Search results for: parallel algorithms

Authors: Uraib Sharaha, Ahmad Salman, Eladio Rodriguez-Diaz, Elad Shufan, Klaris Riesenberg, Irving J. Bigio, Mahmoud Huleihel

Abstract:

Antimicrobial drugs have played an indispensable role in controlling illness and death associated with infectious diseases in animals and humans. However, the increasing resistance of bacteria to a broad spectrum of commonly used antibiotics has become a global healthcare problem. Many antibiotics had lost their effectiveness since the beginning of the antibiotic era because many bacteria have adapted defenses against these antibiotics. Rapid determination of antimicrobial susceptibility of a clinical isolate is often crucial for the optimal antimicrobial therapy of infected patients and in many cases can save lives. The conventional methods for susceptibility testing require the isolation of the pathogen from a clinical specimen by culturing on the appropriate media (this culturing stage lasts 24 h-first culturing). Then, chosen colonies are grown on media containing antibiotic(s), using micro-diffusion discs (second culturing time is also 24 h) in order to determine its bacterial susceptibility. Other methods, genotyping methods, E-test and automated methods were also developed for testing antimicrobial susceptibility. Most of these methods are expensive and time-consuming. Fourier transform infrared (FTIR) microscopy is rapid, safe, effective and low cost method that was widely and successfully used in different studies for the identification of various biological samples including bacteria; nonetheless, its true potential in routine clinical diagnosis has not yet been established. The new modern infrared (IR) spectrometers with high spectral resolution enable measuring unprecedented biochemical information from cells at the molecular level. Moreover, the development of new bioinformatics analyses combined with IR spectroscopy becomes a powerful technique, which enables the detection of structural changes associated with resistivity. The main goal of this study is to evaluate the potential of the FTIR microscopy in tandem with machine learning algorithms for rapid and reliable identification of bacterial susceptibility to antibiotics in time span of few minutes. The UTI E.coli bacterial samples, which were identified at the species level by MALDI-TOF and examined for their susceptibility by the routine assay (micro-diffusion discs), are obtained from the bacteriology laboratories in Soroka University Medical Center (SUMC). These samples were examined by FTIR microscopy and analyzed by advanced statistical methods. Our results, based on 700 E.coli samples, were promising and showed that by using infrared spectroscopic technique together with multivariate analysis, it is possible to classify the tested bacteria into sensitive and resistant with success rate higher than 90% for eight different antibiotics. Based on these preliminary results, it is worthwhile to continue developing the FTIR microscopy technique as a rapid and reliable method for identification antibiotic susceptibility.

Keywords: antibiotics, E.coli, FTIR, multivariate analysis, susceptibility, UTI

Procedia PDF Downloads 152

Authors: Efstratios Karavasilis, Foteini Christidi, Georgios Velonakis, Agapi Plousi, Kalliopi Platoni, Nikolaos Kelekis, Ioannis Evdokimidis, Efstathios Efstathopoulos

Abstract:

Introduction: Advanced structural and functional neuroimaging techniques contribute to the study of anatomical and functional brain connectivity and its role in the pathophysiology and symptoms’ heterogeneity in several neurodegenerative disorders, including multiple sclerosis (MS). Aim: In the present study, we applied multiparametric neuroimaging techniques to investigate the structural and functional cortico-cerebellar changes in MS patients. Material: We included 51 MS patients (28 with clinically isolated syndrome [CIS], 31 with relapsing-remitting MS [RRMS]) and 51 age- and gender-matched healthy controls (HC) who underwent MRI in a 3.0T MRI scanner. Methodology: The acquisition protocol included high-resolution 3D T1 weighted, diffusion-weighted imaging and echo planar imaging sequences for the analysis of volumetric, tractography and functional resting state data, respectively. We performed between-group comparisons (CIS, RRMS, HC) using CAT12 and CONN16 MATLAB toolboxes for the analysis of volumetric (cerebellar gray matter density) and functional (cortico-cerebellar resting-state functional connectivity) data, respectively. Brainance suite was used for the analysis of tractography data (cortico-cerebellar white matter integrity; fractional anisotropy [FA]; axial and radial diffusivity [AD; RD]) to reconstruct the cerebellum tracts. Results: Patients with CIS did not show significant gray matter (GM) density differences compared with HC. However, they showed decreased FA and increased diffusivity measures in cortico-cerebellar tracts, and increased cortico-cerebellar functional connectivity. Patients with RRMS showed decreased GM density in cerebellar regions, decreased FA and increased diffusivity measures in cortico-cerebellar WM tracts, as well as a pattern of increased and mostly decreased functional cortico-cerebellar connectivity compared to HC. The comparison between CIS and RRMS patients revealed significant GM density difference, reduced FA and increased diffusivity measures in WM cortico-cerebellar tracts and increased/decreased functional connectivity. The identification of decreased WM integrity and increased functional cortico-cerebellar connectivity without GM changes in CIS and the pattern of decreased GM density decreased WM integrity and mostly decreased functional connectivity in RRMS patients emphasizes the role of compensatory mechanisms in early disease stages and the disintegration of structural and functional networks with disease progression. Conclusions: In conclusion, our study highlights the added value of multimodal neuroimaging techniques for the in vivo investigation of cortico-cerebellar brain changes in neurodegenerative disorders. An extension and future opportunity to leverage multimodal neuroimaging data inevitably remain the integration of such data in the recently-applied mathematical approaches of machine learning algorithms to more accurately classify and predict patients’ disease course.

Keywords: advanced neuroimaging techniques, cerebellum, MRI, multiple sclerosis

Procedia PDF Downloads 117

Authors: Todd H. Buxton, Yong G. Lai

Abstract:

Temperature management in regulated rivers can involve significant expenditures of water to meet the cold-water requirements of species in summer. For this purpose, flows released from Lewiston Dam on the Trinity River in Northern California are 12.7 cms with temperatures around 11oC in July through September to provide adult spring Chinook cold water to hold in deep pools and mature until spawning in fall. The releases are more than double the flow and 10oC colder temperatures than the natural conditions before the dam was built. The high, cold releases provide springers the habitat they require but may suppress the stream food base and limit future populations of salmon by reducing the juvenile fish size and survival to adults via the positive relationship between the two. Field and modeling research was undertaken to explore whether lowering summer releases from Lewiston Dam may promote thermal stratification in river pools so that both the cold-water needs of adult salmon and warmer water requirements of other organisms in the stream biome may be met. For this investigation, a three-dimensional (3D) computational fluid dynamics (CFD) model was developed and validated with field measurements in two deep pools on the Trinity River. Modeling and field observations were then used to identify the flows and temperatures that may form and maintain thermal stratification under different meteorologic conditions. Under low flows, a pool was found to be well mixed and thermally homogenous until temperatures began to stratify shortly after sunrise. Stratification then strengthened through the day until shading from trees and mountains cooled the inlet flow and decayed the thermal gradient, which collapsed shortly before sunset and returned the pool to a well-mixed state. This diurnal process of stratification formation and destruction was closely predicted by the 3D CFD model. Both the model and field observations indicate that thermal stratification maintained the coldest temperatures of the day at ≥2m depth in a pool and provided water that was around 8oC warmer in the upper 2m of the pool. Results further indicate that the stratified pool under low flows provided almost the same daily average temperatures as when flows were an order of magnitude higher and stratification was prevented, indicating significant water savings may be realized in regulated streams while also providing a diversity in water temperatures the ecosystem requires. With confidence in the 3D CFD model, the model is now being applied to a dozen pools in the Trinity River to understand how pool bathymetry influences thermal stratification under variable flows and diurnal temperature variations. This knowledge will be used to expand the results to 52 pools in a 64 km reach below Lewiston Dam that meet the depth criteria (≥2 m) for spring Chinook holding. From this, rating curves will be developed to relate discharge to the volume of pool habitat that provides springers the temperature (<15.6oC daily average), velocity (0.15 to 0.4 m/s) and depths that accommodate the escapement target for spring Chinook (6,000 adults) under maximum fish densities measured in other streams (3.1 m3/fish) during the holding time of year (May through August). Flow releases that meet these goals will be evaluated for water savings relative to the current flow regime and their influence on indicator species, including the Foothill Yellow-Legged Frog, and aspects of the stream biome that support salmon populations, including macroinvertebrate production and juvenile Chinook growth rates.

