Search results for: mean absolute deviation

Authors: Nervana Elbakary, Sami Ouanes, Sadaf Riaz, Oraib Abdallah, Islam Mahran, Noriya Al-Khuzaei, Yassin Eltorki

Abstract:

Major Depressive Disorder (MDD) requires therapeutic interventions during the initial month after being diagnosed for better disease outcomes. International guidelines recommend a duration of 4–12 weeks for an initial antidepressant (IAD) trial at an optimized dose to get a response. If depressive symptoms persist after this duration, guidelines recommend switching, augmenting, or combining strategies as the next step. Most patients with MDD in the mental health setting have been labeled incorrectly as treatment-resistant where in fact they have not been subjected to an adequate trial of guideline-recommended therapy. Premature discontinuation of IAD due to ineffectiveness can cause unfavorable consequences. Avoiding irrational practices such as subtherapeutic doses of IAD, premature switching between the ADs, and refraining from unjustified polypharmacy can help the disease to go into a remission phase We aimed to determine the prevalence and the patterns of strategies applied after an IAD was changed because of a suboptimal response as a primary outcome. Secondary outcomes included the median survival time on IAD before any change; and the predictors that were associated with IAD change. This was a retrospective cross- sectional study conducted in Mental Health Services in Qatar. A dataset between January 1, 2018, and December 31, 2019, was extracted from the electronic health records. Inclusion and exclusion criteria were defined and applied. The sample size was calculated to be at least 379 patients. Descriptive statistics were reported as frequencies and percentages, in addition, to mean and standard deviation. The median time of IAD to any change strategy was calculated using survival analysis. Associated predictors were examined using two unadjusted and adjusted cox regression models. A total of 487 patients met the inclusion criteria of the study. The average age for participants was 39.1 ± 12.3 years. Patients with first experience MDD episode 255 (52%) constituted a major part of our sample comparing to the relapse group 206(42%). About 431 (88%) of the patients had an occurrence of IAD change to any strategy before end of the study. Almost half of the sample (212 (49%); 95% CI [44–53%]) had their IAD changed less than or equal to 30 days. Switching was consistently more common than combination or augmentation at any timepoint. The median time to IAD change was 43 days with 95% CI [33.2–52.7]. Five independent variables (age, bothersome side effects, un-optimization of the dose before any change, comorbid anxiety, first onset episode) were significantly associated with the likelihood of IAD change in the unadjusted analysis. The factors statistically associated with higher hazard of IAD change in the adjusted analysis were: younger age, un-optimization of the IAD dose before any change, and comorbid anxiety. Because almost half of the patients in this study changed their IAD as early as within the first month, efforts to avoid treatment failure are needed to ensure patient-treatment targets are met. The findings of this study can have direct clinical guidance for health care professionals since an optimized, evidence-based use of AD medication can improve the clinical outcomes of patients with MDD; and also, to identify high-risk factors that could worsen the survival time on IAD such as young age and comorbid anxiety

Keywords: initial antidepressant, dose optimization, major depressive disorder, comorbid anxiety, combination, augmentation, switching, premature discontinuation

Procedia PDF Downloads 118

Authors: Mohammad Shajid Rahman, Tarik Kaya, Edgar Matida

Abstract:

