Search results for: error estimation

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 34

Authors: Gospel Iyioku, Jana Mazancova, Jiri Hejkrlik

Abstract:

The “Agricultural Promotion Policy (2016–2020)” represents a strategic initiative by the Nigerian government to address domestic food shortages and the challenges in exporting products at the required quality standards. Hindered by an inefficient system for setting and enforcing food quality standards, coupled with a lack of market knowledge, the Federal Ministry of Agriculture and Rural Development (FMARD) aims to enhance support for the production and activities of key crops like cashew. By collaborating with farmers, processors, investors, and stakeholders in the cashew sector, the policy seeks to define and uphold high-quality standards across the cashew value chain. Given the challenges and opportunities faced by Nigerian cashew farmers, active participation in cashew marketing groups becomes imperative. These groups serve as essential platforms for farmers to collectively navigate market intricacies, access resources, share knowledge, improve output quality, and bolster their overall bargaining power. Through engagement in these cooperative initiatives, farmers not only boost their economic prospects but can also contribute significantly to the sustainable growth of the cashew industry, fostering resilience and community development. This study explores the perceptions and intentions of farmers regarding their involvement in cashew marketing cooperatives, utilizing an expanded version of the Theory of Planned Behaviour. Drawing insights from a diverse sample of 321 cashew farmers in Southwest Nigeria, the research sheds light on the factors influencing decision-making in cooperative participation. The demographic analysis reveals a diverse landscape, with a substantial presence of middle-aged individuals contributing significantly to the agricultural sector and cashew-related activities emerging as a primary income source for a substantial proportion (23.99%). Employing Structural Equation Modelling (SEM) with Maximum Likelihood Robust (MLR) estimation in R, the research elucidates the associations among latent variables. Despite the model’s complexity, the goodness-of-fit indices attest to the validity of the structural model, explaining approximately 40% of the variance in the intention to join cooperatives. Moral norms emerge as a pivotal construct, highlighting the profound influence of ethical considerations in decision-making processes, while perceived behavioural control presents potential challenges in active participation. Attitudes toward joining cooperatives reveal nuanced perspectives, with strong beliefs in enhanced connections with other farmers but varying perceptions on improved access to essential information. The SEM analysis establishes positive and significant effects of moral norms, perceived behavioural control, subjective norms, and attitudes on farmers’ intention to join cooperatives. The knowledge construct positively affects key factors influencing intention, emphasizing the importance of informed decision-making. A supplementary analysis using partial least squares (PLS) SEM corroborates the robustness of our findings, aligning with covariance-based SEM results. This research unveils the determinants of cooperative participation and provides valuable insights for policymakers and practitioners aiming to empower and support this vital demographic in the cashew industry.

Keywords: marketing cooperatives, theory of planned behaviour, structural equation modelling, cashew farmers

Procedia PDF Downloads 34

Authors: Christian J. Kennett, Mark A. Baldwin

Abstract:

As several companies are working towards returning American astronauts back to space on US-made spacecraft, NASA developed a human flight certification-by-test and analysis approach due to the cost-prohibitive nature of extensive testing. This process relies heavily on the quality of analytical models to accurately predict crew injury potential specific to each spacecraft and under dynamic environments not tested. As the prime contractor on the Orion spacecraft, Lockheed Martin was tasked with quantifying the correlation of analytical anthropometric test devices (ATDs), also known as crash test dummies, against test measurements under representative impact conditions. Multiple dynamic impact sled tests were conducted to characterize Hybrid III 5th ATD lumbar, head, and neck responses with and without a modified shuttle-era advanced crew escape suit (ACES) under simulated Orion landing and abort conditions. Each ATD was restrained via a 5-point harness in a mockup Orion seat fixed to a dynamic impact sled at the Wright Patterson Air Force Base (WPAFB) Biodynamics Laboratory in the horizontal impact accelerator (HIA). ATDs were subject to multiple impact magnitudes, half-sine pulse rise times, and XZ - ‘eyeballs out/down’ or Z-axis ‘eyeballs down’ orientations for landing or an X-axis ‘eyeballs in’ orientation for abort. Several helmet constraint devices were evaluated during suited testing. Unique finite element models (FEMs) were developed of the unsuited and suited sled test configurations using an analytical 5th ATD model developed by LSTC (Livermore, CA) and deformable representations of the seat, suit, helmet constraint countermeasures, and body restraints. Explicit FE analyses were conducted using the non-linear solver LS-DYNA. Head linear and rotational acceleration, head rotational velocity, upper neck force and moment, and lumbar force time histories were compared between test and analysis using the enhanced error assessment of response time histories (EEARTH) composite score index. The EEARTH rating paired with the correlation and analysis (CORA) corridor rating provided a composite ISO score that was used to asses model correlation accuracy. NASA occupant protection subject matter experts established an ISO score of 0.5 or greater as the minimum expectation for correlating analytical and experimental ATD responses. Unsuited 5th ATD head X, Z, and resultant linear accelerations, head Y rotational accelerations and velocities, neck X and Z forces, and lumbar Z forces all showed consistent ISO scores above 0.5 in the XZ impact orientation, regardless of peak g-level or rise time. Upper neck Y moments were near or above the 0.5 score for most of the XZ cases. Similar trends were found in the XZ and Z-axis suited tests despite the addition of several different countermeasures for restraining the helmet. For the X-axis ‘eyeballs in’ loading direction, only resultant head linear acceleration and lumbar Z-axis force produced ISO scores above 0.5 whether unsuited or suited. The analytical LSTC 5th ATD model showed good correlation across multiple head, neck, and lumbar responses in both the unsuited and suited configurations when loaded in the XZ ‘eyeballs out/down’ direction. Upper neck moments were consistently the most difficult to predict, regardless of impact direction or test configuration.

Keywords: impact biomechanics, manned spaceflight, model correlation, multi-axial loading

Procedia PDF Downloads 89

Authors: Nanine Fouche

Abstract:

The Cape Flats is a low-lying sand-covered expanse of approximately 460 square kilometres, situated to the southeast of the central business district of Cape Town in the Western Cape of South Africa. The aeolian sands masking this area are often loose and compressible in the upper 1m to 1.5m of the surface, and there is a general exceedance of the maximum allowable settlement in these sands. The settlement of shallow foundations on Cape Flats sands is commonly predicted using the results of in-situ tests such as the SPT or DPSH due to the difficulty of retrieving undisturbed samples for laboratory testing. Varying degrees of accuracy and reliability are associated with these methods. More recently, shear wave velocity (Vs) profiles obtained from seismic testing, such as continuous surface wave tests (CSW), are being used for settlement prediction. Such predictions have the advantage of considering non-linear stress-strain behaviour of soil and the degradation of stiffness with increasing strain. CSW tests are rarely executed in the Cape Flats, whereas SPT’s are commonly performed. For this reason, and to facilitate better settlement predictions in Cape Flats sand, equations representing shear wave velocity (Vs) as a function of SPT blow count (N60) and vertical effective stress (v’) were generated by statistical regression of site investigation data. To reveal the most appropriate method of overburden correction, analyses were performed with a separate overburden term (Pa/σ’v) as well as using stress corrected shear wave velocity and SPT blow counts (correcting Vs. and N60 to Vs1and (N1)60respectively). Shear wave velocity profiles and SPT blow count data from three sites masked by Cape Flats sands were utilised to generate 80 Vs-SPT N data pairs for analysis. Investigated terrains included sites in the suburbs of Athlone, Muizenburg, and Atlantis, all underlain by windblown deposits comprising fine and medium sand with varying fines contents. Elastic settlement analysis was also undertaken for the Cape Flats sands, using a non-linear stepwise method based on small-strain stiffness estimates, which was obtained from the best Vs-N60 model and compared to settlement estimates using the general elastic solution with stiffness profiles determined using Stroud’s (1989) and Webb’s (1969) SPT N60-E transformation models. Stroud’s method considers strain level indirectly whereasWebb’smethod does not take account of the variation in elastic modulus with strain. The expression of Vs. in terms of N60 and Pa/σv’ derived from the Atlantis data set revealed the best fit with R2 = 0.83 and a standard error of 83.5m/s. Less accurate Vs-SPT N relations associated with the combined data set is presumably the result of inversion routines used in the analysis of the CSW results showcasing significant variation in relative density and stiffness with depth. The regression analyses revealed that the inclusion of a separate overburden term in the regression of Vs and N60, produces improved fits, as opposed to the stress corrected equations in which the R2 of the regression is notably lower. It is the correction of Vs and N60 to Vs1 and (N1)60 with empirical constants ‘n’ and ‘m’ prior to regression, that introduces bias with respect to overburden pressure. When comparing settlement prediction methods, both Stroud’s method (considering strain level indirectly) and the small strain stiffness method predict higher stiffnesses for medium dense and dense profiles than Webb’s method, which takes no account of strain level in the determination of soil stiffness. Webb’s method appears to be suitable for loose sands only. The Versak software appears to underestimate differences in settlement between square and strip footings of similar width. In conclusion, settlement analysis using small-strain stiffness data from the proposed Vs-N60 model for Cape Flats sands provides a way to take account of the non-linear stress-strain behaviour of the sands when calculating settlement.

