Search results for: processed fly ash
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 939

Search results for: processed fly ash

789 Breast Cancer Metastasis Detection and Localization through Transfer-Learning Convolutional Neural Network Classification Based on Convolutional Denoising Autoencoder Stack

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 106
788 Magnesium Alloys for Biomedical Applications Processed by Severe Plastic Deformation

Authors: Mariana P. Medeiros, Amanda P. Carvallo, Augusta Isaac, Milos Janecek, Peter Minarik, Mayerling Martinez Celis, Roberto. R. Figueiredo

Abstract:

The effect of high pressure torsion processing on mechanical properties and corrosion behavior of pure magnesium and Mg-Zn, Mg-Zn-Ca, Mg-Li-Y, and Mg-Y-RE alloys is investigated. Micro-tomography and SEM characterization are used to estimate corrosion rate and evaluate non-uniform corrosion features. The results show the severe plastic deformation processing improves the strength of all magnesium alloys, but deformation localization can take place in the Mg-Zn-Ca and Mg-Y-RE alloys. The occurrence of deformation localization is associated with low strain rate sensitivity in these alloys and with severe corrosion localization. Pure magnesium and Mg-Zn and Mg-Li-Y alloys display good corrosion resistance with low corrosion rate and maintained integrity after 28 days of immersion in Hank`s solution.

Keywords: magnesium alloys, severe plastic deformation, corrosion, biodegradable alloys

Procedia PDF Downloads 69
787 Multiple Fault Detection and Classification in a Coupled Motor with Rotor Using Artificial Neural Network

Authors: Mehrdad Nouri Khajavi, Gollamhassan Payganeh, Mohsen Fallah Tafti

Abstract:

Fault diagnosis is an important aspect of maintaining rotating machinery health and increasing productivity. Many researches has been done in this regards. Many faults such as unbalance, misalignment, looseness, bearing faults, etc. have been considered and diagnosed with different techniques. Most of the researches in fault diagnosis of rotating machinery deal with single fault. Where as in reality faults usually occur simultaneously and it is, therefore, necessary to recognize them at the same time. In this research, two of the most common faults namely unbalance and misalignment have been considered simultaneously with different intensity and then identified and classified with the use of Multi-Layer Perception Neural Network (MLPNN). Processed Vibration signals are used as the input to the MLPNN, and the class of mixed unbalancy, and misalignment is the output of the NN.

Keywords: unbalance, parallel misalignment, combined faults, vibration signals

Procedia PDF Downloads 319
786 Neuron Imaging in Lateral Geniculate Nucleus

Authors: Sandy Bao, Yankang Bao

Abstract:

The understanding of information that is being processed in the brain, especially in the lateral geniculate nucleus (LGN), has been proven challenging for modern neuroscience and for researchers with a focus on how neurons process signals and images. In this paper, we are proposing a method to image process different colors within different layers of LGN, that is, green information in layers 4 & 6 and red & blue in layers 3 & 5 based on the surface dimension of layers. We take into consideration the images in LGN and visual cortex, and that the edge detected information from the visual cortex needs to be considered in order to return back to the layers of LGN, along with the image in LGN to form the new image, which will provide an improved image that is clearer, sharper, and making it easier to identify objects in the image. Matrix Laboratory (MATLAB) simulation is performed, and results show that the clarity of the output image has significant improvement.

Keywords: lateral geniculate nucleus, matrix laboratory, neuroscience, visual cortex

Procedia PDF Downloads 230
785 Investigation of the Usability of Biochars Obtained from Olive Pomace and Smashed Olive Seeds as Additives for Bituminous Binders

Authors: Muhammed Ertugrul Celoglu, Beyza Furtana, Mehmet Yilmaz, Baha Vural Kok

Abstract:

Biomass, which is considered to be one of the largest renewable energy sources in the world, has a potential to be utilized as a bitumen additive after it is processed by a wide variety of thermochemical methods. Furthermore, biomasses are renewable in short amounts of time, and they possess a hydrocarbon structure. These characteristics of biomass promote their usability as additives. One of the most common ways to create materials with significant economic values from biomasses is the processes of pyrolysis. Pyrolysis is defined as the process of an organic matter’s thermochemical degradation (carbonization) at a high temperature and in an anaerobic environment. The resultant liquid substance at the end of the pyrolysis is defined as bio-oil, whereas the resultant solid substance is defined as biochar. Olive pomace is the resultant mildly oily pulp with seeds after olive is pressed and its oil is extracted. It is a significant source of biomass as the waste of olive oil factories. Because olive pomace is waste material, it could create problems just as other waste unless there are appropriate and acceptable areas of utilization. The waste material, which is generated in large amounts, is generally used as fuel and fertilizer. Generally, additive materials are used in order to improve the properties of bituminous binders, and these are usually expensive materials, which are produced chemically. The aim of this study is to investigate the usability of biochars obtained after subjecting olive pomace and smashed olive seeds, which are considered as waste materials, to pyrolysis as additives in bitumen modification. In this way, various ways of use will be provided for waste material, providing both economic and environmental benefits. In this study, olive pomace and smashed olive seeds were used as sources of biomass. Initially, both materials were ground and processed through a No.50 sieve. Both of the sieved materials were subjected to pyrolysis (carbonization) at 400 ℃. Following the process of pyrolysis, bio-oil and biochar were obtained. The obtained biochars were added to B160/220 grade pure bitumen at 10% and 15% rates and modified bitumens were obtained by mixing them in high shear mixtures at 180 ℃ for 1 hour at 2000 rpm. Pure bitumen and four different types of bitumen obtained as a result of the modifications were tested with penetration, softening point, rotational viscometer, and dynamic shear rheometer, evaluating the effects of additives and the ratios of additives. According to the test results obtained, both biochar modifications at both ratios provided improvements in the performance of pure bitumen. In the comparison of the test results of the binders modified with the biochars of olive pomace and smashed olive seed, it was revealed that there was no notable difference in their performances.

Keywords: bituminous binders, biochar, biomass, olive pomace, pomace, pyrolysis

Procedia PDF Downloads 102
784 A Study on the Determinants of Earnings Response Coefficient in an Emerging Market

Authors: Bita Mashayekhi, Zeynab Lotfi Aghel

Abstract:

The determinants of Earnings Response Coefficient (ERC), including firm size, earnings growth, and earnings persistence are studied in this research. These determinants are supposed to be moderator variables that affect ERC and Return Response Coefficient. The research sample contains 82 Iranian listed companies in Tehran Stock Exchange (TSE) from 2001 to 2012. Gathered data have been processed by EVIEWS Software. Results show a significant positive relation between firm size and ERC, and also between earnings growth and ERC; however, there is no significant relation between earnings persistence and ERC. Also, the results show that ERC will be increased by firm size and earnings growth, but there is no relation between earnings persistence and ERC.

Keywords: earnings response coefficient (ERC), return response coefficient (RRC), firm size, earnings growth, earnings persistence

Procedia PDF Downloads 292
783 Durability Aspects of Recycled Aggregate Concrete: An Experimental Study

Authors: Smitha Yadav, Snehal Pathak

Abstract:

Aggregate compositions in the construction and demolition (C&D) waste have potential to replace normal aggregates. However, to re-utilise these aggregates, the concrete produced with these recycled aggregates needs to provide the desired compressive strength and durability. This paper examines the performance of recycled aggregate concrete made up of 60% recycled aggregates of 20 mm size in terms of durability tests namely rapid chloride permeability, drying shrinkage, water permeability, modulus of elasticity and creep without compromising the compressive strength. The experimental outcome indicates that recycled aggregate concrete provides strength and durability same as controlled concrete when processed for removal of adhered mortar.

Keywords: compressive strength, recycled aggregate, shrinkage, rapid chloride permeation test, modulus of elasticity, water permeability

Procedia PDF Downloads 273
782 In Search of CO₂: Gravity and Magnetic Data for Enhanced Oil Recovery (EOR) Prospect Generation in Central Libya

Authors: Ahmed Saheel

Abstract:

Enhanced oil recovery using carbon dioxide (CO₂-EOR) is a method that can increase oil production beyond what is typically achievable using conventional recovery methods by injecting, and hence storing, carbon dioxide (CO₂) in the oil reservoir. In Libya, plans are under way to source a proportion of this CO₂ from subsurface geology that is known from previous drilling to contain high volumes of CO₂. But first these subsurface volumes need to be more clearly defined and understood. Focusing on the Al-Harouj region of central Libya, ground gravity and airborne magnetic data from the LPI database and the African Magnetic Mapping Project respectively have been prepared and processed by Libyan Petroleum Institute (LPI) and Reid Geophysics Limited (RGL) to produce a range of grids and related products suitable for interpreting geological structure and to make recommendations for subsequent work that will assist CO₂ exploration for purposes of enhanced oil recovery (EOR).