Electronic cigarettes, also known as e-cigarettes, may have become a tool to improve smoking cessation due to their ability to provide nicotine at a selected rate. Unlike traditional cigarettes, which produce toxic elements from tobacco combustion, e-cigarettes generate aerosols by heating a liquid solution (commonly a mixture of propylene glycol, vegetable glycerin, nicotine and some flavoring agents). However, caution still needs to be taken when using e-cigarettes due to the presence of addictive nicotine and some harmful substances produced from the heating process. Particle size distribution (PSD) and associated velocities generated by e-cigarettes have significant influence on aerosol deposition in different regions of human respiratory tracts. On another note, low actuation power is beneficial in aerosol generating devices since it exhibits a reduced emission of toxic chemicals. In case of e-cigarettes, lower heating powers can be considered as powers lower than 10 W compared to a wide range of powers (0.6 to 70.0 W) studied in literature. Due to the importance regarding inhalation risk reduction, deeper understanding of particle size characteristics of e-cigarettes demands thorough investigation. However, comprehensive study on PSD and velocities of e-cigarettes with a standard testing condition at relatively low heating powers is still lacking. The present study aims to measure particle number count and size distribution of undiluted aerosols of a latest fourth-generation e-cigarette at low powers, within 6.5 W using real-time particle counter (time-of-flight method). Also, temporal and spatial evolution of particle size and velocity distribution of aerosol jets are examined using phase Doppler anemometry (PDA) technique. To the authors’ best knowledge, application of PDA in e-cigarette aerosol measurement is rarely reported. In the present study, preliminary results about particle number count of undiluted aerosols measured by time-of-flight method depicted that an increase of heating power from 3.5 W to 6.5 W resulted in an enhanced asymmetricity in PSD, deviating from log-normal distribution. This can be considered as an artifact of rapid vaporization, condensation and coagulation processes on aerosols caused by higher heating power. A novel mathematical expression, combining exponential, Gaussian and polynomial (EGP) distributions, was proposed to describe asymmetric PSD successfully. The value of count median aerodynamic diameter and geometric standard deviation laid within a range of about 0.67 μm to 0.73 μm, and 1.32 to 1.43, respectively while the power varied from 3.5 W to 6.5 W. Laser Doppler velocimetry (LDV) and PDA measurement suggested a typical centerline streamwise mean velocity decay of aerosol jet along with a reduction of particle sizes. In the final submission, a thorough literature review, detailed description of experimental procedure and discussion of the results will be provided. Particle size and turbulent characteristics of aerosol jets will be further examined, analyzing arithmetic mean diameter, volumetric mean diameter, volume-based mean diameter, streamwise mean velocity and turbulence intensity. The present study has potential implications in PSD simulation and validation of aerosol dosimetry model, leading to improving related aerosol generating devices.

Keywords: E-cigarette aerosol, laser doppler velocimetry, particle size distribution, particle velocity, phase Doppler anemometry

Procedia PDF Downloads 17

Authors: Adiba Matin, Daniel Cabrera, Javiera Bellolio, Jasmine Stewart, Dana Gerberi (librarian), Nathan Cummins, Fernanda Bellolio

Abstract:

OBJECTIVES: Artificial intelligence (AI) tools are becoming more prevalent in healthcare settings, particularly for diagnostic and therapeutic recommendations, with an expected surge in the incoming years. The bedside use of this technology for clinicians opens the possibility of disagreements between the recommendations from AI algorithms and clinicians’ judgment. There is a paucity in the literature analyzing nature and possible outcomes of these potential conflicts, particularly related to ethical considerations. The goal of this scoping review is to identify, analyze and classify current themes and potential strategies addressing ethical conflicts originating from the conflict between AI and human recommendations. METHODS: A protocol was written prior to the initiation of the study. Relevant literature was searched by a medical librarian for the terms of artificial intelligence, healthcare and liability, ethics, or conflict. Search was run in 2021 in Ovid Cochrane Central Register of Controlled Trials, Embase, Medline, IEEE Xplore, Scopus, and Web of Science Core Collection. Articles describing the role of AI in healthcare that mentioned conflict between humans and AI were included in the primary search. Two investigators working independently and in duplicate screened titles and abstracts and reviewed full-text of potentially eligible studies. Data was abstracted into tables and reported by themes. We followed methodological guidelines for Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR). RESULTS: Of 6846 titles and abstracts, 225 full texts were selected, and 48 articles included in this review. 23 articles were included as original research and review papers. 25 were included as editorials and commentaries with similar themes. There was a lack of consensus in the included articles on who would be held liable for mistakes incurred by following AI recommendations. It appears that there is a dichotomy of the perceived ethical consequences depending on if the negative outcome is a result of a human versus AI conflict or secondary to a deviation from standard of care. Themes identified included transparency versus opacity of recommendations, data bias, liability of outcomes, regulatory framework, and the overall scope of artificial intelligence in healthcare. A relevant issue identified was the concern by clinicians of the “black box” nature of these recommendations and the ability to judge appropriateness of AI guidance. CONCLUSION AI clinical tools are being rapidly developed and adopted, and the use of this technology will create conflicts between AI algorithms and healthcare workers with various outcomes. In turn, these conflicts may have legal, and ethical considerations. There is limited consensus about the focus of ethical and liability for outcomes originated from disagreements. This scoping review identified the importance of framing the problem in terms of conflict between standard of care or not, and informed by the themes of transparency/opacity, data bias, legal liability, absent regulatory frameworks and understanding of the technology. Finally, limited recommendations to mitigate ethical conflicts between AI and humans have been identified. Further work is necessary in this field.

