Search results for: odor classification

Authors: Burçin Saltık, Levent Genç

Abstract:

In this study, it was aimed to determine a route for identification of rice cultivation areas within Thrace and Marmara regions of Turkey using remote sensing and GIS. Landsat 8 (OLI-TIRS) imageries acquired in production season of 2013 with 181/32 Path/Row number were used. Four different seasonal images were generated utilizing original bands and different transformation techniques. All images were classified individually using supervised classification techniques and Land Use Land Cover Maps (LULC) were generated with 8 classes. Areas (ha, %) of each classes were calculated. In addition, district-based rice distribution maps were developed and results of these maps were compared with Turkish Statistical Institute (TurkSTAT; TSI)’s actual rice cultivation area records. Accuracy assessments were conducted, and most accurate map was selected depending on accuracy assessment and coherency with TSI results. Additionally, rice areas on over 4° slope values were considered as mis-classified pixels and they eliminated using slope map and GIS tools. Finally, randomized rice zones were selected to obtain maximum-minimum value ranges of each date (May, June, July, August, September images separately) NDVI, LSWI, and LST images to test whether they may be used for rice area determination via raster calculator tool of ArcGIS. The most accurate classification for rice determination was obtained from seasonal LSWI LULC map, and considering TSI data and accuracy assessment results and mis-classified pixels were eliminated from this map. According to results, 83151.5 ha of rice areas exist within study area. However, this result is higher than TSI records with an area of 12702.3 ha. Use of maximum-minimum range of rice area NDVI, LSWI, and LST was tested in Meric district. It was seen that using the value ranges obtained from July imagery, gave the closest results to TSI records, and the difference was only 206.4 ha. This difference is normal due to relatively low resolution of images. Thus, employment of images with higher spectral, spatial, temporal and radiometric resolutions may provide more reliable results.

Keywords: landsat 8 (OLI-TIRS), LST, LSWI, LULC, NDVI, rice

Procedia PDF Downloads 227

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 92

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 149

Authors: Ahmet Karagoz, Irfan Karagoz

Abstract:

Synthetic Aperture Radar (SAR) is a radar mechanism that can be integrated into manned and unmanned aerial vehicles to create high-resolution images in all weather conditions, regardless of day and night. In this study, SAR images of military vehicles with different azimuth and descent angles are pre-processed at the first stage. The main purpose here is to reduce the high speckle noise found in SAR images. For this, the Wiener adaptive filter, the mean filter, and the median filters are used to reduce the amount of speckle noise in the images without causing loss of data. During the image segmentation phase, pixel values are ordered so that the target vehicle region is separated from other regions containing unnecessary information. The target image is parsed with the brightest 20% pixel value of 255 and the other pixel values of 0. In addition, by using appropriate parameters of statistical region merging algorithm, segmentation comparison is performed. In the step of feature extraction, the feature vectors belonging to the vehicles are obtained by using Gabor filters with different orientation, frequency and angle values. A number of Gabor filters are created by changing the orientation, frequency and angle parameters of the Gabor filters to extract important features of the images that form the distinctive parts. Finally, images are classified by sparse representation method. In the study, l₁ norm analysis of sparse representation is used. A joint database of the feature vectors generated by the target images of military vehicle types is obtained side by side and this database is transformed into the matrix form. In order to classify the vehicles in a similar way, the test images of each vehicle is converted to the vector form and l₁ norm analysis of the sparse representation method is applied through the existing database matrix form. As a result, correct recognition has been performed by matching the target images of military vehicles with the test images by means of the sparse representation method. 97% classification success of SAR images of different military vehicle types is obtained.

Keywords: automatic target recognition, sparse representation, image classification, SAR images

Procedia PDF Downloads 364

Authors: H. Jung, N. Kim, B. Kang, J. Choe

Abstract:

History matching is a crucial procedure for predicting reservoir performances and making future decisions. However, it is difficult due to uncertainties of initial reservoir models. Therefore, it is important to have reliable initial models for successful history matching of highly heterogeneous reservoirs such as channel reservoirs. In this paper, we proposed a novel scheme for regenerating geological models using support vector machine (SVM) and principal component analysis (PCA). First, we perform PCA for figuring out main geological characteristics of models. Through the procedure, permeability values of each model are transformed to new parameters by principal components, which have eigenvalues of large magnitude. Secondly, the parameters are projected into two-dimensional plane by multi-dimensional scaling (MDS) based on Euclidean distances. Finally, we train an SVM classifier using 20% models which show the most similar or dissimilar well oil production rates (WOPR) with the true values (10% for each). Then, the other 80% models are classified by trained SVM. We select models on side of low WOPR errors. One hundred channel reservoir models are initially generated by single normal equation simulation. By repeating the classification process, we can select models which have similar geological trend with the true reservoir model. The average field of the selected models is utilized as a probability map for regeneration. Newly generated models can preserve correct channel features and exclude wrong geological properties maintaining suitable uncertainty ranges. History matching with the initial models cannot provide trustworthy results. It fails to find out correct geological features of the true model. However, history matching with the regenerated ensemble offers reliable characterization results by figuring out proper channel trend. Furthermore, it gives dependable prediction of future performances with reduced uncertainties. We propose a novel classification scheme which integrates PCA, MDS, and SVM for regenerating reservoir models. The scheme can easily sort out reliable models which have similar channel trend with the reference in lowered dimension space.

Keywords: history matching, principal component analysis, reservoir modelling, support vector machine

Procedia PDF Downloads 158

Authors: Sašo Pečnik, Borut Žalik

Abstract:

This paper presents a real-time visualization technique and filtering of classified LiDAR point clouds. The visualization is capable of displaying filtered information organized in layers by the classification attribute saved within LiDAR data sets. We explain the used data structure and data management, which enables real-time presentation of layered LiDAR data. Real-time visualization is achieved with LOD optimization based on the distance from the observer without loss of quality. The filtering process is done in two steps and is entirely executed on the GPU and implemented using programmable shaders.

Keywords: filtering, graphics, level-of-details, LiDAR, real-time visualization

Procedia PDF Downloads 306

Authors: Meenal Badki

Abstract:

We address the issue of active feature determination, where the objective is to determine the set of examples on which additional data (such as lab tests) needs to be gathered, given a large number of examples with some features (such as demographics) and some examples with all the features (such as the complete Electronic Health Record). We note that certain features may be more costly, unique, or laborious to gather. Our proposal is a general active learning approach that is independent of classifiers and similarity metrics. It allows us to identify examples that differ from the full data set and obtain all the features for the examples that match. Our comprehensive evaluation shows the efficacy of this approach, which is driven by four authentic clinical tasks.

Keywords: feature determination, classification, active learning, sample-efficiency

Procedia PDF Downloads 73

Authors: Fuad M. Alkoot

Abstract:

The main component of a machine learning system is the classifier. Classifiers are mathematical models that can perform classification tasks for a specific application area. Additionally, many classifiers are combined using any of the available methods to reduce the classifier error rate. The benefits gained from the combination of multiple classifier designs has motivated the development of diverse approaches to multiple classifiers. We aim to investigate using fractal geometry to develop an improved classifier combiner. Initially we experiment with measuring the fractal dimension of data and use the results in the development of a combiner strategy.

Keywords: fractal geometry, machine learning, classifier, fractal dimension

Procedia PDF Downloads 213

Authors: Mohammed Arif, Abdessalam Kifouche

Abstract:

Optical character recognition (OCR) has a main role in the present time. It's capable to solve many serious problems and simplify human activities. The OCR yields to 70's, since many solutions has been proposed, but unfortunately, it was supportive to nothing but Latin languages. This work proposes a system of recognition of an off-line Arabic handwriting. This system is based on a structural segmentation method and uses support vector machines (SVM) in the classification phase. We have presented a state of art of the characters segmentation methods, after that a view of the OCR area, also we will address the normalization problems we went through. After a comparison between the Arabic handwritten characters & the segmentation methods, we had introduced a contribution through a segmentation algorithm.

