Search results for: synthetic dataset

Authors: Chulsang Yoo, Gildo Kim

Abstract:

Dual polarization radar provides comprehensive information about rainfall by measuring multiple parameters. In Korea, for the rainfall estimation, JPOLE and CSU-HIDRO algorithms are generally used. This study evaluated the local applicability of JPOLE and CSU-HIDRO algorithms in Korea by using the observed rainfall data collected on August, 2014 by the Biseulsan dual polarization radar data and KMA AWS. A total of 11,372 pairs of radar-ground rain rate data were classified according to thresholds of synthetic algorithms into suitable and unsuitable data. Then, evaluation criteria were derived by comparing radar rain rate and ground rain rate, respectively, for entire, suitable, unsuitable data. The results are as follows: (1) The radar rain rate equation including KDP, was found better in the rainfall estimation than the other equations for both JPOLE and CSU-HIDRO algorithms. The thresholds were found to be adequately applied for both algorithms including specific differential phase. (2) The radar rain rate equation including horizontal reflectivity and differential reflectivity were found poor compared to the others. The result was not improved even when only the suitable data were applied. Acknowledgments: This work was supported by the Basic Science Research Program through the National Research Foundation of Korea, funded by the Ministry of Education (NRF-2013R1A1A2011012).

Keywords: CSU-HIDRO algorithm, dual polarization radar, JPOLE algorithm, radar rainfall estimation algorithm

Procedia PDF Downloads 213

Authors: Parnaz Boodagh, Danila Vella, Antonio Damore, Laura Modica De Mohac, Sang-Ho Ye, Garret Coyan, Gaetano Burriesci, William Wagner, Federica Cosentino

Abstract:

The use of cardiac patches is among the main therapeutic solution for cardiovascular diseases, a leading mortality cause in the world with an increasing trend, responsible of 19 millions deaths in 2020. Several classes of biomaterials serve that purpose, both of synthetic origin and biological derivation, and many bioengineered treatment alternatives were proposed to satisfy two main requirements, providing structural support and promoting tissue remodeling. The objective of this paper is to compare the mechanical properties and the characterization of four cardiac patches: the Adeka, PhotoFix, CorPatch, and CardioCel patches. In vitro and in vivo tests included: biaxial, uniaxial, ball burst, suture retention for mechanical characterization; 2D surface topography, 3D volume and microstructure, and histology assessments for structure characterization; in vitro test to evaluate platelet deposition, calcium deposition, and macrophage polarization; rat right ventricular outflow tract (RVOT) models at 8- and 16-week time points to characterize the patch-host interaction. Lastly, the four patches were used to produce four stented aortic valve prosthesis, subjected to hydrodynamic assessment as well as durability testing to verify compliance with the standard ISO.

Keywords: cardiac patch, cardiovascular disease, cardiac repair, blood contact biomaterial

Procedia PDF Downloads 153

Authors: Soujanya Pasumarthi

Abstract:

Inverse docking is a relatively new technique that has been used to identify potential receptor targets of small molecules. Our docking software package MDock is well suited for such an application as it is both computationally efficient, yet simultaneously shows adequate results in binding affinity predictions and enrichment tests. As a validation study, we present the first stage results of an inverse-docking study which seeks to identify potential direct targets of PRIMA-1. PRIMA-1 is well known for its ability to restore mutant p53's tumor suppressor function, leading to apoptosis in several types of cancer cells. For this reason, we believe that potential direct targets of PRIMA-1 identified in silico should be experimentally screened for their ability to inhibitcancer cell growth. The highest-ranked human protein of our PRIMA-1 docking results is oxidosqualene cyclase (OSC), which is part of the cholesterol synthetic pathway. The results of two followup experiments which treat OSC as a possible anti-cancer target are promising. We show that both PRIMA-1 and Ro 48-8071, a known potent OSC inhibitor, significantly reduce theviability of BT-474 breast cancer cells relative to normal mammary cells. In addition, like PRIMA-1, we find that Ro 48-8071 results in increased binding of mutant p53 to DNA in BT- 474cells (which highly express p53). For the first time, Ro 48-8071 is shown as a potent agent in killing human breast cancer cells. The potential of OSC as a new target for developing anticancer therapies is worth further investigation.

Keywords: inverse docking, in silico screening, protein-ligand interactions, molecular docking

Procedia PDF Downloads 446

Authors: Wajid Mumtaz, Aamir Saeed Malik, Syed Saad Azhar Ali, Mohd Azhar Mohd Yasin

Abstract:

In this paper, a technique based on electroencephalogram (EEG) analysis is presented, aiming for diagnosing major depressive disorder (MDD) among a potential population of MDD patients and healthy controls. EEG is recognized as a clinical modality during applications such as seizure diagnosis, index for anesthesia, detection of brain death or stroke. However, its usability for psychiatric illnesses such as MDD is less studied. Therefore, in this study, for the sake of diagnosis, 2 groups of study participants were recruited, 1) MDD patients, 2) healthy people as controls. EEG data acquired from both groups were analyzed involving inter-hemispheric asymmetry and composite permutation entropy index (CPEI). To automate the process, derived quantities from EEG were utilized as inputs to classifier such as logistic regression (LR) and support vector machine (SVM). The learning of these classification models was tested with a test dataset. Their learning efficiency is provided as accuracy of classifying MDD patients from controls, their sensitivities and specificities were reported, accordingly (LR =81.7 % and SVM =81.5 %). Based on the results, it is concluded that the derived measures are indicators for diagnosing MDD from a potential population of normal controls. In addition, the results motivate further exploring other measures for the same purpose.

