Search results for: measurement accuracy

Authors: Mostafa Shahriari, Sergio Rojas, David Pardo, Angel Rodriguez- Rozas, Shaaban A. Bakr, Victor M. Calo, Ignacio Muga

Abstract:

Logging-While Drilling (LWD) is a technique to record down-hole logging measurements while drilling the well. Nowadays, LWD devices (e.g., nuclear, sonic, resistivity) are mostly used commercially for geo-steering applications. Modern borehole resistivity tools are able to measure all components of the magnetic field by incorporating tilted coils. The depth of investigation of LWD tools is limited compared to the thickness of the geological layers. Thus, it is a common practice to approximate the Earth’s subsurface with a sequence of 1D models. For a 1D model, we can reduce the dimensionality of the problem using a Hankel transform. We can solve the resulting system of ordinary differential equations (ODEs) either (a) analytically, which results in a so-called semi-analytic method after performing a numerical inverse Hankel transform, or (b) numerically. Semi-analytic methods are used by the industry due to their high performance. However, they have major limitations, namely: -The analytical solution of the aforementioned system of ODEs exists only for piecewise constant resistivity distributions. For arbitrary resistivity distributions, the solution of the system of ODEs is unknown by today’s knowledge. -In geo-steering, we need to solve inverse problems with respect to the inversion variables (e.g., the constant resistivity value of each layer and bed boundary positions) using a gradient-based inversion method. Thus, we need to compute the corresponding derivatives. However, the analytical derivatives of cross-bedded formation and the analytical derivatives with respect to the bed boundary positions have not been published to the best of our knowledge. The main contribution of this work is to overcome the aforementioned limitations of semi-analytic methods by solving each 1D model (associated with each Hankel mode) using an efficient multi-scale finite element method. The main idea is to divide our computations into two parts: (a) offline computations, which are independent of the tool positions and we precompute only once and use them for all logging positions, and (b) online computations, which depend upon the logging position. With the above method, (a) we can consider arbitrary resistivity distributions along the 1D model, and (b) we can easily and rapidly compute the derivatives with respect to any inversion variable at a negligible additional cost by using an adjoint state formulation. Although the proposed method is slower than semi-analytic methods, its computational efficiency is still high. In the presentation, we shall derive the mathematical variational formulation, describe the proposed multi-scale finite element method, and verify the accuracy and efficiency of our method by performing a wide range of numerical experiments and comparing the numerical solutions to semi-analytic ones when the latest are available.

Keywords: logging-While-Drilling, resistivity measurements, multi-scale finite elements, Hankel transform

Procedia PDF Downloads 387

Authors: Vangmayee V. Subban, Suzan Deelan. Pinto, Somashekara Haralakatta Shivananjappa, Shwetha Prabhu, Jayashree S. Bhat

Abstract:

Introduction and Need: During early years of schooling, the instruction in the schools mainly focus on children’s word decoding abilities. However, the skilled readers should master all the components of reading such as word decoding, reading fluency and comprehension. Nevertheless, the relationship between each component during the process of learning to read is less clear. The studies conducted in alphabetical languages have mixed opinion on relative contribution of word decoding and reading fluency on reading comprehension. However, the scenarios in alphasyllabary languages are unexplored. Aim and Objectives: The aim of the study was to explore the role of word decoding, reading fluency on reading comprehension abilities in children learning to read Kannada between the age ranges of 5.6 to 8.6 years. Method: In this cross sectional study, a total of 60 typically developing children, 20 each from Grade I, Grade II, Grade III maintaining equal gender ratio between the age range of 5.6 to 6.6 years, 6.7 to 7.6 years and 7.7 to 8.6 years respectively were selected from Kannada medium schools. The reading fluency and reading comprehension abilities of the children were assessed using Grade level passages selected from the Kannada text book of children core curriculum. All the passages consist of five questions to assess reading comprehension. The pseudoword decoding skills were assessed using 40 pseudowords with varying syllable length and their Akshara composition. Pseudowords are formed by interchanging the syllables within the meaningful word while maintaining the phonotactic constraints of Kannada language. The assessment material was subjected to content validation and reliability measures before collecting the data on the study samples. The data were collected individually, and reading fluency was assessed for words correctly read per minute. Pseudoword decoding was scored for the accuracy of reading. Results: The descriptive statistics indicated that the mean pseudoword reading, reading comprehension, words accurately read per minute increased with the Grades. The performance of Grade III children found to be higher, Grade I lower and Grade II remained intermediate of Grade III and Grade I. The trend indicated that reading skills gradually improve with the Grades. Pearson’s correlation co-efficient showed moderate and highly significant (p=0.00) positive co-relation between the variables, indicating the interdependency of all the three components required for reading. The hierarchical regression analysis revealed 37% variance in reading comprehension was explained by pseudoword decoding and was highly significant. Subsequent entry of reading fluency measure, there was no significant change in R-square and was only change 3%. Therefore, pseudoword-decoding evolved as a single most significant predictor of reading comprehension during early Grades of reading acquisition. Conclusion: The present study concludes that the pseudoword decoding skills contribute significantly to reading comprehension than reading fluency during initial years of schooling in children learning to read Kannada language.

Keywords: alphasyllabary, pseudo-word decoding, reading comprehension, reading fluency

Procedia PDF Downloads 266

Authors: Thomas Q. Pan, Anika Basu, Chamith S. Rajapakse

Abstract:

Machine learning requires data that is categorized into features that models train on. This topic is important to the field of sports medicine due to the many tools it provides to physicians such as diagnosis support and risk assessment. Physician note that healthcare professionals take are usually unclean and not suitable for model training. The objective of this study was to develop and evaluate an advanced approach for extracting key features from sports medicine data without the need for extensive model training or data labeling. An LLM (Large Language Model) was given a narrative (Physician’s Notes) and prompted to extract four features (details about the patient). The narrative was found in a datasheet that contained six columns: Case Number, Validation Age, Validation Gender, Validation Diagnosis, Validation Body Part, and Narrative. The validation columns represent the accurate responses that the LLM attempts to output. With the given narrative, the LLM would output its response and extract the age, gender, diagnosis, and injured body part with each category taking up one line. The output would then be cleaned, matched, and added to new columns containing the extracted responses. Five ways of checking the accuracy were used: unclear count, substring comparison, LLM comparison, LLM re-check, and hand-evaluation. The unclear count essentially represented the extractions the LLM missed. This can be also understood as the recall score ([total - false negatives] over total). The rest of these correspond to the precision score ([total - false positives] over total). Substring comparison evaluated the validation (X) and extracted (Y) columns’ likeness by checking if X’s results were a substring of Y's findings and vice versa. LLM comparison directly asked an LLM if the X and Y’s results were similar. LLM Re-check prompted the LLM to see if the extracted results can be found in the narrative. Lastly, A selection of 1,000 random narratives was also selected and hand-evaluated to give an estimate of how well the LLM-based feature extraction model performed. With a selection of 10,000 narratives, the LLM-based approach had a recall score of roughly 98%. However, the precision scores of the substring comparison and LLM comparison models were around 72% and 76% respectively. The reason for these low figures is due to the minute differences between answers. For example, the ‘chest’ is a part of the ‘upper trunk’ however, these models cannot detect that. On the other hand, the LLM re-check and subset of hand-tested narratives showed a precision score of 96% and 95%. If this subset is used to extrapolate the possible outcome of the whole 10,000 narratives, the LLM-based approach would be strong in both precision and recall. These results indicated that an LLM-based feature extraction model could be a useful way for medical data in sports to be collected and analyzed by machine learning models. Wide use of this method could potentially increase the availability of data thus improving machine learning algorithms and supporting doctors with more enhanced tools.

