Search results for: classification size
6845 Diversity in Finance Literature Revealed through the Lens of Machine Learning: A Topic Modeling Approach on Academic Papers
Authors: Oumaima Lahmar
Abstract:
This paper aims to define a structured topography for finance researchers seeking to navigate the body of knowledge in their extrapolation of finance phenomena. To make sense of the body of knowledge in finance, a probabilistic topic modeling approach is applied on 6000 abstracts of academic articles published in three top journals in finance between 1976 and 2020. This approach combines both machine learning techniques and natural language processing to statistically identify the conjunctions between research articles and their shared topics described each by relevant keywords. The topic modeling analysis reveals 35 coherent topics that can well depict finance literature and provide a comprehensive structure for the ongoing research themes. Comparing the extracted topics to the Journal of Economic Literature (JEL) classification system, a significant similarity was highlighted between the characterizing keywords. On the other hand, we identify other topics that do not match the JEL classification despite being relevant in the finance literature.Keywords: finance literature, textual analysis, topic modeling, perplexity
Procedia PDF Downloads 1596844 Ways to Prevent Increased Wear of the Drive Box Parts and the Central Drive of the Civil Aviation Turbo Engine Based on Tribology
Authors: Liudmila Shabalinskaya, Victor Golovanov, Liudmila Milinis, Sergey Loponos, Alexander Maslov, D. O. Frolov
Abstract:
The work is devoted to the rapid laboratory diagnosis of the condition of aircraft friction units, based on the application of the nondestructive testing method by analyzing the parameters of wear particles, or tribodiagnostics. The most important task of tribodiagnostics is to develop recommendations for the selection of more advanced designs, materials and lubricants based on data on wear processes for increasing the life and ensuring the safety of the operation of machines and mechanisms. The object of tribodiagnostics in this work are the tooth gears of the central drive and the gearboxes of the gas turbine engine of the civil aviation PS-90A type, in which rolling friction and sliding friction with slip occur. The main criterion for evaluating the technical state of lubricated friction units of a gas turbine engine is the intensity and rate of wear of the friction surfaces of the friction unit parts. When the engine is running, oil samples are taken and the state of the friction surfaces is evaluated according to the parameters of the wear particles contained in the oil sample, which carry important and detailed information about the wear processes in the engine transmission units. The parameters carrying this information include the concentration of wear particles and metals in the oil, the dispersion composition, the shape, the size ratio and the number of particles, the state of their surfaces, the presence in the oil of various mechanical impurities of non-metallic origin. Such a morphological analysis of wear particles has been introduced into the order of monitoring the status and diagnostics of various aircraft engines, including a gas turbine engine, since the type of wear characteristic of the central drive and the drive box is surface fatigue wear and the beginning of its development, accompanied by the formation of microcracks, leads to the formation of spherical, up to 10 μm in size, and in the aftermath of flocculent particles measuring 20-200 μm in size. Tribodiagnostics using the morphological analysis of wear particles includes the following techniques: ferrography, filtering, and computer analysis of the classification and counting of wear particles. Based on the analysis of several series of oil samples taken from the drive box of the engine during their operating time, a study was carried out of the processes of wear kinetics. Based on the results of the study and comparing the series of criteria for tribodiagnostics, wear state ratings and statistics of the results of morphological analysis, norms for the normal operating regime were developed. The study allowed to develop levels of wear state for friction surfaces of gearing and a 10-point rating system for estimating the likelihood of the occurrence of an increased wear mode and, accordingly, prevention of engine failures in flight.Keywords: aviation, box of drives, morphological analysis, tribodiagnostics, tribology, ferrography, filtering, wear particle
Procedia PDF Downloads 2526843 SIRT1 Gene Polymorphisms and Its Protein Level in Colorectal Cancer
Authors: Olfat Shaker, Miriam Wadie, Reham Ali, Ayman Yosry
Abstract:
Colorectal cancer (CRC) is a major cause of mortality and morbidity and accounts for over 9% of cancer incidence worldwide. Silent information regulator 2 homolog 1 (SIRT1) gene is located in the nucleus and exert its effects via modulation of histone and non-histone targets. They function in the cell via histone deacetylase (HDAC) and/or adenosine diphosphate ribosyl transferase (ADPRT) enzymatic activity. The aim of this work was to study the relationship between SIRT1 polymorphism and its protein level in colorectal cancer patients in comparison to control cases. This study includes 2 groups: thirty healthy subjects (control group) & one hundred CRC patients. All subjects were subjected to: SIRT-1 serum level was measured by ELISA and gene polymorphisms of rs12778366, rs375891 and rs3740051 were detected by real time PCR. For CRC patients clinical data were collected (size, site of tumor as well as its grading, obesity) CRC patients showed high significant increase in the mean level of serum SIRT-1 compared to control group (P<0.001). Mean serum level of SIRT-1 showed high significant increase in patients with tumor size ≥5 compared to the size < 5 cm (P<0.05). In CRC patients, percentage of T allele of rs12778366 was significantly lower than controls, CC genotype and C allele C of rs 375891 were significantly higher than control group. In CRC patients, the CC genotype of rs12778366, was 75% in rectosigmoid and 25% in cecum & ascending colon. According to tumor size, the percentage of CC genotype was 87.5% in tumor size ≥5 cm. Conclusion: serum level of SIRT-1 and T allele, C allele of rs12778366 and rs 375891 respectively can be used as diagnostic markers for CRC patients.Keywords: CRC, SIRT1, polymorphisms, ELISA