Keywords: ethics, artificial intelligence, emergency medicine, review

Procedia PDF Downloads 69

Authors: Ye Xue, Zhenhua Deng

Abstract:

Objectives: Facial soft tissue thickness (FSTT) data could be obtained from CT scans by measuring the face-to-skull distances at sparsely distributed anatomical landmarks by manually located on face and skull. However, automated measurement using 3D facial and skull models by dense points using open-source software has become a viable option due to the development of computed assisted imaging technologies. By utilizing dense FSTT information, it becomes feasible to generate plausible automated facial approximations. Therefore, establishing a comprehensive and detailed, densely calculated FSTT database is crucial in enhancing the accuracy of facial approximation. Materials and methods: This study utilized head CT scans from 250 Chinese adults of Han ethnicity, with 170 participants originally born and residing in northern China and 80 participants in southern China. The age of the participants ranged from 14 to 82 years, and all samples were divided into five non-overlapping age groups. Additionally, samples were also divided into three categories based on BMI information. The 3D Slicer software was utilized to segment bone and soft tissue based on different Hounsfield Unit (HU) thresholds, and surface models of the face and skull were reconstructed for all samples from CT data. Following procedures were performed unsing MeshLab, including converting the face models into hollowed cropped surface models amd automatically measuring the Hausdorff Distance (referred to as FSTT) between the skull and face models. Hausdorff point clouds were colorized based on depth value and exported as PLY files. A histogram of the depth distributions could be view and subdivided into smaller increments. All PLY files were visualized of Hausdorff distance value of each vertex. Basic descriptive statistics (i.e., mean, maximum, minimum and standard deviation etc.) and distribution of FSTT were analysis considering the sex, age, BMI and birthplace. Statistical methods employed included Multiple Regression Analysis, ANOVA, principal component analysis (PCA). Results: The distribution of FSTT is mainly influenced by BMI and sex, as further supported by the results of the PCA analysis. Additionally, FSTT values exceeding 30mm were found to be more sensitive to sex. Birthplace-related differences were observed in regions such as the forehead, orbital, mandibular, and zygoma. Specifically, there are distribution variances in the depth range of 20-30mm, particularly in the mandibular region. Northern males exhibit thinner FSTT in the frontal region of the forehead compared to southern males, while females shows fewer distribution differences between the northern and southern, except for the zygoma region. The observed distribution variance in the orbital region could be attributed to differences in orbital size and shape. Discussion: This study provides a database of Chinese individuals distribution of FSTT and suggested opening source tool shows fine function for FSTT measurement. By incorporating birthplace as an influential factor in the distribution of FSTT, a greater level of detail can be achieved in facial approximation.

Keywords: forensic anthropology, forensic imaging, cranial facial reconstruction, facial soft tissue thickness, CT, open-source tool

Procedia PDF Downloads 36

Authors: Divya Palaniappan

Abstract:

Early Childhood assessment tools must measure the quality and the appropriateness of a curriculum with respect to culture and age of the children. Preschool assessment tools lack psychometric properties and were developed to measure only few areas of development such as specific skills in music, art and adaptive behavior. Existing preschool assessment tools in India are predominantly informal and are fraught with judgmental bias of observers. The World of Discovery TM curriculum focuses on accelerating the physical, cognitive, language, social and emotional development of pre-schoolers in India through various activities. The curriculum caters to every child irrespective of their dominant intelligence as per Gardner’s Theory of Multiple Intelligence which concluded "even students as young as four years old present quite distinctive sets and configurations of intelligences". The curriculum introduces a new theme every week where, concepts are explained through various activities so that children with different dominant intelligences could understand it. For example: The ‘Insects’ theme is explained through rhymes, craft and counting corner, and hence children with one of these dominant intelligences: Musical, bodily-kinesthetic and logical-mathematical could grasp the concept. The child’s progress is evaluated using an assessment tool that measures a cluster of inter-dependent developmental areas: physical, cognitive, language, social and emotional development, which for the first time renders a multi-domain approach. The assessment tool is a 5-point rating scale that measures these Developmental aspects: Cognitive, Language, Physical, Social and Emotional. Each activity strengthens one or more of the developmental aspects. During cognitive corner, the child’s perceptual reasoning, pre-math abilities, hand-eye co-ordination and fine motor skills could be observed and evaluated. The tool differs from traditional assessment methodologies by providing a framework that allows teachers to assess a child’s continuous development with respect to specific activities in real time objectively. A pilot study of the tool was done with a sample data of 100 children in the age group 2.5 to 3.5 years. The data was collected over a period of 3 months across 10 centers in Chennai, India, scored by the class teacher once a week. The teachers were trained by psychologists on age-appropriate developmental milestones to minimize observer’s bias. The norms were calculated from the mean and standard deviation of the observed data. The results indicated high internal consistency among parameters and that cognitive development improved with physical development. A significant positive relationship between physical and cognitive development has been observed among children in a study conducted by Sibley and Etnier. In Children, the ‘Comprehension’ ability was found to be greater than ‘Reasoning’ and pre-math abilities as indicated by the preoperational stage of Piaget’s theory of cognitive development. The average scores of various parameters obtained through the tool corroborates the psychological theories on child development, offering strong face validity. The study provides a comprehensive mechanism to assess a child’s development and differentiate high performers from the rest. Based on the average scores, the difficulty level of activities could be increased or decreased to nurture the development of pre-schoolers and also appropriate teaching methodologies could be devised.

