmentation from 2015 to 2020. The study also found patches with consistent increasing connectivity in settlement areas indicating the influence of oil discovery developments and fragmentation tendencies in rubber, shrubland, cropland, and palm, indicating springing up of smaller rubber farms, the disappearance of shrubland, and splitting up of cropland and palm areas respectively. The results revealed a trend in land-use transitions in favor of smallholder rubber plantation expansion and oil discovery developments, which suggest serious implications on food production systems and poses a risk for food security and landscape multifunctional characteristics. To ensure sustainability in land uses, this paper recommends the enforcement of legislative instruments governing spatial planning and land use in Ghana as embedded in the 2016 land-use and spatial planning act.

Keywords: food production systems, food security, Ghana’s west coast, land-use transitions, multifunctional rural landscapes

Procedia PDF Downloads 119

Authors: Lesley Northrop, Justin DeGrazia, Jessica Greenwood

Abstract:

ASPIRA Labs now offers an en-suit and ready-to-implement technology transfer solution to enable labs and hospitals that lack the resources to build it themselves to offer in-house genetic testing. This unique platform employs a patented Molecular Inversion Probe (MIP) technology that combines the specificity of a hybrid capture protocol with the ease of an amplicon-based protocol and utilizes an advanced bioinformatics analysis pipeline based on machine learning. To demonstrate its efficacy, two independent genetic tests were validated on this technology transfer platform: expanded carrier screening (ECS) and hereditary cancer testing (HC). The analytical performance of ECS and HC was validated separately in a blinded manner for calling three different types of variants: SNVs, short indels (typically, <50 bp), and large indels/CNVs defined as multi-exonic del/dup events. The reference set was constructed using samples from Coriell Institute, an external clinical genetic testing laboratory, Maine Molecular Quality Controls Inc. (MMQCI), SeraCare and GIAB Consortium. Overall, the analytical performance showed a sensitivity and specificity of >99.4% for both ECS and HC in detecting SNVs. For indels, both tests reported specificity of 100%, and ECS demonstrated a sensitivity of 100%, whereas HC exhibited a sensitivity of 96.5%. The bioinformatics pipeline also correctly called all reference CNV events resulting in a sensitivity of 100% for both tests. No additional calls were made in the HC panel, leading to a perfect performance (specificity and F-measure of 100%). In the carrier panel, however, three additional positive calls were made outside the reference set. Two of these calls were confirmed using an orthogonal method and were re-classified as true positives leaving only one false positive. The pipeline also correctly identified all challenging carrier statuses, such as positive cases for spinal muscular atrophy and alpha-thalassemia, resulting in 100% sensitivity. After confirmation of additional positive calls via long-range PCR and MLPA, specificity for such cases was estimated at 99%. These performance metrics demonstrate that this tech-transfer solution can be confidently internalized by clinical labs and hospitals to offer mainstream ECS and HC as part of their test catalog, substantially increasing access to quality germline genetic testing for labs of all sizes and resources levels.

Keywords: clinical genetics, genetic testing, molecular genetics, technology transfer

Procedia PDF Downloads 155

Authors: Jonathan Turner, Julie Doyle, Laura O’Philbin, Dympna O’Sullivan

Abstract:

People living with dementia should be at the centre of decision-making regarding goals for daily living. These goals include basic activities (dressing, hygiene, and mobility), advanced activities (finances, transportation, and shopping), and meaningful activities that promote well-being (pastimes and intellectual pursuits). However, there is limited involvement of people living with dementia in the design of technology to support their goals. A project is described that is co-designing intelligent computer-based support for, and with, people affected by dementia and their carers. The technology will support self-management, empower participation in shared decision-making with carers and help people living with dementia remain healthy and independent in their homes for longer. It includes information from the patient’s care plan, which documents medications, contacts, and the patient's wishes on end-of-life care. Importantly for this work, the plan can outline activities that should be maintained or worked towards, such as exercise or social contact. The authors discuss how to integrate care goal information from such a care plan with data collected from passive sensors in the patient’s home in order to deliver individualized planning and interventions for persons with dementia. A number of scientific challenges are addressed: First, to co-design with dementia patients and their carers computerized support for shared decision-making about their care while allowing the patient to share the care plan. Second, to develop a new and open monitoring framework with which to configure sensor technologies to collect data about whether goals and actions specified for a person in their care plan are being achieved. This is developed top-down by associating care quality types and metrics elicited from the co-design activities with types of data that can be collected within the home, from passive and active sensors, and from the patient’s feedback collected through a simple co-designed interface. These activities and data will be mapped to appropriate sensors and technological infrastructure with which to collect the data. Third, the application of machine learning models to analyze data collected via the sensing devices in order to investigate whether and to what extent activities outlined via the care plan are being achieved. The models will capture longitudinal data to track disease progression over time; as the disease progresses and captured data show that activities outlined in the care plan are not being achieved, the care plan may recommend alternative activities. Disease progression may also require care changes, and a data-driven approach can capture changes in a condition more quickly and allow care plans to evolve and be updated.

Keywords: care goals, decision-making, dementia, self-care, sensors

Procedia PDF Downloads 145

Authors: Vishal Kumar, Soumitra Satapathi

Abstract:

Föster Resonance Energy Transfer (FRET) is a powerful technique used to probe close-range molecular interactions. Physically, the FRET phenomenon manifests as a dipole–dipole interaction between closely juxtaposed fluorescent molecules (10–100 Å). Our effort is to employ this FRET technique to make a prototype device for highly sensitive detection of environment pollutant. Among the most common environmental pollutants, nitroaromatic compounds (NACs) are of particular interest because of their durability and toxicity. That’s why, sensitive and selective detection of small amounts of nitroaromatic explosives, in particular, 2,4,6-trinitrophenol (TNP), 2,4-dinitrotoluene (DNT) and 2,4,6-trinitrotoluene (TNT) has been a critical challenge due to the increasing threat of explosive-based terrorism and the need of environmental monitoring of drinking and waste water. In addition, the excessive utilization of TNP in several other areas such as burn ointment, pesticides, glass and the leather industry resulted in environmental accumulation, and is eventually contaminating the soil and aquatic systems. To the date, high number of elegant methods, including fluorimetry, gas chromatography, mass, ion-mobility and Raman spectrometry have been successfully applied for explosive detection. Among these efforts, fluorescence-quenching methods based on the mechanism of FRET show good assembly flexibility, high selectivity and sensitivity. Here, we report a FRET-based sensor system for the highly selective detection of NACs, such as TNP, DNT and TNT. The sensor system is composed of a copolymer Poly [(N,N-dimethylacrylamide)-co-(Boc-Trp-EMA)] (RP) bearing tryptophan derivative in the side chain as donor and dansyl tagged copolymer P(MMA-co-Dansyl-Ala-HEMA) (DCP) as an acceptor. Initially, the inherent fluorescence of RP copolymer is quenched by non-radiative energy transfer to DCP which only happens once the two molecules are within Förster critical distance (R0). The excellent spectral overlap (Jλ= 6.08×10¹⁴ nm⁴M⁻¹cm⁻¹) between donors’ (RP) emission profile and acceptors’ (DCP) absorption profile makes them an exciting and efficient FRET pair i.e. further confirmed by the high rate of energy transfer from RP to DCP i.e. 0.87 ns⁻¹ and lifetime measurement by time correlated single photon counting (TCSPC) to validate the 64% FRET efficiency. This FRET pair exhibited a specific fluorescence response to NACs such as DNT, TNT and TNP with 5.4, 2.3 and 0.4 µM LODs, respectively. The detection of NACs occurs with high sensitivity by photoluminescence quenching of FRET signal induced by photo-induced electron transfer (PET) from electron-rich FRET pair to electron-deficient NAC molecules. The estimated stern-volmer constant (KSV) values for DNT, TNT and TNP are 6.9 × 10³, 7.0 × 10³ and 1.6 × 104 M⁻¹, respectively. The mechanistic details of molecular interactions are established by time-resolved fluorescence, steady-state fluorescence and absorption spectroscopy confirmed that the sensing process is of mixed type, i.e. both dynamic and static quenching as lifetime of FRET system (0.73 ns) is reduced to 0.55, 0.57 and 0.61 ns DNT, TNT and TNP, respectively. In summary, the simplicity and sensitivity of this novel FRET sensor opens up the possibility of designing optical sensor of various NACs in one single platform for developing multimodal sensor for environmental monitoring and future field based study.

Keywords: FRET, nitroaromatic, stern-Volmer constant, tryptophan and dansyl tagged copolymer

Procedia PDF Downloads 104

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 120

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest

Procedia PDF Downloads 209

Authors: Varis Ransibrahmanakul, Doug Pirhalla, Scott Sheridan, Cameron Lee

Abstract:

U.S. coastal areas and ecosystems are facing multiple sea level rise threats and effects: heavy rain events, cyclones, and changing wind and weather patterns all influence coastal flooding, sedimentation, and erosion along critical barrier islands and can strongly impact habitat resiliency and water quality in protected habitats. These impacts are increasing over time and have accelerated the need for new tracking techniques, models and tools of flood risk to support enhanced preparedness for coastal management and mitigation. To address this issue, NOAA National Ocean Service (NOS) evaluated new metrics from satellite altimetry AVISO/Copernicus and MODIS IR flood extents to isolate nodes atmospheric variability indicative of elevated sea level and nuisance flood events. Using de-trended time series of cross-shelf sea surface heights (SSH), we identified specific Self Organizing Maps (SOM) nodes and transitions having a strongest regional association with oceanic spatial patterns (e.g., heightened downwelling favorable wind-stress and enhanced southward coastal transport) indicative of elevated coastal sea levels. Results show the impacts of the inverted barometer effect as well as the effects of surface wind forcing; Ekman-induced transport along broad expanses of the U.S. eastern coastline. Higher sea levels and corresponding localized flooding are associated with either pattern indicative of enhanced on-shore flow, deepening cyclones, or local- scale winds, generally coupled with an increased local to regional precipitation. These findings will support an integration of satellite products and will inform seasonal outlook model development supported through NOAAs Climate Program Office and NOS office of Center for Operational Oceanographic Products and Services (CO-OPS). Overall results will prioritize ecological areas and coastal lab facilities at risk based on numbers of nuisance flood projected and inform coastal management of flood risk around low lying areas subjected to bank erosion.

Keywords: AVISO satellite altimetry SSHA, MODIS IR flood map, nuisance flood, remote sensing of flood

Procedia PDF Downloads 118

Authors: Asma Omri, Noureddine Benothman, Sofiane Sayahi, Fethi Tlili, Hichem Besbes

Abstract:

Cycling, a popular mode of transportation, can also be perilous due to cyclists' vulnerability to collisions with vehicles and obstacles. This paper presents an innovative cyclist safety system based on radar technology designed to offer real-time collision risk warnings to cyclists. The system incorporates a low-power radar sensor affixed to the bicycle and connected to a microcontroller. It leverages radar point cloud detections, a clustering algorithm, and a supervised classifier. These algorithms are optimized for efficiency to run on the TI’s AWR 1843 BOOST radar, utilizing a coarse classification approach distinguishing between cars, trucks, two-wheeled vehicles, and other objects. To enhance the performance of clustering techniques, we propose a 2-Level clustering approach. This approach builds on the state-of-the-art Density-based spatial clustering of applications with noise (DBSCAN). The objective is to first cluster objects based on their velocity, then refine the analysis by clustering based on position. The initial level identifies groups of objects with similar velocities and movement patterns. The subsequent level refines the analysis by considering the spatial distribution of these objects. The clusters obtained from the first level serve as input for the second level of clustering. Our proposed technique surpasses the classical DBSCAN algorithm in terms of geometrical metrics, including homogeneity, completeness, and V-score. Relevant cluster features are extracted and utilized to classify objects using an SVM classifier. Potential obstacles are identified based on their velocity and proximity to the cyclist. To optimize the system, we used the View of Delft dataset for hyperparameter selection and SVM classifier training. The system's performance was assessed using our collected dataset of radar point clouds synchronized with a camera on an Nvidia Jetson Nano board. The radar-based cyclist safety system is a practical solution that can be easily installed on any bicycle and connected to smartphones or other devices, offering real-time feedback and navigation assistance to cyclists. We conducted experiments to validate the system's feasibility, achieving an impressive 85% accuracy in the classification task. This system has the potential to significantly reduce the number of accidents involving cyclists and enhance their safety on the road.