Keywords: major depressive disorder, diagnosis based on EEG, EEG derived features, CPEI, inter-hemispheric asymmetry

Procedia PDF Downloads 546

Authors: Sukhwinder K. Bhullar, M. B. G. Jun

Abstract:

The developments in biomedical industry have demanded the development of biocompatible, high performance materials to meet higher engineering specifications. The general requirements of such materials are to provide a combination of high stiffness and strength with significant weight savings, resistance to corrosion, chemical resistance, low maintenance, and reduced costs. Auxetic materials which come under the category of smart materials offer huge potential through measured enhancements in mechanical properties. Unique deformation mechanism, providing cushioning on indentation, automatically adjustable with its strength and thickness in response to forces and having memory returns to its neutral state on dissipation of stresses make them good candidate in biomedical industry. As simple extension and compression of tissues is of fundamental importance in biomechanics, therefore, to study the elastic behaviour of auxetic soft tissues implant is targeted in this paper. Therefore development and characterization of auxetic soft tissue implant is studied in this paper. This represents a real life configuration where soft tissue such as meniscus in knee replacement, ligaments and tendons often are taken as transversely isotropic. Further, as composition of alternating polydisperse blocks of soft and stiff segments combined with excellent biocompatibility make polyurethanes one of the most promising synthetic biomaterials. Hence selecting auxetic polyurathylene foam functional characterization is performed and compared with conventional polyurathylene foam.

Keywords: auxetic materials, deformation mechanism, enhanced mechanical properties, soft tissues

Procedia PDF Downloads 459

Authors: Chayakarn Bamrungbutr, James Sillitoe

Abstract:

The term ‘shadow port’ is used to describe a port whose markets are dominated by an adjacent port that has a more competitive capability. Recently, researchers have put effort into studying the mechanisms of how a regional port, in the shadow of a nearby predominant port which is a capital city port, can compete and grow. However, such mechanism is still unclear. This study thus focuses on understanding the growth of shadow port and the type of shadow port by using the two capital city ports of Thailand; Bangkok port (the former main port) and Laem Chabang port (the current main port), as the case study. By developing an understanding of the mechanisms of shadow, port could ultimately lead to an increase in the competitiveness. In this study, a framework of opportunity capture (introduced by Magala, 2004) will be used to create a framework for the study of the growth of the selected shadow port. In the process of building this framework, five groups of port development experts, consisting of government, council, academia, logistics provider and industry, will be interviewed. To facilitate this work, the Noticing, Collecting and Thinking model which was developed by Seidel (1998) will be used in an analysis of the dataset. The resulting analysis will be used to classify the type of shadow port. The type of these ports will be a significant factor for developing a feasible strategic guideline for the future management planning of ports, particularly, shadow ports, and then to increase the competitiveness of a nation’s maritime transport industry, and eventually lead to a boost in the national economy.

Keywords: shadow port, Bangkok Port, Laem Chabang Port, port growth

Procedia PDF Downloads 177

Authors: Iqra Yaseen

Abstract:

One of the well-known areas of computer science and engineering, image processing in the context of computer vision has been essential to automation. In remote sensing, medical science, and many other fields, it has made it easier to uncover previously undiscovered facts. Grading of diverse items is now possible because of neural network algorithms, categorization, and digital image processing. Its use in the classification of agricultural products, particularly in the grading of seeds or grains and their cultivars, is widely recognized. A grading and sorting system enables the preservation of time, consistency, and uniformity. Global population growth has led to an increase in demand for food staples, biofuel, and other agricultural products. To meet this demand, available resources must be used and managed more effectively. Image processing is rapidly growing in the field of agriculture. Many applications have been developed using this approach for crop identification and classification, land and disease detection and for measuring other parameters of crop. Vegetation localization is the base of performing these task. Vegetation helps to identify the area where the crop is present. The productivity of the agriculture industry can be increased via image processing that is based upon Unmanned Aerial Vehicle photography and satellite. In this paper we use the machine learning techniques like Convolutional Neural Network, deep learning, image processing, classification, You Only Live Once to UAV imaging dataset to divide the crop into distinct groups and choose the best way to use it.