Keywords: child development, early childhood assessment, early childhood curriculum, quantitative assessment of preschool curriculum

Procedia PDF Downloads 338

Authors: Sonia Butalia, Huong Luu, Alexis Guigue, Karen J. B. Martins, Khanh Vu, Scott W. Klarenbach

Abstract:

Obesity is associated with significant personal impacts on health and has a substantial economic burden on payers due to increased healthcare use. A contemporary estimate of the healthcare costs associated with obesity at the population level are lacking. This evidence may provide further rationale for weight management strategies. Methods: Adults who underwent a medical procedure between 2012 and 2019 in Alberta, Canada were categorized into the investigational cohort (had body mass index [BMI]-defined class 2 or 3 obesity based on a procedure-associated code) and the control cohort (did not have the BMI procedure-associated code); those who had bariatric surgery were excluded. Characteristics were presented and healthcare costs ($CDN) determined over a 1-year observation period (2019/2020). Logistic regression and a generalized linear model with log link and gamma distribution were used to assess total healthcare costs (comprised of hospitalizations, emergency department visits, ambulatory care visits, physician visits, and outpatient prescription drugs); potential confounders included age, sex, region of residence, and whether the medical procedure was performed within 6-months before the observation period in the partial adjustment, and also the type of procedure performed, socioeconomic status, Charlson Comorbidity Index (CCI), and seven obesity-related health conditions in the full adjustment. Cost ratios and estimated cost differences with 95% confidence intervals (CI) were reported; incremental cost differences within the adjusted models represent referent cases. Results: The investigational cohort (n=220,190) was older (mean age: 53 standard deviation [SD]±17 vs 50 SD±17 years), had more females (71% vs 57%), lived in rural areas to a greater extent (20% vs 14%), experienced a higher overall burden of disease (CCI: 0.6 SD±1.3 vs 0.3 SD±0.9), and were less socioeconomically well-off (material/social deprivation was lower [14%/14%] in the most well-off quintile vs 20%/19%) compared with controls (n=1,955,548). Unadjusted total healthcare costs were estimated to be 1.77-times (95% CI: 1.76, 1.78) higher in the investigational versus control cohort; each healthcare resource contributed to the higher cost ratio. After adjusting for potential confounders, the total healthcare cost ratio decreased, but remained higher in the investigational versus control cohort (partial adjustment: 1.57 [95% CI: 1.57, 1.58]; full adjustment: 1.21 [95% CI: 1.20, 1.21]); each healthcare resource contributed to the higher cost ratio. Among urban-dwelling 50-year old females who previously had non-operative procedures, no procedures performed within 6-months before the observation period, a social deprivation index score of 3, a CCI score of 0.32, and no history of select obesity-related health conditions, the predicted cost difference between those living with and without obesity was $386 (95% CI: $376, $397). Conclusions: If these findings hold for the Canadian population, one would expect an estimated additional $3.0 billion per year in healthcare costs nationally related to BMI-defined obesity (based on an adult obesity rate of 26% and an estimated annual incremental cost of $386 [21%]); incremental costs are higher when obesity-related health conditions are not adjusted for. Results of this study provide additional rationale for investment in interventions that are effective in preventing and treating obesity and its complications.

Keywords: administrative data, body mass index-defined obesity, healthcare cost, real world evidence

Procedia PDF Downloads 81

Authors: Marian Mihalik, Kornel Csach, Martin Kovalik, Matúš Mihalik, Martina Kubovčíková, Maria Zentková, Martin Vavra, Vladimír Girman, Jaroslav Briančin, Marija Perovic, Marija Boškovic, Magdalena Fitta, Robert Pelka

Abstract:

Current nanomaterials for use in biomedicine are based mainly on iron oxides and on present knowledge on magnetic nanostructures. Manganites can represent another material which can be used optionally. Manganites and their unique electronic properties have been extensively studied in the last decades not only due to fundamental interest but to possible applications of colossal magnetoresistance, magnetocaloric effect, and ferroelectric properties. It was found that the oxygen-reduction reaction on perovskite oxide is intimately connected with metal ion e.g., orbital occupation. The effect of oxygen deviation from the stoichiometric composition on crystal structure was studied very carefully by many authors on LaMnO₃. Depending on oxygen content, the crystal structure changes from orthorhombic one to rhombohedric for oxygen content 3.1. In the case of hole-doped manganites, the change from the orthorhombic crystal structure, which is typical for La1-xCaxMnO3 based manganites, to the rhombohedric crystal structure (La1-xMxMnO₃ where M = K, Ag, and Sr based materials) results in an enormous increase of the Curie temperature. In our paper, we study the effect of oxygen content on crystal structure, thermal, and magnetic properties (including magnetocaloric effect) of La1-xAgxMnO₃nano particle system. The content of oxygen in samples was tuned by heat treatment in different thermal regimes and in various environment (air, oxygen, argon). Water nanosuspensions based on La0.80Ag0.15MnO₃ magnetic particles with the Curie temperature of about 43oC were prepared by two different approaches. First, by using a laboratory circulation mill for milling of powder in the presence of sodium dodecyl sulphate (SDS) and subsequent centrifugation. Second nanosuspension was prepared using an agate bowl, etching in citric acid and HNO3, ultrasound homogeniser, centrifugation, and dextran 40 kDA or 15 kDA as surfactant. Electrostatic stabilisation obtained by the first approach did not offer long term kinetic and aggregation colloidal stability and was unable to compensate for attractive forces between particles under a magnetic field. By the second approach, we prepared suspension oversaturated by dextran 40 kDA for steric stabilisation, with evidence of the presence of superparamagnetic behaviour. Low concentration of nanoparticles and not ideal coverage of nanoparticles impacting the stability of ferrofluids was the disadvantage of this approach. Strong steric stabilisation was observable at alcaic conditions under pH = ~10. Application of dextran 15 kDA leads to relatively stable ferrofluid with pH around physiological conditions, but desegregation of powder by HNO₃ was not effective enough, and the average size of fragments was to large of about 150 nm, and we did not see any signature of superparamagnetic behaviour. The prepared ferrofluids were characterised by scanning and transition microscope method, thermogravimetry, magnetization, and AC susceptibility measurements. Specific Absorption Rate measurements were undertaken on powder as well on ferrofluids in order to estimate the potential application of La₀.₈₀Ag₀.₁₅MnO₃ magnetic particles based ferrofluid for hyperthermia. Our complex study contains an investigation of biocompatibility and potential biohazard of this material.

Keywords: manganites, magnetic nanoparticles, oxygen content, magnetic phase transition, magnetocaloric effect, ferrofluid, hyperthermia

Procedia PDF Downloads 65

Authors: Jing Jin

Abstract:

The incorporation of artificial intelligence (AI) and machine learning (ML) in aircraft manufacturing and aerospace supply chains leads to the generation of a substantial amount of data among various tiers of suppliers and OEMs. Identifying the high-quality information challenges decision-makers. The application of AI/ML models necessitates access to 'high-quality' information to yield desired outputs. However, the process of information sharing introduces complexities, including distortion through various communication channels and biases introduced by both human and AI entities. This phenomenon significantly influences the quality of information, impacting decision-makers engaged in configuring supply chain systems. Traditionally, distorted information is categorized as 'low-quality'; however, this study challenges this perception, positing that distorted information, contributing to stakeholder goals, can be deemed high-quality within supply chains. The main aim of this study is to identify and evaluate the dimensions of information quality crucial to the UK aerospace supply chain. Guided by a central research question, "What information quality dimensions are considered when defining information quality in the UK aerospace supply chain?" the study delves into the intricate dynamics of information quality in the aerospace industry. Additionally, the research explores the nuanced impact of information distortion on stakeholders' decision-making processes, addressing the question, "How does the information distortion phenomenon influence stakeholders’ decisions regarding information quality in the UK aerospace supply chain system?" This study employs deductive methodologies rooted in positivism, utilizing a cross-sectional approach and a mono-quantitative method -a questionnaire survey. Data is systematically collected from diverse tiers of supply chain stakeholders, encompassing end-customers, OEMs, Tier 0.5, Tier 1, and Tier 2 suppliers. Employing robust statistical data analysis methods, including mean values, mode values, standard deviation, one-way analysis of variance (ANOVA), and Pearson’s correlation analysis, the study interprets and extracts meaningful insights from the gathered data. Initial analyses challenge conventional notions, revealing that information distortion positively influences the definition of information quality, disrupting the established perception of distorted information as inherently low-quality. Further exploration through correlation analysis unveils the varied perspectives of different stakeholder tiers on the impact of information distortion on specific information quality dimensions. For instance, Tier 2 suppliers demonstrate strong positive correlations between information distortion and dimensions like access security, accuracy, interpretability, and timeliness. Conversely, Tier 1 suppliers emphasise strong negative influences on the security of accessing information and negligible impact on information timeliness. Tier 0.5 suppliers showcase very strong positive correlations with dimensions like conciseness and completeness, while OEMs exhibit limited interest in considering information distortion within the supply chain. Introducing social network analysis (SNA) provides a structural understanding of the relationships between information distortion and quality dimensions. The moderately high density of ‘information distortion-by-information quality’ underscores the interconnected nature of these factors. In conclusion, this study offers a nuanced exploration of information quality dimensions in the UK aerospace supply chain, highlighting the significance of individual perspectives across different tiers. The positive influence of information distortion challenges prevailing assumptions, fostering a more nuanced understanding of information's role in the Industry 4.0 landscape.