Procedia PDF Downloads 2066842 A Framework for Auditing Multilevel Models Using Explainability Methods
Authors: Debarati Bhaumik, Diptish Dey
Abstract:
Multilevel models, increasingly deployed in industries such as insurance, food production, and entertainment within functions such as marketing and supply chain management, need to be transparent and ethical. Applications usually result in binary classification within groups or hierarchies based on a set of input features. Using open-source datasets, we demonstrate that popular explainability methods, such as SHAP and LIME, consistently underperform inaccuracy when interpreting these models. They fail to predict the order of feature importance, the magnitudes, and occasionally even the nature of the feature contribution (negative versus positive contribution to the outcome). Besides accuracy, the computational intractability of SHAP for binomial classification is a cause of concern. For transparent and ethical applications of these hierarchical statistical models, sound audit frameworks need to be developed. In this paper, we propose an audit framework for technical assessment of multilevel regression models focusing on three aspects: (i) model assumptions & statistical properties, (ii) model transparency using different explainability methods, and (iii) discrimination assessment. To this end, we undertake a quantitative approach and compare intrinsic model methods with SHAP and LIME. The framework comprises a shortlist of KPIs, such as PoCE (Percentage of Correct Explanations) and MDG (Mean Discriminatory Gap) per feature, for each of these three aspects. A traffic light risk assessment method is furthermore coupled to these KPIs. The audit framework will assist regulatory bodies in performing conformity assessments of AI systems using multilevel binomial classification models at businesses. It will also benefit businesses deploying multilevel models to be future-proof and aligned with the European Commission’s proposed Regulation on Artificial Intelligence.Keywords: audit, multilevel model, model transparency, model explainability, discrimination, ethics
Procedia PDF Downloads 856841 Large Neural Networks Learning From Scratch With Very Few Data and Without Explicit Regularization
Authors: Christoph Linse, Thomas Martinetz
Abstract:
Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets
Procedia PDF Downloads 786840 Assessment of the Two-Way Relationship between Capital Structure and Operation Performance of Listed Companies on Vietnam’s Stock
Authors: Uyen Tran Tu
Abstract:
The decision on capital structure is one of the most important and sophisticated decisions in financial management in order to improve firm performance. This article would study the two-way impact between capital structure and firm performance. The study use EVIEWS 6.0 software to determine a two-way relationship between the capital structure and firm performance based on two-stage regression (2SLS - Two-Stage Least Squares). The findings are: capital structure has the opposite effect on the business efficiency and vice versa, factors that effect on business efficiency include Size and Opportunities. Factors effects on the capital structure are size; liquidity. These factors also affect the ratio of capital structure (total debt/ total asset) of companies. In particular, liquidity has the opposite effect; and the size of the business has the same impact. The results of the study are in line with the theory and empirical studies presented, and the results of the study are unchanged for all three years 2015-2017.Keywords: capital structure, firm performance, factors, two-way relationship
Procedia PDF Downloads 1466839 Developing an Advanced Algorithm Capable of Classifying News, Articles and Other Textual Documents Using Text Mining Techniques
Authors: R. B. Knudsen, O. T. Rasmussen, R. A. Alphinas
Abstract:
The reason for conducting this research is to develop an algorithm that is capable of classifying news articles from the automobile industry, according to the competitive actions that they entail, with the use of Text Mining (TM) methods. It is needed to test how to properly preprocess the data for this research by preparing pipelines which fits each algorithm the best. The pipelines are tested along with nine different classification algorithms in the realm of regression, support vector machines, and neural networks. Preliminary testing for identifying the optimal pipelines and algorithms resulted in the selection of two algorithms with two different pipelines. The two algorithms are Logistic Regression (LR) and Artificial Neural Network (ANN). These algorithms are optimized further, where several parameters of each algorithm are tested. The best result is achieved with the ANN. The final model yields an accuracy of 0.79, a precision of 0.80, a recall of 0.78, and an F1 score of 0.76. By removing three of the classes that created noise, the final algorithm is capable of reaching an accuracy of 94%.Keywords: Artificial Neural network, Competitive dynamics, Logistic Regression, Text classification, Text mining
Procedia PDF Downloads 1166838 Enhancing the Interpretation of Group-Level Diagnostic Results from Cognitive Diagnostic Assessment: Application of Quantile Regression and Cluster Analysis
Authors: Wenbo Du, Xiaomei Ma
Abstract:
With the empowerment of Cognitive Diagnostic Assessment (CDA), various domains of language testing and assessment have been investigated to dig out more diagnostic information. What is noticeable is that most of the extant empirical CDA-based research puts much emphasis on individual-level diagnostic purpose with very few concerned about learners’ group-level performance. Even though the personalized diagnostic feedback is the unique feature that differentiates CDA from other assessment tools, group-level diagnostic information cannot be overlooked in that it might be more practical in classroom setting. Additionally, the group-level diagnostic information obtained via current CDA always results in a “flat pattern”, that is, the mastery/non-mastery of all tested skills accounts for the two highest proportion. In that case, the outcome does not bring too much benefits than the original total score. To address these issues, the present study attempts to apply cluster analysis for group classification and quantile regression analysis to pinpoint learners’ performance at different proficiency levels (beginner, intermediate and advanced) thus to enhance the interpretation of the CDA results extracted from a group of EFL learners’ reading performance on a diagnostic reading test designed by PELDiaG research team from a key university in China. The results show that EM method in cluster analysis yield more appropriate classification results than that of CDA, and quantile regression analysis does picture more insightful characteristics of learners with different reading proficiencies. The findings are helpful and practical for instructors to refine EFL reading curriculum and instructional plan tailored based on the group classification results and quantile regression analysis. Meanwhile, these innovative statistical methods could also make up the deficiencies of CDA and push forward the development of language testing and assessment in the future.Keywords: cognitive diagnostic assessment, diagnostic feedback, EFL reading, quantile regression
Procedia PDF Downloads 1416837 Modeling Engagement with Multimodal Multisensor Data: The Continuous Performance Test as an Objective Tool to Track Flow
Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat
Abstract:
Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.Keywords: affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, student engagement
Procedia PDF Downloads 826836 Improved Rare Species Identification Using Focal Loss Based Deep Learning Models
Authors: Chad Goldsworthy, B. Rajeswari Matam
Abstract:
The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation
Procedia PDF Downloads 1766835 Spatial Data Mining by Decision Trees
Authors: Sihem Oujdi, Hafida Belbachir
Abstract:
Existing methods of data mining cannot be applied on spatial data because they require spatial specificity consideration, as spatial relationships. This paper focuses on the classification with decision trees, which are one of the data mining techniques. We propose an extension of the C4.5 algorithm for spatial data, based on two different approaches Join materialization and Querying on the fly the different tables. Similar works have been done on these two main approaches, the first - Join materialization - favors the processing time in spite of memory space, whereas the second - Querying on the fly different tables- promotes memory space despite of the processing time. The modified C4.5 algorithm requires three entries tables: a target table, a neighbor table, and a spatial index join that contains the possible spatial relationship among the objects in the target table and those in the neighbor table. Thus, the proposed algorithms are applied to a spatial data pattern in the accidentology domain. A comparative study of our approach with other works of classification by spatial decision trees will be detailed.Keywords: C4.5 algorithm, decision trees, S-CART, spatial data mining
Procedia PDF Downloads 6066834 Structural and Magnetic Properties of NiFe2O4 Spinel Ferrite Nanoparticles Synthesized by Starch-Assisted Sol-Gel Auto-Combustion Method
Authors: R. S. Yadav, J. Havlica, I. Kuřitka, Z. Kozakova, J. Masilko, L. Kalina, M. Hajdúchová, V. Enev, J. Wasserbauer
Abstract:
Nickel spinel ferrite NiFe2O4 nanoparticles with different particle size at different annealing temperature were synthesized using the starch-assisted sol-gel auto-combustion method. The synthesized nanoparticles were characterized by conventional powder X-ray diffraction (XRD) spectroscopy, Raman Spectroscopy, Fourier Transform Infrared Spectroscopy, Field-Emission Scanning Electron Microscopy, X-ray Photoelectron Spectroscopy and Vibrating Sample Magnetometer. The XRD patterns confirmed the formation of NiFe2O4 spinel ferrite nanoparticles. Field-Emission Scanning Electron Microscopy revealed that particles are of spherical morphology with particle size 5-20 nm at lower annealing temperature. An infrared spectroscopy study showed the presence of two principal absorption bands in the frequency range around 525 cm-1 (ν1) and around 340 cm-1 (ν2); which indicate the presence of tetrahedral and octahedral group complexes, respectively, within the spinel ferrite nanoparticles. Raman spectroscopy study also indicated the change in octahedral and tetrahedral site related Raman modes in nickel ferrite nanoparticles with change of particle size. This change in magnetic behavior with change of particle size of NiFe2O4 nanoparticles was observed.Keywords: nickel ferrite, nanoparticles, magnetic property, NiFe2O4
Procedia PDF Downloads 3726833 A Comparative Analysis of Asymmetric Encryption Schemes on Android Messaging Service
Authors: Mabrouka Algherinai, Fatma Karkouri
Abstract:
Today, Short Message Service (SMS) is an important means of communication. SMS is not only used in informal environment for communication and transaction, but it is also used in formal environments such as institutions, organizations, companies, and business world as a tool for communication and transactions. Therefore, there is a need to secure the information that is being transmitted through this medium to ensure security of information both in transit and at rest. But, encryption has been identified as a means to provide security to SMS messages in transit and at rest. Several past researches have proposed and developed several encryption algorithms for SMS and Information Security. This research aims at comparing the performance of common Asymmetric encryption algorithms on SMS security. The research employs the use of three algorithms, namely RSA, McEliece, and RABIN. Several experiments were performed on SMS of various sizes on android mobile device. The experimental results show that each of the three techniques has different key generation, encryption, and decryption times. The efficiency of an algorithm is determined by the time that it takes for encryption, decryption, and key generation. The best algorithm can be chosen based on the least time required for encryption. The obtained results show the least time when McEliece size 4096 is used. RABIN size 4096 gives most time for encryption and so it is the least effective algorithm when considering encryption. Also, the research shows that McEliece size 2048 has the least time for key generation, and hence, it is the best algorithm as relating to key generation. The result of the algorithms also shows that RSA size 1024 is the most preferable algorithm in terms of decryption as it gives the least time for decryption.Keywords: SMS, RSA, McEliece, RABIN
Procedia PDF Downloads 1556832 A Robust System for Foot Arch Type Classification from Static Foot Pressure Distribution Data Using Linear Discriminant Analysis
Authors: R. Periyasamy, Deepak Joshi, Sneh Anand
Abstract:
Foot posture assessment is important to evaluate foot type, causing gait and postural defects in all age groups. Although different methods are used for classification of foot arch type in clinical/research examination, there is no clear approach for selecting the most appropriate measurement system. Therefore, the aim of this study was to develop a system for evaluation of foot type as clinical decision-making aids for diagnosis of flat and normal arch based on the Arch Index (AI) and foot pressure distribution parameter - Power Ratio (PR) data. The accuracy of the system was evaluated for 27 subjects with age ranging from 24 to 65 years. Foot area measurements (hind foot, mid foot, and forefoot) were acquired simultaneously from foot pressure intensity image using portable PedoPowerGraph system and analysis of the image in frequency domain to obtain foot pressure distribution parameter - PR data. From our results, we obtain 100% classification accuracy of normal and flat foot by using the linear discriminant analysis method. We observe there is no misclassification of foot types because of incorporating foot pressure distribution data instead of only arch index (AI). We found that the mid-foot pressure distribution ratio data and arch index (AI) value are well correlated to foot arch type based on visual analysis. Therefore, this paper suggests that the proposed system is accurate and easy to determine foot arch type from arch index (AI), as well as incorporating mid-foot pressure distribution ratio data instead of physical area of contact. Hence, such computational tool based system can help the clinicians for assessment of foot structure and cross-check their diagnosis of flat foot from mid-foot pressure distribution.Keywords: arch index, computational tool, static foot pressure intensity image, foot pressure distribution, linear discriminant analysis
Procedia PDF Downloads 4926831 Modified Naive Bayes-Based Prediction Modeling for Crop Yield Prediction
Authors: Kefaya Qaddoum
Abstract:
Most of greenhouse growers desire a determined amount of yields in order to accurately meet market requirements. The purpose of this paper is to model a simple but often satisfactory supervised classification method. The original naive Bayes have a serious weakness, which is producing redundant predictors. In this paper, utilized regularization technique was used to obtain a computationally efficient classifier based on naive Bayes. The suggested construction, utilized L1-penalty, is capable of clearing redundant predictors, where a modification of the LARS algorithm is devised to solve this problem, making this method applicable to a wide range of data. In the experimental section, a study conducted to examine the effect of redundant and irrelevant predictors, and test the method on WSG data set for tomato yields, where there are many more predictors than data, and the urge need to predict weekly yield is the goal of this approach. Finally, the modified approach is compared with several naive Bayes variants and other classification algorithms (SVM and kNN), and is shown to be fairly good.Keywords: tomato yield prediction, naive Bayes, redundancy, WSG
Procedia PDF Downloads 2256830 Earthquake Classification in Molluca Collision Zone Using Conventional Statistical Methods
Authors: H. J. Wattimanela, U. S. Passaribu, A. N. T. Puspito, S. W. Indratno
Abstract:
Molluca Collision Zone is located at the junction of the Eurasian plate, Australian, Pacific, and the Philippines. Between the Sangihe arc, west of the collision zone, and to the east of Halmahera arc is active collision and convex toward the Molluca Sea. This research will analyze the behavior of earthquake occurrence in Molluca Collision Zone related to the distributions of an earthquake in each partition regions, determining the type of distribution of a occurrence earthquake of partition regions, and the mean occurrence of earthquakes each partition regions, and the correlation between the partitions region. We calculate number of earthquakes using partition method and its behavioral using conventional statistical methods. The data used is the data type of shallow earthquakes with magnitudes ≥ 4 SR for the period 1964-2013 in the Molluca Collision Zone. From the results, we can classify partitioned regions based on the correlation into two classes: strong and very strong. This classification can be used for early warning system in disaster management.Keywords: molluca collision zone, partition regions, conventional statistical methods, earthquakes, classifications, disaster management
Procedia PDF Downloads 4866829 Unveiling Comorbidities in Irritable Bowel Syndrome: A UK BioBank Study utilizing Supervised Machine Learning
Authors: Uswah Ahmad Khan, Muhammad Moazam Fraz, Humayoon Shafique Satti, Qasim Aziz
Abstract:
Approximately 10-14% of the global population experiences a functional disorder known as irritable bowel syndrome (IBS). The disorder is defined by persistent abdominal pain and an irregular bowel pattern. IBS significantly impairs work productivity and disrupts patients' daily lives and activities. Although IBS is widespread, there is still an incomplete understanding of its underlying pathophysiology. This study aims to help characterize the phenotype of IBS patients by differentiating the comorbidities found in IBS patients from those in non-IBS patients using machine learning algorithms. In this study, we extracted samples coding for IBS from the UK BioBank cohort and randomly selected patients without a code for IBS to create a total sample size of 18,000. We selected the codes for comorbidities of these cases from 2 years before and after their IBS diagnosis and compared them to the comorbidities in the non-IBS cohort. Machine learning models, including Decision Trees, Gradient Boosting, Support Vector Machine (SVM), AdaBoost, Logistic Regression, and XGBoost, were employed to assess their accuracy in predicting IBS. The most accurate model was then chosen to identify the features associated with IBS. In our case, we used XGBoost feature importance as a feature selection method. We applied different models to the top 10% of features, which numbered 50. Gradient Boosting, Logistic Regression and XGBoost algorithms yielded a diagnosis of IBS with an optimal accuracy of 71.08%, 71.427%, and 71.53%, respectively. Among the comorbidities most closely associated with IBS included gut diseases (Haemorrhoids, diverticular diseases), atopic conditions(asthma), and psychiatric comorbidities (depressive episodes or disorder, anxiety). This finding emphasizes the need for a comprehensive approach when evaluating the phenotype of IBS, suggesting the possibility of identifying new subsets of IBS rather than relying solely on the conventional classification based on stool type. Additionally, our study demonstrates the potential of machine learning algorithms in predicting the development of IBS based on comorbidities, which may enhance diagnosis and facilitate better management of modifiable risk factors for IBS. Further research is necessary to confirm our findings and establish cause and effect. Alternative feature selection methods and even larger and more diverse datasets may lead to more accurate classification models. Despite these limitations, our findings highlight the effectiveness of Logistic Regression and XGBoost in predicting IBS diagnosis.Keywords: comorbidities, disease association, irritable bowel syndrome (IBS), predictive analytics
Procedia PDF Downloads 1036828 Distangling Biological Noise in Cellular Images with a Focus on Explainability
Authors: Manik Sharma, Ganapathy Krishnamurthi
Abstract:
The cost of some drugs and medical treatments has risen in recent years, that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. If successful, we could dramatically improve the industry's ability to model cellular images according to their relevant biology. In turn, greatly decreasing the cost of treatments and ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model.Keywords: cellular images, genetic perturbations, deep-learning, explainability
Procedia PDF Downloads 1006827 Detection and Classification of Rubber Tree Leaf Diseases Using Machine Learning
Authors: Kavyadevi N., Kaviya G., Gowsalya P., Janani M., Mohanraj S.
Abstract:
Hevea brasiliensis, also known as the rubber tree, is one of the foremost assets of crops in the world. One of the most significant advantages of the Rubber Plant in terms of air oxygenation is its capacity to reduce the likelihood of an individual developing respiratory allergies like asthma. To construct such a system that can properly identify crop diseases and pests and then create a database of insecticides for each pest and disease, we must first give treatment for the illness that has been detected. We shall primarily examine three major leaf diseases since they are economically deficient in this article, which is Bird's eye spot, algal spot and powdery mildew. And the recommended work focuses on disease identification on rubber tree leaves. It will be accomplished by employing one of the superior algorithms. Input, Preprocessing, Image Segmentation, Extraction Feature, and Classification will be followed by the processing technique. We will use time-consuming procedures that they use to detect the sickness. As a consequence, the main ailments, underlying causes, and signs and symptoms of diseases that harm the rubber tree are covered in this study.Keywords: image processing, python, convolution neural network (CNN), machine learning
Procedia PDF Downloads 696826 Classifications of Sleep Apnea (Obstructive, Central, Mixed) and Hypopnea Events Using Wavelet Packet Transform and Support Vector Machines (VSM)
Authors: Benghenia Hadj Abd El Kader
Abstract:
Sleep apnea events as obstructive, central, mixed or hypopnea are characterized by frequent breathing cessations or reduction in upper airflow during sleep. An advanced method for analyzing the patterning of biomedical signals to recognize obstructive sleep apnea and hypopnea is presented. In the aim to extract characteristic parameters, which will be used for classifying the above stated (obstructive, central, mixed) sleep apnea and hypopnea, the proposed method is based first on the analysis of polysomnography signals such as electrocardiogram signal (ECG) and electromyogram (EMG), then classification of the (obstructive, central, mixed) sleep apnea and hypopnea. The analysis is carried out using the wavelet transform technique in order to extract characteristic parameters whereas classification is carried out by applying the SVM (support vector machine) technique. The obtained results show good recognition rates using characteristic parameters.Keywords: obstructive, central, mixed, sleep apnea, hypopnea, ECG, EMG, wavelet transform, SVM classifier
Procedia PDF Downloads 3656825 Physico-Mechanical Properties of Wood-Plastic Composites Produced from Polyethylene Terephthalate Plastic Bottle Wastes and Sawdust of Three Tropical Hardwood Species