Keywords: gravity, magnetic, deduced lineaments, upward continuation

Procedia PDF Downloads 90
781 Burden of Cardiovascular Diseases in Dubrovnik- Neretva County 2018-2021

Authors: Tarnai Tena, Strinić Dean

Abstract:

Chronic non-communicable diseases are today the leading cause of mortality, morbidity and mortality disability at the world level and in Croatia. Among them are the most represented precisely cardiovascular diseases (CVD), so today we are talking about their global card epidemic. From 2018 to 2021, cardiovascular diseases are the leading cause of death for both women and men in the Dubrovnik- Neretva County. With regard to the COVID-19 pandemic, which has taken over, without forgetting how much these patients are additionally affected, we are still talking about the primary cause of sickness and death in the population of this county and region. In this record, we present collected data processed according to gender and disease classification. We also bring a kind of overview because, for years, we have been following how the population of one of the origins of the Mediterranean diet has been struggling with cardiovascular diseases.

Keywords: cardiovascular disease, burden, COVID-19, epidemiology, ishemic heart disease, cardiovascular medicine

Procedia PDF Downloads 53
780 Effect of Sub Supercritical CO2 Processing on Microflora and Shelf Life Tempe

Authors: M. Kustyawati, F. Pratama, D. Saputra, A. Wijaya

Abstract:

Tempe composes of not only molds but also bacteria and yeasts. The structure of microorganisms needs to be in balance number in order the tempe to be an acceptable quality for an extended time. Sub supercritical carbon dioxide can be a promising preservation method for tempe as it induces microbial inactivation avoiding alterations of its quality attributes. Fresh tempe were processed using supercritical and sub supercritical CO2 for a defined holding times, then the growth ability of molds and bacteria were analyzed. The results showed that the supercritical CO2 processing for 5 minutes reduced the number of bacteria and molds to 0.30 log cycle and 1.17 log cycles, respectively. In addition, sub supercritical CO2 processing for 20 minutes had fungicidal effect against mold tempe; whereas, the sub supercritical CO2 for 10 minutes had reducing effect against bacteria tempe, and had fungistatic affect against mold tempe. It suggested that sub-supercritical CO2 processing for 10 min could be useful alternative technique for preservation of tempe.

Keywords: tempe, sub supercritical CO2, fungistatic effect, preservation

Procedia PDF Downloads 243
779 Dietary Exposure to Pesticide Residues by Various Physiological Groups of Population in Andhra Pradesh, South India

Authors: Padmaja R. Jonnalagadda

Abstract:

Dietary exposure assessment of fifteen pesticide residues was done in Andhra Pradesh. Twelve commonly consumed foods including water, which were representative of the diet, were collected, processed as table ready and analysed for the presence of various Organochlorines, organophosphates and synthetic pyrethroids. All the samples were contaminated with one or more of the 15 pesticide residues and all of them were within the MRLs. DDT and its isomers, Chlorpyriphos and Cypermethrin were frequently detected in many of the food samples. The mean concentration of the pesticide residues ranged from 0.02 μg kg-1 to 5.1 μg kg-1 (fresh weight) in the analysed foods. When exposure assessments was carried out for different age, sex and physiological groups it was found that the estimates of daily dietary intakes of the analysed pesticide residues in the present study are much lower than the violative levels in all age groups that were computed.

Keywords: table ready foods, pesticide residues, dietary intake, physiological groups, risk

Procedia PDF Downloads 487
778 The Friction and Wear Behavior of 0.35 VfTiC-Ti3SiC2 Composite

Authors: M. Hadji, A. Haddad, Y. Hadji

Abstract:

The effects of boronizing treatment on the friction coefficient and wear behavior of 0.35 Vf TiC- Ti3 SiC2 composite were investigated. In order to modify the surface properties of Ti3SiC2, boronizing treatment was carried out through powder pack cementation in the 1150-1350 °C temperature range. After boronizing treatment, one mixture layer, composed of TiB2 and SiC, forms on the surface of Ti3SiC2. The growth of the coating is processed by inward diffusion of Boron and obeys a linear rule. The Boronizing treatment increases the hardness of Ti3SiC2 from 6 GPa to 13 GPa. In the pin-on-disc test, i twas found that the material undergoes a steady-state coefficient of friction of around 0.8 and 0.45 in case of Ti3SiC2/Al2O3 tribocouple under 7 N load for the non treated and the boronized samples, respectively. The wear resistance of Ti3SiC2 under Al2O3 ball sliding has been significantly improved, which indicated that the boronizing treatment is a promising surface modification way of Ti3SiC2.

Keywords: MAX phase, boronizing, hardness, wear

Procedia PDF Downloads 320
777 A Calibration Method for Temperature Distribution Measurement of Thermochromic Liquid Crystal Based on Mathematical Morphology of Hue Image

Authors: Risti Suryantari, Flaviana

Abstract:

The aim of this research is to design calibration method of Thermochromic Liquid Crystal for temperature distribution measurement based on mathematical morphology of hue image A glass of water is placed on the surface of sample TLC R25C5W at certain temperature. We use scanner for image acquisition. The true images in RGB format is converted to HSV (hue, saturation, value) by taking of hue without saturation and value. Then the hue images is processed based on mathematical morphology using Matlab2013a software to get better images. There are differences on the final images after processing at each temperature variation based on visualization observation and the statistic value. The value of maximum and mean increase with rising temperature. It could be parameter to identify the temperature of the human body surface like hand or foot surface.