Keywords: image processing, UAV, YOLO, CNN, deep learning, classification

Procedia PDF Downloads 107

Authors: Syed Atif Hassan, Luv Mehta, Syed Asif Hassan

Abstract:

Hit song science is a field of investigation wherein machine learning techniques are applied to music tracks in order to extract such features from audio signals which can capture information that could explain the popularity of respective tracks. Record companies invest huge amounts of money into recruiting fresh talents and churning out new music each year. Gaining insight into the basis of why a song becomes popular will result in tremendous benefits for the music industry. This paper aims to extract basic musical and more advanced, acoustic features from songs while also taking into account external factors that play a role in making a particular song popular. We use a dataset derived from popular Spotify playlists divided by genre. We use ten genres (blues, classical, country, disco, hip-hop, jazz, metal, pop, reggae, rock), chosen on the basis of clear to ambiguous delineation in the typical sound of their genres. We feed these features into three different classifiers, namely, SVM with RBF kernel, a deep neural network, and a recurring neural network, to build separate predictive models and choosing the best performing model at the end. Predicting song popularity is particularly important for the music industry as it would allow record companies to produce better content for the masses resulting in a more competitive market.

Keywords: classifier, machine learning, music tracks, popularity, prediction

Procedia PDF Downloads 663

Authors: Arth J. Shah, Madhu R. Kamble

Abstract:

Voice biometric liveness detection is customized to certify an authentication process of the voice data presented is genuine and not a recording or synthetic voice. With the rise of deepfakes and other equivalently sophisticated spoofing generation techniques, it’s becoming challenging to ensure that the person on the other end is a live speaker or not. Voice Liveness Detection (VLD) system is a group of security measures which detect and prevent voice spoofing attacks. Motivated by the recent development of the Kolmogorov-Arnold Network (KAN) based on the Kolmogorov-Arnold theorem, we proposed KAN for the VLD task. To date, multilayer perceptron (MLP) based classifiers have been used for the classification tasks. We aim to capture not only the compositional structure of the model but also to optimize the values of univariate functions. This study explains the mathematical as well as experimental analysis of KAN for VLD tasks, thereby opening a new perspective for scientists to work on speech and signal processing-based tasks. This study emerges as a combination of traditional signal processing tasks and new deep learning models, which further proved to be a better combination for VLD tasks. The experiments are performed on the POCO and ASVSpoof 2017 V2 database. We used Constant Q-transform, Mel, and short-time Fourier transform (STFT) based front-end features and used CNN, BiLSTM, and KAN as back-end classifiers. The best accuracy is 91.26 % on the POCO database using STFT features with the KAN classifier. In the ASVSpoof 2017 V2 database, the lowest EER we obtained was 26.42 %, using CQT features and KAN as a classifier.

Keywords: Kolmogorov Arnold networks, multilayer perceptron, pop noise, voice liveness detection

Procedia PDF Downloads 39

Authors: D. Karibasavaraja, Ramesh M.R., Sufiyan Ahmed, Noyonika M.R., Sameeksha A. V., Mamatha J., Samiksha S. Urs

Abstract:

This research paper gives an overview of the experimental analysis of natural fibers with polymer composite. The whole world is concerned about conserving the environment. Henceforth, the demand for natural and decomposable materials is increasing. The application of natural fibers is widely used in aerospace for manufacturing aircraft bodies, and ship construction in navy fields. Based on the literature review, researchers and scientists are replacing synthetic fibers with natural fibers. The selection of these fibers mainly depends on lightweight, easily available, and economical and has its own physical and chemical properties and many other properties that make them a fine quality fiber. The pineapple fiber has desirable properties of good mechanical strength, high cellulose content, and fiber length. Hybrid composite was prepared using different proportions of pineapple fiber and banana fiber, and their ratios were varied in 90% polypropylene mixed with 5% banana fiber and 5% pineapple fiber, 85% polypropylene mixed with 7.5% banana fiber and 7.5% pineapple fiber and 80% polypropylene mixed with 10% banana fiber and 10% pineapple fiber. By impact experimental analysis, we concluded that the combination of 90% polypropylene and 5% banana fiber and 5% pineapple fiber exhibits a higher toughness value with mechanical strength. We also conducted scanning electron microscopy (SEM) analysis which showed better fiber orientation bonding between the banana and pineapple fibers with polypropylene composites. The main aim of the present research is to evaluate the properties of pineapple fiber and banana fiber reinforced with hybrid polypropylene composites.

Keywords: toughness, fracture, impact strength, banana fibers, pineapple fibers, tensile strength, SEM analysis

Procedia PDF Downloads 156

Authors: R. Hassan, J. Duncombe, E. Darke, A. Dias, K. Anderson, R. G. Middleton

Abstract:

Background: NHS England has set itself the task of delivering a “Net Zero” National Health service by 2040. It is incumbent upon all health care practioners to work towards this goal. Orthopaedic surgeons are no exception. Distal radial fractures are the most common fractures sustained by the adult population. However, studiesare shortcoming on individual patient experience. The aim of this study was to assess the patient’ssatisfaction and outcomes with woodcast used in the conservative management of distal radius fractures. Methods: For all patients managed with woodcast in our unit, we undertook a structured questionnairethat included the Patient Rated Wrist Evaluation (PRWE) score, The EQ-5D-5L score, and the pain numerical score at the time of injury and six weeks after. Results: 30 patients were initially managed with woodcast.80% of patients tolerated woodcast for the full duration of their treatment. Of these, 20% didn’t tolerate woodcast and had their casts removed within 48 hours. Of the remaining, 79.1% were satisfied about woodcast comfort, 66% were very satisfied about woodcast weight, 70% were satisfied with temperature and sweatiness, 62.5% were very satisfied about the smell/odour, and 75% were satisfied about the level of support woodcast provided. During their treatment, 83.3% of patients rated their pain as five or less. Conclusion: For those who completed their treatment in woodcast, none required any further intervention or utilised the open appointment because of ongoing wrist problems. In conclusion, when woodcast is tolerated, patients’ satisfaction and outcome levels were good. However, we acknowledged 20% of patients in our series were not able to tolerate woodacst, Therefore, we suggest a comparison between the widely used synthetic plaster of Pariscasting and woodcast to come in order.

Keywords: distal radius fractures, ecological cast, sustainability, woodcast

Procedia PDF Downloads 85

Authors: Vinicius Marzall, Jussanã Milograna

Abstract:

The urban drainwatering remains a major challenge for most of the Brazilian cities. Not so different of the most part, Goiania, a state capital located in Midwest of the country has few legislations about the subject matter and only one registered solution of compensative techniques for drainwater. This paper clam to show some solutions which are adopted in other Brazilian cities with consolidated legislation, suggesting technics about detention tanks in a building sit. This study analyzed and compared the legislation of Curitiba, Porto Alegre e Sao Paulo, with the actual legislation and politics of Goiania. After this, were created models with adopted data for dimensioning the size of detention tanks using the envelope curve method considering synthetic series for intense precipitations and building sits between 250 m² and 600 m², with an impermeabilization tax of 50%. The results showed great differences between the legislation of Goiania and the documentation of the others cities analyzed, like the number of techniques for drainwatering applied to the reality of the cities, educational actions to awareness the population about care the water courses and political management by having a specified funds for drainwater subjects, for example. Besides, the use of detention tank showed itself practicable, have seen that the occupation of the tank is minor than 3% of the building sit, whatever the size of the terrain, granting the exit flow to pre-occupational taxes in extreme rainfall events. Also, was developed a linear equation to measure the detention tank based in the size of the building sit in Goiania, making simpler the calculation and implementation for non-specialized people.

Keywords: clean technology, legislation, rainwater management, urban drainwater

Procedia PDF Downloads 159

Authors: Jing Zhao, Dayong Liu, Shihao Wang, Xinghua Zhu, Delong Li

Abstract:

Uhumanned Underwater Vehicles generally operate in the deep sea, which has its own unique working conditions. Lithium-ion power batteries should have the necessary stability and endurance for use as an underwater vehicle’s power source. Therefore, it is essential to accurately forecast how long lithium-ion batteries will last in order to maintain the system’s reliability and safety. In order to model and forecast lithium battery Remaining Useful Life (RUL), this research suggests a model based on Complete Ensemble Empirical Mode Decomposition with Adaptive noise-Temporal Convolutional Net (CEEMDAN-TCN). In this study, two datasets, NASA and CALCE, which have a specific gap in capacity data fluctuation, are used to verify the model and examine the experimental results in order to demonstrate the generalizability of the concept. The experiments demonstrate the network structure’s strong universality and ability to achieve good fitting outcomes on the test set for various battery dataset types. The evaluation metrics reveal that the CEEMDAN-TCN prediction performance of TCN is 25% to 35% better than that of a single neural network, proving that feature expansion and modal decomposition can both enhance the model’s generalizability and be extremely useful in industrial settings.

Keywords: lithium-ion battery, remaining useful life, complete EEMD with adaptive noise, temporal convolutional net

Procedia PDF Downloads 152

Authors: Gaetano Zazzaro, Angelo Martone, Roberto V. Montaquila, Luigi Pavone

Abstract:

Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.

Keywords: artificial neural network, data mining, electroencephalogram, epilepsy, feature extraction, seizure detection, signal processing

Procedia PDF Downloads 188

Authors: Timo Avikainen, Tuukka Verho

Abstract:

The use of natural fibers as reinforcements is growing increasingly in polymers which are involved in e.g. structural, vibration, and acoustic applications. The use of bio composites is being investigated as lightweight materials with specific properties like the ability to dissipate vibration energy and positive environmental profile and are thus considered as potential replacements for synthetic composites. The macro-level mechanical properties of the biocomposite material depend on several parameters in the detailed architecture and morphology of the reinforcing fiber structure. The polymer matrix phase is often applied to remain the fiber structure in touch. A big role in the packaging details of the fibers is related to the used manufacturing processes like extrusion, injection molding and treatments. There are typically big variances in the detailed parameters of the microstructure fibers. The study addressed the question of how the multiscale simulation methodology works in bio composites with short pulp fibers. The target is to see how the vibro – acoustic performance of thin–walled panels can be controlled by the detailed characteristics of the fiber material. Panels can be used in sound-producing speakers or sound insulation applications. The multiscale analysis chain is tested starting from the microstructural level and continuing via macrostructural material parameters to the product component part/assembly levels. Another application is the dynamic impact type of loading, exposing the material to the crack type damages that is in this study modeled as the Charpy impact tests.