Keywords: AI, LLM, ML, sports

Procedia PDF Downloads 18

Authors: Akbar Gharbali, Ali Abbasian Ardekani, Afshin Mohammadi

Abstract:

Introduction: Thyroid nodules have an incidence of 33-68% in the general population. More than 5-15% of these nodules are malignant. Early detection and treatment of thyroid nodules increase the cure rate and provide optimal treatment. Between the medical imaging methods, Ultrasound is the chosen imaging technique for assessment of thyroid nodules. The confirming of the diagnosis usually demands repeated fine-needle aspiration biopsy (FNAB). So, current management has morbidity and non-zero mortality. Objective: To explore diagnostic potential of automatic texture analysis (TA) methods in differentiation benign and malignant thyroid nodules by ultrasound imaging in order to help for reliable diagnosis and monitoring of the thyroid nodules in their early stages with no need biopsy. Material and Methods: The thyroid US image database consists of 70 patients (26 benign and 44 malignant) which were reported by Radiologist and proven by the biopsy. Two slices per patient were loaded in Mazda Software version 4.6 for automatic texture analysis. Regions of interests (ROIs) were defined within the abnormal part of the thyroid nodules ultrasound images. Gray levels within an ROI normalized according to three normalization schemes: N1: default or original gray levels, N2: +/- 3 Sigma or dynamic intensity limited to µ+/- 3σ, and N3: present intensity limited to 1% - 99%. Up to 270 multiscale texture features parameters per ROIs per each normalization schemes were computed from well-known statistical methods employed in Mazda software. From the statistical point of view, all calculated texture features parameters are not useful for texture analysis. So, the features based on maximum Fisher coefficient and the minimum probability of classification error and average correlation coefficients (POE+ACC) eliminated to 10 best and most effective features per normalization schemes. We analyze this feature under two standardization states (standard (S) and non-standard (NS)) with Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Non-Linear Discriminant Analysis (NDA). The 1NN classifier was performed to distinguish between benign and malignant tumors. The confusion matrix and Receiver operating characteristic (ROC) curve analysis were used for the formulation of more reliable criteria of the performance of employed texture analysis methods. Results: The results demonstrated the influence of the normalization schemes and reduction methods on the effectiveness of the obtained features as a descriptor on discrimination power and classification results. The selected subset features under 1%-99% normalization, POE+ACC reduction and NDA texture analysis yielded a high discrimination performance with the area under the ROC curve (Az) of 0.9722, in distinguishing Benign from Malignant Thyroid Nodules which correspond to sensitivity of 94.45%, specificity of 100%, and accuracy of 97.14%. Conclusions: Our results indicate computer-aided diagnosis is a reliable method, and can provide useful information to help radiologists in the detection and classification of benign and malignant thyroid nodules.

Keywords: ultrasound imaging, thyroid nodules, computer aided diagnosis, texture analysis, PCA, LDA, NDA

Procedia PDF Downloads 281

Authors: Thi Thi Zin, Pyke Tin, Ikuo Kobayashi, Yoichiro Horii

Abstract:

Today dairy farm experts and farmers have well recognized the importance of dairy cow Body Condition Score (BCS) since these scores can be used to optimize milk production, managing feeding system and as an indicator for abnormality in health even can be utilized to manage for having healthy calving times and process. In tradition, BCS measures are done by animal experts or trained technicians based on visual observations focusing on pin bones, pin, thurl and hook area, tail heads shapes, hook angles and short and long ribs. Since the traditional technique is very manual and subjective, the results can lead to different scores as well as not cost effective. Thus this paper proposes an algebraic geometric imaging approach for an automatic dairy cow BCS system. The proposed system consists of three functional modules. In the first module, significant landmarks or anatomical points from the cow image region are automatically extracted by using image processing techniques. To be specific, there are 23 anatomical points in the regions of ribs, hook bones, pin bone, thurl and tail head. These points are extracted by using block region based vertical and horizontal histogram methods. According to animal experts, the body condition scores depend mainly on the shape structure these regions. Therefore the second module will investigate some algebraic and geometric properties of the extracted anatomical points. Specifically, the second order polynomial regression is employed to a subset of anatomical points to produce the regression coefficients which are to be utilized as a part of feature vector in scoring process. In addition, the angles at thurl, pin, tail head and hook bone area are computed to extend the feature vector. Finally, in the third module, the extracted feature vectors are trained by using Markov Classification process to assign BCS for individual cows. Then the assigned BCS are revised by using multiple regression method to produce the final BCS score for dairy cows. In order to confirm the validity of proposed method, a monitoring video camera is set up at the milk rotary parlor to take top view images of cows. The proposed method extracts the key anatomical points and the corresponding feature vectors for each individual cows. Then the multiple regression calculator and Markov Chain Classification process are utilized to produce the estimated body condition score for each cow. The experimental results tested on 100 dairy cows from self-collected dataset and public bench mark dataset show very promising with accuracy of 98%.

Keywords: algebraic geometric imaging approach, body condition score, Markov classification, polynomial regression

Procedia PDF Downloads 163

Authors: Navid Kaboudi, Ali Shayanfar

Abstract:

Introduction: Feeding infants with safe milk from the beginning of their life is an important issue. Drugs which are used by mothers can affect the composition of milk in a way that is not only unsuitable, but also toxic for infants. Consuming permeable drugs during that sensitive period by mother could lead to serious side effects to the infant. Due to the ethical restrictions of drug testing on humans, especially women, during their lactation period, computational approaches based on structural parameters could be useful. The aim of this study is to develop mechanistic models to predict the M/P ratio of drugs during breastfeeding period based on their structural descriptors. Methods: Two hundred and nine different chemicals with their M/P ratio were used in this study. All drugs were categorized into two groups based on their M/P value as Malone classification: 1: Drugs with M/P>1, which are considered as high risk 2: Drugs with M/P>1, which are considered as low risk Thirty eight chemical descriptors were calculated by ACD/labs 6.00 and Data warrior software in order to assess the penetration during breastfeeding period. Later on, four specific models based on the number of hydrogen bond acceptors, polar surface area, total surface area, and number of acidic oxygen were established for the prediction. The mentioned descriptors can predict the penetration with an acceptable accuracy. For the remaining compounds (N= 147, 158, 160, and 174 for models 1 to 4, respectively) of each model binary regression with SPSS 21 was done in order to give us a model to predict the penetration ratio of compounds. Only structural descriptors with p-value<0.1 remained in the final model. Results and discussion: Four different models based on the number of hydrogen bond acceptors, polar surface area, and total surface area were obtained in order to predict the penetration of drugs into human milk during breastfeeding period About 3-4% of milk consists of lipids, and the amount of lipid after parturition increases. Lipid soluble drugs diffuse alongside with fats from plasma to mammary glands. lipophilicity plays a vital role in predicting the penetration class of drugs during lactation period. It was shown in the logistic regression models that compounds with number of hydrogen bond acceptors, PSA and TSA above 5, 90 and 25 respectively, are less permeable to milk because they are less soluble in the amount of fats in milk. The pH of milk is acidic and due to that, basic compounds tend to be concentrated in milk than plasma while acidic compounds may consist lower concentrations in milk than plasma. Conclusion: In this study, we developed four regression-based models to predict the penetration class of drugs during the lactation period. The obtained models can lead to a higher speed in drug development process, saving energy, and costs. Milk/plasma ratio assessment of drugs requires multiple steps of animal testing, which has its own ethical issues. QSAR modeling could help scientist to reduce the amount of animal testing, and our models are also eligible to do that.

Keywords: logistic regression, breastfeeding, descriptors, penetration

Procedia PDF Downloads 76

Authors: W. Staiano, S. Marcora

Abstract:

Introduction: It has been proposed that acute negative effect of mental fatigue (MF) could potentially become a training stimulus for the brain (Brain endurance training (BET)) to adapt and improve its ability to attenuate MF states during sport competitions. Purpose: The aim of this study was to test the efficacy of 6 weeks of BET on cognitive and cycling tests in a group of well-trained subjects. We hypothesised that combination of BET and standard physical training (SPT) would increase cognitive capacity and cycling performance by reducing rating of perceived exertion (RPE) and increase resilience to fatigue more than SPT alone. Methods: In a randomized controlled trial design, 26 well trained participants, after a familiarization session, cycled to exhaustion (TTE) at 80% peak power output (PPO) and, after 90 min rest, at 65% PPO, before and after random allocation to a 6 week BET or active placebo control. Cognitive performance was measured using 30 min of STROOP coloured task performed before cycling performance. During the training, BET group performed a series of cognitive tasks for a total of 30 sessions (5 sessions per week) with duration increasing from 30 to 60 min per session. Placebo engaged in a breathing relaxation training. Both groups were monitored for physical training and were naïve to the purpose of the study. Physiological and perceptual parameters of heart rate, lactate (LA) and RPE were recorded during cycling performances, while subjective workload (NASA TLX scale) was measured during the training. Results: Group (BET vs. Placebo) x Test (Pre-test vs. Post-test) mixed model ANOVA’s revealed significant interaction for performance at 80% PPO (p = .038) or 65% PPO (p = .011). In both tests, groups improved their TTE performance; however, BET group improved significantly more compared to placebo. No significant differences were found for heart rate during the TTE cycling tests. LA did not change significantly at rest in both groups. However, at completion of 65% TTE, it was significantly higher (p = 0.043) in the placebo condition compared to BET. RPE measured at ISO-time in BET was significantly lower (80% PPO, p = 0.041; 65% PPO p= 0.021) compared to placebo. Cognitive results in the STROOP task showed that reaction time in both groups decreased at post-test. However, BET decreased significantly (p = 0.01) more compared to placebo despite no differences accuracy. During training sessions, participants in the BET showed, through NASA TLX questionnaires, constantly significantly higher (p < 0.01) mental demand rates compared to placebo. No significant differences were found for physical demand. Conclusion: The results of this study provide evidences that combining BET and SPT seems to be more effective than SPT alone in increasing cognitive and cycling performance in well trained endurance participants. The cognitive overload produced during the 6-week training of BET can induce a reduction in perception of effort at a specific power, and thus improving cycling performance. Moreover, it provides evidence that including neurocognitive interventions will benefit athletes by increasing their mental resilience, without affecting their physical training load and routine.