Keywords: 2-level clustering, coarse classification, cyclist safety, warning system based on radar technology

Procedia PDF Downloads 49

Authors: Farzad Hosseini Hossein Abadi, Cristina Prieto Sierra, Cesar Álvarez Díaz

Abstract:

Predicting streamflow accurately in flashy catchments prone to floods is a major research and operational challenge in hydrological modeling. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have shown to be promising in achieving accurate hydrological predictions at daily and hourly time scales. In this work, a multi-timescale LSTM (MTS-LSTM) network was applied to the context of regional hydrological predictions at an hourly time scale in flashy catchments. The case study includes 40 catchments allocated in the Basque Country, north of Spain. We explore the impact of hyperparameters on the performance of streamflow predictions given by regional deep learning models through systematic hyperparameter tuning - where optimal regional values for different catchments are identified. The results show that predictions are highly accurate, with Nash-Sutcliffe (NSE) and Kling-Gupta (KGE) metrics values as high as 0.98 and 0.97, respectively. A principal component analysis reveals that a hyperparameter related to the length of the input sequence contributes most significantly to the prediction performance. The findings suggest that input sequence lengths have a crucial impact on the model prediction performance. Moreover, employing catchment-scale analysis reveals distinct sequence lengths for individual basins, highlighting the necessity of customizing this hyperparameter based on each catchment’s characteristics. This aligns with well known “uniqueness of the place” paradigm. In prior research, tuning the length of the input sequence of LSTMs has received limited focus in the field of streamflow prediction. Initially it was set to 365 days to capture a full annual water cycle. Later, performing limited systematic hyper-tuning using grid search, revealed a modification to 270 days. However, despite the significance of this hyperparameter in hydrological predictions, usually studies have overlooked its tuning and fixed it to 365 days. This study, employing a simultaneous systematic hyperparameter tuning approach, emphasizes the critical role of input sequence length as an influential hyperparameter in configuring LSTMs for regional streamflow prediction. Proper tuning of this hyperparameter is essential for achieving accurate hourly predictions using deep learning models.

Keywords: LSTMs, streamflow, hyperparameters, hydrology

Procedia PDF Downloads 23

Authors: Amina Naidja, Zedira Khammar, Ines Soltani

Abstract:

This study investigates the impact of urban development on the urban heat island (UHI) effect in the semi-arid Aures region of Algeria, integrating remote sensing data with statistical analysis and community surveys to examine the interconnected environmental and social dynamics. Using Landsat 8 satellite imagery, temporal variations in the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), and land use/land cover (LULC) changes are analyzed to understand patterns of urbanization and environmental transformation. These environmental metrics are correlated with land surface temperature (LST) data derived from remote sensing to quantify the UHI effect. To incorporate the social dimension, a structured questionnaire survey is conducted among residents in selected urban areas. The survey assesses community perceptions of urban heat, its impacts on daily life, health concerns, and coping strategies. Statistical analysis is employed to analyze survey responses, identifying correlations between demographic factors, socioeconomic status, and perceived heat stress. Preliminary findings reveal significant correlations between built-up areas (NDBI) and higher LST, indicating the contribution of urbanization to local warming. Conversely, areas with higher vegetation cover (NDVI) exhibit lower LST, highlighting the cooling effect of green spaces. Social survey results provide insights into how UHI affects different demographic groups, with vulnerable populations experiencing greater heat-related challenges. By integrating remote sensing analysis with statistical modeling and community surveys, this study offers a comprehensive understanding of the environmental and social implications of urban development in semi-arid climates. The findings contribute to evidence-based urban planning strategies that prioritize environmental sustainability and social well-being. Future research should focus on policy recommendations and community engagement initiatives to mitigate UHI impacts and promote climate-resilient urban development.

Keywords: urban heat island, remote sensing, social analysis, NDVI, NDBI, LST, community perception

Procedia PDF Downloads 7

Authors: Saahith M. S., Sivakami R.

Abstract:

In the realm of football analytics, particularly focusing on predicting football player performance, the ability to forecast player success accurately is of paramount importance for teams, managers, and fans. This study introduces an elaborate examination of predicting football player performance through the integration of data visualization methods and machine learning algorithms. The research entails the compilation of an extensive dataset comprising player attributes, conducting data preprocessing, feature selection, model selection, and model training to construct predictive models. The analysis within this study will involve delving into feature significance using methodologies like Select Best and Recursive Feature Elimination (RFE) to pinpoint pertinent attributes for predicting player performance. Various machine learning algorithms, including Random Forest, Decision Tree, Linear Regression, Support Vector Regression (SVR), and Artificial Neural Networks (ANN), will be explored to develop predictive models. The evaluation of each model's performance utilizing metrics such as Mean Squared Error (MSE) and R-squared will be executed to gauge their efficacy in predicting player performance. Furthermore, this investigation will encompass a top player analysis to recognize the top-performing players based on the anticipated overall performance scores. Nationality analysis will entail scrutinizing the player distribution based on nationality and investigating potential correlations between nationality and player performance. Positional analysis will concentrate on examining the player distribution across various positions and assessing the average performance of players in each position. Age analysis will evaluate the influence of age on player performance and identify any discernible trends or patterns associated with player age groups. The primary objective is to predict a football player's overall performance accurately based on their individual attributes, leveraging data-driven insights to enrich the comprehension of player success on the field. By amalgamating data visualization and machine learning methodologies, the aim is to furnish valuable tools for teams, managers, and fans to effectively analyze and forecast player performance. This research contributes to the progression of sports analytics by showcasing the potential of machine learning in predicting football player performance and offering actionable insights for diverse stakeholders in the football industry.