Keywords: bio composite, pulp fiber, vibration, acoustics, impact, FEM

Procedia PDF Downloads 82

Authors: Sharon Li, Zhonghang Xia

Abstract:

Post-database search is an essential phase in peptide identification using tandem mass spectrometry (MS/MS) to refine peptide-spectrum matches (PSMs) produced by database search engines. These engines frequently face difficulty differentiating between correct and incorrect peptide assignments. Despite advances in statistical and machine learning methods aimed at improving the accuracy of peptide identification, challenges remain in selecting critical features for these models. In this study, two machine learning models—a random forest tree and a support vector machine—were applied to three datasets to enhance PSMs. SHAP values were utilized to determine the significance of each feature within the models. The experimental results indicate that the random forest model consistently outperformed the SVM across all datasets. Further analysis of SHAP values revealed that the importance of features varies depending on the dataset, indicating that a feature's role in model predictions can differ significantly. This variability in feature selection can lead to substantial differences in model performance, with false discovery rate (FDR) differences exceeding 50% between different feature combinations. Through SHAP value analysis, the most effective feature combinations were identified, significantly enhancing model performance.

Keywords: peptide identification, SHAP value, feature selection, random forest tree, support vector machine

Procedia PDF Downloads 23

Authors: Jain Jyoti, Jain Shorab, Sinha Shishir

Abstract:

In the field of material engineering, composites are in great concern for their nonbiodegradability and their cost. In order to reduce its cost and weight, plant derived fibers witnessed miraculous triumph. Plant fibers can be of different types like seed fibers, blast fibers, leaf fibers, etc. Composites can be reinforced with exclusively one type of natural fiber or also can be combined with two or more different types of natural or synthetic fibers to boost up their specific properties. Among all natural fibers, wheat straw, bagasse, kenaf, pineapple leaf, banana, coir, ramie, flax, etc. pineapple leaf fibers have very good mechanical properties. Being hydrophilic in nature, pineapple leaf fibers have very less affinity towards all types of polymer matrixes like HDPE, LDPE, PET, epoxy, etc. Surface treatments like alkaline treatment in different concentrations were conducted to improve its adhesion and compatibility towards hydrophobic polymer matrix i.e. epoxy resin. Pineapple leaf fiber epoxy composites have been prepared using hand layup method. Effect of fiber loading and surface treatments have been studied for different mechanical properties i.e. tensile strength, flexural strength and impact properties of pineapple leaf fiber composites. Analysis of fiber morphology has also been studied using FTIR, XRD. Scanning electron microscopy has also been used to study and compare the morphology of untreated and treated fibers. Also, the fracture surface has been reviewed comparing the reported literature of other eminent researchers of this field.

Keywords: composite, mechanical, natural fiber, pineapple leaf fiber

Procedia PDF Downloads 257

Authors: Kristian Bautista, Ruben A. Idoy

Abstract:

A bio-inspired metaheuristic algorithm inspired by the theory of collective animal behavior (CAB) was integrated to density-based clustering modeled as multimodal optimization problem. The algorithm was tested on synthetic, Iris, Glass, Pima and Thyroid data sets in order to measure its effectiveness relative to CDE-based Clustering algorithm. Upon preliminary testing, it was found out that one of the parameter settings used was ineffective in performing clustering when applied to the algorithm prompting the researcher to do an investigation. It was revealed that fine tuning distance δ3 that determines the extent to which a given data point will be clustered helped improve the quality of cluster output. Even though the modification of distance δ3 significantly improved the solution quality and cluster output of the algorithm, results suggest that there is no difference between the population mean of the solutions obtained using the original and modified parameter setting for all data sets. This implies that using either the original or modified parameter setting will not have any effect towards obtaining the best global and local animal positions. Results also suggest that CDE-based clustering algorithm is better than CAB-density clustering algorithm for all data sets. Nevertheless, CAB-density clustering algorithm is still a good clustering algorithm because it has correctly identified the number of classes of some data sets more frequently in a thirty trial run with a much smaller standard deviation, a potential in clustering high dimensional data sets. Thus, the researcher recommends further investigation in the post-processing stage of the algorithm.