Keywords: cognitive training, perception of effort, endurance performance, neuro-performance

Procedia PDF Downloads 124

Authors: L. Sudbury-Riley, P. Hunter-Jones, L. Menzies, M. Pyrah, H. Knight

Abstract:

Just as manufacturing firms aim for zero defects, service providers strive to avoid service failures where customer expectations are not met. However, because services comprise unique human interactions, service failures are almost inevitable. Consequently, firms focus on service recovery strategies to fix problems and retain their customers for the future. Because a hospice offers care to terminally ill patients, it may not get the opportunity to correct a service failure. This situation makes the identification of what hospice users really need and want, and to ascertain perceptions of the hospice’s service delivery from the user’s perspective, even more important than for other service providers. A well-documented and fundamental barrier to improving end-of-life care is a lack of service quality measurement tools that capture the experiences of user’s from their own perspective. In palliative care, many quantitative measures are used and these focus on issues such as how quickly patients are assessed, whether they receive information leaflets, whether a discussion about their emotional needs is documented, and so on. Consequently, quality of service from the user’s perspective is overlooked. The current study was designed to overcome these limitations by adapting service blueprinting - never before used in the hospice sector - in order to undertake a ‘deep-dive’ to examine the impact of hospice services upon different users. Service blueprinting is a customer-focused approach for service innovation and improvement, where the ‘onstage’ visible service user and provider interactions must be supported by the ‘backstage’ employee actions and support processes. The study was conducted in conjunction with East Cheshire Hospice in England. The Hospice provides specialist palliative care for patients with progressive life-limiting illnesses, offering services to patients, carers and families via inpatient and outpatient units. Using service blueprinting to identify every service touchpoint, in-depth qualitative interviews with 38 in-patients, outpatients, visitors and bereaved families enabled a ‘deep-dive’ to uncover perceptions of the whole service experience among these diverse users. Interviews were recorded and transcribed, and thematic analysis of over 104,000 words of data revealed many excellent aspects of Hospice service. Staff frequently exceed people’s expectations. Striking gratifying comparisons to hospitals emerged. The Hospice makes people feel safe. Nevertheless, the technique uncovered many areas for improvement, including serendipity of referrals processes, the need for better communications with external agencies, improvements amid the daunting arrival and admissions process, a desperate need for more depression counselling, clarity of communication pertaining to actual end of life, and shortcomings in systems dealing with bereaved families. The study reveals that the adapted service blueprinting tool has major advantages of alternative quantitative evaluation techniques, including uncovering the complex nature of service user’s experiences in health-care service systems, highlighting more fully the interconnected configurations within the system and making greater sense of the impact of the service upon different service users. Unlike other tools, this in-depth examination reveals areas for improvement, many of which have already been implemented by the Hospice. The technique has potential to improve experiences of palliative and end-of-life care among patients and their families.

Keywords: hospices, end-of-life-care, service blueprinting, service delivery

Procedia PDF Downloads 196

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 151

Authors: Diego Santibañez Oyarce, Fernanda Bravo Cornejo, Camilo Cerda Sarabia, Belén Díaz Díaz, Esteban Gómez Terán, Hugo Osses Prado, Raúl Caulier-Cisterna, Jorge Vergara-Quezada, Ana Moya-Beltrán

Abstract:

The advent of high-throughput sequencing technologies has revolutionized genomics, generating vast amounts of genetic data that challenge traditional bioinformatics methods. Machine learning addresses these challenges by leveraging computational power to identify patterns and extract information from large datasets. However, biological sequence data, being symbolic and non-numeric, must be converted into numerical formats for machine learning algorithms to process effectively. So far, some encoding methods, such as one-hot encoding or k-mers, have been explored. This work proposes additional approaches for encoding DNA sequences in order to compare them with existing techniques and determine if they can provide improvements or if current methods offer superior results. Data from the 16S rRNA gene, a universal marker, was used to analyze eight bacterial groups that are significant in the pulmonary environment and have clinical implications. The bacterial genes included in this analysis are Prevotella, Abiotrophia, Acidovorax, Streptococcus, Neisseria, Veillonella, Mycobacterium, and Megasphaera. These data were downloaded from the NCBI database in Genbank file format, followed by a syntactic analysis to selectively extract relevant information from each file. For data encoding, a sequence normalization process was carried out as the first step. From approximately 22,000 initial data points, a subset was generated for testing purposes. Specifically, 55 sequences from each bacterial group met the length criteria, resulting in an initial sample of approximately 440 sequences. The sequences were encoded using different methods, including one-hot encoding, k-mers, Fourier transform, and Wavelet transform. Various machine learning algorithms, such as support vector machines, random forests, and neural networks, were trained to evaluate these encoding methods. The performance of these models was assessed using multiple metrics, including the confusion matrix, ROC curve, and F1 Score, providing a comprehensive evaluation of their classification capabilities. The results show that accuracies between encoding methods vary by up to approximately 15%, with the Fourier transform obtaining the best results for the evaluated machine learning algorithms. These findings, supported by the detailed analysis using the confusion matrix, ROC curve, and F1 Score, provide valuable insights into the effectiveness of different encoding methods and machine learning algorithms for genomic data analysis, potentially improving the accuracy and efficiency of bacterial classification and related genomic studies.

Keywords: DNA encoding, machine learning, Fourier transform, Fourier transformation

Procedia PDF Downloads 31

Authors: E. Saeedian, M. Shakerian, A. Zarif Sanayei, Z. Rakeb, F. N. Alizadeh, S. Sarshough, S. Sina

Abstract:

Radiological protection for plants and animals is an area of regulatory importance. Acute doses of 0.1 Gy/d (10 rad/d) or below are highly unlikely to produce permanent, measurable negative effects on populations or communities of plants or animals. The advancement of radio diagnostics for domestic animals, particularly dogs and cats, has gained popularity in veterinary medicine. As pets are considered to be members of the family worldwide, they are entitled to the same care and protection. It is important to have a system of radiological protection for nonhuman organisms that complies with the focus on human health as outlined in ICRP publication 19. The present study attempts to assess surface-skin entrance doses in small pets undergoing abdominal radio diagnostic procedures utilizing a direct measurements technique with a thermoluminescent dosimeter. These measurements allow the determination of the entrance skin dose (ESD) by calculating the amount of radiation absorbed by the skin during exposure. A group of Thirty TLD-100 dosimeters produced by Harshaw Company, each with repeatability greater than 95% and calibration using ¹³⁷Cs gamma source, were utilized to measure doses to ten small pets, including cats and dogs in the radiological department in a veterinary clinic in Shiraz, Iran. Radiological procedures were performed using a portable imaging unit (Philips Super M100, Philips Medical System, Germany) to acquire images of the abdomen; ten exams of abdomen images of different pets were monitored, measuring the thicknesses of the two projections (lateral and ventrodorsal) and the distance of the X-ray source from the surface of each pet during the exams. A group of two dosimeters was used for each pet which has been stacked on their skin on the abdomen region. The outcome of this study involved medical procedures with the same kVp, mAs, and nearly identical positions for different diagnostic X-ray procedures executed over a period of two months. The result showed the mean ESD value was 260.34±50.06 µGy due to the approximate size of pets. Based on the results, the ESD value is associated with animal size, and larger animals have higher values. If a procedure doesn't require repetition, the dose can be optimized. For smaller animals, the main challenge in veterinary radiology is the dose increase caused by repetitions, which is most noticeable in the ventrodorsal position due to the difficulty in immobilizing the animal. Animals are an area of regulatory importance. Acute doses of 0.1 Gy/d (10 rad/d) or below are highly unlikely to produce permanent, measurable negative effects on populations or communities of plants or animals. The advancement of radio diagnostics for domestic animals, particularly dogs and cats, has gained popularity in veterinary medicine. As pets are considered to be members of the family worldwide, they are entitled to the same care and protection. It is important to have a system of radiological protection for nonhuman organisms that complies with the focus on human health as outlined in ICRP publication 19. The present study attempts to assess surface-skin entrance doses in small pets undergoing abdominal radio diagnostic procedures utilizing direct measurements.