Keywords: football analytics, player performance prediction, data visualization, machine learning algorithms, random forest, decision tree, linear regression, support vector regression, artificial neural networks, model evaluation, top player analysis, nationality analysis, positional analysis

Procedia PDF Downloads 18

Authors: Aliasghar Mehdizadeh Dastjerdi, Francisco Camara Pereira

Abstract:

The increasing complexity and demand of transport services strains transportation systems especially in urban areas with limited possibilities for building new infrastructure. The solution to this challenge requires changes of travel behavior. One of the proposed means to induce such change is multimodal travel apps. This paper describes a study of the intention to use a real-time multi-modal travel app aimed at motivating travel behavior change in the Greater Copenhagen Region (Denmark) toward promoting sustainable transport options. The proposed app is a multi-faceted smartphone app including both travel information and persuasive strategies such as health and environmental feedback, tailoring travel options, self-monitoring, tunneling users toward green behavior, social networking, nudging and gamification elements. The prospective for mobility management travel apps to stimulate sustainable mobility rests not only on the original and proper employment of the behavior change strategies, but also on explicitly anchoring it on established theoretical constructs from behavioral theories. The theoretical foundation is important because it positively and significantly influences the effectiveness of the system. However, there is a gap in current knowledge regarding the study of mobility-management travel app with support in behavioral theories, which should be explored further. This study addresses this gap by a social cognitive theory‐based examination. However, compare to conventional method in technology adoption research, this study adopts a reverse approach in which the associations between theoretical constructs are explored by Max-Min Hill-Climbing (MMHC) algorithm as a hybrid causal discovery method. A technology-use preference survey was designed to collect data. The survey elicited different groups of variables including (1) three groups of user’s motives for using the app including gain motives (e.g., saving travel time and cost), hedonic motives (e.g., enjoyment) and normative motives (e.g., less travel-related CO2 production), (2) technology-related self-concepts (i.e. technophile attitude) and (3) use Intention of the travel app. The questionnaire items led to the formulation of causal relationships discovery to learn the causal structure of the data. Causal relationships discovery from observational data is a critical challenge and it has applications in different research fields. The estimated causal structure shows that the two constructs of gain motives and technophilia have a causal effect on adoption intention. Likewise, there is a causal relationship from technophilia to both gain and hedonic motives. In line with the findings of the prior studies, it highlights the importance of functional value of the travel app as well as technology self-concept as two important variables for adoption intention. Furthermore, the results indicate the effect of technophile attitude on developing gain and hedonic motives. The causal structure shows hierarchical associations between the three groups of user’s motive. They can be explained by “frustration-regression” principle according to Alderfer's ERG (Existence, Relatedness and Growth) theory of needs meaning that a higher level need remains unfulfilled, a person may regress to lower level needs that appear easier to satisfy. To conclude, this study shows the capability of causal discovery methods to learn the causal structure of theoretical model, and accordingly interpret established associations.

Keywords: travel app, behavior change, persuasive technology, travel information, causality

Procedia PDF Downloads 115

Authors: Feng Yue, Fei Dai

Abstract:

With the rapid development of urbanization process in China, its environmental protection pressure is severely tested. So, analyzing and optimizing the landscape pattern is an important measure to ease the pressure on the ecological environment. This paper takes Wuhan Urban Development Zone as the research object, and studies its landscape pattern evolution and quantitative optimization strategy. First, remote sensing image data from 1990 to 2015 were interpreted by using Erdas software. Next, the landscape pattern index of landscape level, class level, and patch level was studied based on Fragstats. Then five indicators of ecological environment based on National Environmental Protection Standard of China were selected to evaluate the impact of landscape pattern evolution on the ecological environment. Besides, the cost distance analysis of ArcGIS was applied to simulate wildlife migration thus indirectly measuring the improvement of ecological environment quality. The result shows that the area of land for construction increased 491%. But the bare land, sparse grassland, forest, farmland, water decreased 82%, 47%, 36%, 25% and 11% respectively. They were mainly converted into construction land. On landscape level, the change of landscape index all showed a downward trend. Number of patches (NP), Landscape shape index (LSI), Connection index (CONNECT), Shannon's diversity index (SHDI), Aggregation index (AI) separately decreased by 2778, 25.7, 0.042, 0.6, 29.2%, all of which indicated that the NP, the degree of aggregation and the landscape connectivity declined. On class level, the construction land and forest, CPLAND, TCA, AI and LSI ascended, but the Distribution Statistics Core Area (CORE_AM) decreased. As for farmland, water, sparse grassland, bare land, CPLAND, TCA and DIVISION, the Patch Density (PD) and LSI descended, yet the patch fragmentation and CORE_AM increased. On patch level, patch area, Patch perimeter, Shape index of water, farmland and bare land continued to decline. The three indexes of forest patches increased overall, sparse grassland decreased as a whole, and construction land increased. It is obvious that the urbanization greatly influenced the landscape evolution. Ecological diversity and landscape heterogeneity of ecological patches clearly dropped. The Habitat Quality Index continuously declined by 14%. Therefore, optimization strategy based on greenway network planning is raised for discussion. This paper contributes to the study of landscape pattern evolution in planning and design and to the research on spatial layout of urbanization.

Keywords: landscape pattern, optimization strategy, ArcGIS, Erdas, landscape metrics, landscape architecture

Procedia PDF Downloads 134

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 68

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 137

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.

Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning

Procedia PDF Downloads 137

Authors: Aneal Khan, Elleine Allapitan, Desmond Koo, Katherine-Ann Piedalue, Shaneel Pathak, Utkarsh Subnis

Abstract:

Background: Disease management of metabolic, genetic disorders is long-term and can be cumbersome to patients and caregivers. Patient-Reported Outcome Measures (PROMs) have been a useful tool in capturing patient perspectives to help enhance treatment compliance and engagement with health care providers, reduce utilization of emergency services, and increase satisfaction with their treatment choices. Currently, however, PROMs are collected during infrequent and decontextualized clinic visits, which makes translation of patient experiences challenging over time. The GRIT study aims to evaluate a digital health journal application called Zamplo that provides a personalized health diary to record self-reported health outcomes accurately and efficiently in patients with metabolic, genetic disorders. Methods: This is a randomized controlled trial (RCT) (1:1) that assesses the efficacy of Zamplo to increase patient activation (primary outcome), improve healthcare satisfaction and confidence to manage medications (secondary outcomes), and reduce costs to the healthcare system (exploratory). Using standardized online surveys, assessments will be collected at baseline, 1 month, 3 months, 6 months, and 12 months. Outcomes will be compared between patients who were given access to the application versus those with no access. Results: Seventy-seven patients were recruited as of November 30, 2021. Recruitment for the study commenced in November 2020 with a target of n=150 patients. The accrual rate was 50% from those eligible and invited for the study, with the majority of patients having Fabry disease (n=48) and the remaining having Pompe disease and mitochondrial disease. Real-time clinical responses, such as pain, are being measured and correlated to disease-modifying therapies, supportive treatments like pain medications, and lifestyle interventions. Engagement with the application, along with compliance metrics of surveys and journal entries, are being analyzed. An interim analysis of the engagement data along with preliminary findings from this pilot RCT, and qualitative patient feedback will be presented. Conclusions: The digital self-care journal provides a unique approach to disease management, allowing patients direct access to their progress and actively participating in their care. Findings from the study can help serve the virtual care needs of patients with metabolic, genetic disorders in North America and the world over.

Keywords: eHealth, mobile health, rare disease, patient outcomes, quality of life (QoL), pain, Fabry disease, Pompe disease

Procedia PDF Downloads 128

Authors: Shayla He

Abstract:

Background and Purpose: According to Chamie (2017), it’s estimated that no less than 150 million people, or about 2 percent of the world’s population, are homeless. The homeless population in the United States has grown rapidly in the past four decades. In New York City, the sheltered homeless population has increased from 12,830 in 1983 to 62,679 in 2020. Knowing the trend on the homeless population is crucial at helping the states and the cities make affordable housing plans, and other community service plans ahead of time to better prepare for the situation. This study utilized the data from New York City, examined the key factors associated with the homelessness, and developed systematic modeling to predict homeless populations of the future. Using the best model developed, named HP-RNN, an analysis on the homeless population change during the months of 2020 and 2021, which were impacted by the COVID-19 pandemic, was conducted. Moreover, HP-RNN was tested on the data from Seattle. Methods: The methodology involves four phases in developing robust prediction methods. Phase 1 gathered and analyzed raw data of homeless population and demographic conditions from five urban centers. Phase 2 identified the key factors that contribute to the rate of homelessness. In Phase 3, three models were built using Linear Regression, Random Forest, and Recurrent Neural Network (RNN), respectively, to predict the future trend of society's homeless population. Each model was trained and tuned based on the dataset from New York City for its accuracy measured by Mean Squared Error (MSE). In Phase 4, the final phase, the best model from Phase 3 was evaluated using the data from Seattle that was not part of the model training and tuning process in Phase 3. Results: Compared to the Linear Regression based model used by HUD et al (2019), HP-RNN significantly improved the prediction metrics of Coefficient of Determination (R2) from -11.73 to 0.88 and MSE by 99%. HP-RNN was then validated on the data from Seattle, WA, which showed a peak %error of 14.5% between the actual and the predicted count. Finally, the modeling results were collected to predict the trend during the COVID-19 pandemic. It shows a good correlation between the actual and the predicted homeless population, with the peak %error less than 8.6%. Conclusions and Implications: This work is the first work to apply RNN to model the time series of the homeless related data. The Model shows a close correlation between the actual and the predicted homeless population. There are two major implications of this result. First, the model can be used to predict the homeless population for the next several years, and the prediction can help the states and the cities plan ahead on affordable housing allocation and other community service to better prepare for the future. Moreover, this prediction can serve as a reference to policy makers and legislators as they seek to make changes that may impact the factors closely associated with the future homeless population trend.

Keywords: homeless, prediction, model, RNN

Procedia PDF Downloads 95

Authors: Mladen Milicevic

Abstract:

This presentation will address how the statistical analysis of digitized popular music influences the music creation and emotionally manipulates consumers.Furthermore, it will deal with semiological aspect of uniformization of musical taste in order to predict the potential revenues generated by popular music sales. In the USA, we live in an age where most of the popular music (i.e. music that generates substantial revenue) has been digitized. It is safe to say that almost everything that was produced in last 10 years is already digitized (either available on iTunes, Spotify, YouTube, or some other platform). Depending on marketing viability and its potential to generate additional revenue most of the “older” music is still being digitized. Once the music gets turned into a digital audio file,it can be computer-analyzed in all kinds of respects, and the similar goes for the lyrics because they also exist as a digital text file, to which any kin of N Capture-kind of analysis may be applied. So, by employing statistical examination of different popular music metrics such as tempo, form, pronouns, introduction length, song length, archetypes, subject matter,and repetition of title, the commercial result may be predicted. Polyphonic HMI (Human Media Interface) introduced the concept of the hit song science computer program in 2003.The company asserted that machine learning could create a music profile to predict hit songs from its audio features Thus,it has been established that a successful pop song must include: 100 bpm or more;an 8 second intro;use the pronoun 'you' within 20 seconds of the start of the song; hit the bridge middle 8 between 2 minutes and 2 minutes 30 seconds; average 7 repetitions of the title; create some expectations and fill that expectation in the title. For the country song: 100 bpm or less for a male artist; 14-second intro; uses the pronoun 'you' within the first 20 seconds of the intro; has a bridge middle 8 between 2 minutes and 2 minutes 30 seconds; has 7 repetitions of title; creates an expectation,fulfills it in 60 seconds.This approach to commercial popular music minimizes the human influence when it comes to which “artist” a record label is going to sign and market. Twenty years ago,music experts in the A&R (Artists and Repertoire) departments of the record labels were making personal aesthetic judgments based on their extensive experience in the music industry. Now, the computer music analyzing programs, are replacing them in an attempt to minimize investment risk of the panicking record labels, in an environment where nobody can predict the future of the recording industry.The impact on the consumers taste through the narrow bottleneck of the above mentioned music selection by the record labels,created some very peculiar effects not only on the taste of popular music consumers, but also the creative chops of the music artists as well. What is the meaning of this semiological shift is the main focus of this research and paper presentation.