Keywords: thermochromic liquid crystal, TLC, mathematical morphology, hue image

Procedia PDF Downloads 449
776 Improved K-Means Clustering Algorithm Using RHadoop with Combiner

Authors: Ji Eun Shin, Dong Hoon Lim

Abstract:

Data clustering is a common technique used in data analysis and is used in many applications, such as artificial intelligence, pattern recognition, economics, ecology, psychiatry and marketing. K-means clustering is a well-known clustering algorithm aiming to cluster a set of data points to a predefined number of clusters. In this paper, we implement K-means algorithm based on MapReduce framework with RHadoop to make the clustering method applicable to large scale data. RHadoop is a collection of R packages that allow users to manage and analyze data with Hadoop. The main idea is to introduce a combiner as a function of our map output to decrease the amount of data needed to be processed by reducers. The experimental results demonstrated that K-means algorithm using RHadoop can scale well and efficiently process large data sets on commodity hardware. We also showed that our K-means algorithm using RHadoop with combiner was faster than regular algorithm without combiner as the size of data set increases.

Keywords: big data, combiner, K-means clustering, RHadoop

Procedia PDF Downloads 401
775 Determination of the Botanical Origin of Honey by the Artificial Neural Network Processing of PARAFAC Scores of Fluorescence Data

Authors: Lea Lenhardt, Ivana Zeković, Tatjana Dramićanin, Miroslav D. Dramićanin

Abstract:

Fluorescence spectroscopy coupled with parallel factor analysis (PARAFAC) and artificial neural networks (ANN) were used for characterization and classification of honey. Excitation emission spectra were obtained for 95 honey samples of different botanical origin (acacia, sunflower, linden, meadow, and fake honey) by recording emission from 270 to 640 nm with excitation in the range of 240-500 nm. Fluorescence spectra were described with a six-component PARAFAC model, and PARAFAC scores were further processed with two types of ANN’s (feed-forward network and self-organizing maps) to obtain algorithms for classification of honey on the basis of their botanical origin. Both ANN’s detected fake honey samples with 100% sensitivity and specificity.

Keywords: honey, fluorescence, PARAFAC, artificial neural networks

Procedia PDF Downloads 925
774 The Effects of Boronizing Treatment on the Friction and Wear Behavior of 0.35 VfTiC- Ti3SiC2 Composite

Authors: M. Hadji, A. Haddad, Y. Hadji

Abstract:

The effects of boronizing treatment on the friction coefficient and wear behavior of 0.35 Vf TiC- Ti3 SiC2 composite were investigated. In order to modity the surface properties of Ti3SiC2, boronizing treatment was carried out through powder pack cementation in the 1150-1350 °C temperature range. After boronizing treatment, one mixture layer, composed of TiB2 and SiC, forms on the surface of Ti3SiC2. The growth of the coating is processed by inward diffusion of Boron and obeys a linear rule. The Boronizing treatment increases the hardness of Ti3SiC2 from 6 GPa to 13 GPa. In the pin-on-disc test, i twas found that the material undergoes a steady-state coefficient of friction of around 0.8 and 0.45 in case of Ti3SiC2/Al2O3 tribocouple under 7N load for the non treated and the boronized samples, respectively. The wear resistance of Ti3SiC2 underAl2O3 ball sliding has been significantly improved, which indicated that the boronizing treatment is a promising surface modification way of Ti3SiC2.

Keywords: MAX phase, wearing, friction, boronizing

Procedia PDF Downloads 425
773 Pre-Service EFL Teachers' Perceptions of Written Corrective Feedback in a Wiki-Based Environment

Authors: Mabel Ortiz, Claudio Díaz

Abstract:

This paper explores Chilean pre-service teachers' perceptions about the provision of corrective feedback in a wiki environment during the collaborative writing of an argumentative essay. After conducting a semi-structured interview on 22 participants, the data were processed through the content analysis technique. The results show that students have positive perceptions about corrective feedback, provided through a wiki virtual environment, which in turn facilitates feedback provision and impacts language learning effectively. Some of the positive perceptions about virtual feedback refer to permanent access, efficiency, simultaneous revision and immediacy. It would then be advisable to integrate wiki-based feedback as a methodology for the language classroom and collaborative writing tasks.

