Search results for: PV modeling
9 Interpretable Deep Learning Models for Medical Condition Identification
Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji
Abstract:
Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.Keywords: deep learning, interpretability, attention, big data, medical conditions
Procedia PDF Downloads 888 Contactless Heart Rate Measurement System based on FMCW Radar and LSTM for Automotive Applications
Authors: Asma Omri, Iheb Sifaoui, Sofiane Sayahi, Hichem Besbes
Abstract:
Future vehicle systems demand advanced capabilities, notably in-cabin life detection and driver monitoring systems, with a particular emphasis on drowsiness detection. To meet these requirements, several techniques employ artificial intelligence methods based on real-time vital sign measurements. In parallel, Frequency-Modulated Continuous-Wave (FMCW) radar technology has garnered considerable attention in the domains of healthcare and biomedical engineering for non-invasive vital sign monitoring. FMCW radar offers a multitude of advantages, including its non-intrusive nature, continuous monitoring capacity, and its ability to penetrate through clothing. In this paper, we propose a system utilizing the AWR6843AOP radar from Texas Instruments (TI) to extract precise vital sign information. The radar allows us to estimate Ballistocardiogram (BCG) signals, which capture the mechanical movements of the body, particularly the ballistic forces generated by heartbeats and respiration. These signals are rich sources of information about the cardiac cycle, rendering them suitable for heart rate estimation. The process begins with real-time subject positioning, followed by clutter removal, computation of Doppler phase differences, and the use of various filtering methods to accurately capture subtle physiological movements. To address the challenges associated with FMCW radar-based vital sign monitoring, including motion artifacts due to subjects' movement or radar micro-vibrations, Long Short-Term Memory (LSTM) networks are implemented. LSTM's adaptability to different heart rate patterns and ability to handle real-time data make it suitable for continuous monitoring applications. Several crucial steps were taken, including feature extraction (involving amplitude, time intervals, and signal morphology), sequence modeling, heart rate estimation through the analysis of detected cardiac cycles and their temporal relationships, and performance evaluation using metrics such as Root Mean Square Error (RMSE) and correlation with reference heart rate measurements. For dataset construction and LSTM training, a comprehensive data collection system was established, integrating the AWR6843AOP radar, a Heart Rate Belt, and a smart watch for ground truth measurements. Rigorous synchronization of these devices ensured data accuracy. Twenty participants engaged in various scenarios, encompassing indoor and real-world conditions within a moving vehicle equipped with the radar system. Static and dynamic subject’s conditions were considered. The heart rate estimation through LSTM outperforms traditional signal processing techniques that rely on filtering, Fast Fourier Transform (FFT), and thresholding. It delivers an average accuracy of approximately 91% with an RMSE of 1.01 beat per minute (bpm). In conclusion, this paper underscores the promising potential of FMCW radar technology integrated with artificial intelligence algorithms in the context of automotive applications. This innovation not only enhances road safety but also paves the way for its integration into the automotive ecosystem to improve driver well-being and overall vehicular safety.Keywords: ballistocardiogram, FMCW Radar, vital sign monitoring, LSTM
Procedia PDF Downloads 637 Risks for Cyanobacteria Harmful Algal Blooms in Georgia Piedmont Waterbodies Due to Land Management and Climate Interactions
Authors: Sam Weber, Deepak Mishra, Susan Wilde, Elizabeth Kramer
Abstract:
The frequency and severity of cyanobacteria harmful blooms (CyanoHABs) have been increasing over time, with point and non-point source eutrophication and shifting climate paradigms being blamed as the primary culprits. Excessive nutrients, warm temperatures, quiescent water, and heavy and less regular rainfall create more conducive environments for CyanoHABs. CyanoHABs have the potential to produce a spectrum of toxins that cause gastrointestinal stress, organ failure, and even death in humans and animals. To promote enhanced, proactive CyanoHAB management, risk modeling using geospatial tools can act as predictive mechanisms to supplement current CyanoHAB monitoring, management and mitigation efforts. The risk maps would empower water managers to focus their efforts on high risk water bodies in an attempt to prevent CyanoHABs before they occur, and/or more diligently observe those waterbodies. For this research, exploratory spatial data analysis techniques were used to identify the strongest predicators for CyanoHAB blooms based on remote sensing-derived cyanobacteria cell density values for 771 waterbodies in the Georgia Piedmont and landscape characteristics of their