Authors: Amos Olajide Oluyege, Akpanobong Akpan Ekong, Emmanuel Uchechukwu Opara, Sunday Adeniyi Adedutan, Joseph Adeola Fuwape, Olawale John Olukunle
Abstract:
This study was carried out to evaluate the influence of wood species and wood plastic ratio on the physical and mechanical properties of wood plastic composites (WPCs) produced from polyethylene terephthalate (PET) plastic bottle wastes and sawdust from three hardwood species, namely, Terminalia superba, Gmelina arborea, and Ceiba pentandra. The experimental WPCs were prepared from sawdust particle size classes of ≤ 0.5, 0.5 – 1.0, and 1.0 – 2.0 mm at wood/plastic ratios of 40:60, 50:50 and 60:40 (percentage by weight). The WPCs for each study variable combination were prepared in 3 replicates and laid out in a randomized complete block design (RCBD). The physical properties investigated water absorption (WA), linear expansion (LE) and thickness swelling (TS) while the mechanical properties evaluated were Modulus of Elasticity (MOE) and Modulus of Rupture (MOR). The mean values for WA, LE and TS ranged from 1.07 to 34.04, 0.11 to 1.76 and 0.11 to 4.05 %, respectively. The mean values of the three physical properties increased with decrease in wood plastic ratio. Wood plastic ratio of 40:60 at each particle size class generally resulted in the lowest values while wood plastic ratio of 60:40 had the highest values for each of the three species. For each of the physical properties, T. superba had the least mean values followed by G. arborea, while the highest values were observed C. pentandra. The mean values for MOE and MOR ranged from 458.17 to 1875.67 and 2.64 to 18.39 N/mm2, respectively. The mean values of the two mechanical properties decreased with increase in wood plastic ratio. Wood plastic ratio of 40:60 at each wood particle size class generally had the highest values while wood plastic ratio of 60:40 had the least values for each of the three species. For each of the mechanical properties, C. pentandra had the highest mean values followed by G. arborea, while the least values were observed T. superba. There were improvements in both the physical and mechanical properties due to decrease in sawdust particle size class with the particle size class of ≤ 0.5 mm giving the best result. The results of the Analysis of variance revealed significant (P < 0.05) effects of the three study variables – wood species, sawdust particle size class and wood/plastic ratio on all the physical and mechanical properties of the WPCs. It can be concluded from the results of this study that wood plastic composites from sawdust particle size ≤ 0.5 and PET plastic bottle wastes with acceptable physical and mechanical properties are better produced using 40:60 wood/plastic ratio, and that at this ratio, all the three species are suitable for the production of wood plastic composites.Keywords: polyethylene terephthalate plastic bottle wastes, wood plastic composite, physical properties, mechanical properties
Procedia PDF Downloads 1916824 Board Composition and Performance of Listed Deposit Money Banks in Nigeria
Authors: Mary David, Denis Basila
Abstract:
This study assessed the Impact of Board Composition on the Performance of Listed Deposit Money Banks in Nigeria. A sample of ten (10) deposit money banks formed the sample of this study. Board size, gender diversity, and board independence were used as the independent variables, and firm size as a control variable, whiles the bank performance was proxy with Tobin’s Q (TQ) as the dependent variable. Secondary data was collected from secondary source through the annual report and account of the banks and was analyzed through the support of STATA 14 versions. Descriptive statistics, correlation matrix, and OLS multiple regression model were adopted for the study. Breusch and pagan lagrangian multiplier test for random effect was conducted. The findings of the study reveal that board size has positive and significant impact on Tobin’s Q, gender diversity has positive and significant impact on Tobin’s Q, while board independent had a negative and nonsignificant influence on the Tobin’s Q, Similarly, firm size was found to have a negative and nonsignificant impact on Tobin’s Q of the study banks. This study recommended that policy makers, stakeholders, and corporate managers of deposit money banks of Nigeria and related industries are encouraged to adopt board sizes and gender diversity that impact positively on bank performance.Keywords: board composition, performance, deposit money banks, nigeria
Procedia PDF Downloads 576823 Nature of Body Image Distortion in Eating Disorders
Authors: Katri K. Cornelissen, Lise Gulli Brokjob, Kristofor McCarty, Jiri Gumancik, Martin J. Tovee, Piers L. Cornelissen
Abstract:
Recent research has shown that body size estimation of healthy women is driven by independent attitudinal and perceptual components. The attitudinal component represents psychological concerns about body, coupled to low self-esteem and a tendency towards depressive symptomatology, leading to over-estimation of body size, independent of the Body Mass Index (BMI) someone actually has. The perceptual component is a normal bias known as contraction bias, which, for bodies is dependent on actual BMI. Women with a BMI less than the population norm tend to overestimate their size, while women with a BMI greater than the population norm tend to underestimate their size. Women whose BMI is close to the population mean are most accurate. This is indexed by a regression of estimated BMI on actual BMI with a slope less than one. It is well established that body dissatisfaction, i.e. an attitudinal distortion, leads to body size overestimation in eating disordered individuals. However, debate persists as to whether women with eating disorders may also suffer a perceptual body distortion. Therefore, the current study was set to ask whether women with eating disorders exhibit the normal contraction bias when they estimate their own body size. If they do not, this would suggest differences in the way that women with eating disorders process the perceptual aspects of body shape and size in comparison to healthy controls. 