Keywords: direct dose measuring, dosimetry, radiation protection, veterinary medicine

Procedia PDF Downloads 75

Authors: Baha Eddine Aissou, Aichouche Belhadj Aissa

Abstract:

Light detection and ranging (LiDAR) is an active remote sensing technology used for several applications. Airborne LiDAR is becoming an important technology for the acquisition of a highly accurate dense point cloud. A classification of airborne laser scanning (ALS) point cloud is a very important task that still remains a real challenge for many scientists. Support vector machine (SVM) is one of the most used statistical learning algorithms based on kernels. SVM is a non-parametric method, and it is recommended to be used in cases where the data distribution cannot be well modeled by a standard parametric probability density function. Using a kernel, it performs a robust non-linear classification of samples. Often, the data are rarely linearly separable. SVMs are able to map the data into a higher-dimensional space to become linearly separable, which allows performing all the computations in the original space. This is one of the main reasons that SVMs are well suited for high-dimensional classification problems. Only a few training samples, called support vectors, are required. SVM has also shown its potential to cope with uncertainty in data caused by noise and fluctuation, and it is computationally efficient as compared to several other methods. Such properties are particularly suited for remote sensing classification problems and explain their recent adoption. In this poster, the SVM classification of ALS LiDAR data is proposed. Firstly, connected component analysis is applied for clustering the point cloud. Secondly, the resulting clusters are incorporated in the SVM classifier. Radial basic function (RFB) kernel is used due to the few numbers of parameters (C and γ) that needs to be chosen, which decreases the computation time. In order to optimize the classification rates, the parameters selection is explored. It consists to find the parameters (C and γ) leading to the best overall accuracy using grid search and 5-fold cross-validation. The exploited LiDAR point cloud is provided by the German Society for Photogrammetry, Remote Sensing, and Geoinformation. The ALS data used is characterized by a low density (4-6 points/m²) and is covering an urban area located in residential parts of the city Vaihingen in southern Germany. The class ground and three other classes belonging to roof superstructures are considered, i.e., a total of 4 classes. The training and test sets are selected randomly several times. The obtained results demonstrated that a parameters selection can orient the selection in a restricted interval of (C and γ) that can be further explored but does not systematically lead to the optimal rates. The SVM classifier with hyper-parameters is compared with the most used classifiers in literature for LiDAR data, random forest, AdaBoost, and decision tree. The comparison showed the superiority of the SVM classifier using parameters selection for LiDAR data compared to other classifiers.

Keywords: classification, airborne LiDAR, parameters selection, support vector machine

Procedia PDF Downloads 151

Authors: Shiyi He, Yan Xia, Xiaoping Ouyang, Liang Chen, Zhongbing Zhang, Jinlu Ruan

Abstract:

As the key system of the spacecraft, various propelling system have been developing rapidly, including ion thrust, laser thrust, solar sail and other micro-thrusters. However, there still are some shortages in these systems. The ion thruster requires the high-voltage or magnetic field to accelerate, resulting in extra system, heavy quantity and large volume. The laser thrust now is mostly ground-based and providing pulse thrust, restraint by the station distribution and the capacity of laser. The thrust direction of solar sail is limited to its relative position with the Sun, so it is hard to propel toward the Sun or adjust in the shadow.In this paper, a novel nuclear thruster based on alpha decay and spontaneous fission is proposed and the principle of this radiation-thrust with alpha particle has been expounded. Radioactive materials with different released energy, such as 210Po with 5.4MeV and 238Pu with 5.29MeV, attached to a metal film will provides various thrust among 0.02-5uN/cm2. With this repulsive force, radiation is able to be a power source. With the advantages of low system quantity, high accuracy and long active time, the radiation thrust is promising in the field of space debris removal, orbit control of nano-satellite array and deep space exploration. To do further study, a formula lead to the amplitude and direction of thrust by the released energy and decay coefficient is set up. With the initial formula, the alpha radiation elements with the half life period longer than a hundred days are calculated and listed. As the alpha particles emit continuously, the residual charge in metal film grows and affects the emitting energy distribution of alpha particles. With the residual charge or extra electromagnetic field, the emitting of alpha particles performs differently and is analyzed in this paper. Furthermore, three more complex situations are discussed. Radiation element generating alpha particles with several energies in different intensity, mixture of various radiation elements, and cascaded alpha decay are studied respectively. In combined way, it is more efficient and flexible to adjust the thrust amplitude. The propelling model of the spontaneous fission is similar with the one of alpha decay, which has a more complex angular distribution. A new quasi-sphere space propelling system based on the radiation-thrust has been introduced, as well as the collecting and processing system of excess charge and reaction heat. The energy and spatial angular distribution of emitting alpha particles on unit area and certain propelling system have been studied. As the alpha particles are easily losing energy and self-absorb, the distribution is not the simple stacking of each nuclide. With the change of the amplitude and angel of radiation-thrust, orbital variation strategy on space debris removal is shown and optimized.

Keywords: alpha decay, angular distribution, emitting energy, orbital variation, radiation-thruster

Procedia PDF Downloads 214

Authors: Z. Zaman Asam, M. Ajmal, R. Saeed, H. Miraj, M. Muhammad Ahtisham, B. Hameed, A. -Sattar Nizami

Abstract:

In Pakistan, environmental degradation and consequent human health deterioration has rapidly accelerated in the past decade due to solid waste mismanagement. As the situation worsens with time, establishment of proper waste management practices is urgently needed especially in semi urban and rural areas of Pakistan. This study uses a concept of Waste Bank, which involves a transfer station for collection of sorted waste fractions and its delivery to the targeted market such as recycling industries, biogas plants, composting facilities etc. The management efficiency and effectiveness of Waste Bank depend strongly on the proficient sorting and collection of solid waste fractions at household level. However, the social attitude towards such a solution in semi urban/rural areas of Pakistan demands certain prerequisites to make it workable. Considering these factors the objectives of this study are to: [A] Obtain reliable data about quantity and characteristics of generated waste to define feasibility of business and design factors, such as required storage area, retention time, transportation frequency of the system etc. [B] Analyze the effects of various social factors on waste generation to foresee future projections. [C] Quantify the improvement in waste sorting efficiency after awareness campaign. We selected Gujrat city of Central Punjab province of Pakistan as it is semi urban adjoined by rural areas. A total of 60 houses (20 from each of the three selected colonies), belonging to different social status were selected. Awareness sessions about waste segregation were given through brochures and individual lectures in each selected household. Sampling of waste, that households had attempted to sort, was then carried out in the three colored bags that were provided as part of the awareness campaign. Finally, refined waste sorting, weighing of various fractions and measurement of dry mass was performed in environmental laboratory using standard methods. It was calculated that sorting efficiency of waste improved from 0 to 52% as a result of the awareness campaign. The generation of waste (dry mass basis) on average from one household was 460 kg/year whereas per capita generation was 68 kg/year. Extrapolating these values for Gujrat Tehsil, the total waste generation per year is calculated to be 101921 tons dry mass (DM). Characteristics found in waste were (i) organic decomposable (29.2%, 29710 tons/year DM), (ii) recyclables (37.0%, 37726 tons/year DM) that included plastic, paper, metal and glass, and (iii) trash (33.8%, 34485 tons/year DM) that mainly comprised of polythene bags, medicine packaging, pampers and wrappers. Waste generation was more in colonies with comparatively higher income and better living standards. In future, data collection for all four seasons and improvements due to expansion of awareness campaign to educational institutes will be quantified. This waste management system can potentially fulfill vital sustainable development goals (e.g. clean water and sanitation), reduce the need to harvest fresh resources from the ecosystem, create business and job opportunities and consequently solve one of the most pressing environmental issues of the country.

Keywords: integrated solid waste management, waste segregation, waste bank, community development

Procedia PDF Downloads 146

Authors: Takahiro Nishimura, Kouki Doi, Hiroshi Fujimoto

Abstract:

Touch-sensitive screens that serve as displays and input devices have been adopted in many portable terminals such as smartphones and personal media players, and the market of touch-sensitive screens has expanded greatly. One of the advantages of touch-sensitive screen is the flexibility in the graphical user interface (GUI) design, and it is imperative to design an appropriate GUI to realize an easy-to-use interface. Moreover, it is important to evaluate the relationship between pointing performance and GUI design. There is much knowledge regarding easy-to-use GUI designs for portable terminals with touch-sensitive screens, and most have focused on GUI design approaches for women or children with small hands. In contrast, GUI design approaches for users with large hands have not received sufficient attention. In this study, to obtain knowledge that contributes to the establishment of individualized easy-to-use GUI design guidelines, we conducted experiments to investigate the relationship between thumb length and pointing performance on portable terminals with touch-sensitive screens. In this study, fourteen college students who participated in the experiment were divided into two groups based on the length of their thumbs. Specifically, we categorized the participants into two groups, thumbs longer than 64.2 mm into L (Long) group, and thumbs longer than 57.4 mm but shorter than 64.2 mm into A (Average) group, based on Japanese anthropometric database. They took part in this study under the authorization of Waseda University’s ‘Ethics Review Committee on Research with Human Subjects’. We created an application for the experimental task and implemented it on the projected capacitive touch-sensitive screen portable terminal (iPod touch (4th generation)). The display size was 3.5 inch and 960 × 640 - pixel resolution at 326 ppi (pixels per inch). This terminal was selected as the experimental device, because of its wide use and market share. The operational procedure of the application is as follows. First, the participants placed their thumb on the start position. Then, one cross-shaped target in a 10 × 7 array of 70 positions appeared at random. The participants pointed the target with their thumb as accurately and as fast as possible. Then, they returned their thumb to the start position and waited. The operation ended when this procedure had been repeated until all 70 targets had each been pointed at once by the participants. We adopted the evaluation indices for absolute error, variable error, and pointing time to investigate pointing performance when using the portable terminal. The results showed that pointing performance varied with thumb length. In particular, on the lower right side of the screen, the performance of L group with long thumb was low. Further, we presented an approach for designing easy-to- use button GUI for users with long thumbs. The contributions of this study include revelation of the relationship between pointing performance and user’s thumb length when using a portable terminal in terms of accuracy, precision, and speed of pointing. We hope that these findings contribute to an easy-to-use GUI design for users with large hands.