Keywords: music, semiology, commercial, taste

Procedia PDF Downloads 366

Authors: Jeremie Coullon, Robert J. Webber

Abstract:

We introduce a Markov chain Monte Carlo (MCMC) sam-pler for infinite-dimensional inverse problems. Our sam-pler is based on the affine invariant ensemble sampler, which uses interacting walkers to adapt to the covariance structure of the target distribution. We extend this ensem-ble sampler for the first time to infinite-dimensional func-tion spaces, yielding a highly efficient gradient-free MCMC algorithm. Because our ensemble sampler does not require gradients or posterior covariance estimates, it is simple to implement and broadly applicable. In many Bayes-ian inverse problems, Markov chain Monte Carlo (MCMC) meth-ods are needed to approximate distributions on infinite-dimensional function spaces, for example, in groundwater flow, medical imaging, and traffic flow. Yet designing efficient MCMC methods for function spaces has proved challenging. Recent gradi-ent-based MCMC methods preconditioned MCMC methods, and SMC methods have improved the computational efficiency of functional random walk. However, these samplers require gradi-ents or posterior covariance estimates that may be challenging to obtain. Calculating gradients is difficult or impossible in many high-dimensional inverse problems involving a numerical integra-tor with a black-box code base. Additionally, accurately estimating posterior covariances can require a lengthy pilot run or adaptation period. These concerns raise the question: is there a functional sampler that outperforms functional random walk without requir-ing gradients or posterior covariance estimates? To address this question, we consider a gradient-free sampler that avoids explicit covariance estimation yet adapts naturally to the covariance struc-ture of the sampled distribution. This sampler works by consider-ing an ensemble of walkers and interpolating and extrapolating between walkers to make a proposal. This is called the affine in-variant ensemble sampler (AIES), which is easy to tune, easy to parallelize, and efficient at sampling spaces of moderate dimen-sionality (less than 20). The main contribution of this work is to propose a functional ensemble sampler (FES) that combines func-tional random walk and AIES. To apply this sampler, we first cal-culate the Karhunen–Loeve (KL) expansion for the Bayesian prior distribution, assumed to be Gaussian and trace-class. Then, we use AIES to sample the posterior distribution on the low-wavenumber KL components and use the functional random walk to sample the posterior distribution on the high-wavenumber KL components. Alternating between AIES and functional random walk updates, we obtain our functional ensemble sampler that is efficient and easy to use without requiring detailed knowledge of the target dis-tribution. In past work, several authors have proposed splitting the Bayesian posterior into low-wavenumber and high-wavenumber components and then applying enhanced sampling to the low-wavenumber components. Yet compared to these other samplers, FES is unique in its simplicity and broad applicability. FES does not require any derivatives, and the need for derivative-free sam-plers has previously been emphasized. FES also eliminates the requirement for posterior covariance estimates. Lastly, FES is more efficient than other gradient-free samplers in our tests. In two nu-merical examples, we apply FES to challenging inverse problems that involve estimating a functional parameter and one or more scalar parameters. We compare the performance of functional random walk, FES, and an alternative derivative-free sampler that explicitly estimates the posterior covariance matrix. We conclude that FES is the fastest available gradient-free sampler for these challenging and multimodal test problems.

Keywords: Bayesian inverse problems, Markov chain Monte Carlo, infinite-dimensional inverse problems, dimensionality reduction

Procedia PDF Downloads 129

Authors: Fahimeh Palizban, Farshad Noravesh, Amir Hossein Saeidian, Mahya Mehrmohamadi

Abstract:

In the recent decade, the emergence of liquid biopsy has significantly improved cancer monitoring and detection. Dying cells, including those originating from tumors, shed their DNA into the blood and contribute to a pool of circulating fragments called cell-free DNA. Accordingly, identifying the tissue origin of these DNA fragments from the plasma can result in more accurate and fast disease diagnosis and precise treatment protocols. Open chromatin regions are important epigenetic features of DNA that reflect cell types of origin. Profiling these features by DNase-seq, ATAC-seq, and histone ChIP-seq provides insights into tissue-specific and disease-specific regulatory mechanisms. There have been several studies in the area of cancer liquid biopsy that integrate distinct genomic and epigenomic features for early cancer detection along with tissue of origin detection. However, multimodal analysis requires several types of experiments to cover the genomic and epigenomic aspects of a single sample, which will lead to a huge amount of cost and time. To overcome these limitations, the idea of predicting OCRs from WGS is of particular importance. In this regard, we proposed a computational approach to target the prediction of open chromatin regions as an important epigenetic feature from cell-free DNA whole genome sequence data. To fulfill this objective, local sequencing depth will be fed to our proposed algorithm and the prediction of the most probable open chromatin regions from whole genome sequencing data can be carried out. Our method integrates the signal processing method with sequencing depth data and includes count normalization, Discrete Fourie Transform conversion, graph construction, graph cut optimization by linear programming, and clustering. To validate the proposed method, we compared the output of the clustering (open chromatin region+, open chromatin region-) with previously validated open chromatin regions related to human blood samples of the ATAC-DB database. The percentage of overlap between predicted open chromatin regions and the experimentally validated regions obtained by ATAC-seq in ATAC-DB is greater than 67%, which indicates meaningful prediction. As it is evident, OCRs are mostly located in the transcription start sites (TSS) of the genes. In this regard, we compared the concordance between the predicted OCRs and the human genes TSS regions obtained from refTSS and it showed proper accordance around 52.04% and ~78% with all and the housekeeping genes, respectively. Accurately detecting open chromatin regions from plasma cell-free DNA-seq data is a very challenging computational problem due to the existence of several confounding factors, such as technical and biological variations. Although this approach is in its infancy, there has already been an attempt to apply it, which leads to a tool named OCRDetector with some restrictions like the need for highly depth cfDNA WGS data, prior information about OCRs distribution, and considering multiple features. However, we implemented a graph signal clustering based on a single depth feature in an unsupervised learning manner that resulted in faster performance and decent accuracy. Overall, we tried to investigate the epigenomic pattern of a cell-free DNA sample from a new computational perspective that can be used along with other tools to investigate genetic and epigenetic aspects of a single whole genome sequencing data for efficient liquid biopsy-related analysis.