100 healthy controls and 33 women with a history of eating disorders were recruited. Critically, it was ensured that both groups of participants represented comparable and adequate ranges of actual BMI (e.g. ~18 to ~40). Of those with eating disorders, 19 had a history of anorexia nervosa, 6 bulimia nervosa, and 8 OSFED. 87.5% of the women with a history of eating disorders self-reported that they were either recovered or recovering, and 89.7% of them self-reported that they had had one or more instances of relapse. The mean time lapsed since first diagnosis was 5 years and on average participants had experienced two relapses. Participants were asked to fill number of psychometric measures (EDE-Q, BSQ, RSE, BDI) to establish the attitudinal component of their body image as well as their tendency to internalize socio-cultural body ideals. Additionally, participants completed a method of adjustment psychophysical task, using photorealistic avatars calibrated for BMI, in order to provide an estimate of their own body size and shape. The data from the healthy controls replicate previous findings, revealing independent contributions to body size estimation from both attitudinal and perceptual (i.e. contraction bias) body image components, as described above. For the eating disorder group, once the adequacy of their actual BMI ranges was established, a regression of estimated BMI on actual BMI had a slope greater than 1, significantly different to that from controls. This suggests that (some) eating disordered individuals process the perceptual aspects of body image differently from healthy controls. It therefore is necessary to develop interventions which are specific to the perceptual processing of body shape and size for the management of (some) individuals with eating disorders.Keywords: body image distortion, perception, recovery, relapse, BMI, eating disorders
Procedia PDF Downloads 576822 Asset Pricing Puzzle and GDP-Growth: Pre and Post Covid-19 Pandemic Effect on Pakistan Stock Exchange
Authors: Mohammad Azam
Abstract:
This work is an endeavor to empirically investigate the Gross Domestic Product-Growth as mediating variable between various factors and portfolio returns using a broad sample of 522 financial and non-financial firms enlisted on Pakistan Stock Exchange between January-1993 and June-2022. The study employs the Structural Equation modeling and Ordinary Least Square regression to determine the findings before and during the Covid-19 epidemiological situation, which has not received due attention by researchers. The analysis reveals that market and investment factors are redundant, whereas size and value show significant results, whereas Gross Domestic Product-Growth performs significant mediating impact for the whole time frame. Using before Covid-19 period, the results reveal that market, value, and investment are redundant, but size, profitability, and Gross Domestic Product-Growth are significant. During the Covid-19, the statistics indicate that market and investment are redundant, though size and Gross Domestic Product-Growth are highly significant, but value and profitability are moderately significant. The Ordinary Least Square regression shows that market and investment are statistically insignificant, whereas size is highly significant but value and profitability are marginally significant. Using the Gross Domestic Product-Growth augmented model, a slight growth in R-square is observed. The size, value and profitability factors are recommended to the investors for Pakistan Stock Exchange. Conclusively, in the Pakistani market, the Gross Domestic Product-Growth indicates a feeble moderating effect between risk-premia and portfolio returns.Keywords: asset pricing puzzle, mediating role of GDP-growth, structural equation modeling, COVID-19 pandemic, Pakistan stock exchange
Procedia PDF Downloads 666821 Discrimination and Classification of Vestibular Neuritis Using Combined Fisher and Support Vector Machine Model
Authors: Amine Ben Slama, Aymen Mouelhi, Sondes Manoubi, Chiraz Mbarek, Hedi Trabelsi, Mounir Sayadi, Farhat Fnaiech
Abstract:
Vertigo is a sensation of feeling off balance; the cause of this symptom is very difficult to interpret and needs a complementary exam. Generally, vertigo is caused by an ear problem. Some of the most common causes include: benign paroxysmal positional vertigo (BPPV), Meniere's disease and vestibular neuritis (VN). In clinical practice, different tests of videonystagmographic (VNG) technique are used to detect the presence of vestibular neuritis (VN). The topographical diagnosis of this disease presents a large diversity in its characteristics that confirm a mixture of problems for usual etiological analysis methods. In this study, a vestibular neuritis analysis method is proposed with videonystagmography (VNG) applications using an estimation of pupil movements in the case of an uncontrolled motion to obtain an efficient and reliable diagnosis results. First, an estimation of the pupil displacement vectors using with Hough Transform (HT) is performed to approximate the location of pupil region. Then, temporal and frequency features are computed from the rotation angle variation of the pupil motion. Finally, optimized features are selected using Fisher criterion evaluation for discrimination and classification of the VN disease.Experimental results are analyzed using two categories: normal and pathologic. By classifying the reduced features using the Support Vector Machine (SVM), 94% is achieved as classification accuracy. Compared to recent studies, the proposed expert system is extremely helpful and highly effective to resolve the problem of VNG analysis and provide an accurate diagnostic for medical devices.Keywords: nystagmus, vestibular neuritis, videonystagmographic system, VNG, Fisher criterion, support vector machine, SVM
Procedia PDF Downloads 1316820 Machine Learning Techniques in Bank Credit Analysis
Authors: Fernanda M. Assef, Maria Teresinha A. Steiner
Abstract:
The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines
Procedia PDF Downloads 956819 Applications of Nanoparticles via Laser Ablation in Liquids: A Review
Authors: Fawaz M. Abdullah, Abdulrahman M. Al-Ahmari, Madiha Rafaqat
Abstract:
Laser ablation of any solid target in the liquid leads to fabricate nanoparticles (NPs) with metal or different compositions of materials such as metals, alloys, oxides, carbides, hydroxides. The fabrication of NPs in liquids based on laser ablation has grown up rapidly in the last decades compared to other techniques. Nowadays, laser ablation has been improved to prepare different types of NPs with special morphologies, microstructures, phases, and sizes, which can be applied in various fields. The paper reviews and highlights the different sizes, shapes and application field of nanoparticles that are produced by laser ablation under different liquids and materials. Also, the paper provides a case study for producing a titanium NPs produced by laser ablation submerged in distilled water. The size of NPs is an important parameter, especially for their usage and applications. The size and shape have been analyzed by SEM, (EDAX) was applied to evaluate the oxidation and elements of titanium NPs and the XRD was used to evaluate the phase composition and the peaks of both titanium and some element. SEM technique showed that the synthesized NPs size ranges were between 15-35 nm which can be applied in various field such as annihilator for cancerous cell etc.Keywords: nanoparticles, laser ablation, titanium NPs, applications
Procedia PDF Downloads 1326818 Machine Learning Approach for Yield Prediction in Semiconductor Production
Authors: Heramb Somthankar, Anujoy Chakraborty
Abstract:
This paper presents a classification study on yield prediction in semiconductor production using machine learning approaches. A complicated semiconductor production process is generally monitored continuously by signals acquired from sensors and measurement sites. A monitoring system contains a variety of signals, all of which contain useful information, irrelevant information, and noise. In the case of each signal being considered a feature, "Feature Selection" is used to find the most relevant signals. The open-source UCI SECOM Dataset provides 1567 such samples, out of which 104 fail in quality assurance. Feature extraction and selection are performed on the dataset, and useful signals were considered for further study. Afterward, common machine learning algorithms were employed to predict whether the signal yields pass or fail. The most relevant algorithm is selected for prediction based on the accuracy and loss of the ML model.Keywords: deep learning, feature extraction, feature selection, machine learning classification algorithms, semiconductor production monitoring, signal processing, time-series analysis
Procedia PDF Downloads 1016817 Pattern Recognition Based on Simulation of Chemical Senses (SCS)
Authors: Nermeen El Kashef, Yasser Fouad, Khaled Mahar
Abstract:
No AI-complete system can model the human brain or behavior, without looking at the totality of the whole situation and incorporating a combination of senses. This paper proposes a Pattern Recognition model based on Simulation of Chemical Senses (SCS) for separation and classification of sign language. The model based on human taste controlling strategy. The main idea of the introduced model is motivated by the facts that the tongue cluster input substance into its basic tastes first, and then the brain recognizes its flavor. To implement this strategy, two level architecture is proposed (this is inspired from taste system). The separation-level of the architecture focuses on hand posture cluster, while the classification-level of the architecture to recognizes the sign language. The efficiency of proposed model is demonstrated experimentally by recognizing American Sign Language (ASL) data set. The recognition accuracy obtained for numbers of ASL is 92.9 percent.Keywords: artificial intelligence, biocybernetics, gustatory system, sign language recognition, taste sense
Procedia PDF Downloads 2846816 Effects of Gelatin on Characteristics and Dental Pathogen Inhibition by Silver Nanoparticles Synthesized from Ascorbic Acid
Authors: Siriporn Okonogi, Temsiri Suwan, Sakornrat Khongkhunthian, Jakkapan Sirithunyalug
Abstract:
In this study, silver nanoparticles (AgNPs) were prepared using ascorbic acid as a reducing agent and silver nitrate as a precursor. The effects of gelatin (G) on particle characteristics and dental pathogen inhibition were investigated. The spectra of AgNPs and G-AgNPs were compared using UV-Vis and Energy-dispersive X-ray (EDX) spectroscopy. The obtained AgNPs and G-AgNPs showed the maximum absorption at 410 and 430 nm, respectively, and EDX spectra of both systems confirmed Ag element. Scanning electron microscope showed that AgNPs and G-AgNPs were spherical in shape. Particles size, size distribution, and zeta potential were determined using dynamic light scattering approach. The size of AgNPs and G-AgNPs were 56 ± 2.4 and 67 ± 3.6 nm, respectively with a size distribution of 0.23 ± 0.03 and 0.19 ± 0.02, respectively. AgNPs and G-AgNPs exhibited negative zeta potential of 24.1 ± 2.7 mV and 32.7 ± 1.2 mV, respectively. Minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) of the obtained AgNPs and G-AgNPs against three strains of dental pathogenic bacteria; Streptococcus gordonii, Streptococcus mutans, and Staphylococcus aureus were determined using broth dilution method. AgNPs and G-AgNPs showed the strongest inhibition against S. gordonii with the MIC of 0.05 and 0.025 mg/mL, respectively and the MBC of 0.1 and 0.05 mg/mL, respectively. Cytotoxicity test of AgNPs and G-AgNPs on human breast cancer cells using MTT assay indicated that G-AgNPs (0.1 mg/mL) was significantly stronger toxic than AgNPs with the cell inhibition of 91.1 ± 5.4%. G-AgNPs showed significantly less aggregation after storage at room temperature for 90 days than G-AgNPs.Keywords: antipathogenic activity, ascorbic acid, cytotoxicity, stability
Procedia PDF Downloads 137