Keywords: OCR, segmentation, Arabic characters, PAW, post-processing, SVM

Procedia PDF Downloads 69

Authors: Raphael C. Zero, Marita V. Cardozo, Thiago A. S. S. Rocha, Mariana T. Kihara, Fernando A. Ávila, Fabrício S. Oliveira

Abstract:

There are several fixative and preservative solutions for use on cadavers, many of them using formaldehyde as the fixative or anatomical part preservative. In some countries, such as Brazil, this toxic agent has been increasingly restricted. The objective of this study was to microbiologically identify and quantify the key agents in tanks containing 96GL ethanol or sodium chloride solutions, used respectively as fixatives and preservatives of cat cadavers. Eight adult cat corpses, three females and five males, with an average weight of 4.3 kg, were used. After injection via the external common carotid artery (120 ml/kg, 95% 96GL ethyl alcohol and 5% pure glycerin), the cadavers were fixed in a plastic tank with 96GL ethanol for 60 days. After fixing, they were stored in a 30% sodium chloride aqueous solution for 120 days in a similar tank. Samples were collected at the start of the experiment - before the animals were placed in the ethanol tanks, and monthly thereafter. The bacterial count was performed by Pour Plate Method in BHI agar (Brain Heart Infusion) and the plates were incubated aerobically and anaerobically for 24h at 37ºC. MacConkey agar, SPS agar (Sulfite Polymyxin Sulfadizine) and MYP Agar Base were used to isolate the microorganisms. There was no microbial growth in the samples prior to alcohol fixation. After 30 days of fixation in the alcohol solution, total aerobic and anaerobic (<1.0 x 10 CFU/ml) were found and Pseudomonas sp., Staphylococcus sp., Clostridium sp. were the identified agents. After 60 days in the alcohol fixation solution, total aerobes (<1.0 x 10 CFU/ml) and total anaerobes (<2.2 x 10 CFU/mL) were found, and the identified agents were the same. After 30 days of storage in the aqueous solution of 30% sodium chloride, total aerobic (<5.2 x 10 CFU/ml) and total anaerobes (<3.7 x 10 CFU/mL) were found and the agents identified were Staphylococcus sp., Clostridium sp., and fungi. After 60 days of sodium chloride storage, total aerobic (<3.0 x 10 CFU / ml) and total anaerobes (<7.0 x 10 CFU/mL) were found and the identified agents remained the same: Staphylococcus sp., Clostridium sp., and fungi. The microbiological count was low and visual inspection did not reveal signs of contamination in the tanks. There was no strong odor or purification, which proved the technique to be microbiologically effective in fixing and preserving the cat cadavers for the four-month period in which they are provided to undergraduate students of University of Veterinary Medicine for surgery practice. All experimental procedures were approved by the Municipal Legal Department (protocol 02.2014.000027-1). The project was funded by FAPESP (protocol 2015-08259-9).

Keywords: anatomy, fixation, microbiology, small animal, surgery

Procedia PDF Downloads 289

Authors: Erin Lynne Plettenberg, Jeremy Vickery

Abstract:

In an access-control situation, the role of a user determines whether a data request is appropriate. This paper combines vetted web mining and logic modeling to build a lightweight system for determining the role of a health care provider based only on their prior authorized requests. The model identifies provider roles with 100% recall from very little data. This shows the value of vetted web mining in AI systems, and suggests the impact of the ICD classification on medical practice.

Keywords: electronic medical records, information extraction, logic modeling, ontology, vetted web mining

Procedia PDF Downloads 171

Authors: Emmanuelle Merat, Arnaud Aubert, Sophie Cambos, Francis Vial, Patrick Beau

Abstract:

Basically, consumers are sensitive to many stimuli when applying a cream: brand, packaging and indeed formulation compositions. Many studies demonstrated the influence of some stimuli such as brand, packaging, formula color and odor (e.g. in make-up applications). Those parameters influence perceived quality of the product. The objective of this work is to further investigate the relationship between nude skincare basic compositions with different textures and consumer experience. A tentative final step will be to connect the consumer feelings with key ingredients in the compositions. A new approach was developed to better understand touch-related subjective experience in consumers based on a combination of methods: sensory analysis with ten experts, preference mapping on one hundred female consumers and emotional assessments on thirty consumers (verbal and non-verbal through prosody and gesture monitoring). Finally, a methodology based on ‘sensorial trip’ (after olfactory, haptic and musical stimuli) has been experimented on the most interesting textures with 10 consumers. The results showed more or less impact depending on compositions and also on key ingredients. Three types of formulation particularly attracted the consumer: an aqueous gel, an oil-in-water emulsion, and a patented gel-in-oil formulation type. Regarding these three formulas, the preferences were both revealed through sensory and emotion tests. One was recognized as the most innovative in consumer sensory test whereas the two other formulas were discriminated in emotions evaluation. The positive emotions were highlighted especially in prosody criteria. The non-verbal analysis, which corresponds to the physical parameters of the voice, showed high pitch and amplitude values; linked to positive emotions. Verbatim, verbal content of responses (i.e., ideas, concepts, mental images), confirmed the first conclusion. On the formulas selected for their positive emotions generation, the ‘sensorial trip’ provided complementary information to characterize each emotional profile. In the second step, dedicated to better understand ingredients power, two types of ingredients demonstrated an obvious input on consumer preference: rheology modifiers and emollients. As a conclusion, nude cosmetic compositions with well-chosen textures and ingredients can positively stimulate consumer emotions contributing to capture their preference. For a complete achievement of the study, a global approach (Asia, America territories...) should be developed.