Keywords: 3D CFD modeling, flow regulation, thermal stratification, chinook salmon, foothill yellow-legged frogs, water managment

Procedia PDF Downloads 34

Authors: Jean-Philippe Amat, Timothée Vergne, Aymeric Hans, Bénédicte Ferry, Pascal Hendrikx, Jackie Tapprest, Barbara Dufour, Agnès Leblond

Abstract:

The surveillance of infectious diseases is necessary to describe their occurrence and help the planning, implementation and evaluation of risk mitigation activities. However, the exact number of detected cases may remain unknown whether surveillance is based on serological tests because identifying seroconversion may be difficult. Moreover, incomplete detection of cases or outbreaks is a recurrent issue in the field of disease surveillance. This study addresses these two issues. Using a viral animal disease as an example (equine viral arteritis), the goals were to establish suitable rules for identifying seroconversion in order to estimate the number of cases and outbreaks detected by a surveillance system in France between 2006 and 2013, and to assess the sensitivity of this system by estimating the total number of outbreaks that occurred during this period (including unreported outbreaks) using a capture-recapture model. Data from horses which exhibited at least one positive result in serology using viral neutralization test between 2006 and 2013 were used for analysis (n=1,645). Data consisted of the annual antibody titers and the location of the subjects (towns). A consensus among multidisciplinary experts (specialists in the disease and its laboratory diagnosis, epidemiologists) was reached to consider seroconversion as a change in antibody titer from negative to at least 32 or as a three-fold or greater increase. The number of seroconversions was counted for each town and modeled using a unilist zero-truncated binomial (ZTB) capture-recapture model with R software. The binomial denominator was the number of horses tested in each infected town. Using the defined rules, 239 cases located in 177 towns (outbreaks) were identified from 2006 to 2013. Subsequently, the sensitivity of the surveillance system was estimated as the ratio of the number of detected outbreaks to the total number of outbreaks that occurred (including unreported outbreaks) estimated using the ZTB model. The total number of outbreaks was estimated at 215 (95% credible interval CrI95%: 195-249) and the surveillance sensitivity at 82% (CrI95%: 71-91). The rules proposed for identifying seroconversion may serve future research. Such rules, adjusted to the local environment, could conceivably be applied in other countries with surveillance programs dedicated to this disease. More generally, defining ad hoc algorithms for interpreting the antibody titer could be useful regarding other human and animal diseases and zoonosis when there is a lack of accurate information in the literature about the serological response in naturally infected subjects. This study shows how capture-recapture methods may help to estimate the sensitivity of an imperfect surveillance system and to valorize surveillance data. The sensitivity of the surveillance system of equine viral arteritis is relatively high and supports its relevance to prevent the disease spreading.

Keywords: Bayesian inference, capture-recapture, epidemiology, equine viral arteritis, infectious disease, seroconversion, surveillance

Procedia PDF Downloads 265

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: Joel A. Gordon, Nazmiye Balta-Ozkan, Seyed Ali Nabavi

Abstract:

Hydrogen-fueled technologies are rapidly advancing as a critical component of the low-carbon energy transition. In countries historically reliant on natural gas for home heating, such as the UK, hydrogen may prove fundamental for decarbonizing the residential sector, alongside other technologies such as heat pumps and district heat networks. While the UK government is set to take a long-term policy decision on the role of domestic hydrogen by 2026, there are considerable uncertainties regarding consumer preferences for ‘hydrogen homes’ (i.e., hydrogen-fueled appliances for space heating, hot water, and cooking. In comparison to other hydrogen energy technologies, such as road transport applications, to date, few studies have engaged with the social acceptance aspects of the domestic hydrogen transition, resulting in a stark knowledge deficit and pronounced risk to policymaking efforts. In response, this study aims to safeguard against undesirable policy measures by revealing the underlying relationships between the factors of domestic hydrogen acceptance and their respective dimensions: attitudinal, socio-political, community, market, and behavioral acceptance. The study employs an online survey (n=~2100) to gauge how different UK householders perceive the proposition of switching from natural gas to hydrogen-fueled appliances. In addition to accounting for housing characteristics (i.e., housing tenure, property type and number of occupants per dwelling) and several other socio-structural variables (e.g. age, gender, and location), the study explores the impacts of consumer heterogeneity on hydrogen acceptance by recruiting respondents from across five distinct groups: (1) fuel poor householders, (2) technology engaged householders, (3) environmentally engaged householders, (4) technology and environmentally engaged householders, and (5) a baseline group (n=~700) which filters out each of the smaller targeted groups (n=~350). This research design reflects the notion that supporting a socially fair and efficient transition to hydrogen will require parallel engagement with potential early adopters and demographic groups impacted by fuel poverty while also accounting strongly for public attitudes towards net zero. Employing a second-order multigroup confirmatory factor analysis (CFA) in Mplus, the proposed hydrogen acceptance model is tested to fit the data through a partial least squares (PLS) approach. In addition to testing differences between and within groups, the findings provide policymakers with critical insights regarding the significance of knowledge and awareness, safety perceptions, perceived community impacts, cost factors, and trust in key actors and stakeholders as potential explanatory factors of hydrogen acceptance. Preliminary results suggest that knowledge and awareness of hydrogen are positively associated with support for domestic hydrogen at the household, community, and national levels. However, with the exception of technology and/or environmentally engaged citizens, much of the population remains unfamiliar with hydrogen and somewhat skeptical of its application in homes. Knowledge and awareness present as critical to facilitating positive safety perceptions, alongside higher levels of trust and more favorable expectations for community benefits, appliance performance, and potential cost savings. Based on these preliminary findings, policymakers should be put on red alert about diffusing hydrogen into the public consciousness in alignment with energy security, fuel poverty, and net-zero agendas.

Keywords: hydrogen homes, social acceptance, consumer heterogeneity, heat decarbonization

Procedia PDF Downloads 78

Authors: Mozhdeh Khalili Kordabadi

Abstract:

Textiles play a vital role in human life, particularly in the form of clothing. However, the alarming rate at which textiles end up in landfills presents a significant environmental risk. With approximately one garbage truck per second being filled with discarded textiles, urgent measures are required to mitigate this trend. Governments and responsible organizations are calling upon various stakeholders to shift from a linear economy to a circular economy model in the textile industry. This article highlights several key approaches that can be undertaken to address this pressing issue. These approaches include the creation of renewable raw material sources, rethinking production processes, maximizing the use and reuse of textile products, implementing reproduction and recycling strategies, exploring redistribution to new markets, and finding innovative means to extend the lifespan of textiles. By adopting these strategies, the textile industry can contribute to a more sustainable and environmentally friendly future. Introduction: Textiles, particularly clothing, are essential to human existence. However, the rapid accumulation of textiles in landfills poses a significant threat to the environment. This article explores the urgent need for the textile industry to transition from a linear economy model to a circular economy model. The linear model, characterized by the creation, use, and disposal of textiles, is unsustainable in the long term. By adopting a circular economy approach, the industry can minimize waste, reduce environmental impact, and promote sustainable practices. This article outlines key approaches that can be undertaken to drive this transition. Approaches to Address Environmental Challenges: Creation of Renewable Raw Materials Sources: Exploring and promoting the use of renewable and sustainable raw materials, such as organic cotton, hemp, and recycled fibers, can significantly reduce the environmental footprint of textile production. Rethinking Production Processes: Implementing cleaner production techniques, optimizing resource utilization, and minimizing waste generation are crucial steps in reducing the environmental impact of textile manufacturing. Maximizing Use and Reuse of Textile Products: Encouraging consumers to prolong the lifespan of textile products through proper care, maintenance, and repair services can reduce the frequency of disposal and promote a culture of sustainability. Reproduction and Recycling Strategies: Investing in innovative technologies and infrastructure to enable efficient reproduction and recycling of textiles can close the loop and minimize waste generation. Redistribution of Textiles to New Markets: Exploring opportunities to redistribute textiles to new and parallel markets, such as resale platforms, can extend their lifecycle and prevent premature disposal. Improvising Means to Extend Textile Lifespan: Encouraging design practices that prioritize durability, versatility, and timeless aesthetics can contribute to prolonging the lifespan of textiles. Conclusion: The textile industry must urgently transition from a linear economy to a circular economy model to mitigate the adverse environmental impact caused by textile waste. By implementing the outlined approaches, such as sourcing renewable raw materials, rethinking production processes, promoting reuse and recycling, exploring new markets, and extending the lifespan of textiles, stakeholders can work together to create a more sustainable and environmentally friendly textile industry. These measures require collective action and collaboration between governments, organizations, manufacturers, and consumers to drive positive change and safeguard the planet for future generations.

Keywords: textiles, circular economy, environmental challenges, renewable raw materials, production processes, reuse, recycling, redistribution, textile lifespan extension.