Keywords: pointing performance, portable terminal, thumb length, touch-sensitive screen

Procedia PDF Downloads 165

Authors: Jose Daniel Hoyos Giraldo, Jesus Hernan Jimenez Giraldo, Juan Pablo Alvarado Perilla

Abstract:

Range and endurance are the main limitations of electric aircraft due to the nature of its source of power. The improvement of efficiency on this kind of systems is extremely meaningful to encourage the aircraft operation with less environmental impact. The propeller efficiency highly affects the overall efficiency of the propulsion system; hence its optimization can have an outstanding effect on the aircraft performance. An optimization method is applied to an aircraft propeller in order to maximize its range and endurance by estimating the best combination of geometrical parameters such as diameter and airfoil, chord and pitch distribution for a specific aircraft design at a certain cruise speed, then the rotational speed at which the propeller operates at minimum current consumption is estimated. The optimization is based on the Blade Element Momentum (BEM) method, additionally corrected to account for tip and hub losses, Mach number and rotational effects; furthermore an airfoil lift and drag coefficients approximation is implemented from Computational Fluid Dynamics (CFD) simulations supported by preliminary studies of grid independence and suitability of different turbulence models, to feed the BEM method, with the aim of achieve more reliable results. Additionally, Vortex Theory is employed to find the optimum pitch and chord distribution to achieve a minimum induced loss propeller design. Moreover, the optimization takes into account the well-known brushless motor model, thrust constraints for take-off runway limitations, maximum allowable propeller diameter due to aircraft height and maximum motor power. The BEM-CFD method is validated by comparing its predictions for a known APC propeller with both available experimental tests and APC reported performance curves which are based on Vortex Theory fed with the NASA Transonic Airfoil code, showing a adequate fitting with experimental data even more than reported APC data. Optimal propeller predictions are validated by wind tunnel tests, CFD propeller simulations and a study of how the propeller will perform if it replaces the one of on known aircraft. Some tendency charts relating a wide range of parameters such as diameter, voltage, pitch, rotational speed, current, propeller and electric efficiencies are obtained and discussed. The implementation of CFD tools shows an improvement in the accuracy of BEM predictions. Results also showed how a propeller has higher efficiency peaks when it operates at high rotational speed due to the higher Reynolds at which airfoils present lower drag. On the other hand, the behavior of the current consumption related to the propulsive efficiency shows counterintuitive results, the best range and endurance is not necessary achieved in an efficiency peak.

Keywords: BEM, blade design, CFD, electric aircraft, endurance, optimization, range

Procedia PDF Downloads 114

Authors: Stephen Dankwa, Zheng Wenfeng, Xiaolu Li

Abstract:

Climate change is recently gaining the attention of many countries across the world. Climate change, which is also known as global warming, referring to the increasing in average surface temperature has been a concern to the Environmental Protection Agency of Ghana. Recently, Ghana has become vulnerable to the effect of the climate change as a result of the dependence of the majority of the population on agriculture. The clearing down of trees to grow crops and burning of charcoal in the country has been a contributing factor to the rise in temperature nowadays in the country as a result of releasing of carbon dioxide and greenhouse gases into the air. Recently, petroleum stations across the cities have been on fire due to this climate changes and which have position Ghana in a way not able to withstand this climate event. As a result, the significant of this research paper is to project how the rise in the average surface temperature will be like at the end of the mid-21st century when agriculture and deforestation are allowed to continue for some time in the country. This study uses the Coupled Modeled Intercomparison Project phase 5 (CMIP5) experiment RCP 8.5 model output data to monitor the future climate changes from 2041-2050, at the end of the mid-21st century over the ten (10) major cities (Accra, Bolgatanga, Cape Coast, Koforidua, Kumasi, Sekondi-Takoradi, Sunyani, Ho, Tamale, Wa) in Ghana. In the models, Support Vector Machine and Random forest, where the cities as a function of heat wave metrics (minimum temperature, maximum temperature, mean temperature, heat wave duration and number of heat waves) assisted to provide more than 50% accuracy to predict and monitor the pattern of the surface air temperature. The findings identified were that the near-surface air temperature will rise between 1°C-2°C (degrees Celsius) over the coastal cities (Accra, Cape Coast, Sekondi-Takoradi). The temperature over Kumasi, Ho and Sunyani by the end of 2050 will rise by 1°C. In Koforidua, it will rise between 1°C-2°C. The temperature will rise in Bolgatanga, Tamale and Wa by 0.5°C by 2050. This indicates how the coastal and the southern part of the country are becoming hotter compared with the north, even though the northern part is the hottest. During heat waves from 2041-2050, Bolgatanga, Tamale, and Wa will experience the highest mean daily air temperature between 34°C-36°C. Kumasi, Koforidua, and Sunyani will experience about 34°C. The coastal cities (Accra, Cape Coast, Sekondi-Takoradi) will experience below 32°C. Even though, the coastal cities will experience the lowest mean temperature, they will have the highest number of heat waves about 62. Majority of the heat waves will last between 2 to 10 days with the maximum 30 days. The surface temperature will continue to rise by the end of the mid-21st century (2041-2050) over the major cities in Ghana and so needs to be addressed to the Environmental Protection Agency in Ghana in order to mitigate this problem.

Keywords: climate changes, CMIP5, Ghana, heat waves, random forest, SVM

Procedia PDF Downloads 202

Authors: Alessandra Aparecida Vieira França, Adriana de Paula Lacerda Santos, Mauro Lacerda Santos Filho

Abstract:

The purpose of this research i to study the behavior of precast prestressed hollow core slabs subjected to shear. In order to achieve this goal, shear tests were performed using hollow core slabs 26,5cm thick, with and without a concrete cover of 5 cm, without cores filled, with two cores filled and three cores filled with concrete. The tests were performed according to the procedures recommended by FIP (1992), the EN 1168:2005 and following the method presented in Costa (2009). The ultimate shear strength obtained within the tests was compared with the values of theoretical resistant shear calculated in accordance with the codes, which are being used in Brazil, noted: NBR 6118:2003 and NBR 14861:2011. When calculating the shear resistance through the equations presented in NBR 14861:2011, it was found that provision is much more accurate for the calculation of the shear strength of hollow core slabs than the NBR 6118 code. Due to the large difference between the calculated results, even for slabs without cores filled, the authors consulted the committee that drafted the NBR 14861:2011 and found that there is an error in the text of the standard, because the coefficient that is suggested, actually presents the double value than the needed one! The ABNT, later on, soon issued an amendment of NBR 14861:2011 with the necessary corrections. During the tests for the present study, it was confirmed that the concrete filling the cores contributes to increase the shear strength of hollow core slabs. But in case of slabs 26,5 cm thick, the quantity should be limited to a maximum of two cores filled, because most of the results for slabs with three cores filled were smaller. This confirmed the recommendation of NBR 14861:2011which is consistent with standard practice. After analyzing the configuration of cracking and failure mechanisms of hollow core slabs during the shear tests, strut and tie models were developed representing the forces acting on the slab at the moment of rupture. Through these models the authors were able to calculate the tensile stress acting on the concrete ties (ribs) and scaled the geometry of these ties. The conclusions of the research performed are the experiments results have shown that the mechanism of failure of the hollow-core slabs can be predicted using the strut-and-tie procedure, within a good range of accuracy. In addition, the needed of the correction of the Brazilian standard to review the correction factor σcp duplicated (in NBR14861/2011), and the limitation of the number of cores (Holes) to be filled with concrete, to increase the strength of the slab for the shear resistance. It is also suggested the increasing the amount of test results with 26.5 cm thick, and a larger range of thickness slabs, in order to obtain results of shear tests with cores concreted after the release of prestressing force. Another set of shear tests on slabs must be performed in slabs with cores filled and cover concrete reinforced with welded steel mesh for comparison with results of theoretical values calculated by the new revision of the standard NBR 14861:2011.