Keywords: sensory, emotion, cosmetic formulations, ingredients' influence

Procedia PDF Downloads 178

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations of previous approaches, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with attention mechanism. In a previous work on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: transformers, generative ai, gene expression design, classification

Procedia PDF Downloads 59

Authors: Muhammad Irfan Marwat, Sadaqat Jan, Syed Zafar Ali Shah

Abstract:

Software architecture plays a key role in software development but absence of formal description of software architecture causes different impede in software development. To cope with these difficulties, ontology has been used as artifact. This paper proposes ontology for software architectural design based on IEEE model for architecture description and Kruchten 4+1 model for viewpoints classification. For categorization of style and views, ISO/IEC 42010 has been used. Corpus method has been used to evaluate ontology. The main aim of the proposed ontology is to classify and locate software architectural design information.

Keywords: semantic-based software architecture, software architecture, ontology, software engineering

Procedia PDF Downloads 546

Authors: Kristina Sakalauskiene, Renaldas Raisutis, Gintare Linkeviciute, Skaidra Valiukeviciene

Abstract:

Cutaneous melanoma is a melanocytic skin tumour, which has a very poor prognosis while is highly resistant to treatment and tends to metastasize. Thickness of melanoma is one of the most important biomarker for stage of disease, prognosis and surgery planning. In this study, we hypothesized that the automatic analysis of spectrophotometric images and high-frequency ultrasonic 2D data can improve differential diagnosis of cutaneous melanoma and provide additional information about tumour penetration depth. This paper presents the novel complex automatic system for non-invasive melanocytic skin tumour differential diagnosis and penetration depth evaluation. The system is composed of region of interest segmentation in spectrophotometric images and high-frequency ultrasound data, quantitative parameter evaluation, informative feature extraction and classification with linear regression classifier. The segmentation of melanocytic skin tumour region in ultrasound image is based on parametric integrated backscattering coefficient calculation. The segmentation of optical image is based on Otsu thresholding. In total 29 quantitative tissue characterization parameters were evaluated by using ultrasound data (11 acoustical, 4 shape and 15 textural parameters) and 55 quantitative features of dermatoscopic and spectrophotometric images (using total melanin, dermal melanin, blood and collagen SIAgraphs acquired using spectrophotometric imaging device SIAscope). In total 102 melanocytic skin lesions (including 43 cutaneous melanomas) were examined by using SIAscope and ultrasound system with 22 MHz center frequency single element transducer. The diagnosis and Breslow thickness (pT) of each MST were evaluated during routine histological examination after excision and used as a reference. The results of this study have shown that automatic analysis of spectrophotometric and high frequency ultrasound data can improve non-invasive classification accuracy of early-stage cutaneous melanoma and provide supplementary information about tumour penetration depth.

Keywords: cutaneous melanoma, differential diagnosis, high-frequency ultrasound, melanocytic skin tumours, spectrophotometric imaging

Procedia PDF Downloads 268

Authors: Jung-Hun Cho, Tae-Heon Moon, Sun-Young Heo

Abstract:

A lot of urban problems, caused by urbanization and industrialization, have occurred around the world. In particular, the creation of satellite towns, which was attributed to the explicit expansion of the city, has led to the traffic problems and the hollowization of old towns, raising the necessity of urban regeneration in old towns along with the aging of existing urban infrastructure. To select urban regeneration priority regions for the strategic execution of urban regeneration in Korea, the number of population, the number of businesses, and deterioration degree were chosen as standards. Existing standards had a limit in coping with solving urban problems fundamentally and rapidly changing reality. Therefore, it was necessary to add new indicators that can reflect the decline in relevant cities and conditions. In this regard, this study selected Busan Metropolitan City, Korea as the target area as a leading city, where urban regeneration such as an international port city has been activated like Yokohama, Japan. Prior to setting the urban regeneration priority region, the conditions of reality should be reflected because uniform and uncharacterized projects have been implemented without a quantitative analysis about population behavior within the region. For this reason, this study conducted a characterization analysis and type classification, based on the user behaviors by using representative floating population of the big data, which is a hot issue all over the society in recent days. The target areas were analyzed in this study. While 23 regions were classified as three types in existing Busan Metropolitan City urban regeneration priority region, 23 regions were classified as four types in existing Busan Metropolitan City urban regeneration priority region in terms of the type classification on the basis of user behaviors. Four types were classified as follows; type (Ⅰ) of young people - morning type, Type (Ⅱ) of the old and middle-aged- general type with sharp floating population, type (Ⅲ) of the old and middle aged-24hour-type, and type (Ⅳ) of the old and middle aged with less floating population. Characteristics were shown in each region of four types, and the study results of user behaviors were different from those of existing urban regeneration priority region. According to the results, in type (Ⅰ) young people were the majority around the existing old built-up area, where floating population at dawn is four times more than in other areas. In Type (Ⅱ), there were many old and middle-aged people around the existing built-up area and general neighborhoods, where the average floating population was more than in other areas due to commuting, while in type (Ⅲ), there was no change in the floating population throughout 24 hours, although there were many old and middle aged people in population around the existing general neighborhoods. Type (Ⅳ) includes existing economy-based type, central built-up area type, and general neighborhood type, where old and middle aged people were the majority as a general type of commuting with less floating population. Unlike existing urban regeneration priority region, these types were sub-divided according to types, and in this study, approach methods and basic orientations of urban regeneration were set to reflect the reality to a certain degree including the indicators of effective floating population to identify the dynamic activity of urban areas and existing regeneration priority areas in connection with urban regeneration projects by regions. Therefore, it is possible to make effective urban plans through offering the substantial ground by utilizing scientific and quantitative data. To induce more realistic and effective regeneration projects, the regeneration projects tailored to the present local conditions should be developed by reflecting the present conditions on the formulation of urban regeneration strategic plans.

Keywords: floating population, big data, urban regeneration, urban regeneration priority region, type classification

Procedia PDF Downloads 213

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

The increasing use of deep learning applications in production is becoming a competitive advantage. Predictive quality enables the assurance of product quality by using data-driven forecasts via machine learning models as a basis for decisions on test results. The use of real Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the leakage of directional valves.

Keywords: artificial neural networks, classification, hydraulics, predictive quality, deep learning

Procedia PDF Downloads 242

Authors: Mouna Zitouni, Mariem Tounsi

Abstract:

This research introduces an application of the Riesz mixture model for medical image segmentation for accurate diagnosis and treatment of brain tumors. We propose a pixel classification technique based on the Riesz distribution, derived from an extended Bartlett decomposition. To our knowledge, this is the first study addressing this approach. The Expectation-Maximization algorithm is implemented for parameter estimation. A comparative analysis, using both synthetic and real brain images, demonstrates the superiority of the Riesz model over a recent method based on the Wishart distribution.

Keywords: EM algorithm, segmentation, Riesz probability distribution, Wishart probability distribution

Procedia PDF Downloads 16

Authors: Zeinabsadat Haghshenas

Abstract:

Bloom’s Taxonomy has been changed during the years. The idea of this writing is about the revision that has happened in both facts and terms. It also contains case studies of using cognitive Bloom’s taxonomy in teaching geometric solids to the secondary school students, affective objectives in a creative workshop for adults and psychomotor objectives in fixing a malfunctioned refrigerator lamp. There is also pointed to the important role of classification objectives in adult education as a way to prevent memory loss.