Procedia PDF Downloads 57

Authors: Avi Shrivastava

Abstract:

Our world continues to grapple with a lot of social issues. Economic growth and scientific advancements have not completely eradicated poverty, homelessness, discrimination and bias, gender inequality, health issues, mental illness, addiction, and other social issues. So, how do we improve the human condition in a world driven by advanced technology? The answer is simple: we will have to leverage technology to address some of the most important social challenges of the day. AI, or artificial intelligence, has emerged as a critical tool in the battle against issues that deprive marginalized and disadvantaged groups of the right to enjoy benefits that a society offers. Social work professionals can transform their lives by harnessing it. The lack of reliable data is one of the reasons why a lot of social work projects fail. Social work professionals continue to rely on expensive and time-consuming primary data collection methods, such as observation, surveys, questionnaires, and interviews, instead of tapping into AI-based technology to generate useful, real-time data and necessary insights. By leveraging AI’s data-mining ability, we can gain a deeper understanding of how to solve complex social problems and change lives of people. We can do the right work for the right people and at the right time. For example, AI can enable social work professionals to focus their humanitarian efforts on some of the world’s poorest regions, where there is extreme poverty. An interdisciplinary team of Stanford scientists, Marshall Burke, Stefano Ermon, David Lobell, Michael Xie, and Neal Jean, used AI to spot global poverty zones – identifying such zones is a key step in the fight against poverty. The scientists combined daytime and nighttime satellite imagery with machine learning algorithms to predict poverty in Nigeria, Uganda, Tanzania, Rwanda, and Malawi. In an article published by Stanford News, Stanford researchers use dark of night and machine learning, Ermon explained that they provided the machine-learning system, an application of AI, with the high-resolution satellite images and asked it to predict poverty in the African region. “The system essentially learned how to solve the problem by comparing those two sets of images [daytime and nighttime].” This is one example of how AI can be used by social work professionals to reach regions that need their aid the most. It can also help identify sources of inequality and conflict, which could reduce inequalities, according to Nature’s study, titled The role of artificial intelligence in achieving the Sustainable Development Goals, published in 2020. The report also notes that AI can help achieve 79 percent of the United Nation’s (UN) Sustainable Development Goals (SDG). AI is impacting our everyday lives in multiple amazing ways, yet some people do not know much about it. If someone is not familiar with this technology, they may be reluctant to use it to solve social issues. So, before we talk more about the use of AI to accomplish social work objectives, let’s put the spotlight on how AI and social work can complement each other.

Keywords: social work, artificial intelligence, AI based social work, machine learning, technology

Procedia PDF Downloads 76

Authors: Domenico Carmelo Mongelli

Abstract:

The context is that of great uncertainty in the 27 countries belonging to the European Union which has adopted an epochal measure: the elimination of internal combustion engines for the traction of road vehicles starting from 2035 with complete replacement with electric vehicles. If on the one hand there is great concern at various levels for the unpreparedness for this change, on the other the Scientific Community is not preparing accurate studies on the problem, as the scientific literature deals with single aspects of the issue, moreover addressing the issue at the level of individual countries, losing sight of the global implications of the issue for the entire EU. The aim of the research is to fill these gaps: the technological, plant engineering, environmental, economic and employment aspects of the energy transition in question are addressed and connected to each other, comparing the current situation with the different scenarios that could exist in 2035 and in the following years until total disposal of the internal combustion engine vehicle fleet for the entire EU. The methodologies adopted by the research consist in the analysis of the entire life cycle of electric vehicles and batteries, through the use of specific databases, and in the dynamic simulation, using specific calculation codes, of the application of the results of this analysis to the entire EU electric vehicle fleet from 2035 onwards. Energy balance sheets will be drawn up (to evaluate the net energy saved), plant balance sheets (to determine the surplus demand for power and electrical energy required and the sizing of new plants from renewable sources to cover electricity needs), economic balance sheets (to determine the investment costs for this transition, the savings during the operation phase and the payback times of the initial investments), the environmental balances (with the different energy mix scenarios in anticipation of 2035, the reductions in CO2eq and the environmental effects are determined resulting from the increase in the production of lithium for batteries), the employment balances (it is estimated how many jobs will be lost and recovered in the reconversion of the automotive industry, related industries and in the refining, distribution and sale of petroleum products and how many will be products for technological innovation, the increase in demand for electricity, the construction and management of street electric columns). New algorithms for forecast optimization are developed, tested and validated. Compared to other published material, the research adds an overall picture of the energy transition, capturing the advantages and disadvantages of the different aspects, evaluating the entities and improvement solutions in an organic overall picture of the topic. The results achieved allow us to identify the strengths and weaknesses of the energy transition, to determine the possible solutions to mitigate these weaknesses and to simulate and then evaluate their effects, establishing the most suitable solutions to make this transition feasible.

Keywords: engines, Europe, mobility, transition

Procedia PDF Downloads 33

Authors: Magdalena Idzikowska, Katarzyna Pająk, Kamil Kowalczyk

Abstract:

Seafloor topography is a fundamental issue in geological, geophysical, and oceanographic studies. Single-beam or multibeam sonars attached to the hulls of ships are used to emit a hydroacoustic signal from transducers and reproduce the topography of the seabed. This solution provides relevant accuracy and spatial resolution. Bathymetric data from ships surveys provides National Centers for Environmental Information – National Oceanic and Atmospheric Administration. Unfortunately, most of the seabed is still unidentified, as there are still many gaps to be explored between ship survey tracks. Moreover, such measurements are very expensive and time-consuming. The solution is raster bathymetric models shared by The General Bathymetric Chart of the Oceans. The offered products are a compilation of different sets of data - raw or processed. Indirect data for the development of bathymetric models are also measurements of gravity anomalies. Some forms of seafloor relief (e.g. seamounts) increase the force of the Earth's pull, leading to changes in the sea surface. Based on satellite altimetry data, Sea Surface Height and marine gravity anomalies can be estimated, and based on the anomalies, it’s possible to infer the structure of the seabed. The main goal of the work is to create regional bathymetric models and models of the sea surface in the area of the east coast of North America – a region of seamounts and undulating seafloor. The research includes an analysis of the methods and techniques used, an evaluation of the interpolation algorithms used, model thickening, and the creation of grid models. Obtained data are raster bathymetric models in NetCDF format, survey data from multibeam soundings in MB-System format, and satellite altimetry data from Copernicus Marine Environment Monitoring Service. The methodology includes data extraction, processing, mapping, and spatial analysis. Visualization of the obtained results was carried out with Geographic Information System tools. The result is an extension of the state of the knowledge of the quality and usefulness of the data used for seabed and sea surface modeling and knowledge of the accuracy of the generated models. Sea level is averaged over time and space (excluding waves, tides, etc.). Its changes, along with knowledge of the topography of the ocean floor - inform us indirectly about the volume of the entire water ocean. The true shape of the ocean surface is further varied by such phenomena as tides, differences in atmospheric pressure, wind systems, thermal expansion of water, or phases of ocean circulation. Depending on the location of the point, the higher the depth, the lower the trend of sea level change. Studies show that combining data sets, from different sources, with different accuracies can affect the quality of sea surface and seafloor topography models.

Keywords: seafloor, sea surface height, bathymetry, satellite altimetry

Procedia PDF Downloads 53

Authors: Ionut Vintu, Stefan Laible, Ruth Schulz

Abstract:

Agricultural robotics has been developing steadily over recent years, with the goal of reducing and even eliminating pesticides used in crops and to increase productivity by taking over human labor. The majority of crops are arranged in rows. The first step towards autonomous robots, capable of driving in fields and performing crop-handling tasks, is for robots to robustly detect the rows of plants. Recent work done towards autonomous driving between plant rows offers big robotic platforms equipped with various expensive sensors as a solution to this problem. These platforms need to be driven over the rows of plants. This approach lacks flexibility and scalability when it comes to the height of plants or distance between rows. This paper proposes instead an algorithm that makes use of cheaper sensors and has a higher variability. The main application is in tree nurseries. Here, plant height can range from a few centimeters to a few meters. Moreover, trees are often removed, leading to gaps within the plant rows. The core idea is to combine row detection algorithms with graph-based localization methods as they are used in SLAM. Nodes in the graph represent the estimated pose of the robot, and the edges embed constraints between these poses or between the robot and certain landmarks. This setup aims to improve individual plant detection and deal with exception handling, like row gaps, which are falsely detected as an end of rows. Four methods were developed for detecting row structures in the fields, all using a point cloud acquired with a 3D LiDAR as an input. Comparing the field coverage and number of damaged plants, the method that uses a local map around the robot proved to perform the best, with 68% covered rows and 25% damaged plants. This method is further used and combined with a graph-based localization algorithm, which uses the local map features to estimate the robot’s position inside the greater field. Testing the upgraded algorithm in a variety of simulated fields shows that the additional information obtained from localization provides a boost in performance over methods that rely purely on perception to navigate. The final algorithm achieved a row coverage of 80% and an accuracy of 27% damaged plants. Future work would focus on achieving a perfect score of 100% covered rows and 0% damaged plants. The main challenges that the algorithm needs to overcome are fields where the height of the plants is too small for the plants to be detected and fields where it is hard to distinguish between individual plants when they are overlapping. The method was also tested on a real robot in a small field with artificial plants. The tests were performed using a small robot platform equipped with wheel encoders, an IMU and an FX10 3D LiDAR. Over ten runs, the system achieved 100% coverage and 0% damaged plants. The framework built within the scope of this work can be further used to integrate data from additional sensors, with the goal of achieving even better results.