Keywords: prestressed hollow core slabs, shear, strut, tie models

Procedia PDF Downloads 336

Authors: Rajkumar Ghosh

Abstract:

Earthquakes are natural disasters that pose a significant risk to human life and infrastructure. Effective earthquake mitigation measures require a thorough understanding of the dynamics of seismic occurrences, including thrust movement. Traditionally, estimating thrust movement has relied on typical techniques that may not capture the full complexity of these events. Therefore, investigating alternative approaches, such as incorporating out-of-sequence thrust movement data, could enhance earthquake mitigation strategies. This review aims to provide an overview of the applications of out-of-sequence thrust movement in earthquake mitigation. By examining existing research and studies, the objective is to understand how precise estimation of thrust movement can contribute to improving structural design, analyzing infrastructure risk, and developing early warning systems. The study demonstrates how to estimate out-of-sequence thrust movement using multiple data sources, including GPS measurements, satellite imagery, and seismic recordings. By analyzing and synthesizing these diverse datasets, researchers can gain a more comprehensive understanding of thrust movement dynamics during seismic occurrences. The review identifies potential advantages of incorporating out-of-sequence data in earthquake mitigation techniques. These include improving the efficiency of structural design, enhancing infrastructure risk analysis, and developing more accurate early warning systems. By considering out-of-sequence thrust movement estimates, researchers and policymakers can make informed decisions to mitigate the impact of earthquakes. This study contributes to the field of seismic monitoring and earthquake risk assessment by highlighting the benefits of incorporating out-of-sequence thrust movement data. By broadening the scope of analysis beyond traditional techniques, researchers can enhance their knowledge of earthquake dynamics and improve the effectiveness of mitigation measures. The study collects data from various sources, including GPS measurements, satellite imagery, and seismic recordings. These datasets are then analyzed using appropriate statistical and computational techniques to estimate out-of-sequence thrust movement. The review integrates findings from multiple studies to provide a comprehensive assessment of the topic. The study concludes that incorporating out-of-sequence thrust movement data can significantly enhance earthquake mitigation measures. By utilizing diverse data sources, researchers and policymakers can gain a more comprehensive understanding of seismic dynamics and make informed decisions. However, challenges exist, such as data quality difficulties, modelling uncertainties, and computational complications. To address these obstacles and improve the accuracy of estimates, further research and advancements in methodology are recommended. Overall, this review serves as a valuable resource for researchers, engineers, and policymakers involved in earthquake mitigation, as it encourages the development of innovative strategies based on a better understanding of thrust movement dynamics.

Keywords: earthquake, out-of-sequence thrust, disaster, human life

Procedia PDF Downloads 81

Authors: Angelis P. Barlampas

Abstract:

Learning Objectives: The purpose of this study is to inform briefly the reader about the applications of AI in chest radiology. Background: Currently, there are 190 FDA-approved radiology AI applications, with 42 (22%) pertaining specifically to thoracic radiology. Imaging findings OR Procedure details Aids of AI in chest radiology1: Detects and segments pulmonary nodules. Subtracts bone to provide an unobstructed view of the underlying lung parenchyma and provides further information on nodule characteristics, such as nodule location, nodule two-dimensional size or three dimensional (3D) volume, change in nodule size over time, attenuation data (i.e., mean, minimum, and/or maximum Hounsfield units [HU]), morphological assessments, or combinations of the above. Reclassifies indeterminate pulmonary nodules into low or high risk with higher accuracy than conventional risk models. Detects pleural effusion . Differentiates tension pneumothorax from nontension pneumothorax. Detects cardiomegaly, calcification, consolidation, mediastinal widening, atelectasis, fibrosis and pneumoperitoneum. Localises automatically vertebrae segments, labels ribs and detects rib fractures. Measures the distance from the tube tip to the carina and localizes both endotracheal tubes and central vascular lines. Detects consolidation and progression of parenchymal diseases such as pulmonary fibrosis or chronic obstructive pulmonary disease (COPD).Can evaluate lobar volumes. Identifies and labels pulmonary bronchi and vasculature and quantifies air-trapping. Offers emphysema evaluation. Provides functional respiratory imaging, whereby high-resolution CT images are post-processed to quantify airflow by lung region and may be used to quantify key biomarkers such as airway resistance, air-trapping, ventilation mapping, lung and lobar volume, and blood vessel and airway volume. Assesses the lung parenchyma by way of density evaluation. Provides percentages of tissues within defined attenuation (HU) ranges besides furnishing automated lung segmentation and lung volume information. Improves image quality for noisy images with built-in denoising function. Detects emphysema, a common condition seen in patients with history of smoking and hyperdense or opacified regions, thereby aiding in the diagnosis of certain pathologies, such as COVID-19 pneumonia. It aids in cardiac segmentation and calcium detection, aorta segmentation and diameter measurements, and vertebral body segmentation and density measurements. Conclusion: The future is yet to come, but AI already is a helpful tool for the daily practice in radiology. It is assumed, that the continuing progression of the computerized systems and the improvements in software algorithms , will redder AI into the second hand of the radiologist.

Keywords: artificial intelligence, chest imaging, nodule detection, automated diagnoses

Procedia PDF Downloads 75

Authors: Yen Yen Tan, Lynn Lam, Cynthia Lam, Angela Koh, Edwin Seng

Abstract:

Entrepreneurial education plays a crucial role in nurturing future innovators and change-makers. Over time, significant progress has been made in refining instructional approaches to develop the necessary skills among learners effectively. Two highly valuable frameworks, Kearney's "4 Principles of Entrepreneurial Pedagogy" and Bloom's "Three Domains of Learning," serve as guiding principles in entrepreneurial education. Kearney's principles align with experiential and student-centric learning, which are crucial for cultivating an entrepreneurial mindset. The potential synergies between these frameworks hold great promise for enhancing entrepreneurial acumen among students. However, despite this potential, their integration remains largely unexplored. This study aims to bridge this gap by building upon the Business Essentials through Action (BETA) module and investigating its contributions to nurturing the entrepreneurial mindset. This study employs a quasi-experimental mixed-methods approach, combining quantitative and qualitative elements to ensure comprehensive and insightful data. A cohort of 235 students participated, with 118 enrolled in the BETA module and 117 in a traditional curriculum. Their Personal Entrepreneurial Competencies (PECs) were assessed before admission (pre-Y1) and one year into the course (post-Y1) using a comprehensive 55-item PEC questionnaire, enabling measurement of critical traits such as opportunity-seeking, persistence, and risk-taking. Rigorous computations of individual entrepreneurial competencies and overall PEC scores were performed, including a correction factor to mitigate potential self-assessment bias. The orchestration of Kearney's principles and Bloom's domains within the BETA module necessitates a granular examination. Here, qualitative revelations surface, courtesy of structured interviews aligned with contemporary research methodologies. These interviews act as a portal, ushering us into the transformative journey undertaken by students. Meanwhile, the study pivots to explore the BETA module's influence on students' entrepreneurial competencies from the vantage point of faculty members. A symphony of insights emanates from intimate focus group discussions featuring six dedicated lecturers, who share their perceptions, experiences, and reflective narratives, illuminating the profound impact of pedagogical practices embedded within the BETA module. Preliminary findings from ongoing data analysis indicate promising results, showcasing a substantial improvement in entrepreneurial skills among students participating in the BETA module. This study promises not only to elevate students' entrepreneurial competencies but also to illuminate the broader canvas of applicability for Kearney's principles and Bloom's domains. The dynamic interplay of quantitative analyses, proffering precise competency metrics, and qualitative revelations, delving into the nuanced narratives of transformative journeys, engenders a holistic understanding of this educational endeavour. Through a rigorous quasi-experimental mixed-methods approach, this research aims to establish the BETA module's effectiveness in fostering entrepreneurial acumen among students at Singapore Polytechnic, thereby contributing valuable insights to the broader discourse on educational methodologies.

Keywords: entrepreneurial education, experiential learning, pedagogical frameworks, innovative competencies

Procedia PDF Downloads 69

Authors: Helga Heylen

Abstract:

With dogs saving wildlife in New Zealand since 1890 and governments in Africa, Australia and Canada trusting them to give the best results, Conservation Dogs Ireland want to introduce more detection dogs to protect Europe's native wildlife. Conservation detection dogs are fast, portable and endlessly trainable. They are a cost-effective, highly sensitive and non-invasive way to detect protected and invasive species and wildlife disease. Conservation dogs find targets up to 40 times faster than any other method. They give results instantly, with near-perfect accuracy. They can search for multiple targets simultaneously, with no reduction in efficacy The European Red List indicates the decline in biodiversity has been most rapid in the past 50 years, and the risk of extinction never higher. Just two examples of major threats dogs are trained to tackle are: (I)Japanese Knotweed (Fallopia Japonica), not only a serious threat to ecosystems, crops, structures like bridges and roads - it can wipe out the entire value of a house. The property industry and homeowners are only just waking up to the full extent of the nightmare. When those working in construction on the roads move topsoil with a trace of Japanese Knotweed, it suffices to start a new colony. Japanese Knotweed grows up to 7cm a day. It can stay dormant and resprout after 20 years. In the UK, the cost of removing Japanese Knotweed from the London Olympic site in 2012 was around £70m (€83m). UK banks already no longer lend on a house that has Japanese Knotweed on-site. Legally, landowners are now obliged to excavate Japanese Knotweed and have it removed to a landfill. More and more, we see Japanese Knotweed grow where a new house has been constructed, and topsoil has been brought in. Conservation dogs are trained to detect small fragments of any part of the plant on sites and in topsoil. (II)Zebra mussels (Dreissena Polymorpha) are a threat to many waterways in the world. They colonize rivers, canals, docks, lakes, reservoirs, water pipes and cooling systems. They live up to 3 years and will release up to one million eggs each year. Zebra mussels attach to surfaces like rocks, anchors, boat hulls, intake pipes and boat engines. They cause changes in nutrient cycles, reduction of plankton and increased plant growth around lake edges, leading to the decline of Europe's native mussel and fish populations. There is no solution, only costly measures to keep it at bay. With many interconnected networks of waterways, they have spread uncontrollably. Conservation detection dogs detect the Zebra mussel from its early larvae stage, which is still invisible to the human eye. Detection dogs are more thorough and cost-effective than any other conservation method, and will greatly complement and speed up the work of biologists, surveyors, developers, ecologists and researchers.