watersheds. In-situ datasets for cyanobacteria cell density, nutrients, temperature, and rainfall patterns are not widely available, so free gridded geospatial datasets were used as proxy variables for assessing CyanoHAB risk. For example, the percent of a watershed that is agriculture was used as a proxy for nutrient loading, and the summer precipitation within a watershed was used as a proxy for water quiescence. Cyanobacteria cell density values were calculated using atmospherically corrected images from the European Space Agency’s Sentinel-2A satellite and multispectral instrument sensor at a 10-meter ground resolution. Seventeen explanatory variables were calculated for each watershed utilizing the multi-petabyte geospatial catalogs available within the Google Earth Engine cloud computing interface. The seventeen variables were then used in a multiple linear regression model, and the strongest predictors of cyanobacteria cell density were selected for the final regression model. The seventeen explanatory variables included land cover composition, winter and summer temperature and precipitation data, topographic derivatives, vegetation index anomalies, and soil characteristics. Watershed maximum summer temperature, percent agriculture, percent forest, percent impervious, and waterbody area emerged as the strongest predictors of cyanobacteria cell density with an adjusted R-squared value of 0.31 and a p-value ~ 0. The final regression equation was used to make a normalized cyanobacteria cell density index, and a Jenks Natural Break classification was used to assign waterbodies designations of low, medium, or high risk. Of the 771 waterbodies, 24.38% were low risk, 37.35% were medium risk, and 38.26% were high risk. This study showed that there are significant relationships between free geospatial datasets representing summer maximum temperatures, nutrient loading associated with land use and land cover, and the area of a waterbody with cyanobacteria cell density. This data analytics approach to CyanoHAB risk assessment corroborated the literature-established environmental triggers for CyanoHABs, and presents a novel approach for CyanoHAB risk mapping in waterbodies across the greater southeastern United States.Keywords: cyanobacteria, land use/land cover, remote sensing, risk mapping
Procedia PDF Downloads 2076 Catastrophic Health Expenditures: Evaluating the Effectiveness of Nepal's National Health Insurance Program Using Propensity Score Matching and Doubly Robust Methodology
Authors: Simrin Kafle, Ulrika Enemark
Abstract:
Catastrophic health expenditure (CHE) is a critical issue in low- and middle-income countries like Nepal, exacerbating financial hardship among vulnerable households. This study assesses the effectiveness of Nepal’s National Health Insurance Program (NHIP), launched in 2015, to reduce out-of-pocket (OOP) healthcare costs and mitigate CHE. Conducted in Pokhara Metropolitan City, the study used an analytical cross-sectional design, sampling 1276 households through a two-stage random sampling method. Data was collected via face-to-face interviews between May and October 2023. The analysis was conducted using SPSS version 29, incorporating propensity score matching to minimize biases and create comparable groups of enrolled and non-enrolled households in the NHIP. PSM helped reduce confounding effects by matching households with similar baseline characteristics. Additionally, a doubly robust methodology was employed, combining propensity score adjustment with regression modeling to enhance the reliability of the results. This comprehensive approach ensured a more accurate estimation of the impact of NHIP enrollment on CHE. Among the 1276 samples, 534 households (41.8%) were enrolled in NHIP. Of them, 84.3% of households renewed their insurance card, though some cited long waiting times, lack of medications, and complex procedures as barriers to renewal. Approximately 57.3% of households reported known diseases before enrollment, with 49.8% attending routine health check-ups in the past year. The primary motivation for enrollment was encouragement from insurance employees (50.2%). The data indicates that 12.5% of enrolled households experienced CHE versus 7.5% among non-enrolled. Enrollment into NHIP does not contribute to lower CHE (AOR: 1.98, 95% CI: 1.21-3.24). Key factors associated with increased CHE risk were presence of non-communicable diseases (NCDs) (AOR: 3.94, 95% CI: 2.10-7.39), acute illnesses/injuries (AOR: 6.70, 95% CI: 3.97-11.30), larger household size (AOR: 3.09, 95% CI: 1.81-5.28), and households below the poverty line (AOR: 5.82, 95% CI: 3.05-11.09). Other factors such as gender, education level, caste/ethnicity, presence of elderly members, and under-five children also showed varying associations with CHE, though not all were statistically significant. The study concludes that enrollment in the NHIP does not significantly reduce the risk of CHE. The reason for this could be inadequate coverage, where high-cost medicines, treatments, and transportation costs are not fully included in the insurance package, leading to significant out-of-pocket expenses. We