Keywords: clustering, metaheuristics, collective animal behavior algorithm, density-based clustering, multimodal optimization

Procedia PDF Downloads 230

Authors: Rodolfo Lorbieski, Silvia Modesto Nassar

Abstract:

Many supervised machine learning tasks require decision making across numerous different classes. Multi-class classification has several applications, such as face recognition, text recognition and medical diagnostics. The objective of this article is to analyze an adapted method of Stacking in multi-class problems, which combines ensembles within the ensemble itself. For this purpose, a training similar to Stacking was used, but with three levels, where the final decision-maker (level 2) performs its training by combining outputs from the tree-based pair of meta-classifiers (level 1) from Bayesian families. These are in turn trained by pairs of base classifiers (level 0) of the same family. This strategy seeks to promote diversity among the ensembles forming the meta-classifier level 2. Three performance measures were used: (1) accuracy, (2) area under the ROC curve, and (3) time for three factors: (a) datasets, (b) experiments and (c) levels. To compare the factors, ANOVA three-way test was executed for each performance measure, considering 5 datasets by 25 experiments by 3 levels. A triple interaction between factors was observed only in time. The accuracy and area under the ROC curve presented similar results, showing a double interaction between level and experiment, as well as for the dataset factor. It was concluded that level 2 had an average performance above the other levels and that the proposed method is especially efficient for multi-class problems when compared to binary problems.

Keywords: stacking, multi-layers, ensemble, multi-class

Procedia PDF Downloads 269

Authors: Tal Remez, Or Litany, Alex Bronstein

Abstract:

The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots), which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.

Keywords: binary pixels, maximum likelihood, neural networks, sparse coding

Procedia PDF Downloads 201

Authors: Muhtasim Shafi Kader, Fizar Ahmed, Annesha Acharjee

Abstract:

Machine learning and data mining are crucial in health care, as well as medical information and detection. Machine learning approaches are now being utilized to improve awareness of a variety of critical health issues, including diabetes detection, neuron cell tumor diagnosis, COVID 19 identification, and so on. Parkinson’s disease is basically a disease for our senior citizens in Bangladesh. Parkinson's Disease indications often seem progressive and get worst with time. People got affected trouble walking and communicating with the condition advances. Patients can also have psychological and social vagaries, nap problems, hopelessness, reminiscence loss, and weariness. Parkinson's disease can happen in both men and women. Though men are affected by the illness at a proportion that is around partial of them are women. In this research, we have to get out the accurate ML algorithm to find out the disease with a predictable dataset and the model of the following machine learning classifiers. Therefore, nine ML classifiers are secondhand to portion study to use machine learning approaches like as follows, Naive Bayes, Adaptive Boosting, Bagging Classifier, Decision Tree Classifier, Random Forest classifier, XBG Classifier, K Nearest Neighbor Classifier, Support Vector Machine Classifier, and Gradient Boosting Classifier are used.

Keywords: naive bayes, adaptive boosting, bagging classifier, decision tree classifier, random forest classifier, XBG classifier, k nearest neighbor classifier, support vector classifier, gradient boosting classifier

Procedia PDF Downloads 129

Authors: Yi-Chun Wu, Nai-Yun Chang, Chuan LI

Abstract:

This study investigates a feasible range of composition for the mixture of gelatin and polyvinyl alcohol to form nanofibers by electrospinning. Gelatin, one of the most available naturally derived hydrogels of amino acids, is a popular choice for food additives, cosmetic ingredients, biomedical implants, or dressing of its non-toxic and biodegradable nature. Nevertheless, synthetic hydrogel polyvinyl alcohol has long been used as a thickening agent for adhesion purposes. Many biomedical devices are also containing polyvinyl-alcohol as a major content, such as eye drops and contact lenses. To discover appropriate compositions of gelatin and polyvinyl-alcohol for electrospun nanofibers, polymer solutions of different volumetric ratios between gelatin and polyvinyl alcohol were prepared for electrospinning. The viscosity, surface tension, pH value, and electrical conductance of polymer solutions were measured. On the nanofibers, the vibrational modes of molecular structures in nanofibers were investigated by Fourier-transform infrared spectroscopy. The morphologies and surface chemical elements of fibers were examined by the scanning electron microscope and the energy-dispersive X-ray spectroscopy. The hydrophilicity of nanofiberswas evaluated by the water contact angles on the surface of the fibers. To further test the biotoxicity of nanofibers, an in-vitro 3T3 fibroblasts culture further tested the biotoxicity of the electrospun nanofibers. Throughstatistical analyses of the experimental data, it is found that the polyvinyl-alcohol rich composition (the volumetric ratio of gelatin/polyvinyl-alcohol < 1) would be a preferable choice for the formation of nanofibers by the current setup of electrospinning. These electrospun nanofibers tend to be hydrophilic with no biotoxicity threat to the 3T3 fibroblasts.

Keywords: gelatin, polyvinyl-alcohol, nanofibers, electrospinning, spin coating

Procedia PDF Downloads 85

Authors: Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

Abstract:

We propose to record Activities of Daily Living (ADLs) of elderly people using a vision-based system so as to provide better assistive and personalization technologies. Current ADL-related research is based on data collected with help from non-elderly subjects in laboratory environments and the activities performed are predetermined for the sole purpose of data collection. To obtain more realistic datasets for the application, we recorded ADLs for the elderly with data collected from real-world environment involving real elderly subjects. Motivated by the need to collect data for more effective research related to elderly care, we chose to collect data in the room of an elderly person. Specifically, we installed Kinect, a vision-based sensor on the ceiling, to capture the activities that the elderly subject performs in the morning every day. Based on the data, we identified 12 morning activities that the elderly person performs daily. To recognize these activities, we created a HARELCARE framework to investigate into the effectiveness of existing Human Activity Recognition (HAR) algorithms and propose the use of a transfer learning algorithm for HAR. We compared the performance, in terms of accuracy, and training progress. Although the collected dataset is relatively small, the proposed algorithm has a good potential to be applied to all daily routine activities for healthcare purposes such as evidence-based diagnosis and treatment.