Keywords: 3D LiDAR, agricultural robots, graph-based localization, row detection

Procedia PDF Downloads 102

Authors: Devansh Desai, Rahul Nigam

Abstract:

Crop water stress (W) at a given growth stage starts to set in as moisture availability (M) to roots falls below 75% of maximum. It has been found that ratio of crop evapotranspiration (ET) and reference evapotranspiration (ET0) is an indicator of moisture adequacy and is strongly correlated with ‘M’ and ‘W’. The spatial variability of ET0 is generally less over an agricultural farm of 1-5 ha than ET, which depends on both surface and atmospheric conditions, while the former depends only on atmospheric conditions. Solutions from surface energy balance (SEB) and thermal infrared (TIR) remote sensing are now known to estimate latent heat flux of ET. In the present study, ET and moisture adequacy index (MAI) (=ET/ET0) have been estimated over two contrasting western India agricultural farms having rice-wheat system in semi-arid climate and arid grassland system, limited by moisture availability. High-resolution multi-band TIR sensing observations at 65m from ECOSTRESS (ECOsystemSpaceborne Thermal Radiometer Experiment on Space Station) instrument on-board International Space Station (ISS) were used in an analytical SEB model, STIC (Surface Temperature Initiated Closure) to estimate ET and MAI. The ancillary variables used in the ET modeling and MAI estimation were land surface albedo, NDVI from close-by LANDSAT data at 30m spatial resolution, ET0 product at 4km spatial resolution from INSAT 3D, meteorological forcing variables from short-range weather forecast on air temperature and relative humidity from NWP model. Farm-scale ET estimates at 65m spatial resolution were found to show low RMSE of 16.6% to 17.5% with R2 >0.8 from 18 datasets as compared to reported errors (25 – 30%) from coarser-scale ET at 1 to 8 km spatial resolution when compared to in situ measurements from eddy covariance systems. The MAI was found to show lower (<0.25) and higher (>0.5) magnitudes in the contrasting agricultural farms. The study showed the potential need of high-resolution high-repeat spaceborne multi-band TIR payloads alongwith optical payload in estimating farm-scale ET and MAI for estimating consumptive water use and water stress. A set of future high-resolution multi-band TIR sensors are planned on-board Indo-French TRISHNA, ESA’s LSTM, NASA’s SBG space-borne missions to address sustainable irrigation water management at farm-scale to improve crop water productivity. These will provide precise and fundamental variables of surface energy balance such as LST (Land Surface Temperature), surface emissivity, albedo and NDVI. A synchronization among these missions is needed in terms of observations, algorithms, product definitions, calibration-validation experiments and downstream applications to maximize the potential benefits.

Keywords: thermal remote sensing, land surface temperature, crop water stress, evapotranspiration

Procedia PDF Downloads 43

Authors: Alexander Guzman Urbina, Atsushi Aoyama

Abstract:

The sustainability of traditional technologies employed in energy and chemical infrastructure brings a big challenge for our society. Making decisions related with safety of industrial infrastructure, the values of accidental risk are becoming relevant points for discussion. However, the challenge is the reliability of the models employed to get the risk data. Such models usually involve large number of variables and with large amounts of uncertainty. The most efficient techniques to overcome those problems are built using Artificial Intelligence (AI), and more specifically using hybrid systems such as Neuro-Fuzzy algorithms. Therefore, this paper aims to introduce a hybrid algorithm for risk assessment trained using near-miss accident data. As mentioned above the sustainability of traditional technologies related with energy and chemical infrastructure constitutes one of the major challenges that today’s societies and firms are facing. Besides that, the adaptation of those technologies to the effects of the climate change in sensible environments represents a critical concern for safety and risk management. Regarding this issue argue that social consequences of catastrophic risks are increasing rapidly, due mainly to the concentration of people and energy infrastructure in hazard-prone areas, aggravated by the lack of knowledge about the risks. Additional to the social consequences described above, and considering the industrial sector as critical infrastructure due to its large impact to the economy in case of a failure the relevance of industrial safety has become a critical issue for the current society. Then, regarding the safety concern, pipeline operators and regulators have been performing risk assessments in attempts to evaluate accurately probabilities of failure of the infrastructure, and consequences associated with those failures. However, estimating accidental risks in critical infrastructure involves a substantial effort and costs due to number of variables involved, complexity and lack of information. Therefore, this paper aims to introduce a well trained algorithm for risk assessment using deep learning, which could be capable to deal efficiently with the complexity and uncertainty. The advantage point of the deep learning using near-miss accidents data is that it could be employed in risk assessment as an efficient engineering tool to treat the uncertainty of the risk values in complex environments. The basic idea of using a Near-Miss Deep Learning Approach for Neuro-Fuzzy Risk Assessment in Pipelines is focused in the objective of improve the validity of the risk values learning from near-miss accidents and imitating the human expertise scoring risks and setting tolerance levels. In summary, the method of Deep Learning for Neuro-Fuzzy Risk Assessment involves a regression analysis called group method of data handling (GMDH), which consists in the determination of the optimal configuration of the risk assessment model and its parameters employing polynomial theory.

Keywords: deep learning, risk assessment, neuro fuzzy, pipelines

Procedia PDF Downloads 262

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 72

Authors: Dan W. Rhodes, Juliane Hey, Magali Karagueuzian, Florianne Martinez, Yael Sandowski, Vanessa Roulet, Mahmoud Badawi, Mohammed-Amine Chakir, Valérie Simon, Jérémie Gautier, Françoise Le Boulaire, Catherine Coignard, Claire Vincent, Sandrine Greaume, Isabelle Voisin

Abstract:

Background: Beckman Coulter, Inc. (BEC) has recently developed a fully automated second-generation anti-HCV test on a new immunoassay platform. The objective of this multicenter study conducted in Europe was to evaluate the performance of the ACCESS anti-HCV assay on the recently CE-marked DxI 9000 ACCESS Immunoassay Analyzer as an aid in the diagnosis of HCV (Hepatitis C Virus) infection and as a screening test for blood and plasma donors. Methods: The clinical specificity of the ACCESS anti-HCV assay was determined using HCV antibody-negative samples from blood donors and hospitalized patients. Sample antibody status was determined by a CE-marked anti-HCV assay (Abbott ARCHITECTTM anti-HCV assay or Abbott PRISM HCV assay) with an additional confirmation method (Immunoblot testing with INNO-LIATM HCV Score - Fujirebio), if necessary, according to pre-determined testing algorithms. The clinical sensitivity was determined using known HCV antibody-positive samples, identified positive by Immunoblot testing with INNO-LIATM HCV Score - Fujirebio. HCV RNA PCR or genotyping was available on all Immunoblot positive samples for further characterization. The false initial reactive rate was determined on fresh samples from blood donors and hospitalized patients. Thirty (30) commercially available seroconversion panels were tested to assess the sensitivity for early detection of HCV infection. The study was conducted from November 2019 to March 2022. Three (3) external sites and one (1) internal site participated. Results: Clinical specificity (95% CI) was 99.7% (99.6 – 99.8%) on 5852 blood donors and 99.0% (98.4 – 99.4%) on 1527 hospitalized patient samples. There were 15 discrepant samples (positive on ACCESS anti-HCV assay and negative on both ARCHITECT and Immunoblot) observed with hospitalized patient samples, and of note, additional HCV RNA PCR results showed five (5) samples had positive HCV RNA PCR results despite the absence of HCV antibody detection by ARCHITECT and Immunoblot, suggesting a better sensitivity of the ACCESS anti-HCV assay with these five samples compared to the ARCHITECT and Immunoblot anti-HCV assays. Clinical sensitivity (95% CI) on 510 well-characterized, known HCV antibody-positive samples was 100.0% (99.3 – 100.0%), including 353 samples with known HCV genotypes (1 to 6). The overall false initial reactive rate (95% CI) on 6630 patient samples was 0.02% (0.00 – 0.09%). Results obtained on 30 seroconversion panels demonstrated that the ACCESS anti-HCV assay had equivalent sensitivity performances, with an average bleed difference since the first reactive bleed below one (1), compared to the ARCHITECTTM anti-HCV assay. Conclusion: The newly developed ACCESS anti-HCV assay from BEC for use on the DxI 9000 ACCESS Immunoassay Analyzer demonstrated high clinical sensitivity and specificity, equivalent to currently marketed anti-HCV assays, as well as a low false initial reactive rate.