Keywords: native biodiversity, conservation detection dogs, invasive species, Japanese Knotweed, zebra mussel

Procedia PDF Downloads 199

Authors: Lina Psarra, Manogj Sundaresan, Purjeet Sutar

Abstract:

In response to the global imperative for sustainable solutions, this article proposes the development of a comprehensive circularity index applicable to a wide range of products across various industries. The absence of a consensus on using a universal metric to assess circularity performance presents a significant challenge in prioritizing and effectively managing sustainable initiatives. This circularity index serves as a quantitative measure to evaluate the adherence of products, processes, and systems to the principles of a circular economy. Unlike traditional distinct metrics such as recycling rates or material efficiency, this index considers the entire lifecycle of a product in one single metric, also incorporating additional factors such as reusability, scarcity of materials, reparability, and recyclability. Through a systematic approach and by reviewing existing metrics and past methodologies, this work aims to address this gap by formulating a circularity index that can be applied to diverse product portfolio and assist in comparing the circularity of products on a scale of 0%-100%. Project objectives include developing a formula, designing and implementing a pilot tool based on the developed Product Circularity Index (PCI), evaluating the effectiveness of the formula and tool using real product data, and assessing the feasibility of integration into various sustainability initiatives. The research methodology involves an iterative process of comprehensive research, analysis, and refinement where key steps include defining circularity parameters, collecting relevant product data, applying the developed formula, and testing the tool in a pilot phase to gather insights and make necessary adjustments. Major findings of the study indicate that the PCI provides a robust framework for evaluating product circularity across various dimensions. The Excel-based pilot tool demonstrated high accuracy and reliability in measuring circularity, and the database proved instrumental in supporting comprehensive assessments. The PCI facilitated the identification of key areas for improvement, enabling more informed decision-making towards circularity and benchmarking across different products, essentially assisting towards better resource management. In conclusion, the development of the Product Circularity Index represents a significant advancement in global sustainability efforts. By providing a standardized metric, the PCI empowers companies and stakeholders to systematically assess product circularity, track progress, identify improvement areas, and make informed decisions about resource management. This project contributes to the broader discourse on sustainable development by offering a practical approach to enhance circularity within industrial systems, thus paving the way towards a more resilient and sustainable future.

Keywords: circular economy, circular metrics, circularity assessment, circularity tool, sustainable product design, product circularity index

Procedia PDF Downloads 38

Authors: Ali Kadir, O. Anwar Beg

Abstract:

Thermal barrier coatings are among the most popular methods for providing corrosion protection in high temperature applications including aircraft engine systems, external spacecraft structures, rocket chambers etc. Many different materials are available for such coatings, of which ceramics generally perform the best. Motivated by these applications, the current investigation presents detailed finite element simulations of coating stress analysis for a 3- dimensional, 3-layered model of a test sample representing a typical gas turbine component scenario. Structural steel is selected for the main inner layer, Titanium (Ti) alloy for the middle layer and Silicon Carbide (SiC) for the outermost layer. The model dimensions are 20 mm (width), 10 mm (height) and three 1mm deep layers. ANSYS software is employed to conduct three types of analysis- static structural, thermal stress analysis and also computational fluid dynamic erosion/corrosion analysis (via ANSYS FLUENT). The specified geometry which corresponds to corrosion test samples exactly is discretized using a body-sizing meshing approach, comprising mainly of tetrahedron cells. Refinements were concentrated at the connection points between the layers to shift the focus towards the static effects dissipated between them. A detailed grid independence study is conducted to confirm the accuracy of the selected mesh densities. To recreate gas turbine scenarios; in the stress analysis simulations, static loading and thermal environment conditions of up to 1000 N and 1000 degrees Kelvin are imposed. The default solver was used to set the controls for the simulation with the fixed support being set as one side of the model while subjecting the opposite side to a tabular force of 500 and 1000 Newtons. Equivalent elastic strain, total deformation, equivalent stress and strain energy were computed for all cases. Each analysis was duplicated twice to remove one of the layers each time, to allow testing of the static and thermal effects with each of the coatings. ANSYS FLUENT simulation was conducted to study the effect of corrosion on the model under similar thermal conditions. The momentum and energy equations were solved and the viscous heating option was applied to represent improved thermal physics of heat transfer between the layers of the structures. A Discrete Phase Model (DPM) in ANSYS FLUENT was employed which allows for the injection of continuous uniform air particles onto the model, thereby enabling an option for calculating the corrosion factor caused by hot air injection (particles prescribed 5 m/s velocity and 1273.15 K). Extensive visualization of results is provided. The simulations reveal interesting features associated with coating response to realistic gas turbine loading conditions including significantly different stress concentrations with different coatings.

Keywords: thermal coating, corrosion, ANSYS FEA, CFD

Procedia PDF Downloads 139

Authors: Getaneh Berie Tarekegn, Li-Chia Tai

Abstract:

With the rapid advancement of artificial intelligence, low-power built-in sensors on Internet of Things devices, and communication technologies, location-aware services have become increasingly popular and have permeated every aspect of people’s lives. Global navigation satellite systems (GNSSs) are the default method of providing continuous positioning services for ground and aerial vehicles, as well as consumer devices (smartphones, watches, notepads, etc.). However, the environment affects satellite positioning systems, particularly indoors, in dense urban and suburban cities enclosed by skyscrapers, or when deep shadows obscure satellite signals. This is because (1) indoor environments are more complicated due to the presence of many objects surrounding them; (2) reflection within the building is highly dependent on the surrounding environment, including the positions of objects and human activity; and (3) satellite signals cannot be reached in an indoor environment, and GNSS doesn't have enough power to penetrate building walls. GPS is also highly power-hungry, which poses a severe challenge for battery-powered IoT devices. Due to these challenges, IoT applications are limited. Consequently, precise, seamless, and ubiquitous Positioning, Navigation and Timing (PNT) systems are crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarms, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 48

Authors: Hamadi Cherif, Christophe Coquelet, Paolo Stringari, Denis Clodic, Laura Pellegrini, Stefania Moioli, Stefano Langè

Abstract:

Biogas is a promising technology which can be used as a vehicle fuel, for heat and electricity production, or injected in the national gas grid. It is storable, transportable, not intermittent and substitutable for fossil fuels. This gas produced from the wastewater treatment by degradation of organic matter under anaerobic conditions is mainly composed of methane and carbon dioxide. To be used as a renewable fuel, biogas, whose energy comes only from methane, must be purified from carbon dioxide and other impurities such as water vapor, siloxanes and hydrogen sulfide. Purification of biogas for this application particularly requires the removal of hydrogen sulfide, which negatively affects the operation and viability of equipment especially pumps, heat exchangers and pipes, causing their corrosion. Several methods are available to eliminate hydrogen sulfide from biogas. Herein, reactive absorption in structured packed column by means of chemical absorption in aqueous sodium hydroxide solutions is considered. This study is based on simulations using Aspen Plus™ V8.0, and comparisons are done with data from an industrial pilot plant treating 85 Nm3/h of biogas which contains about 30 ppm of hydrogen sulfide. The rate-based model approach has been used for simulations in order to determine the efficiencies of separation for different operating conditions. To describe vapor-liquid equilibrium, a γ/ϕ approach has been considered: the Electrolyte NRTL model has been adopted to represent non-idealities in the liquid phase, while the Redlich-Kwong equation of state has been used for the vapor phase. In order to validate the thermodynamic model, Henry’s law constants of each compound in water have been verified against experimental data. Default values available in Aspen Plus™ V8.0 for the properties of pure components properties as heat capacity, density, viscosity and surface tension have also been verified. The obtained results for physical and chemical properties are in a good agreement with experimental data. Reactions involved in the process have been studied rigorously. Equilibrium constants for equilibrium reactions and the reaction rate constant for the kinetically controlled reaction between carbon dioxide and the hydroxide ion have been checked. Results of simulations of the pilot plant purification section show the influence of low temperatures, concentration of sodium hydroxide and hydrodynamic parameters on the selective absorption of hydrogen sulfide. These results show an acceptable degree of accuracy when compared with the experimental data obtained from the pilot plant. Results show also the great efficiency of sodium hydroxide for the removal of hydrogen sulfide. The content of this compound in the gas leaving the column is under 1 ppm.