Keywords: daily activity recognition, healthcare, IoT sensors, transfer learning

Procedia PDF Downloads 132

Authors: Benjamin M Dauda, Esther Ibrahim, Sylvester Gadimoh, Asabe Mustapha, Jiyah Mohammed

Abstract:

Despite diverse optimization techniques on natural hydrophilic fibers, hydrophobic synthetic fibers are still the best oil sorption materials. However, these hydrophobic fibers are not biodegradable, making their disposal problematic. To this end, this work sets out to develop Nonwoven sorbents from epoxy-coated Cotton fibers. As a way of improving the compatibility of the crude oil and reduction of moisture absorption, cotton fibers were coated with epoxy resin by immersion in acetone-thinned epoxy solution. A needle-punching machine was used to convert the fibers into coherent nonwoven sheets. An oil sorption experiment was then carried out. The result indicates that the developed epoxy-modified sorbent has a higher crude oil-sorption capacity compared with those of untreated cotton and commercial polypropylene sorbents. Absorption Curves show that the coated fiber and polypropylene sorbent saturated faster than the uncoated cotton fiber pad. The result also shows that the coated cotton sorbent adsorbed crude faster than the polypropylene sorbent, and the equilibrium exhaustion was also higher. After a simple mechanical squeezing process, the Nonwoven pads could be restored to their original form and repeatedly recycled for oil/water separation. The results indicate that the cotton-coated non-woven pads hold promise for the cleanup of oil spills. Our data suggests that the sorption behaviors of the epoxy-coated Nonwoven pads and their crude oil sorption capacity are relatively stable under various environmental conditions compared to the commercial sheet.

Keywords: oil spill, adsorption, cotton, epoxy, nonwoven

Procedia PDF Downloads 55

Authors: K. M. Shahunja, Peter D. Sly, Tahmina Begum, Tuhin Biswas, Abdullah Mamun

Abstract:

Background: Various associations between different environmental exposures and asthma have been reported in different countries and populations. We aimed to investigate the associations between family, neighbourhood, and psychosocial environmental factors and asthma in Australia by conducting a systematic review and meta-analysis. Methods: We analysed the primary research studies conducted in Australia across multiple databases, including PubMed, EMBASE, and Scopus, and published between 2000 and 2020. The reviews and analyses focused on the overall association of different environmental exposures with the development or exacerbation of asthma symptoms or asthma-related hospital visits. Quality-effect meta-analysis was done to estimate the pooled odds ratio for different environmental exposures for asthma symptoms. Findings: Among the 4,799 unique published articles found, 46 were included here for systematic review and 28 for meta-analysis. Our review found that psychosocial factors, including low socioeconomic condition, maternal depression, mental stress, ethnicity, and discrimination, are associated with asthma symptoms. Pooled analysis was conducted on family and neighbourhood environmental factors and revealed that environmental tobacco smoking (ETS) (OR 1·69, 95% CI 1·19–2.38), synthetic bedding (OR 1·91, 95% CI 1·48–2·47) and gas heaters (OR 1·40, 95% CI 1·12–1·76) had significant overall associations with asthma-symptoms in Australia. Conclusion: Although the studies were heterogeneous, both systematic review and meta-analysis found several psychosocial and family environmental exposures to be significantly associated with asthma symptoms. Further study to identify their causal relationship and modification may reduce asthma symptoms in the Australian population.

Keywords: asthma, Australia, environment, systematic review

Procedia PDF Downloads 210

Authors: Bhavana V. Mohite, Satish V. Patil

Abstract:

Bacterial cellulose (BC) is an alternative for plant cellulose (PC) that prevents global warming leads to preservation of nature. Although PC and BC have the same chemical structure, BC is superior with its properties like its size, purity, porosity, degree of polymerization, crystallinity and water holding capacity, thermal stability etc. On this background the present study focus production and applications of BC as antimicrobial wound dressing material. BC was produced by Gluconoacetobacter hansenii (strain NCIM 2529) under shaking condition and statistically enhanced upto 7.2 g/l from 3.0 g/l. BC was analyzed for its physico mechanical, structural and thermal characteristics. BC produced at shaking condition exhibits more suitable properties in support to its high performance applications. The potential of nano silver impregnated BC was determined for sustained release modern antimicrobial wound dressing material by swelling ratio, mechanical properties and antimicrobial activity against Staphylococcus aureus. BC in nanocomposite form with other synthetic polymer like PVA shows improvement in its properties such as swelling ratio (757% to 979%) and sustainable release of antibacterial agent. The high drug loading and release potential of BC was evidenced in support to its nature as antimicrobial wound dressing material. The nontoxic biocompatible nature of BC was confirmed by MTT assay on human epidermal cells with 90% cell viability that allows its application as a regenerative biomaterial. Thus, BC as a promising new generation antimicrobial wound dressing material was projected.