Keywords: sands, settlement prediction, continuous surface wave test, small-strain stiffness, shear wave velocity, penetration resistance

Procedia PDF Downloads 148

Authors: Veenapani Rajeev Verma

Abstract:

Context: Assessing facility readiness is paramount as it can indicate capacity of facilities to provide essential care for resilience to health challenges. In the context of decentralization, estimation of supply side readiness indices at sub national level is imperative for effective evidence based policy but remains a colossal challenge due to lack of dependable and representative data sources. Setting: District Poonch of Jammu and Kashmir was selected for this study. It is remote, rural district with unprecedented topographical barriers and is identified as high priority by government. It is also a fragile area as is bounded by Line of Control with Pakistan bearing the brunt of cease fire violations, military skirmishes and sporadic militant attacks. Hilly geographical terrain, rudimentary/absence of road network and impoverishment are quintessential to this area. Objectives: Objective of the study is to a) Evaluate the service readiness of health facilities and create a concise index subsuming plethora of discrete indicators and b) Ascertain supply side barriers in service provisioning via stakeholder’s analysis. Study also strives to expand analytical domain unravelling context and area specific intricacies associated with service delivery. Methodology: Mixed method approach was employed to triangulate quantitative analysis with qualitative nuances. Facility survey encompassing 90 Subcentres, 44 Primary health centres, 3 Community health centres and 1 District hospital was conducted to gauge general service availability and service specific availability (depth of coverage). Compendium of checklist was designed using Indian Public Health Standards (IPHS) in form of standard core questionnaire and scorecard generated for each facility. Information was collected across dimensions of amenities, equipment, medicines, laboratory and infection control protocols as proposed in WHO’s Service Availability and Readiness Assesment (SARA). Two stage polychoric principal component analysis employed to generate a parsimonious index by coalescing an array of tracer indicators. OLS regression method used to determine factors explaining composite index generated from PCA. Stakeholder analysis was conducted to discern qualitative information. Myriad of techniques like observations, key informant interviews and focus group discussions using semi structured questionnaires on both leaders and laggards were administered for critical stakeholder’s analysis. Results: General readiness score of health facilities was found to be 0.48. Results indicated poorest readiness for subcentres and PHC’s (first point of contact) with composite score of 0.47 and 0.41 respectively. For primary care facilities; principal component was characterized by basic newborn care as well as preparedness for delivery. Results revealed availability of equipment and surgical preparedness having lowest score (0.46 and 0.47) for facilities providing secondary care. Presence of contractual staff, more than 1 hr walk to facility, facilities in zone A (most vulnerable) to cross border shelling and facilities inaccessible due to snowfall and thick jungles was negatively associated with readiness index. Nonchalant staff attitude, unavailability of staff quarters, leakages and constraint in supply chain of drugs and consumables were other impediments identified. Conclusions/Policy Implications: It is pertinent to first strengthen primary care facilities in this setting. Complex dimensions such as geographic barriers, user and provider behavior is not under precinct of this methodology.