also considered the long waiting time, lack of medicines, and complex procedures for the utilization of NHIP benefits, which might result in the underuse of covered services. Finally, gaps in enrollment and retention might leave certain households vulnerable to CHE despite the existence of NHIP. Key factors contributing to increased CHE include NCDs, acute illnesses, larger household sizes, and poverty. To improve the program’s effectiveness, it is recommended that NHIP benefits and coverage be expanded to better protect against high healthcare costs. Additionally, simplifying the renewal process, addressing long waiting times, and enhancing the availability of services could improve member satisfaction and retention. Targeted financial protection measures should be implemented for high-risk groups, and efforts should be made to increase awareness and encourage routine health check-ups to prevent severe health issues that contribute to CHE.Keywords: catastrophic health expenditure, effectiveness, national health insurance program, Nepal
Procedia PDF Downloads 135 Leveraging Digital Transformation Initiatives and Artificial Intelligence to Optimize Readiness and Simulate Mission Performance across the Fleet
Authors: Justin Woulfe
Abstract:
Siloed logistics and supply chain management systems throughout the Department of Defense (DOD) has led to disparate approaches to modeling and simulation (M&S), a lack of understanding of how one system impacts the whole, and issues with “optimal” solutions that are good for one organization but have dramatic negative impacts on another. Many different systems have evolved to try to understand and account for uncertainty and try to reduce the consequences of the unknown. As the DoD undertakes expansive digital transformation initiatives, there is an opportunity to fuse and leverage traditionally disparate data into a centrally hosted source of truth. With a streamlined process incorporating machine learning (ML) and artificial intelligence (AI), advanced M&S will enable informed decisions guiding program success via optimized operational readiness and improved mission success. One of the current challenges is to leverage the terabytes of data generated by monitored systems to provide actionable information for all levels of users. The implementation of a cloud-based application analyzing data transactions, learning and predicting future states from current and past states in real-time, and communicating those anticipated states is an appropriate solution for the purposes of reduced latency and improved confidence in decisions. Decisions made from an ML and AI application combined with advanced optimization algorithms will improve the mission success and performance of systems, which will improve the overall cost and effectiveness of any program. The Systecon team constructs and employs model-based simulations, cutting across traditional silos of data, aggregating maintenance, and supply data, incorporating sensor information, and applying optimization and simulation methods to an as-maintained digital twin with the ability to aggregate results across a system’s lifecycle and across logical and operational groupings of systems. This coupling of data throughout the enterprise enables tactical, operational, and strategic decision support, detachable and deployable logistics services, and configuration-based automated distribution of digital technical and product data to enhance supply and logistics operations. As a complete solution, this approach significantly reduces program risk by allowing flexible configuration of data, data relationships, business process workflows, and early test and evaluation, especially budget trade-off analyses. A true capability to tie resources (dollars) to weapon system readiness in alignment with the real-world scenarios a warfighter may experience has been an objective yet to be realized to date. By developing and solidifying an organic capability to directly relate dollars to readiness and to inform the digital twin, the decision-maker is now empowered through valuable insight and traceability. This type of educated decision-making provides an advantage over the adversaries who struggle with maintaining system readiness at an affordable cost. The M&S capability developed allows program managers to independently evaluate system design and support decisions by quantifying their impact on operational availability and operations and support cost resulting in the ability to simultaneously optimize readiness and cost. This will allow the stakeholders to make data-driven decisions when trading cost and readiness throughout the life of the program. Finally, sponsors are available to validate product deliverables with efficiency and much higher accuracy than in previous years.Keywords: artificial intelligence, digital transformation, machine learning, predictive analytics
Procedia PDF Downloads 1544 Design of DNA Origami Structures Using LAMP Products as a Combined System for the Detection of Extended Spectrum B-Lactamases