Keywords: agitated culture, biopolymer, gluconoacetobacter hansenii, nanocomposite

Procedia PDF Downloads 301

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 118

Authors: Zhou Yang, Heli Sun, Jianbin Huang, Jizhong Zhao, Shaojie Qiao

Abstract:

Traffic prediction is essential in a multitude of ways in modern urban life. The researchers of earlier work in this domain carry out the investigation chiefly with two major focuses: (1) the accurate forecast of future values in multiple time series and (2) knowledge extraction from spatial-temporal correlations. However, two key considerations for traffic prediction are often missed: the completeness of raw data and the full context of the prediction timestamp. Concentrating on the two drawbacks of earlier work, we devise an approach that can address these issues in a two-phase framework. First, we utilize the raw trajectories to a greater extent through building a VLA table and data compression. We obtain the intra-trajectory features with graph-based encoding and the intertrajectory ones with a grid-based model and the technique of back projection that restore their surrounding high-resolution spatial-temporal environment. To the best of our knowledge, we are the first to study direct feature extraction from raw trajectories for traffic prediction and attempt the use of raw data with the least degree of reduction. In the prediction phase, we provide a broader context for the prediction timestamp by taking into account the information that are around it in the training dataset. Extensive experiments on several well-known datasets have verified the effectiveness of our solution that combines the strength of raw trajectory data and prediction context. In terms of performance, our approach surpasses several state-of-the-art methods for traffic prediction.

Keywords: traffic prediction, raw data utilization, context building, data reduction

Procedia PDF Downloads 127

Authors: Elene Tatunashvili, Bun Chan, Philippe E. Nashar, Christopher S. P. McErlean

Abstract:

The reduction of aryl diazonium salts is one of the most efficient ways to generate aryl radicals for use in a wide range of transformations, including Sandmeyer-type reactions, Meerwein arylations of olefins and Gomberg-Bachmann-Hey arylations of heteroaromatic systems. The aryl diazonium species can be reduced electrochemically, by UV irradiation, inner-sphere and outer-sphere single electron transfer processes (SET) from metal salts, SET from photo-excited organic catalysts or fragmentation of adducts with weak bases (acetate, hydroxide, etc.). This paper details an approach for the metal-free reduction of aryl diazonium salts, which facilitates the efficient synthesis of various aromatic compounds under exceedingly mild reaction conditions. By measuring the oxidation potential of a number of organic molecules, a series of nucleophiles were identified that reduce aryl diazonium salts via the addition-fragmentation mechanism. This approach leads to unprecedented operational simplicity: The reactions are very rapid and proceed in the open air; there is no need for external irradiation or heating, and the process is compatible with a large number of radical reactions. We illustrate these advantages by using the addition-fragmentation strategy to regioselectively arylate a series of heterocyclic compounds, to synthesize ketones by arylation of silyl enol ethers, and to synthesize benzothiophene and phenanthrene derivatives by radical annulation reactions.

Keywords: diazonium salts, hantzsch esters, oxygen, radical reactions, synthetic methods

Procedia PDF Downloads 149

Authors: Beryl Apondi Obola

Abstract:

Introduction: Mosquitoes are known to transmit various diseases such as malaria, dengue fever, and Zika virus. Mosquito repellents are commonly used to prevent mosquito bites. However, some of these repellents contain chemicals that can be harmful to human health and the environment. Therefore, there is a need to find alternative mosquito repellents that are safe and effective. Objective: The objective of this research is to investigate the effectiveness of banana leaves as an alternative mosquito repellent on Plasmodium falciparum and Plasmodium vivax. Methodology: The research will be conducted in two phases. In the first phase, the repellent properties of banana leaves will be tested in a laboratory setting. The leaves will be crushed and mixed with water to extract the active ingredients. The extract will be tested against mosquitoes in a controlled environment. The number of mosquitoes that are repelled by the extract will be recorded. In the second phase, the effectiveness of the banana leaf extract will be tested in the field. The extract will be applied to the skin of human volunteers, and the number of mosquito bites will be recorded. The results will be compared to a commercially available mosquito repellent. Expected Outcomes: The expected outcome of this research is to determine whether banana leaves can be used as an effective mosquito repellent. If the results are positive, banana leaves could be used as an alternative to chemical-based mosquito repellents. Conclusion: Banana leaves have been used for various purposes in traditional medicine. This research aims to investigate the potential of banana leaves as an alternative mosquito repellent. The results of this research could have significant implications for public health and the environment

Keywords: banana leaf extract, mosquito repellant, plasmodium falciparum, public health

Procedia PDF Downloads 92