Keywords: DxI 9000 ACCESS Immunoassay Analyzer, HCV, HCV antibody, Hepatitis C virus, immunoassay

Procedia PDF Downloads 68

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 38

Authors: Nir Nissim, Erez Shalom, Tomer Lancewiki, Yuval Elovici, Yuval Shahar

Abstract:

Background: A Medical Device (MD) is an instrument, machine, implant, or similar device that includes a component intended for the purpose of the diagnosis, cure, treatment, or prevention of disease in humans or animals. Medical devices play increasingly important roles in health services eco-systems, including: (1) Patient Diagnostics and Monitoring; Medical Treatment and Surgery; and Patient Life Support Devices and Stabilizers. MDs are part of the medical device eco-system and are connected to the network, sending vital information to the internal medical information systems of medical centers that manage this data. Wireless components (e.g. Wi-Fi) are often embedded within medical devices, enabling doctors and technicians to control and configure them remotely. All these functionalities, roles, and uses of MDs make them attractive targets of cyber-attacks launched for many malicious goals; this trend is likely to significantly increase over the next several years, with increased awareness regarding MD vulnerabilities, the enhancement of potential attackers’ skills, and expanded use of medical devices. Significance: We propose to develop and implement Cyber-Med, a unique collaborative project of Ben-Gurion University of the Negev and the Clalit Health Services Health Maintenance Organization. Cyber-Med focuses on the development of a comprehensive detection framework that relies on a critical attack repository that we aim to create. Cyber-Med will allow researchers and companies to better understand the vulnerabilities and attacks associated with medical devices as well as providing a comprehensive platform for developing detection solutions. Methodology: The Cyber-Med detection framework will consist of two independent, but complementary detection approaches: one for known attacks, and the other for unknown attacks. These modules incorporate novel ideas and algorithms inspired by our team's domains of expertise, including cyber security, biomedical informatics, and advanced machine learning, and temporal data mining techniques. The establishment and maintenance of Cyber-Med’s up-to-date attack repository will strengthen the capabilities of Cyber-Med’s detection framework. Major Findings: Based on our initial survey, we have already found more than 15 types of vulnerabilities and possible attacks aimed at MDs and their eco-system. Many of these attacks target individual patients who use devices such pacemakers and insulin pumps. In addition, such attacks are also aimed at MDs that are widely used by medical centers such as MRIs, CTs, and dialysis engines; the information systems that store patient information; protocols such as DICOM; standards such as HL7; and medical information systems such as PACS. However, current detection tools, techniques, and solutions generally fail to detect both the known and unknown attacks launched against MDs. Very little research has been conducted in order to protect these devices from cyber-attacks, since most of the development and engineering efforts are aimed at the devices’ core medical functionality, the contribution to patients’ healthcare, and the business aspects associated with the medical device.

Keywords: medical device, cyber security, attack, detection, machine learning

Procedia PDF Downloads 325

Authors: B. Neethu, Diptesh Das

Abstract:

The present study investigates the performance of a semi-active controller using magneto-rheological dampers (MR) for seismic response reduction of a multi-span bridge. The application of structural control to the structures during earthquake excitation involves numerous challenges such as proper formulation and selection of the control strategy, mathematical modeling of the system, uncertainty in system parameters and noisy measurements. These problems, however, need to be tackled in order to design and develop controllers which will efficiently perform in such complex systems. A control algorithm, which can accommodate un-certainty and imprecision compared to all the other algorithms mentioned so far, due to its inherent robustness and ability to cope with the parameter uncertainties and imprecisions, is the sliding mode algorithm. A sliding mode control algorithm is adopted in the present study due to its inherent stability and distinguished robustness to system parameter variation and external disturbances. In general a semi-active control scheme using an MR damper requires two nested controllers: (i) an overall system controller, which derives the control force required to be applied to the structure and (ii) an MR damper voltage controller which determines the voltage required to be supplied to the damper in order to generate the desired control force. In the present study a sliding mode algorithm is used to determine the desired optimal force. The function of the voltage controller is to command the damper to produce the desired force. The clipped optimal algorithm is used to find the command voltage supplied to the MR damper which is regulated by a semi active control law based on sliding mode algorithm. The main objective of the study is to propose a robust semi active control which can effectively control the responses of the bridge under real earthquake ground motions. Lumped mass model of the bridge is developed and time history analysis is carried out by solving the governing equations of motion in the state space form. The effectiveness of MR dampers is studied by analytical simulations by subjecting the bridge to real earthquake records. In this regard, it may also be noted that the performance of controllers depends, to a great extent, on the characteristics of the input ground motions. Therefore, in order to study the robustness of the controller in the present study, the performance of the controllers have been investigated for fourteen different earthquake ground motion records. The earthquakes are chosen in such a way that all possible characteristic variations can be accommodated. Out of these fourteen earthquakes, seven are near-field and seven are far-field. Also, these earthquakes are divided into different frequency contents, viz, low-frequency, medium-frequency, and high-frequency earthquakes. The responses of the controlled bridge are compared with the responses of the corresponding uncontrolled bridge (i.e., the bridge without any control devices). The results of the numerical study show that the sliding mode based semi-active control strategy can substantially reduce the seismic responses of the bridge showing a stable and robust performance for all the earthquakes.

Keywords: bridge, semi active control, sliding mode control, MR damper

Procedia PDF Downloads 106

Authors: Aleksandra Jonas, Aleksandra Gronowska, Maciej Ścigacz, Szymon Jadczak

Abstract:

Exact Data is a smart tool which helps with meaningful marketing content creation. It helps marketers achieve this by analyzing the text of an advertisement before and after its publication on social media sites like Facebook or Instagram. In our research we focus on four areas of natural language processing (NLP): grammar correction, sentiment analysis, irony detection and advertisement interpretation. Our research has identified a considerable lack of NLP tools for the Polish language, which specifically aid online marketers. In light of this, our research team has set out to create a robust and versatile NLP tool for the Polish language. The primary objective of our research is to develop a tool that can perform a range of language processing tasks in this language, such as sentiment analysis, text classification, text correction and text interpretation. Our team has been working diligently to create a tool that is accurate, reliable, and adaptable to the specific linguistic features of Polish, and that can provide valuable insights for a wide range of marketers needs. In addition to the Polish language version, we are also developing an English version of the tool, which will enable us to expand the reach and impact of our research to a wider audience. Another area of focus in our research involves tackling the challenge of the limited availability of linguistically diverse corpora for non-English languages, which presents a significant barrier in the development of NLP applications. One approach we have been pursuing is the translation of existing English corpora, which would enable us to use the wealth of linguistic resources available in English for other languages. Furthermore, we are looking into other methods, such as gathering language samples from social media platforms. By analyzing the language used in social media posts, we can collect a wide range of data that reflects the unique linguistic characteristics of specific regions and communities, which can then be used to enhance the accuracy and performance of NLP algorithms for non-English languages. In doing so, we hope to broaden the scope and capabilities of NLP applications. Our research focuses on several key NLP techniques including sentiment analysis, text classification, text interpretation and text correction. To ensure that we can achieve the best possible performance for these techniques, we are evaluating and comparing different approaches and strategies for implementing them. We are exploring a range of different methods, including transformers and convolutional neural networks (CNNs), to determine which ones are most effective for different types of NLP tasks. By analyzing the strengths and weaknesses of each approach, we can identify the most effective techniques for specific use cases, and further enhance the performance of our tool. Our research aims to create a tool, which can provide a comprehensive analysis of advertising effectiveness, allowing marketers to identify areas for improvement and optimize their advertising strategies. The results of this study suggest that a smart tool for advertisement analysis can provide valuable insights for businesses seeking to create effective advertising campaigns.