Keywords: information distortion, information quality, supply chain configuration, UK aerospace industry

Procedia PDF Downloads 28

Authors: Ali Kazemi

Abstract:

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

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

Procedia PDF Downloads 25

Authors: Chung-Ming Lo, Chung-Chien Lee

Abstract:

In many countries, the lifetime prevalence of shoulder pain is up to 70%. In America, the health care system spends 7 billion per year about the healthy issues of shoulder pain. With respect to the origin, up to 70% of shoulder pain is attributed to rotator cuff lesions This study proposed a computer-aided diagnosis (CAD) system to assist radiologists classifying rotator cuff lesions with less operator dependence. Quantitative features were extracted from the shoulder ultrasound images acquired using an ALOKA alpha-6 US scanner (Hitachi-Aloka Medical, Tokyo, Japan) with linear array probe (scan width: 36mm) ranging from 5 to 13 MHz. During examination, the postures of the examined patients are standard sitting position and are followed by the regular routine. After acquisition, the shoulder US images were drawn out from the scanner and stored as 8-bit images with pixel value ranging from 0 to 255. Upon the sonographic appearance, the boundary of each lesion was delineated by a physician to indicate the specific pattern for analysis. The three lesion categories for classification were composed of 20 cases of tendon inflammation, 18 cases of calcific tendonitis, and 18 cases of supraspinatus tear. For each lesion, second-order statistics were quantified in the feature extraction. The second-order statistics were the texture features describing the correlations between adjacent pixels in a lesion. Because echogenicity patterns were expressed via grey-scale. The grey-scale co-occurrence matrixes with four angles of adjacent pixels were used. The texture metrics included the mean and standard deviation of energy, entropy, correlation, inverse different moment, inertia, cluster shade, cluster prominence, and Haralick correlation. Then, the quantitative features were combined in a multinomial logistic regression classifier to generate a prediction model of rotator cuff lesions. Multinomial logistic regression classifier is widely used in the classification of more than two categories such as the three lesion types used in this study. In the classifier, backward elimination was used to select a feature subset which is the most relevant. They were selected from the trained classifier with the lowest error rate. Leave-one-out cross-validation was used to evaluate the performance of the classifier. Each case was left out of the total cases and used to test the trained result by the remaining cases. According to the physician’s assessment, the performance of the proposed CAD system was shown by the accuracy. As a result, the proposed system achieved an accuracy of 86%. A CAD system based on the statistical texture features to interpret echogenicity values in shoulder musculoskeletal ultrasound was established to generate a prediction model for rotator cuff lesions. Clinically, it is difficult to distinguish some kinds of rotator cuff lesions, especially partial-thickness tear of rotator cuff. The shoulder orthopaedic surgeon and musculoskeletal radiologist reported greater diagnostic test accuracy than general radiologist or ultrasonographers based on the available literature. Consequently, the proposed CAD system which was developed according to the experiment of the shoulder orthopaedic surgeon can provide reliable suggestions to general radiologists or ultrasonographers. More quantitative features related to the specific patterns of different lesion types would be investigated in the further study to improve the prediction.