Keywords: biogas, hydrogen sulfide, reactive absorption, sodium hydroxide, structured packed column

Procedia PDF Downloads 356

Authors: Hisham Arab Alkabeya, A. M. Hughes, J. Adams

Abstract:

Background: People with Rheumatoid Arthritis (RA) continue to experience problems with hand function despite new drug advances and targeted medical treatment. Consequently, it is important to identify the factors that influence the impact of RA disease on hand function. This systematic review identified observational studies that reported factors that influenced the impact of RA on hand function. Methods: MEDLINE, EMBASE, CINAL, AMED, PsychINFO, and Web of Science database were searched from January 1990 up to March 2017. Full-text articles published in English that described factors related to hand functional disability in people with RA were selected following predetermined inclusion and exclusion criteria. Pertinent data were thoroughly extracted and documented using a pre-designed data extraction form by the lead author, and cross-checked by the review team for completion and accuracy. Factors related to hand function were classified under the domains of the International Classification of Functioning, Disability, and Health (ICF) framework and health-related factors. Three reviewers independently assessed the methodological quality of the included articles using the quality of cross-sectional studies (AXIS) tool. Factors related to hand function that was investigated in two or more studies were explored using a best-evidence synthesis. Results: Twenty articles form 19 studies met the inclusion criteria from 1,271 citations; all presented cross-sectional data (five high quality and 15 low quality studies), resulting in at best limited evidence in the best-evidence synthesis. For the factors classified under the ICF domains, the best-evidence synthesis indicates that there was a range of body structure and function factors that were related with hand functional disability. However, key factors were hand strength, disease activity, and pain intensity. Low functional status (physical, emotional and social) level was found to be related with limited hand function. For personal factors, there is limited evidence that gender is not related with hand function; whereas, conflicting evidence was found regarding the relationship between age and hand function. In the domain of environmental factors, there was limited evidence that work activity was not related with hand function. Regarding health-related factors, there was limited evidence that the level of the rheumatoid factor (RF) was not related to hand function. Finally, conflicting evidence was found regarding the relationship between hand function and disease duration and general health status. Conclusion: Studies focused on body structure and function factors, highlighting a lack of investigation into personal and environmental factors when considering the impact of RA on hand function. The level of evidence which exists was limited, but identified that modifiable factors such as grip or pinch strength, disease activity and pain are the most influential factors on hand function in people with RA. The review findings suggest that important personal and environmental factors that impact on hand function in people with RA are not yet considered or reported in clinical research. Well-designed longitudinal, preferably cohort, studies are now needed to better understand the causality between personal and environmental factors and hand functional disability in people with RA.

Keywords: factors, hand function, rheumatoid arthritis, systematic review

Procedia PDF Downloads 151

Authors: Elham Koohikerade, Silvio Jose Gumiere

Abstract:

In this research, irrigation is highlighted as crucial for improving both the yield and quality of ‎potatoes due to their high sensitivity to soil moisture changes. The study presents a hybrid Long ‎Short-Term Memory (LSTM) model aimed at optimizing irrigation scheduling in potato fields in ‎Quebec City, Canada. This model integrates model-based and satellite-derived datasets to simulate ‎soil moisture content, addressing the limitations of field data. Developed under the guidance of the ‎Food and Agriculture Organization (FAO), the simulation approach compensates for the lack of direct ‎soil sensor data, enhancing the LSTM model's predictions. The model was calibrated using indices ‎like Surface Soil Moisture (SSM), Normalized Vegetation Difference Index (NDVI), Enhanced ‎Vegetation Index (EVI), and Normalized Multi-band Drought Index (NMDI) to effectively forecast ‎soil moisture reductions. Understanding soil moisture and plant development is crucial for assessing ‎drought conditions and determining irrigation needs. This study validated the spectral characteristics ‎of vegetation and soil using ECMWF Reanalysis v5 (ERA5) and Moderate Resolution Imaging ‎Spectrometer (MODIS) data from 2019 to 2023, collected from agricultural areas in Dolbeau and ‎Peribonka, Quebec. Parameters such as surface volumetric soil moisture (0-7 cm), NDVI, EVI, and ‎NMDI were extracted from these images. A regional four-year dataset of soil and vegetation moisture ‎was developed using a machine learning approach combining model-based and satellite-based ‎datasets. The LSTM model predicts soil moisture dynamics hourly across different locations and ‎times, with its accuracy verified through cross-validation and comparison with existing soil moisture ‎datasets. The model effectively captures temporal dynamics, making it valuable for applications ‎requiring soil moisture monitoring over time, such as anomaly detection and memory analysis. By ‎identifying typical peak soil moisture values and observing distribution shapes, irrigation can be ‎scheduled to maintain soil moisture within Volumetric Soil Moisture (VSM) values of 0.25 to 0.30 ‎m²/m², avoiding under and over-watering. The strong correlations between parcels suggest that a ‎uniform irrigation strategy might be effective across multiple parcels, with adjustments based on ‎specific parcel characteristics and historical data trends. The application of the LSTM model to ‎predict soil moisture and vegetation indices yielded mixed results. While the model effectively ‎captures the central tendency and temporal dynamics of soil moisture, it struggles with accurately ‎predicting EVI, NDVI, and NMDI.‎

Keywords: irrigation scheduling, LSTM neural network, remotely sensed indices, soil and vegetation ‎monitoring

Procedia PDF Downloads 47

Authors: Sonam Behl, Raju, Ginu Rajan, Paul Farrar, B. Gangadhara Prusty

Abstract:

Reinforcing dental composites with micro-sized fibres can significantly improve the physio-mechanical properties of dental composites. The short fibres can be oriented randomly within dental composites, thus providing quasi-isotropic reinforcing efficiency unlike unidirectional/bidirectional fibre reinforced composites enhancing anisotropic properties. Thus, short fibres reinforced dental composites are getting popular among practitioners. However, despite their popularity, resin-based dental composites are prone to failure on account of shrinkage during photo polymerisation. The shrinkage in the structure may lead to marginal gap formation, causing secondary caries, thus ultimately inducing failure of the restoration. The traditional methods to evaluate polymerisation shrinkage using strain gauges, density-based measurements, dilatometer, or bonded-disk focuses on average value of volumetric shrinkage. Moreover, the results obtained from traditional methods are sensitive to the specimen geometry. The present research aims to evaluate the real-time shrinkage strain at selected locations in the material with the help of optical fibre Bragg grating (FBG) sensors. Due to the miniature size (diameter 250 µm) of FBG sensors, they can be easily embedded into small samples of dental composites. Furthermore, an FBG array into the system can map the real-time shrinkage strain at different regions of the composite. The evaluation of real-time monitoring of shrinkage values may help to optimise the physio-mechanical properties of composites. Previously, FBG sensors have been able to rightfully measure polymerisation strains of anisotropic (unidirectional or bidirectional) reinforced dental composites. However, very limited study exists to establish the validity of FBG based sensors to evaluate volumetric shrinkage for randomly oriented fibres reinforced composites. The present study aims to fill this research gap and is focussed on establishing the usage of FBG based sensors for evaluating the shrinkage of dental composites reinforced with randomly oriented fibres. Three groups of specimens were prepared by mixing the resin (80% UDMA/20% TEGDMA) with 55% of silane treated BaAlSiO₂ particulate fillers or by adding 5% of micro-sized fibres of diameter 5 µm, and length 250/350 µm along with 50% of silane treated BaAlSiO₂ particulate fillers into the resin. For measurement of polymerisation shrinkage strain, an array of three fibre Bragg grating sensors was embedded at a depth of 1 mm into a circular Teflon mould of diameter 15 mm and depth 2 mm. The results obtained are compared with the traditional method for evaluation of the volumetric shrinkage using density-based measurements. Degree of conversion was measured using FTIR spectroscopy (Spotlight 400 FT-IR from PerkinElmer). It is expected that the average polymerisation shrinkage strain values for dental composites reinforced with micro-sized fibres can directly correlate with the measured degree of conversion values, implying that more C=C double bond conversion to C-C single bond values also leads to higher shrinkage strain within the composite. Moreover, it could be established the photonics approach could help assess the shrinkage at any point of interest in the material, suggesting that fibre-Bragg grating sensors are a suitable means for measuring real-time polymerisation shrinkage strain for randomly fibre reinforced dental composites as well.

Keywords: dental composite, glass fibre, polymerisation shrinkage strain, fibre-Bragg grating sensors

Procedia PDF Downloads 159

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 125