Keywords: NLP, AI, IT, language, marketing, analysis

Procedia PDF Downloads 52

Authors: Lakshmi N. Reddi, Akanksha Varma Sagi

Abstract:

Studies on biomimetics are largely developed, deriving inspiration from natural processes in our objective world to develop novel technologies. Recent studies are diverse in nature, making their categorization quite challenging. Based on an exhaustive survey, we developed categorizations based on either the essential elements of nature - air, water, land, fire, and space, or on form/shape, functionality, and process. Such diverse studies as aircraft wings inspired by bird wings, a self-cleaning coating inspired by a lotus petal, wetsuits inspired by beaver fur, and search algorithms inspired by arboreal ant path networks lend themselves to these categorizations. Our categorizations of biomimetic studies allowed us to define a different dimension of biomimetics. This new dimension is not restricted to inspiration from the objective world. It is based on the premise that the biological processes observed in the objective world find their reflections in our human bodies in a variety of ways. For example, the lungs provide the most efficient example for liquid-gas phase exchange, the heart exemplifies a very efficient pumping and circulatory system, and the kidneys epitomize the most effective cleaning system. The main focus of this paper is to bring out the magnificence of the cerebro-spinal system (CSS) insofar as it relates to our current computer architecture. In particular, the paper uses four key measures to analyze the differences between CSS and human- engineered computational systems. These are adaptability, sustainability, energy efficiency, and resilience. We found that the cerebrospinal system reveals some important challenges in the development and evolution of our current computer architectures. In particular, the myriad ways in which the CSS is integrated with other systems/processes (circulatory, respiration, etc) offer useful insights on how the human-engineered computational systems could be made more sustainable, energy-efficient, resilient, and adaptable. In our paper, we highlight the energy consumption differences between CSS and our current computational designs. Apart from the obvious differences in materials used between the two, the systemic nature of how CSS functions provides clues to enhance life-cycles of our current computational systems. The rapid formation and changes in the physiology of dendritic spines and their synaptic plasticity causing memory changes (ex., long-term potentiation and long-term depression) allowed us to formulate differences in the adaptability and resilience of CSS. In addition, the CSS is sustained by integrative functions of various organs, and its robustness comes from its interdependence with the circulatory system. The paper documents and analyzes quantifiable differences between the two in terms of the four measures. Our analyses point out the possibilities in the development of computational systems that are more adaptable, sustainable, energy efficient, and resilient. It concludes with the potential approaches for technological advancement through creation of more interconnected and interdependent systems to replicate the effective operation of cerebro-spinal system.

Keywords: cerebrospinal system, computer architecture, adaptability, sustainability, resilience, energy efficiency

Procedia PDF Downloads 55

Authors: Ali Kazemi

Abstract:

The digital evolution of financial services, while offering unprecedented convenience and accessibility, has also escalated the vulnerabilities to fraudulent activities. In this study, we introduce a distinct approach to real-time anomaly detection in financial transactions, aiming to fortify the defenses of banking and financial institutions against such threats. Utilizing unsupervised machine learning algorithms, specifically autoencoders and isolation forests, our research focuses on identifying irregular patterns indicative of fraud within transactional data, thus enabling immediate action to prevent financial loss. The data we used in this study included the monetary value of each transaction. This is a crucial feature as fraudulent transactions may have distributions of different amounts than legitimate ones, such as timestamps indicating when transactions occurred. Analyzing transactions' temporal patterns can reveal anomalies (e.g., unusual activity in the middle of the night). Also, the sector or category of the merchant where the transaction occurred, such as retail, groceries, online services, etc. Specific categories may be more prone to fraud. Moreover, the type of payment used (e.g., credit, debit, online payment systems). Different payment methods have varying risk levels associated with fraud. This dataset, anonymized to ensure privacy, reflects a wide array of transactions typical of a global banking institution, ranging from small-scale retail purchases to large wire transfers, embodying the diverse nature of potentially fraudulent activities. By engineering features that capture the essence of transactions, including normalized amounts and encoded categorical variables, we tailor our data to enhance model sensitivity to anomalies. The autoencoder model leverages its reconstruction error mechanism to flag transactions that deviate significantly from the learned normal pattern, while the isolation forest identifies anomalies based on their susceptibility to isolation from the dataset's majority. Our experimental results, validated through techniques such as k-fold cross-validation, are evaluated using precision, recall, and the F1 score alongside the area under the receiver operating characteristic (ROC) curve. Our models achieved an F1 score of 0.85 and a ROC AUC of 0.93, indicating high accuracy in detecting fraudulent transactions without excessive false positives. This study contributes to the academic discourse on financial fraud detection and provides a practical framework for banking institutions seeking to implement real-time anomaly detection systems. By demonstrating the effectiveness of unsupervised learning techniques in a real-world context, our research offers a pathway to significantly reduce the incidence of financial fraud, thereby enhancing the security and trustworthiness of digital financial services.

Keywords: anomaly detection, financial fraud, machine learning, autoencoders, isolation forest, transactional data analysis

Procedia PDF Downloads 17

Authors: Binder Hans

Abstract:

Cancer is no longer seen as solely a genetic disease where genetic defects such as mutations and copy number variations affect gene regulation and eventually lead to aberrant cell functioning which can be monitored by transcriptome analysis. It has become obvious that epigenetic alterations represent a further important layer of (de-)regulation of gene activity. For example, aberrant DNA methylation is a hallmark of many cancer types, and methylation patterns were successfully used to subtype cancer heterogeneity. Hence, unraveling the interplay between different omics levels such as genome, transcriptome and epigenome is inevitable for a mechanistic understanding of molecular deregulation causing complex diseases such as cancer. This objective requires powerful downstream integrative bioinformatics methods as an essential prerequisite to discover the whole genome mutational, transcriptome and epigenome landscapes of cancer specimen and to discover cancer genesis, progression and heterogeneity. Basic challenges and tasks arise ‘beyond sequencing’ because of the big size of the data, their complexity, the need to search for hidden structures in the data, for knowledge mining to discover biological function and also systems biology conceptual models to deduce developmental interrelations between different cancer states. These tasks are tightly related to cancer biology as an (epi-)genetic disease giving rise to aberrant genomic regulation under micro-environmental control and clonal evolution which leads to heterogeneous cellular states. Machine learning algorithms such as self organizing maps (SOM) represent one interesting option to tackle these bioinformatics tasks. The SOMmethod enables recognizing complex patterns in large-scale data generated by highthroughput omics technologies. It portrays molecular phenotypes by generating individualized, easy to interpret images of the data landscape in combination with comprehensive analysis options. Our image-based, reductionist machine learning methods provide one interesting perspective how to deal with massive data in the discovery of complex diseases, gliomas, melanomas and colon cancer on molecular level. As an important new challenge, we address the combined portrayal of different omics data such as genome-wide genomic, transcriptomic and methylomic ones. The integrative-omics portrayal approach is based on the joint training of the data and it provides separate personalized data portraits for each patient and data type which can be analyzed by visual inspection as one option. The new method enables an integrative genome-wide view on the omics data types and the underlying regulatory modes. It is applied to high and low-grade gliomas and to melanomas where it disentangles transversal and longitudinal molecular heterogeneity in terms of distinct molecular subtypes and progression paths with prognostic impact.

Keywords: integrative bioinformatics, machine learning, molecular mechanisms of cancer, gliomas and melanomas

Procedia PDF Downloads 119

Authors: Ehsan Javanmardemamgheisi, Javad Mehr, Jason Ali-Lavroff, Damien Holloway, Michael Davis

Abstract:

During the last decades, a growing interest in faster and more efficient waterborne transportation has led to the development of high-speed vessels for both commercial and military applications. To satisfy this global demand, a wide variety of arrangements of high-speed crafts have been proposed by designers. Among them, high-speed catamarans have proven themselves to be a suitable Roll-on/Roll-off configuration for carrying passengers and cargo due to widely spaced demi hulls, a wide deck zone, and a high ratio of deadweight to displacement. To improve passenger comfort and crew workability and enhance the operability and performance of high-speed catamarans, mitigating the severity of motions and structural loads using Ride Control Systems (RCS) is essential.In this paper, a set of towing tank tests was conducted on a 2.5 m scaled model of a 112 m Incat Tasmania high-speed catamaran in irregular head seas to investigate the effect of different ride control algorithms including linear and nonlinear versions of the heave control, pitch control, and local control on motion responses and passenger comfort of the full-scale ship. The RCS included a centre bow-fitted T-Foil and two transom-mounted stern tabs. All the experiments were conducted at the Australian Maritime College (AMC) towing tank at a model speed of 2.89 m/s (37 knots full scale), a modal period of 1.5 sec (10 sec full scale) and two significant wave heights of 60 mm and 90 mm, representing full-scale wave heights of 2.7 m and 4 m, respectively. Spectral analyses were performed using Welch’s power spectral density method on the vertical motion time records of the catamaran model to calculate heave and pitch Response Amplitude Operators (RAOs). Then, noting that passenger discomfort arises from vertical accelerations and that the vertical accelerations vary at different longitudinal locations within the passenger cabin due to the variations in amplitude and relative phase of the pitch and heave motions, the vertical accelerations were calculated at three longitudinal locations (LCG, T-Foil, and stern tabs). Finally, frequency-weighted Root Mean Square (RMS) vertical accelerations were calculated to estimate Motion Sickness Dose Value (MSDV) of the ship based on ISO 2631-recommendations. It was demonstrated that in small seas, implementing a nonlinear pitch control algorithm reduces the peak pitch motions by 41%, the vertical accelerations at the forward location by 46%, and motion sickness at the forward position by around 20% which provides great potential for further improvement in passenger comfort, crew workability, and operability of high-speed catamarans.