Authors: Kalaumari Mayoral-Peña, Ana I. Montejano-Montelongo, Josué Reyes-Muñoz, Gonzalo A. Ortiz-Mancilla, Mayrin Rodríguez-Cruz, Víctor Hernández-Villalobos, Jesús A. Guzmán-López, Santiago García-Jacobo, Iván Licona-Vázquez, Grisel Fierros-Romero, Rosario Flores-Vallejo
Abstract:
The group B-lactamic antibiotics include some of the most frequently used small drug molecules against bacterial infections. Nevertheless, an alarming decrease in their efficacy has been reported due to the emergence of antibiotic-resistant bacteria. Infections caused by bacteria expressing extended Spectrum B-lactamases (ESBLs) are difficult to treat and account for higher morbidity and mortality rates, delayed recovery, and high economic burden. According to the Global Report on Antimicrobial Resistance Surveillance, it is estimated that mortality due to resistant bacteria will ascend to 10 million cases per year worldwide. These facts highlight the importance of developing low-cost and readily accessible detection methods of drug-resistant ESBLs bacteria to prevent their spread and promote accurate and fast diagnosis. Bacterial detection is commonly done using molecular diagnostic techniques, where PCR stands out for its high performance. However, this technique requires specialized equipment not available everywhere, is time-consuming, and has a high cost. Loop-Mediated Isothermal Amplification (LAMP) is an alternative technique that works at a constant temperature, significantly decreasing the equipment cost. It yields double-stranded DNA of several lengths with repetitions of the target DNA sequence as a product. Although positive and negative results from LAMP can be discriminated by colorimetry, fluorescence, and turbidity, there is still a large room for improvement in the point-of-care implementation. DNA origami is a technique that allows the formation of 3D nanometric structures by folding a large single-stranded DNA (scaffold) into a determined shape with the help of short DNA sequences (staples), which hybridize with the scaffold. This research aimed to generate DNA origami structures using LAMP products as scaffolds to improve the sensitivity to detect ESBLs in point-of-care diagnosis. For this study, the coding sequence of the CTM-X-15 ESBL of E. coli was used to generate the LAMP products. The set of LAMP primers were designed using PrimerExplorerV5. As a result, a target sequence of 200 nucleotides from CTM-X-15 ESBL was obtained. Afterward, eight different DNA origami structures were designed using the target sequence in the SDCadnano and analyzed with CanDo to evaluate the stability of the 3D structures. The designs were constructed minimizing the total number of staples to reduce costs and complexity for point-of-care applications. After analyzing the DNA origami designs, two structures were selected. The first one was a zig-zag flat structure, while the second one was a wall-like shape. Given the sequence repetitions in the scaffold sequence, both were able to be assembled with only 6 different staples each one, ranging between 18 to 80 nucleotides. Simulations of both structures were performed using scaffolds of different sizes yielding stable structures in all the cases. The generation of the LAMP products were tested by colorimetry and electrophoresis. The formation of the DNA structures was analyzed using electrophoresis and colorimetry. The modeling of novel detection methods through bioinformatics tools allows reliable control and prediction of results. To our knowledge, this is the first study that uses LAMP products and DNA-origami in combination to delect ESBL-producing bacterial strains, which represent a promising methodology for diagnosis in the point-of-care.Keywords: beta-lactamases, antibiotic resistance, DNA origami, isothermal amplification, LAMP technique, molecular diagnosis
Procedia PDF Downloads 2113 Exploring Symptoms, Causes and Treatments of Feline Pruritus Using Thematic Analysis of Pet Owner Social Media Posts
Authors: Sitira Williams, Georgina Cherry, Andrea Wright, Kevin Wells, Taran Rai, Richard Brown, Travis Street, Alasdair Cook
Abstract:
Social media sources (50) were identified, keywords defined by veterinarians and organised into 6 topics known to be indicative of feline pruritus: body areas, behaviors, symptoms, diagnosis, and treatments. These were augmented using academic literature, a cat owner survey, synonyms, and Google Trends. The content was collected using a social intelligence solution, with keywords tagged and filtered. Data were aggregated and de-duplicated. SL content matching body areas, behaviors and symptoms were reviewed manually, and posts were marked relevant if: posted by a pet owner, identifying an itchy cat and not duplicated. A sub-set of 493 posts published from 2009-2022 was used for reflexive thematic analysis in NVIVO (Burlington, MA) to identify themes. Five themes were identified: allergy, pruritus, additional behaviors, unusual or undesirable behaviors, diagnosis, and treatment. Most (258) posts reported the cat was excessively licking, itching, and scratching. The majority were indoor cats and were less playful and friendly when itchy. Half of these posts did not indicate a known cause of pruritus. Bald spots and