Keywords: open chromatin regions, cancer, cell-free DNA, epigenomics, graph signal processing, correlation clustering

Procedia PDF Downloads 114

Authors: Gyoomi Kim, Jiyoung Bae

Abstract:

In the field of language education research, there are not many tries to empirically examine learners’ acceptance behavior and related factors of mobile-assisted language learning (MALL). This study is one of the few attempts to propose an integrated theoretical framework that explains MALL users’ acceptance behavior and potential factors. Constructs from technology acceptance model (TAM) and MALL research are tested in the integrated framework. Based on previous studies, a hypothetical model was developed. Four external variables related to the MALL user’s acceptance behavior were selected: subjective norm, content reliability, interactivity, self-regulation. The model was also composed of four other constructs: two latent variables, perceived ease of use and perceived usefulness, were considered as cognitive constructs; attitude toward MALL as an affective construct; behavioral intention to use MALL as a behavioral construct. The participants were 438 undergraduate students who enrolled in an intensive English program at one university in Korea. This particular program was held in January 2018 using the vacation period. The students were given eight hours of English classes each day from Monday to Friday for four weeks and asked to complete MALL courses for practice outside the classroom. Therefore, all participants experienced blended MALL environment. The instrument was a self-response questionnaire, and each construct was measured by five questions. Once the questionnaire was developed, it was distributed to the participants at the final ceremony of the intensive program in order to collect the data from a large number of the participants at a time. The data showed significant evidence to support the hypothetical model. The results confirmed through structural equation modeling analysis are as follows: First, four external variables such as subjective norm, content reliability, interactivity, and self-regulation significantly affected perceived ease of use. Second, subjective norm, content reliability, self-regulation, perceived ease of use significantly affected perceived usefulness. Third, perceived usefulness and perceived ease of use significantly affected attitude toward MALL. Fourth, attitude toward MALL and perceived usefulness significantly affected behavioral intention to use MALL. These results implied that the integrated framework from TAM and MALL could be useful when adopting MALL environment to university students or adult English learners. Key constructs except interactivity showed significant relationships with one another and had direct and indirect impacts on MALL user’s acceptance behavior. Therefore, the constructs and validated metrics is valuable for language researchers and educators who are interested in MALL.

Keywords: blended MALL, learner factors/variables, mobile-assisted language learning, MALL, technology acceptance model, TAM, theoretical framework

Procedia PDF Downloads 204

Authors: Maria Fontenele, Claude-Gilles Dussap, Vincent Dumouilla, Baptiste Boit

Abstract:

Roquette Frères is a producer of plant-based ingredients that employs many processes to extract relevant molecules and often transforms them through chemical and physical processes to create desired ingredients with specific functionalities. In this context, Roquette encounters numerous multi-component complex systems in their processes, including fibers, proteins, and carbohydrates, in an aqueous environment. To develop, control, and optimize both new and old processes, Roquette aims to develop new in silico tools. Currently, Roquette uses process modelling tools which include specific thermodynamic models and is willing to develop computational methodologies such as molecular dynamics simulations to gain insights into the complex interactions in such complex media, and especially hydrogen bonding interactions. The issue at hand concerns aqueous mixtures of polyols with high dry matter content. The polyols mannitol and sorbitol molecules are diastereoisomers that have nearly identical chemical structures but very different physicochemical properties: for example, the solubility of sorbitol in water is 2.5 kg/kg of water, while mannitol has a solubility of 0.25 kg/kg of water at 25°C. Therefore, predicting liquid-solid equilibrium properties in this case requires sophisticated solution models that cannot be based solely on chemical group contributions, knowing that for mannitol and sorbitol, the chemical constitutive groups are the same. Recognizing the significance of solvation phenomena in polyols, the GePEB (Chemical Engineering, Applied Thermodynamics, and Biosystems) team at Institut Pascal has developed the COSMO-UCA model, which has the structural advantage of using quantum mechanics tools to predict formation and phase equilibrium properties. In this work, we use molecular dynamics simulations to elucidate the behavior of polyols in aqueous solution. Specifically, we employ simulations to compute essential metrics such as radial distribution functions and hydrogen bond autocorrelation functions. Our findings illuminate a fundamental contrast: sorbitol and mannitol exhibit disparate hydrogen bond lifetimes within aqueous environments. This observation serves as a cornerstone in elucidating the divergent physicochemical properties inherent to each compound, shedding light on the nuanced interplay between their molecular structures and water interactions. We also present a methodology to predict the physicochemical properties of complex solutions, taking as sole input the three-dimensional structure of the molecules in the medium. Finally, by developing knowledge models, we represent some physicochemical properties of aqueous solutions of sorbitol and mannitol.

Keywords: COSMO models, hydrogen bond, molecular dynamics, thermodynamics

Procedia PDF Downloads 13

Authors: Elaheh Talebi, Fariba Yavari, Lucy Philip, Lesley Town

Abstract:

The mining industry generates vast amounts of data, necessitating robust data management systems and advanced analytics tools to achieve better decision-making processes in the development of mining production and maintaining safety. This paper highlights the advantages of Power BI, a powerful intelligence tool, over traditional Excel-based approaches for effectively managing and harnessing mining data. Power BI enables professionals to connect and integrate multiple data sources, ensuring real-time access to up-to-date information. Its interactive visualizations and dashboards offer an intuitive interface for exploring and analyzing geotechnical data. Advanced analytics is a collection of data analysis techniques to improve decision-making. Leveraging some of the most complex techniques in data science, advanced analytics is used to do everything from detecting data errors and ensuring data accuracy to directing the development of future project phases. However, while Power BI is a robust tool, specific visualizations required by geotechnical engineers may have limitations. This paper studies the capability to use Python or R programming within the Power BI dashboard to enable advanced analytics, additional functionalities, and customized visualizations. This dashboard provides comprehensive tools for analyzing and visualizing key geotechnical data metrics, including spatial representation on maps, field and lab test results, and subsurface rock and soil characteristics. Advanced visualizations like borehole logs and Stereonet were implemented using Python programming within the Power BI dashboard, enhancing the understanding and communication of geotechnical information. Moreover, the dashboard's flexibility allows for the incorporation of additional data and visualizations based on the project scope and available data, such as pit design, rock fall analyses, rock mass characterization, and drone data. This further enhances the dashboard's usefulness in future projects, including operation, development, closure, and rehabilitation phases. Additionally, this helps in minimizing the necessity of utilizing multiple software programs in projects. This geotechnical dashboard in Power BI serves as a user-friendly solution for analyzing, visualizing, and communicating both new and historical geotechnical data, aiding in informed decision-making and efficient project management throughout various project stages. Its ability to generate dynamic reports and share them with clients in a collaborative manner further enhances decision-making processes and facilitates effective communication within geotechnical projects in the mining industry.

Keywords: geotechnical data analysis, power BI, visualization, decision-making, mining industry

Procedia PDF Downloads 61

Authors: Yohannes Haile, Dipo Onipede, Jr., Omar Ashour

Abstract:

The main thrust of our research is to determine Industry 4.0 readiness of small and mid-size manufacturing companies in our region and assist them to implement Cyber Physical Production System (CPPS) capabilities. Adopting CPPS capabilities will help organizations realize improved quality, order delivery, throughput, new value creation, and reduced idle time of machines and work centers of their manufacturing operations. The key metrics for the assessment include the level of intelligence, internal and external connections, responsiveness to internal and external environmental changes, capabilities for customization of products with reference to cost, level of additive manufacturing, automation, and robotics integration, and capabilities to manufacture hybrid products in the near term, where near term is defined as 0 to 18 months. In our initial evaluation of several manufacturing firms which are profitable and successful in what they do, we found low level of Physical-Digital-Physical (PDP) loop in their manufacturing operations, whereas 100% of the firms included in this research have specialized manufacturing core competencies that have differentiated them from their competitors. The level of automation and robotics integration is low to medium range, where low is defined as less than 30%, and medium is defined as 30 to 70% of manufacturing operation to include automation and robotics. However, there is a significant drive to include these capabilities at the present time. As it pertains to intelligence and connection of manufacturing systems, it is observed to be low with significant variance in tying manufacturing operations management to Enterprise Resource Planning (ERP). Furthermore, it is observed that the integration of additive manufacturing in general, 3D printing, in particular, to be low, but with significant upside of integrating it in their manufacturing operations in the near future. To hasten the readiness of the local and regional manufacturing companies to Industry 4.0 and transitions towards CPPS capabilities, our working group (ADMAR Working Group) in partnership with our university have been engaged with the local and regional manufacturing companies. The goal is to increase awareness, share know-how and capabilities, initiate joint projects, and investigate the possibility of establishing the Center for Cyber Physical Production Systems Innovation (C2P2SI). The center is intended to support the local and regional university-industry research of implementing intelligent factories, enhance new value creation through disruptive innovations, the development of hybrid and data enhanced products, and the creation of digital manufacturing enterprises. All these efforts will enhance local and regional economic development and educate students that have well developed knowledge and applications of cyber physical manufacturing systems and Industry 4.0.

Keywords: automation, cyber-physical production system, digital manufacturing enterprises, disruptive innovation, new value creation, physical-digital-physical loop

Procedia PDF Downloads 113

Authors: Ravija Gunawardana, Banuka Athuraliya

Abstract:

Machine learning has emerged as a powerful tool for disease diagnosis and prediction. The use of machine learning algorithms has the potential to improve the accuracy of disease prediction, thereby enabling medical professionals to provide more effective and personalized treatments. This study focuses on developing a machine-learning model for disease prediction using symptoms and X-ray images. The importance of this study lies in its potential to assist medical professionals in accurately diagnosing diseases, thereby improving patient outcomes. Respiratory diseases are a significant cause of morbidity and mortality worldwide, and chest X-rays are commonly used in the diagnosis of these diseases. However, accurately interpreting X-ray images requires significant expertise and can be time-consuming, making it difficult to diagnose respiratory diseases in a timely manner. By incorporating machine learning algorithms, we can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The study utilized the Mask R-CNN algorithm, which is a state-of-the-art method for object detection and segmentation in images, to process chest X-ray images. The model was trained and tested on a large dataset of patient information, which included both symptom data and X-ray images. The performance of the model was evaluated using a range of metrics, including accuracy, precision, recall, and F1-score. The results showed that the model achieved an accuracy rate of over 90%, indicating that it was able to accurately detect and segment regions of interest in the X-ray images. In addition to X-ray images, the study also incorporated symptoms as input data for disease prediction. The study used three different classifiers, namely Random Forest, K-Nearest Neighbor and Support Vector Machine, to predict diseases based on symptoms. These classifiers were trained and tested using the same dataset of patient information as the X-ray model. The results showed promising accuracy rates for predicting diseases using symptoms, with the ensemble learning techniques significantly improving the accuracy of disease prediction. The study's findings indicate that the use of machine learning algorithms can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The model developed in this study has the potential to assist medical professionals in diagnosing respiratory diseases more accurately and efficiently. However, it is important to note that the accuracy of the model can be affected by several factors, including the quality of the X-ray images, the size of the dataset used for training, and the complexity of the disease being diagnosed. In conclusion, the study demonstrated the potential of machine learning algorithms for disease prediction using symptoms and X-ray images. The use of these algorithms can improve the accuracy of disease diagnosis, ultimately leading to better patient care. Further research is needed to validate the model's accuracy and effectiveness in a clinical setting and to expand its application to other diseases.

Keywords: K-nearest neighbor, mask R-CNN, random forest, support vector machine

Procedia PDF Downloads 109