Keywords: argumentative essay, focused corrective feedback, perception, wiki environment

Procedia PDF Downloads 263
772 Comparative Analysis of Spectral Estimation Methods for Brain-Computer Interfaces

Authors: Rafik Djemili, Hocine Bourouba, M. C. Amara Korba

Abstract:

In this paper, we present a method in order to classify EEG signals for Brain-Computer Interfaces (BCI). EEG signals are first processed by means of spectral estimation methods to derive reliable features before classification step. Spectral estimation methods used are standard periodogram and the periodogram calculated by the Welch method; both methods are compared with Logarithm of Band Power (logBP) features. In the method proposed, we apply Linear Discriminant Analysis (LDA) followed by Support Vector Machine (SVM). Classification accuracy reached could be as high as 85%, which proves the effectiveness of classification of EEG signals based BCI using spectral methods.

Keywords: brain-computer interface, motor imagery, electroencephalogram, linear discriminant analysis, support vector machine

Procedia PDF Downloads 471
771 Using AI for Analysing Political Leaders

Authors: Shuai Zhao, Shalendra D. Sharma, Jin Xu

Abstract:

This research uses advanced machine learning models to learn a number of hypotheses regarding political executives. Specifically, it analyses the impact these powerful leaders have on economic growth by using leaders’ data from the Archigos database from 1835 to the end of 2015. The data is processed by the AutoGluon, which was developed by Amazon. Automated Machine Learning (AutoML) and AutoGluon can automatically extract features from the data and then use multiple classifiers to train the data. Use a linear regression model and classification model to establish the relationship between leaders and economic growth (GDP per capita growth), and to clarify the relationship between their characteristics and economic growth from a machine learning perspective. Our work may show as a model or signal for collaboration between the fields of statistics and artificial intelligence (AI) that can light up the way for political researchers and economists.

Keywords: comparative politics, political executives, leaders’ characteristics, artificial intelligence

Procedia PDF Downloads 52
770 Inspection of Railway Track Fastening Elements Using Artificial Vision

Authors: Abdelkrim Belhaoua, Jean-Pierre Radoux

Abstract:

In France, the railway network is one of the main transport infrastructures and is the second largest European network. Therefore, railway inspection is an important task in railway maintenance to ensure safety for passengers using significant means in personal and technical facilities. Artificial vision has recently been applied to several railway applications due to its potential to improve the efficiency and accuracy when analyzing large databases of acquired images. In this paper, we present a vision system able to detect fastening elements based on artificial vision approach. This system acquires railway images using a CCD camera installed under a control carriage. These images are stitched together before having processed. Experimental results are presented to show that the proposed method is robust for detection fasteners in a complex environment.

Keywords: computer vision, image processing, railway inspection, image stitching, fastener recognition, neural network

Procedia PDF Downloads 422
769 A Study on Low Stress Mechanical Properties of Denim Fabric for Hand Evaluation

Authors: S. P. Raut, S. K. Soni, A. W. Kolhatkar

Abstract:

Denim is widely used by every age of people all over the world. As the use of denim is increasing progressively, till now the handle properties of denim fabric not reported at significant level. In the present study, five commercial denim fabric samples were used. Denim samples, weighing from 8.5oz/sq yds to 14.5 oz/sq yds, were processed as per standard commercial procedure for denim finishing. These finished denim samples were tested on Kawabata Evaluation System(KES) for low stress mechanical properties. The results of KES values are used for calculation of Total Hand value(THV) using equation for summer suit. The obtained result for THV using equation for summer suit for denim samples is in the range from 1.62 to 3.30. These values of low stress mechanical properties values given by KES, can be used to engineer the denim fabric for bottom wear.

Keywords: denim, handle value, Kawabata evaluation system, objective evaluation

Procedia PDF Downloads 249
768 Deep-Learning Based Approach to Facial Emotion Recognition through Convolutional Neural Network

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. Accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER, benefiting from deep learning, especially CNN and VGG16. First, the data is pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning

Procedia PDF Downloads 61
767 Applying Biosensors’ Electromyography Signals through an Artificial Neural Network to Control a Small Unmanned Aerial Vehicle

Authors: Mylena McCoggle, Shyra Wilson, Andrea Rivera, Rocio Alba-Flores

Abstract:

This work introduces the use of EMGs (electromyography) from muscle sensors to develop an Artificial Neural Network (ANN) for pattern recognition to control a small unmanned aerial vehicle. The objective of this endeavor exhibits interfacing drone applications beyond manual control directly. MyoWare Muscle sensor contains three EMG electrodes (dual and single type) used to collect signals from the posterior (extensor) and anterior (flexor) forearm and the bicep. Collection of raw voltages from each sensor were connected to an Arduino Uno and a data processing algorithm was developed with the purpose of interpreting the voltage signals given when performing flexing, resting, and motion of the arm. Each sensor collected eight values over a two-second period for the duration of one minute, per assessment. During each two-second interval, the movements were alternating between a resting reference class and an active motion class, resulting in controlling the motion of the drone with left and right movements. This paper further investigated adding up to three sensors to differentiate between hand gestures to control the principal motions of the drone (left, right, up, and land). The hand gestures chosen to execute these movements were: a resting position, a thumbs up, a hand swipe right motion, and a flexing position. The MATLAB software was utilized to collect, process, and analyze the signals from the sensors. The protocol (machine learning tool) was used to classify the hand gestures. To generate the input vector to the ANN, the mean, root means squared, and standard deviation was processed for every two-second interval of the hand gestures. The neuromuscular information was then trained using an artificial neural network with one hidden layer of 10 neurons to categorize the four targets, one for each hand gesture. Once the machine learning training was completed, the resulting network interpreted the processed inputs and returned the probabilities of each class. Based on the resultant probability of the application process, once an output was greater or equal to 80% of matching a specific target class, the drone would perform the motion expected. Afterward, each movement was sent from the computer to the drone through a Wi-Fi network connection. These procedures have been successfully tested and integrated into trial flights, where the drone has responded successfully in real-time to predefined command inputs with the machine learning algorithm through the MyoWare sensor interface. The full paper will describe in detail the database of the hand gestures, the details of the ANN architecture, and confusion matrices results.

Keywords: artificial neural network, biosensors, electromyography, machine learning, MyoWare muscle sensors, Arduino

Procedia PDF Downloads 144
766 Valorisation of Food Waste Residue into Sustainable Bioproducts

Authors: Krishmali N. Ekanayake, Brendan J. Holland, Colin J. Barrow, Rick Wood

Abstract:

Globally, more than one-third of all food produced is lost or wasted, equating to 1.3 billion tonnes per year. Around 31.2 million tonnes of food waste are generated across the production, supply, and consumption chain in Australia. Generally, the food waste management processes adopt environmental-friendly and more sustainable approaches such as composting, anerobic digestion and energy implemented technologies. However, unavoidable, and non-recyclable food waste ends up as landfilling and incineration that involve many undesirable impacts and challenges on the environment. A biorefinery approach contributes to a waste-minimising circular economy by converting food and other organic biomass waste into valuable outputs, including feeds, nutrition, fertilisers, and biomaterials. As a solution, Green Eco Technologies has developed a food waste treatment process using WasteMaster system. The system uses charged oxygen and moderate temperatures to convert food waste, without bacteria, additives, or water, into a virtually odour-free, much reduced quantity of reusable residual material. In the context of a biorefinery, the WasteMaster dries and mills food waste into a form suitable for storage or downstream extraction/separation/concentration to create products. The focus of the study is to determine the nutritional composition of WasteMaster processed residue to potential develop aquafeed ingredients. The global aquafeed industry is projected to reach a high value market in future, which has shown high demand for the aquafeed products. Therefore, food waste can be utilized for aquaculture feed development by reducing landfill. This framework will lessen the requirement of raw crops cultivation for aquafeed development and reduce the aquaculture footprint. In the present study, the nutritional elements of processed residue are consistent with the input food waste type, which has shown that the WasteMaster is not affecting the expected nutritional distribution. The macronutrient retention values of protein, lipid, and nitrogen free extract (NFE) are detected >85%, >80%, and >95% respectively. The sensitive food components including omega 3 and omega 6 fatty acids, amino acids, and phenolic compounds have been found intact in each residue material. Preliminary analysis suggests a price comparability with current aquafeed ingredient cost making the economic feasibility. The results suggest high potentiality of aquafeed development as 5 to 10% of the ingredients to replace/partially substitute other less sustainable ingredients across biorefinery setting. Our aim is to improve the sustainability of aquaculture and reduce the environmental impacts of food waste.

Keywords: biorefinery, ffood waste residue, input, wasteMaster

Procedia PDF Downloads 30
765 Musical Tesla Coil Controlled by an Audio Signal Processed in Matlab

Authors: Sandra Cuenca, Danilo Santana, Anderson Reyes

Abstract:

The following project is based on the manipulation of audio signals through the Matlab software, which has an audio signal that is modified, and its resultant obtained through the auxiliary port of the computer is passed through a signal amplifier whose amplified signal is connected to a tesla coil which has a behavior like a vumeter, the flashes at the output of the tesla coil increase and decrease its intensity depending on the audio signal in the computer and also the voltage source from which it is sent. The amplified signal then passes to the tesla coil being shown in the plasma sphere with the respective flashes; this activation is given through the specified parameters that we want to give in the MATLAB algorithm that contains the digital filters for the manipulation of our audio signal sent to the tesla coil to be displayed in a plasma sphere with flashes of the combination of colors commonly pink and purple that varies according to the tone of the song.