scabs (123) were reported, often causing swelling and fur loss, and 56 reported bumps, lumps, and dry patches. Other impacts on the cat’s quality of life were ear mites, cat self-trauma and stress. Seven posts reported their cats’ symptoms caused them ongoing anxiety and depression. Cats with food allergies to poultry (often chicken and beef) causing bald spots featured in 23 posts. Veterinarians advised switching to a raw food diet and/or changing their bowls. Some cats got worse after switching, leaving owners’ needs unmet. Allergic reactions to flea bites causing excessive itching, red spots, scabs, and fur loss were reported in 13 posts. Some (3) posts indicated allergic reactions to medication. Cats with seasonal and skin allergies, causing sneezing, scratching, headshaking, watery eyes, and nasal discharge, were reported 17 times. Eighty-five posts identified additional behaviors. Of these, 13 reported their cat’s burst pimple or insect bite. Common behaviors were headshaking, rubbing, pawing at their ears, and aggressively chewing. In some cases, bites or pimples triggered previously unseen itchiness, making the cat irritable. Twenty-four reported their cat had anxiety: overgrooming, itching, losing fur, hiding, freaking out, breathing quickly, sleeplessness, hissing and vocalising. Most reported these cats as having itchy skin, fleas, and bumps. Cats were commonly diagnosed with an ear infection, ringworm, acne, or kidney disease. Acne was diagnosed in cats with an allergy flare-up or overgrooming. Ear infections were diagnosed in itchy cats with mites or other parasites. Of the treatments mentioned, steroids were most frequently used, then anti-parasitics, including flea treatments and oral medication (steroids, antibiotics). Forty-six posts reported distress following poor outcomes after medication or additional vet consultations. SL provides veterinarians with unique insights. Verbatim comments highlight the detrimental effects of pruritus on pets and owner quality of life. This study demonstrates the need for veterinarians to communicate management and treatment options more effectively to relieve owner frustrations. Data analysis could be scaled up using machine learning for topic modeling.Keywords: content analysis, feline, itch, pruritus, social media, thematic analysis, veterinary dermatology
Procedia PDF Downloads 1832 Marketing and Business Intelligence and Their Impact on Products and Services through Understanding Based on Experiential Knowledge of Customers in Telecommunications Companies
Authors: Ali R. Alshawawreh, Francisco Liébana-Cabanillas, Francisco J. Blanco-Encomienda
Abstract:
Collaboration between marketing and business intelligence (BI) is crucial in today's ever-evolving business landscape. These two domains play pivotal roles in molding customers' experiential knowledge. Marketing insights offer valuable information regarding customer needs, preferences, and behaviors, thus refining marketing strategies and enhancing overall customer experiences. Conversely, BI facilitates data-driven decision-making, leading to heightened operational efficiency, product quality, and customer satisfaction. The analysis of customer data through BI unveils patterns and trends, informing product development, marketing campaigns, and customer service initiatives aimed at enriching experiences and knowledge. Customer experiential knowledge (CEK) encompasses customers' implicit comprehension of consumption experiences influenced by diverse factors, including social and cultural influences. This study primarily focuses on telecommunications companies in Jordan, scrutinizing how experiential customer knowledge mediates the relationship between marketing intelligence, business intelligence, and innovation in product and service offerings. Drawing on theoretical frameworks such as the resource-based view (RBV) and service-dominant logic (SDL), the research aims to comprehend how organizations utilize their resources, particularly knowledge, to foster innovation. Employing a quantitative research approach, the study collected and analyzed primary data to explore hypotheses. The chosen method was justified for its efficacy in handling large sample sizes. Structural equation modeling (SEM) facilitated by Smart PLS software evaluated the relationships between the constructs, followed by mediation analysis to assess the indirect associations in the model. The study findings offer insights into the intricate dynamics of organizational innovation, uncovering the interconnected relationships between business intelligence, customer experiential knowledge-based innovation (CEK-DI), marketing intelligence (MI), and product and service innovation (PSI), underscoring the pivotal role of advanced intelligence capabilities in developing innovative practices rooted in a profound understanding of customer experiences. Organizations equipped with cutting-edge BI tools are better positioned to devise strategies informed by precise insights into customer needs and behaviors. Furthermore, the positive impact of BI on PSI reaffirms the significance of data-driven decision-making in shaping the innovation