Keywords: high-speed catamarans, ride control system, response amplitude operators, vertical accelerations, motion sickness, irregular waves, towing tank tests.

Procedia PDF Downloads 46

Authors: Ruth Hegarty, Noel Connaughton

Abstract:

Sustainability reporting has become a priority for many global multinational companies. This is associated with ever-increasing expectations from key stakeholders for companies to be transparent about their strategies, activities and management with regard to sustainability issues. The Global Reporting Initiative (GRI) encourages reporters to only provide information on the issues that are really critical in order to achieve the organisation’s goals for sustainability and manage its impact on environment and society. A key challenge for most reporting organisations is how to identify relevant issues for sustainability reporting and prioritise those material issues in accordance with company and stakeholder needs. A recent study indicates that most of the largest companies listed on the world’s stock exchanges are failing to provide data on key sustainability indicators such as employee turnover, energy, greenhouse gas emissions (GHGs), injury rate, pay equity, waste and water. This paper takes an indepth look at the approaches used by a select number of international sustainability leader corporates to identify key sustainability issues. The research methodology involves performing a detailed analysis of the sustainability report content of up to 50 companies listed on the 2014 Dow Jones Sustainability Indices (DJSI). The most recent sustainability report content found on the GRI Sustainability Disclosure Database is then compared with 91 GRI Specific Standard Disclosures and a small number of GRI Standard Disclosures. Preliminary research indicates significant gaps in the information disclosed in corporate sustainability reports versus the indicator content specified in the GRI Content Index. The following outlines some of the key findings to date: Most companies made a partial disclosure with regard to the Economic indicators of climate change risks and infrastructure investments, but did not focus on the associated negative impacts. The top Environmental indicators disclosed were energy consumption and reductions, GHG emissions, water withdrawals, waste and compliance. The lowest rates of indicator disclosure included biodiversity, water discharge, mitigation of environmental impacts of products and services, transport, environmental investments, screening of new suppliers and supply chain impacts. The top Social indicators disclosed were new employee hires, rates of injury, freedom of association in operations, child labour and forced labour. Lesser disclosure rates were reported for employee training, composition of governance bodies and employees, political contributions, corruption and fines for non-compliance. The reporting on most other Social indicators was found to be poor. In addition, most companies give only a brief explanation on how material issues are defined, identified and ranked. Data on the identification of key stakeholders and the degree and nature of engagement for determining issues and their weightings is also lacking. Generally, little to no data is provided on the algorithms used to score an issue. Research indicates that most companies lack a rigorous and thorough methodology to systematically determine the material issues of sustainability reporting in accordance with company and stakeholder needs.

Keywords: identification of key stakeholders, material issues, sustainability reporting, transparency

Procedia PDF Downloads 277

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 136

Authors: Aleksander Ejsmont, Aleksandra Galarda, Joanna Goscianska

Abstract:

Smart porous carriers with defined structure and physicochemical properties are required for releasing the therapeutic drug with precise control of delivery time and location in the body. Due to their non-toxicity, ordered structure, chemical, and thermal stability, mesoporous carbons can be considered as modern carriers for active pharmaceutical ingredients (APIs) whose effectiveness needs frequent dosing algorithms. Such an API-carrier system, if programmed precisely, may stabilize the pharmaceutical and increase its dissolution leading to enhanced bioavailability. The substance conjugated with the material, through its prior adsorption, can later be successfully applied internally to the organism, as well as externally if the API release is feasible under these conditions. In the present study, ordered mesoporous carbons of different morphologies and structures, prepared by hard template method, were applied as carriers in the adsorption and controlled release of active pharmaceutical ingredients. In the first stage, the carbon materials were synthesized and functionalized with carboxylic groups by chemical oxidation using ammonium persulfate solution and then with amine groups. Materials obtained were thoroughly characterized with respect to morphology (scanning electron microscopy), structure (X-ray diffraction, transmission electron microscopy), characteristic functional groups (FT-IR spectroscopy), acid-base nature of surface groups (Boehm titration), parameters of the porous structure (low-temperature nitrogen adsorption) and thermal stability (TG analysis). This was followed by a series of tests of adsorption and release of paracetamol, benzocaine, and losartan potassium. Drug release experiments were performed in the simulated gastric fluid of pH 1.2 and phosphate buffer of pH 7.2 or 6.8 at 37.0 °C. The XRD patterns in the small-angle range and TEM images revealed that functionalization of mesoporous carbons with carboxylic or amine groups leads to the decreased ordering of their structure. Moreover, the modification caused a considerable reduction of the carbon-specific surface area and pore volume, but it simultaneously resulted in changing their acid-base properties. Mesoporous carbon materials exhibit different morphologies, which affect the host-guest interactions during the adsorption process of active pharmaceutical ingredients. All mesoporous carbons show high adsorption capacity towards drugs. The sorption capacity of materials is mainly affected by BET surface area and the structure/size matching between adsorbent and adsorbate. Selected APIs are linked to the surface of carbon materials mainly by hydrogen bonds, van der Waals forces, and electrostatic interactions. The release behavior of API is highly dependent on the physicochemical properties of mesoporous carbons. The release rate of APIs could be regulated by the introduction of functional groups and by changing the pH of the receptor medium. Acknowledgments—This research was supported by the National Science Centre, Poland (project SONATA-12 no: 2016/23/D/NZ7/01347).

Keywords: ordered mesoporous carbons, sorption capacity, drug delivery, carbon nanocarriers

Procedia PDF Downloads 148

Authors: L. Ereku, R. E. Mackay, A. Naveenathayalan, K. Ajayi, W. Balachandran

Abstract:

Over the past decade the increase of sexually transmitted infections (STIs) especially in the developing world due to high cost and lack of sufficient medical testing have given rise to the need for a rapid, low cost point of care medical diagnostic that is disposable and most significantly reproduces equivocal results achieved within centralised laboratories. This paper present the development of a disposable PDMS microfluidic cartridge incorporating blisters filled with reagents required for isothermal DNA amplification in clinical diagnostics and point-of-care testing. In view of circumventing the necessity for external complex microfluidic pumps, designing on-chip pressurised fluid reservoirs is embraced using finger actuation and blister storage. The fabrication of the blisters takes into consideration three proponents that include: material characteristics, fluid volume and structural design. Silicone rubber is the chosen material due to its good chemical stability, considerable tear resistance and moderate tension/compression strength. The case of fluid capacity and structural form go hand in hand as the reagent need for the experimental analysis determines the volume size of the blisters, whereas the structural form has to be designed to provide low compression stress when deformed for fluid expulsion. Furthermore, the top and bottom section of the blisters are embedded with miniature polar opposite magnets at a defined parallel distance. These magnets are needed to lock or restrain the blisters when fully compressed so as to prevent unneeded backflow as a result of elasticity. The integrated chip is bonded onto a large microscope glass slide (50mm x 75mm). Each part is manufactured using a 3D printed mould designed using Solidworks software. Die-casting is employed, using 3D printed moulds, to form the deformable blisters by forcing a proprietary liquid silicone rubber through the positive mould cavity. The set silicone rubber is removed from the cast and prefilled with liquid reagent and then sealed with a thin (0.3mm) burstable layer of recast silicone rubber. The main microfluidic cartridge is fabricated using classical soft lithographic techniques. The cartridge incorporates microchannel circuitry, mixing chamber, inlet port, outlet port, reaction chamber and waste chamber. Polydimethylsiloxane (PDMS, QSil 216) is mixed and degassed using a centrifuge (ratio 10:1) is then poured after the prefilled blisters are correctly positioned on the negative mould. Heat treatment of about 50C to 60C in the oven for about 3hours is needed to achieve curing. The latter chip production stage involves bonding the cured PDMS to the glass slide. A plasma coroner treater device BD20-AC (Electro-Technic Products Inc., US) is used to activate the PDMS and glass slide before they are both joined and adequately compressed together, then left in the oven over the night to ensure bonding. There are two blisters in total needed for experimentation; the first will be used as a wash buffer to remove any remaining cell debris and unbound DNA while the second will contain 100uL amplification reagents. This paper will present results of chemical cell lysis, extraction using a biopolymer paper membrane and isothermal amplification on a low-cost platform using the finger actuated blisters for reagent storage. The platform has been shown to detect 1x105 copies of Chlamydia trachomatis using Recombinase Polymerase Amplification (RPA).