Keywords: shoulder ultrasound, rotator cuff lesions, texture, computer-aided diagnosis

Procedia PDF Downloads 257

Authors: Sopio Totibadze

Abstract:

Although the legal framework of Georgia reflects the main principles of gender equality and is in line with the international situation (UNDP, 2018), Georgia remains a male-dominated society. This means that men prevail in many areas of social, economic, and political life, which frequently gives women a subordinate status in society and the family (UN women). According to the latest study, “violence against women and girls in Georgia is also recognized as a public problem, and it is necessary to focus on it” (UN women). Moreover, the Public Defender's report on the protection of human rights in Georgia (2019) reveals that “in the last five years, 151 women were killed in Georgia due to gender and family violence”. Sadly, these statistics have increased significantly since that time. The issue was acutely reflected in the document published by the Organization for Security and Cooperation in Europe, “Gender Hate Crime” (March 10, 2021). “Unfortunately, the rates of femicide ..... are still high in the country, and distrust of law enforcement agencies often makes such cases invisible, which requires special attention from the state.” More precisely, the cited document considers that there are frequent cases of crimes based on gender-based oppression in Georgia, which pose a threat not only to women but also to people of any gender whose desires and aspirations do not correspond to the gender norms and roles prevailing in society. According to the study, this type of crime has a “significant and lasting impact on the victim(s) and also undermines the safety and cohesion of society and gender equality”. It is well-known that language is often used as a tool for gender oppression (Rusieshvili-Cartledge and Dolidze, 2021; Totibadze, 2021). Therefore, feminist and gender studies in linguistics ultimately serve to represent the problem, reflect on it, and propose ways to solve it. Together with technical advancement in communication, a new form of discrimination has arisen- hate language against women in electronic media discourse. Due to the nature of social media and the internet, messages containing hate language can spread in seconds and reach millions of people. However, only a few know about the detrimental effects they may have on the addressee and society. This paper aims to analyse the hateful comments directed at women on various media platforms to determine (1) the linguistic strategies used while attacking women and (2) the reasons why women may fall victim to this type of hate language. The data have been collected over six months, and overall, 500 comments will be examined for the paper. Qualitative and quantitative analysis was chosen for the methodology of the study. The comments posted on various media platforms, including social media posts, articles, or pictures, have been selected manually due to several reasons, the most important being the problem of identifying hate speech as it can disguise itself in different ways- humour, memes, etc. The comments on the articles, posts, pictures, and videos selected for sociolinguistic analysis depict a woman, a taboo topic, or a scandalous event centred on a woman that triggered a lot of hatred and hate language towards the person to whom the post/article was dedicated. The study has revealed that a woman can become a victim of hatred directed at them if they do something considered to be a deviation from a societal norm, namely, get a divorce, be sexually active, be vocal about feministic values, and talk about taboos. Interestingly, people who utilize hate language are not only men trying to “normalize” the prejudiced patriarchal values but also women who are equally active in bringing down a "strong" woman. The paper also aims to raise awareness about the hate language directed at women, as being knowledgeable about the issue at hand is the first step to tackling it.

Keywords: femicide, hate language, media discourse, sociolinguistics

Procedia PDF Downloads 59

Authors: Teesta Dey

Abstract:

Integrated Transport development with proper traffic management leads to sustainable growth of any urban sphere. Appropriate mass transport planning is essential for the populous cities in third world countries like India. The exponential growth of motor vehicles with unplanned road network is now the common feature of major urban centres in India. Kolkata, the third largest mega city in India, is not an exception of it. The imbalance between demand and supply of unplanned transport services in this city is manifested in the high economic and environmental costs borne by the associated society. With the passage of time, the growth and extent of passenger demand for rapid urban transport has outstripped proper infrastructural planning and causes severe transport problems in the overall urban realm. Hence Kolkata stands out in the world as one of the most crisis-ridden metropolises. The urban transport crisis of this city involves severe traffic congestion, the disparity in mass transport services on changing peripheral land uses, route overlapping, lowering of travel speed and faulty implementation of governmental plans as mostly induced by rapid growth of private vehicles on limited road space with huge carbon footprint. Therefore the paper will critically analyze the extant road network pattern for improving regional connectivity and accessibility, assess the degree of congestion, identify the deviation from demand and supply balance and finally evaluate the emerging alternate transport options as promoted by the government. For this purpose, linear, nodal and spatial transport network have been assessed based on certain selected indices viz. Road Degree, Traffic Volume, Shimbel Index, Direct Bus Connectivity, Average Travel and Waiting Tine Indices, Route Variety, Service Frequency, Bus Intensity, Concentration Analysis, Delay Rate, Quality of Traffic Transmission, Lane Length Duration Index and Modal Mix. Total 20 Traffic Intersection Points (TIPs) have been selected for the measurement of nodal accessibility. Critical Congestion Zones (CCZs) are delineated based on one km buffer zones of each TIP for congestion pattern analysis. A total of 480 bus routes are assessed for identifying the deficiency in network planning. Apart from bus services, the combined effects of other mass and para transit modes, containing metro rail, auto, cab and ferry services, are also analyzed. Based on systematic random sampling method, a total of 1500 daily urban passengers’ perceptions were studied for checking the ground realities. The outcome of this research identifies the spatial disparity among the 15 boroughs of the city with severe route overlapping and congestion problem. North and Central Kolkata-based mass transport services exceed the transport strength of south and peripheral Kolkata. Faulty infrastructural condition, service inadequacy, economic loss and workers’ inefficiency are the most dominant reasons behind the defective mass transport network plan. Hence there is an urgent need to revive the extant road based mass transport system of this city by implementing a holistic management approach by upgrading traffic infrastructure, designing new roads, better cooperation among different mass transport agencies, better coordination of transport and changing land use policies, large increase in funding and finally general passengers’ awareness.