Keywords: auxiliary port, tesla coil, vumeter, plasma sphere

Procedia PDF Downloads 52
764 Eco-Nanofiltration Membranes: Nanofiltration Membrane Technology Utilization-Based Fiber Pineapple Leaves Waste as Solutions for Industrial Rubber Liquid Waste Processing and Fertilizer Crisis in Indonesia

Authors: Andi Setiawan, Annisa Ulfah Pristya

Abstract:

Indonesian rubber plant area reached 2.9 million hectares with productivity reached 1.38 million. High rubber productivity is directly proportional to the amount of waste produced rubber processing industry. Rubber industry would produce a negative impact on the rubber industry in the form of environmental pollution caused by waste that has not been treated optimally. Rubber industrial wastewater containing high-nitrogen compounds (nitrate and ammonia) and phosphate compounds which cause water pollution and odor problems due to the high ammonia content. On the other hand, demand for NPK fertilizers in Indonesia continues to increase from year to year and in need of ammonia and phosphate as raw material. Based on domestic demand, it takes a year to 400,000 tons of ammonia and Indonesia imports 200,000 tons of ammonia per year valued at IDR 4.2 trillion. As well, the lack of phosphoric acid to be imported from Jordan, Morocco, South Africa, the Philippines, and India as many as 225 thousand tons per year. During this time, the process of wastewater treatment is generally done with a rubber on the tank to contain the waste and then precipitated, filtered and the rest released into the environment. However, this method is inefficient and thus require high energy costs because through many stages before producing clean water that can be discharged into the river. On the other hand, Indonesia has the potential of pineapple fruit can be harvested throughout the year in all of Indonesia. In 2010, production reached 1,406,445 tons of pineapple in Indonesia or about 9.36 percent of the total fruit production in Indonesia. Increased productivity is directly proportional to the amount of pineapple waste pineapple leaves are kept continuous and usually just dumped in the ground or disposed of with other waste at the final disposal. Through Eco-Nanofiltration Membrane-Based Fiber Pineapple leaves Waste so that environmental problems can be solved efficiently. Nanofiltration is a process that uses pressure as a driving force that can be either convection or diffusion of each molecule. Nanofiltration membranes that can split water to nano size so as to separate the waste processed residual economic value that N and P were higher as a raw material for the manufacture of NPK fertilizer to overcome the crisis in Indonesia. The raw materials were used to manufacture Eco-Nanofiltration Membrane is cellulose from pineapple fiber which processed into cellulose acetate which is biodegradable and only requires a change of the membrane every 6 months. Expected output target is Green eco-technology so with nanofiltration membranes not only treat waste rubber industry in an effective, efficient and environmentally friendly but also lowers the cost of waste treatment compared to conventional methods.

Keywords: biodegradable, cellulose diacetate, fertilizers, pineapple, rubber

Procedia PDF Downloads 419
763 Bake Hardening Behavior of Ultrafine Grained and Nano-Grained AA6061 Aluminum Alloy

Authors: Hamid Alihosseini, Kamran Dehghani

Abstract:

In this study, the effects of grain size of AA6061 aluminum on the bake hardening have been investigated. The grains of sample sheets refined by applying 4, 8, and 12 passes of ECAP and their microstructures and mechanical properties were investigated. EBSD and TEM studies of the sheets showed grain refinement, and the EBSD micrograph of the alloy ECAPed for 12 passes showed nano-grained (NG) ∼95nm in size. Then, the bake hardenability of processed sheet was compared by pre-straining to 6% followed by baking at 200°C for 20 min. The results show that in case of baking at 200°C, there was an increase about 108%, 93%, and 72% in the bake hardening for 12, 8, and 4 passes, respectively. The maximum in bake hardenability (120 MPa) and final yield stress (583 MPa) were pertaining to the ultra-fine grain specimen pre-strained 6% followed by baking at 200◦C.

Keywords: bake hardening, ultrafine grain, nano grain, AA6061 aluminum,

Procedia PDF Downloads 310
762 The Influence of Active Breaks on the Attention/Concentration Performance in Eighth-Graders

Authors: Christian Andrä, Luisa Zimmermann, Christina Müller

Abstract:

Introduction: The positive relation between physical activity and cognition is commonly known. Relevant studies show that in everyday school life active breaks can lead to improvement in certain abilities (e.g. attention and concentration). A beneficial effect is in particular attributed to moderate activity. It is still unclear whether active breaks are beneficial after relatively short phases of cognitive load and whether the postulated effects of activity really have an immediate impact. The objective of this study was to verify whether an active break after 18 minutes of cognitive load leads to enhanced attention/concentration performance, compared to inactive breaks with voluntary mobile phone activity. Methodology: For this quasi-experimental study, 36 students [age: 14.0 (mean value) ± 0.3 (standard deviation); male/female: 21/15] of a secondary school were tested. In week 1, every student’s maximum heart rate (Hfmax) was determined through maximum effort tests conducted during physical education classes. The task was to run 3 laps of 300 m with increasing subjective effort (lap 1: 60%, lap 2: 80%, lap 3: 100% of the maximum performance capacity). Furthermore, first attention/concentration tests (D2-R) took place (pretest). The groups were matched on the basis of the pretest results. During week 2 and 3, crossover testing was conducted, comprising of 18 minutes of cognitive preload (test for concentration performance, KLT-R), a break and an attention/concentration test after a 2-minutes transition. Different 10-minutes breaks (active break: moderate physical activity with 65% Hfmax or inactive break: mobile phone activity) took place between preloading and transition. Major findings: In general, there was no impact of the different break interventions on the concentration test results (symbols processed after physical activity: 185.2 ± 31.3 / after inactive break: 184.4 ± 31.6; errors after physical activity: 5.7 ± 6.3 / after inactive break: 7.0. ± 7.2). There was, however, a noticeable development of the values over the testing periods. Although no difference in the number of processed symbols was detected (active/inactive break: period 1: 49.3 ± 8.8/46.9 ± 9.0; period 2: 47.0 ± 7.7/47.3 ± 8.4; period 3: 45.1 ± 8.3/45.6 ± 8.0; period 4: 43.8 ± 7.8/44.6 ± 8.0), error rates decreased successively after physical activity and increased gradually after an inactive break (active/inactive break: period 1: 1.9 ± 2.4/1.2 ± 1.4; period 2: 1.7 ± 1.8/ 1.5 ± 2.0, period 3: 1.2 ± 1.6/1.8 ± 2.1; period 4: 0.9 ± 1.5/2.5 ± 2.6; p= .012). Conclusion: Taking into consideration only the study’s overall results, the hypothesis must be dismissed. However, more differentiated evaluation shows that the error rates decreased after active breaks and increased after inactive breaks. Obviously, the effects of active intervention occur with a delay. The 2-minutes transition (regeneration time) used for this study seems to be insufficient due to the longer adaptation time of the cardio-vascular system in untrained individuals, which might initially affect the concentration capacity. To use the positive effects of physical activity for teaching and learning processes, physiological characteristics must also be considered. Only this will ensure optimum ability to perform.

Keywords: active breaks, attention/concentration test, cognitive performance capacity, heart rate, physical activity

Procedia PDF Downloads 289
761 Comparison of Security Challenges and Issues of Mobile Computing and Internet of Things

Authors: Aabiah Nayeem, Fariha Shafiq, Mustabshra Aftab, Rabia Saman Pirzada, Samia Ghazala

Abstract:

In this modern era of technology, the concept of Internet of Things is very popular in every domain. It is a widely distributed system of things in which the data collected from sensory devices is transmitted, analyzed locally/collectively then broadcasted to network where action can be taken remotely via mobile/web apps. Today’s mobile computing is also gaining importance as the services are provided during mobility. Through mobile computing, data are transmitted via computer without physically connected to a fixed point. The challenge is to provide services with high speed and security. Also, the data gathered from the mobiles must be processed in a secured way. Mobile computing is strongly influenced by internet of things. In this paper, we have discussed security issues and challenges of internet of things and mobile computing and we have compared both of them on the basis of similarities and dissimilarities.

Keywords: embedded computing, internet of things, mobile computing, wireless technologies

Procedia PDF Downloads 289
760 Stress Intensity Factor for Dynamic Cracking of Composite Material by X-FEM Method

Authors: S. Lecheb, A. Nour, A. Chellil, H. Mechakra, N. Hamad, H. Kebir

Abstract:

The work involves develops attended by a numerical execution of the eXtend Finite Element Method premises a measurement by the fracture process cracked so many cracked plates an application will be processed for the calculation of the stress intensity factor SIF. In the first we give in statically part the distribution of stress, displacement field and strain of composite plate in two cases uncrack/edge crack, also in dynamical part the first six modes shape. Secondly, we calculate Stress Intensity Factor SIF for different orientation angle θ of central crack with length (2a=0.4mm) in plan strain condition, KI and KII are obtained for mode I and mode II respectively using X-FEM method. Finally from crack inclined involving mixed modes results, the comparison we chose dangerous inclination and the best crack angle when K is minimal.

Keywords: stress intensity factor (SIF), crack orientation, glass/epoxy, natural frequencies, X-FEM

Procedia PDF Downloads 485