Keywords: effective coverage, principal component analysis, readiness index, universal health coverage

Procedia PDF Downloads 84

Authors: Ali Kazemi

Abstract:

Those within the volatile and interconnected international economic markets, appropriately predicting market trends, hold substantial fees for traders and financial establishments. Traditional device mastering strategies have made full-size strides in forecasting marketplace movements; however, monetary data's complicated and networked nature calls for extra sophisticated processes. This observation offers a groundbreaking method for monetary marketplace prediction that leverages the synergistic capability of Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks. Our suggested algorithm is meticulously designed to forecast the traits of inventory market indices and cryptocurrency costs, utilizing a comprehensive dataset spanning from January 1, 2015, to December 31, 2023. This era, marked by sizable volatility and transformation in financial markets, affords a solid basis for schooling and checking out our predictive version. Our algorithm integrates diverse facts to construct a dynamic economic graph that correctly reflects market intricacies. We meticulously collect opening, closing, and high and low costs daily for key inventory marketplace indices (e.g., S&P 500, NASDAQ) and widespread cryptocurrencies (e.g., Bitcoin, Ethereum), ensuring a holistic view of marketplace traits. Daily trading volumes are also incorporated to seize marketplace pastime and liquidity, providing critical insights into the market's shopping for and selling dynamics. Furthermore, recognizing the profound influence of the monetary surroundings on financial markets, we integrate critical macroeconomic signs with hobby fees, inflation rates, GDP increase, and unemployment costs into our model. Our GCN algorithm is adept at learning the relational patterns amongst specific financial devices represented as nodes in a comprehensive market graph. Edges in this graph encapsulate the relationships based totally on co-movement styles and sentiment correlations, enabling our version to grasp the complicated community of influences governing marketplace moves. Complementing this, our LSTM algorithm is trained on sequences of the spatial-temporal illustration discovered through the GCN, enriched with historic fee and extent records. This lets the LSTM seize and expect temporal marketplace developments accurately. Inside the complete assessment of our GCN-LSTM algorithm across the inventory marketplace and cryptocurrency datasets, the version confirmed advanced predictive accuracy and profitability compared to conventional and opportunity machine learning to know benchmarks. Specifically, the model performed a Mean Absolute Error (MAE) of 0.85%, indicating high precision in predicting day-by-day charge movements. The RMSE was recorded at 1.2%, underscoring the model's effectiveness in minimizing tremendous prediction mistakes, which is vital in volatile markets. Furthermore, when assessing the model's predictive performance on directional market movements, it achieved an accuracy rate of 78%, significantly outperforming the benchmark models, averaging an accuracy of 65%. This high degree of accuracy is instrumental for techniques that predict the course of price moves. This study showcases the efficacy of mixing graph-based totally and sequential deep learning knowledge in economic marketplace prediction and highlights the fee of a comprehensive, records-pushed evaluation framework. Our findings promise to revolutionize investment techniques and hazard management practices, offering investors and economic analysts a powerful device to navigate the complexities of cutting-edge economic markets.

Keywords: financial market prediction, graph convolutional networks (GCNs), long short-term memory (LSTM), cryptocurrency forecasting

Procedia PDF Downloads 16