Keywords: finger actuation, point of care, reagent storage, silicone blisters

Procedia PDF Downloads 341

Authors: Andreas Kerstan, Darren Robey, Wesam Alvan, David Troiani

Abstract:

Over the last 3.5 years, Quantum Cascade Lasers (QCL) technology has become increasingly important in infrared (IR) microscopy. The advantages over fourier transform infrared (FTIR) are that large areas of a few square centimeters can be measured in minutes and that the light intensive QCL makes it possible to obtain spectra with excellent S/N, even with just one scan. A firmly established solution of the laser direct infrared imaging (LDIR) 8700 is the analysis of microplastics. The presence of microplastics in the environment, drinking water, and food chains is gaining significant public interest. To study their presence, rapid and reliable characterization of microplastic particles is essential. Significant technical hurdles in microplastic analysis stem from the sheer number of particles to be analyzed in each sample. Total particle counts of several thousand are common in environmental samples, while well-treated bottled drinking water may contain relatively few. While visual microscopy has been used extensively, it is prone to operator error and bias and is limited to particles larger than 300 µm. As a result, vibrational spectroscopic techniques such as Raman and FTIR microscopy have become more popular, however, they are time-consuming. There is a demand for rapid and highly automated techniques to measure particle count size and provide high-quality polymer identification. Analysis directly on the filter that often forms the last stage in sample preparation is highly desirable as, by removing a sample preparation step it can both improve laboratory efficiency and decrease opportunities for error. Recent advances in infrared micro-spectroscopy combining a QCL with scanning optics have created a new paradigm, LDIR. It offers improved speed of analysis as well as high levels of automation. Its mode of operation, however, requires an IR reflective background, and this has, to date, limited the ability to perform direct “on-filter” analysis. This study explores the potential to combine the filter with an infrared reflective surface filter. By combining an IR reflective material or coating on a filter membrane with advanced image analysis and detection algorithms, it is demonstrated that such filters can indeed be used in this way. Vibrational spectroscopic techniques play a vital role in the investigation and understanding of microplastics in the environment and food chain. While vibrational spectroscopy is widely deployed, improvements and novel innovations in these techniques that can increase the speed of analysis and ease of use can provide pathways to higher testing rates and, hence, improved understanding of the impacts of microplastics in the environment. Due to its capability to measure large areas in minutes, its speed, degree of automation and excellent S/N, the LDIR could also implemented for various other samples like food adulteration, coatings, laminates, fabrics, textiles and tissues. This presentation will highlight a few of them and focus on the benefits of the LDIR vs classical techniques.

Keywords: QCL, automation, microplastics, tissues, infrared, speed

Procedia PDF Downloads 34

Authors: Dhanuj M. Gandikota

Abstract:

Sensor-derived three-dimensional (3D) point clouds of trees are invaluable in remote sensing analysis for the accurate measurement of key structural metrics, bio-inventory values, spatial planning/visualization, and ecological modeling. Machine learning (ML) holds the potential in addressing the restrictive tradeoffs in cost, spatial coverage, resolution, and information gain that exist in current point cloud sensing methods. Terrestrial laser scanning (TLS) remains the highest fidelity source of both canopy and below-canopy structural features, but usage is limited in both coverage and cost, requiring manual deployment to map out large, forested areas. While aerial laser scanning (ALS) remains a reliable avenue of LIDAR active remote sensing, ALS is also cost-restrictive in deployment methods. Space-borne photogrammetry from high-resolution satellite constellations is an avenue of passive remote sensing with promising viability in research for the accurate construction of vegetation 3-D point clouds. It provides both the lowest comparative cost and the largest spatial coverage across remote sensing methods. However, both space-borne photogrammetry and ALS demonstrate technical limitations in the capture of valuable below-canopy point cloud data. Looking to minimize these tradeoffs, we explored a class of powerful ML algorithms called Deep Learning (DL) that show promise in recent research on 3-D point cloud reconstruction and interpolation. Our research details the efficacy of applying these DL techniques to reconstruct accurate below-canopy point clouds from space-borne and aerial remote sensing through learned patterns of tree species fractal symmetry properties and the supplementation of locally sourced bio-inventory metrics. From our dataset, consisting of tree point clouds obtained from TLS, we deconstructed the point clouds of each tree into those that would be obtained through ALS and satellite photogrammetry of varying resolutions. We fed this ALS/satellite point cloud dataset, along with the simulated local bio-inventory metrics, into the DL point cloud reconstruction architectures to generate the full 3-D tree point clouds (the truth values are denoted by the full TLS tree point clouds containing the below-canopy information). Point cloud reconstruction accuracy was validated both through the measurement of error from the original TLS point clouds as well as the error of extraction of key structural metrics, such as crown base height, diameter above root crown, and leaf/wood volume. The results of this research additionally demonstrate the supplemental performance gain of using minimum locally sourced bio-inventory metric information as an input in ML systems to reach specified accuracy thresholds of tree point cloud reconstruction. This research provides insight into methods for the rapid, cost-effective, and accurate construction of below-canopy tree 3-D point clouds, as well as the supported potential of ML and DL to learn complex, unmodeled patterns of fractal tree growth symmetry.

Keywords: deep learning, machine learning, satellite, photogrammetry, aerial laser scanning, terrestrial laser scanning, point cloud, fractal symmetry

Procedia PDF Downloads 62

Authors: Mayank Gupta, Siba Prasad Samal, Vasu Kakkirala

Abstract:

The internet world and its priorities have changed considerably in the last decade. Browsing on smart phones has increased manifold and is set to explode much more. Users spent considerable time browsing different websites, that gives a great deal of insight into user’s preferences. Instead of plain information classifying different aspects of browsing like Bookmarks, History, and Download Manager into useful categories would improve and enhance the user’s experience. Most of the classification solutions are server side that involves maintaining server and other heavy resources. It has security constraints and maybe misses on contextual data during classification. On device, classification solves many such problems, but the challenge is to achieve accuracy on classification with resource constraints. This on device classification can be much more useful in personalization, reducing dependency on cloud connectivity and better privacy/security. This approach provides more relevant results as compared to current standalone solutions because it uses content rendered by browser which is customized by the content provider based on user’s profile. This paper proposes a Naive Bayes based lightweight classification engine targeted for a resource constraint devices. Our solution integrates with Web Browser that in turn triggers classification algorithm. Whenever a user browses a webpage, this solution extracts DOM Tree data from the browser’s rendering engine. This DOM data is a dynamic, contextual and secure data that can’t be replicated. This proposal extracts different features of the webpage that runs on an algorithm to classify into multiple categories. Naive Bayes based engine is chosen in this solution for its inherent advantages in using limited resources compared to other classification algorithms like Support Vector Machine, Neural Networks, etc. Naive Bayes classification requires small memory footprint and less computation suitable for smartphone environment. This solution has a feature to partition the model into multiple chunks that in turn will facilitate less usage of memory instead of loading a complete model. Classification of the webpages done through integrated engine is faster, more relevant and energy efficient than other standalone on device solution. This classification engine has been tested on Samsung Z3 Tizen hardware. The Engine is integrated into Tizen Browser that uses Chromium Rendering Engine. For this solution, extensive dataset is sourced from dmoztools.net and cleaned. This cleaned dataset has 227.5K webpages which are divided into 8 generic categories ('education', 'games', 'health', 'entertainment', 'news', 'shopping', 'sports', 'travel'). Our browser integrated solution has resulted in 15% less memory usage (due to partition method) and 24% less power consumption in comparison with standalone solution. This solution considered 70% of the dataset for training the data model and the rest 30% dataset for testing. An average accuracy of ~96.3% is achieved across the above mentioned 8 categories. This engine can be further extended for suggesting Dynamic tags and using the classification for differential uses cases to enhance browsing experience.

Keywords: chromium, lightweight engine, mobile computing, Naive Bayes, Tizen, web browser, webpage classification

Procedia PDF Downloads 136