landscape. Companies leveraging BI demonstrate adeptness in identifying market opportunities guiding the development of novel products and services. The substantial impact of CEK-DI on PSI highlights the crucial role of customer experiences in driving organizational innovation. Firms actively integrating customer insights into their innovation processes are more likely to create offerings aligned with customer expectations, fostering higher levels of product and service innovation. Additionally, the positive and significant effect of MI on CEK-DI underscores the critical role of market insights in shaping innovative strategies. While the relationship between MI and PSI is positive, a slightly weaker significance level indicates a nuanced association, suggesting that while MI contributes to innovation, other factors may also influence the innovation landscape, warranting further exploration. In conclusion, the study underscores the essential role of intelligence capabilities, particularly artificial intelligence, in driving innovation, emphasizing the necessity for organizations to leverage market and customer intelligence for effective and competitive innovation practices. Collaborative efforts between marketing and business intelligence serve as pivotal drivers of innovation, influencing experiential customer knowledge and shaping organizational strategies and practices, ultimately enhancing overall customer experiences and organizational performance.Keywords: marketing intelligence, business intelligence, product, customer experiential knowledge-driven innovation
Procedia PDF Downloads 551 Geomechanics Properties of Tuzluca (Eastern. Turkey) Bedded Rock Salt and Geotechnical Safety
Authors: Mehmet Salih Bayraktutan
Abstract:
Geomechanical properties of Rock Salt Deposits in Tuzluca Salt Mine Area (Eastern Turkey) are studied for modeling the operation- excavation strategy. The purpose of this research focused on calculating the critical value of span height- which will meet the safety requirements. The Mine Site Tuzluca Hills consist of alternating parallel bedding of Salt ( NaCl ) and Gypsum ( CaS04 + 2 H20) rocks. Rock Salt beds are more resistant than narrow Gypsum interlayers. Rock Salt beds formed almost 97 percent of the total height of the Hill. Therefore, the geotechnical safety of Galleries depends on the mechanical criteria of Rock Salt Cores. General deposition of Tuzluca Basin was finally completed by Tuzluca Evaporites, as for the uppermost stratigraphic unit. They are currently running mining operations performed by classic mechanical excavation, room and pillar method. Rooms and Pillars are currently experiencing an initial stage of fracturing in places. Geotechnical safety of the whole mining area evaluated by Rock Mass Rating (RMR), Rock Quality Designation (RQD) spacing of joints, and the interaction of groundwater and fracture system. In general, bedded rock salt Show large lateral deformation capacity (while deformation modulus stays in relative small values, here E= 9.86 GPa). In such litho-stratigraphic environments, creep is a critical mechanism in failure. Rock Salt creep rate in steady-state is greater than interbedding layers. Under long-lasted compressive stresses, creep may cause shear displacements, partly using bedding planes. Eventually, steady-state creep in time returns to accelerated stages. Uniaxial compression creep tests on specimens were performed to have an idea of rock salt strength. To give an idea, on Rock Salt cores, average axial strength and strain are found as 18 - 24 MPa and 0.43-0.45 %, respectively. Uniaxial Compressive strength of 26- 32 MPa, from bedded rock salt cores. Elastic modulus is comparatively low, but lateral deformation of the rock salt is high under the uniaxial compression stress state. Poisson ratio = 0.44, break load = 156 kN, cohesion c= 12.8 kg/cm2, specific gravity SG=2.17 gr/cm3. Fracture System; spacing of fractures, joints, faults, offsets are evaluated under acting geodynamic mechanism. Two sand beds, each 4-6 m thick, exist near to upper level and at the top of the evaporating sequence. They act as aquifers and keep infiltrated water on top for a long duration, which may result in the failure of roofs or pillars. Two major active seismic ( N30W and N70E ) striking Fault Planes and parallel fracture strands have seismically triggered moderate risk of structural deformation of rock salt bedding sequence. Earthquakes and Floods are two prevailing sources of geohazards in this region—the seismotectonic activity of the Mine Site based on the crossing framework of Kagizman Faults and Igdir Faults. Dominant Hazard Risk sources include; a) Weak mechanical properties of rock salt, gypsum, anhydrite beds-creep. b) Physical discontinuities cutting across the thick parallel layers of Evaporite Mass, c) Intercalated beds of weak cemented or loose sand, clayey sandy sediments. On the other hand, absorbing the effects of salt-gyps parallel bedded deposits on seismic wave amplitudes has a reducing effect on the Rock Mass.Keywords: bedded rock salt, creep, failure mechanism, geotechnical safety
Procedia PDF Downloads 186