Keywords: carbon footprint, critical congestion zones, direct bus connectivity, integrated transport development

Procedia PDF Downloads 254

Authors: F. Varga, Z. Liber, J. Jakše, A. Turudić, Z. Šatović, I. Radosavljević, N. Jeran, M. Grdiša

Abstract:

Dalmatian pyrethrum (Tanacetum cinerariifolium (Trevir.) Sch. Bip.; Asteraceae), a source of the commercially dominant plant insecticide pyrethrin, is a species endemic to the eastern Adriatic. Genetic diversity of T. cinerariifolium was previously studied using amplified fragment length polymorphism (AFLP) markers. However, microsatellite markers (single sequence repeats - SSRs) are more informative because they are codominant, highly polymorphic, locus-specific, and more reproducible, and thus are most often used to assess the genetic diversity of plant species. Dalmatian pyrethrum is an outcrossing diploid (2n = 18) whose large genome size and high repeatability have prevented the success of the traditional approach to SSR markers development. The advent of next-generation sequencing combined with the specifically developed method recently enabled the development of, to the author's best knowledge, the first set of SSRs for genomic characterization of Dalmatian pyrethrum, which is essential from the perspective of plant genetic resources conservation. To evaluate the effectiveness of the developed SSR markers in genetic differentiation of Dalmatian pyrethrum populations, a preliminary genetic diversity study was conducted on 30 individuals from three geographically distinct natural populations in Croatia (northern Adriatic island of Mali Lošinj, southern Adriatic island of Čiovo, and Mount Biokovo) based on 12 SSR loci. Analysis of molecular variance (AMOVA) by randomization test with 10,000 permutations was performed in Arlequin 3.5. The average number of alleles per locus, observed and expected heterozygosity, probability of deviations from Hardy-Weinberg equilibrium, and inbreeding coefficient was calculated using GENEPOP 4.4. Genetic distance based on the proportion of common alleles (DPSA) was calculated using MICROSAT. Cluster analysis using the neighbor-joining method with 1,000 bootstraps was performed with PHYLIP to generate a dendrogram. The results of the AMOVA analysis showed that the total SSR diversity was 23% within and 77% between the three populations. A slight deviation from Hardy-Weinberg equilibrium was observed in the Mali Lošinj population. Allele richness ranged from 2.92 to 3.92, with the highest number of private alleles observed in the Mali Lošinj population (17). The average observed DPSA between 30 individuals was 0.557. The highest DPSA (0.875) was observed between several pairs of Dalmatian pyrethrum individuals from the Mali Lošinj and Mt. Biokovo populations, and the lowest between two individuals from the Čiovo population. Neighbor-joining trees, based on DPSA, grouped individuals into clusters according to their population affiliation. The separation of Mt. Biokovo clade was supported (bootstrap value 58%), which is consistent with the previous study on AFLP markers, where isolated populations from Mt. Biokovo differed from the rest of the populations. The developed SSR markers are an effective tool for assessing the genetic diversity and structure of natural Dalmatian pyrethrum populations. These preliminary results are encouraging for a future comprehensive study with a larger sample size across the species' range. Combined with the biochemical data, these highly informative markers could help identify potential genotypes of interest for future development of breeding lines and cultivars that are both resistant to environmental stress and high in pyrethrins. Acknowledgment: This work has been supported by the Croatian Science Foundation under the project ‘Genetic background of Dalmatian pyrethrum (Tanacetum cinerariifolium /Trevir./ Sch. Bip.) insecticidal potential’- (PyrDiv) (IP-06-2016-9034) and by project KK.01.1.1.01.0005, Biodiversity and Molecular Plant Breeding, at the Centre of Excellence for Biodiversity and Molecular Plant Breeding (CoE CroP-BioDiv), Zagreb, Croatia.

Keywords: Asteraceae, genetic diversity, genomic SSRs, NGS, pyrethrum, Tanacetum cinerariifolium

Procedia PDF Downloads 91