Keywords: adult education, affective domain, cognitive domain, memory loss, psychomotor domain

Procedia PDF Downloads 462

Authors: Iris Maria Velez Osorio

Abstract:

There has been in the last decade a concern about the environment, particularly about clean and enough water for human consumption but, some enterprises had some trouble to understand the limited resources in the environment. This research tries to understand how some industries are better oriented to the preservation of the environment through investment for strategic management of scarce resources and try in the best way possible, the contaminants. It was made an industry classification since four different group of theories for Corporate Social Responsibility agree with variables of: investment in environmental care, water protection, and residues treatment finding different levels of commitment with CSR.

Keywords: corporate social responsibility, environment, strategic management, water

Procedia PDF Downloads 375

Authors: Kyle Saltmarsh

Abstract:

Acoustic testing possesses many benefits due to its non-destructive nature and practicality. There hence exists many scenarios in which using acoustic testing for condition testing shows powerful feasibility. A wealth of information is contained within the acoustic and vibration characteristics of structures, allowing the development meaningful features for the classification of their respective condition. In this paper, methods, results, and discussions are presented on the use of non-destructive acoustic testing coupled with acoustic feature extraction and machine learning techniques for the condition testing of manufactured circular steel plates subjected to varied levels of damage.

Keywords: plates, deformation, acoustic features, machine learning

Procedia PDF Downloads 334

Authors: Saroj Bijarnia, Preety Singh

Abstract:

We propose a simple and effective biometrics system based on face verification across aging using a new variant of texture feature, Pyramid Binary Pattern. This employs Local Binary Pattern along with its hierarchical information. Dimension reduction of generated texture feature vector is done using Principal Component Analysis. Support Vector Machine is used for classification. Our proposed method achieves an accuracy of 92:24% and can be used in an automated age-invariant face verification system.

Keywords: biometrics, age invariant, verification, support vector machine

Procedia PDF Downloads 348

Authors: Henry O. Chibudike, Olubamike A. Adeyoju, Bolanle O. Oluwole, Kayode O. Adebowale, Bamidele I. Olu-Owolabi, Chinedum E. Chibudike

Abstract:

Studies on the Mineral Content of Solojo Flour and Protein Isolates from the two varieties (DAS and BS) of Nigeria cultivated solojo cowpeas were conducted to determine their nutritional value. These inorganic elements or minerals were classified into 3 categories: the ultra-trace minerals, which are the third category; the microelements, also known as the trace minerals, in the second category; while the first category is the macro elements, also known as major minerals. Some of the macro-elements are Ca, P, Na and Cl; the second category, micro-elements include iron, copper, cobalt, potassium, magnesium, iodine, zinc, manganese, molybdenum, F, Cr, Se and S. Results show that the proportion of Sodium (Na) which is ingested into the body in the form of NaCl through food intake maintenance of body pH and to retain water ranged from 728.97 to 253.37 ppm (72.90 to 25.34 mg/100 g); 715.24 to 235.45 ppm; 735.28 to 270.37 ppm; 726.59 to 264.35ppm, for FFDAS, FFBS, DAS and BS respectively with all values of the germinated samples all bellow the control. While FFDAS iron content ranged from 4.25 to 13.50 mg/100 g; FFBS ranged from 3.15 to 12.56 mg/100 g; DAS ranged from 3.81 to 12.90 mg/100g; BS ranged from 3.42 to 9.40 mg/100 g. The values of the germinated flours were all greater than the ungerminated flour. Iron helps to transport oxygen round the body and also helps in red blood cells building and to convert food into needed energy by the body. While Manganese an element that is needed in micro quantity but necessary to convert food into energy, is also crucial for healthy bone and cartilage creation. Results also show that zinc quantity increased as germination proceeded, and the values ranged from 38.80 ppm to 230.00 ppm (3.880 mg/100 g to 23.00 mg/100 g; 0.003880% to 0.0230%); 40.84 to 250.01 ppm; 32.85 to 93.41 ppm; 37.07 to 115.00 ppm, for FFDAS, FFBS, DAS and BS respectively. The Ca content improved significantly (p<0.05) with sprouting; the value extended from 250.56 ppm to 760.03 ppm (25.056 to 76.00 mg/100g or 0.0251 to 0.0760 %); 400.40 to 998.22 ppm; 116.87 to 195.69 ppm; 113.48 to 220.75 ppm, for FFDAS, FFBS, DAS and BS respectively. Zinc element although needed at the micro level in the body, is essential for a strong immune system to keep the body in good health. It is also crucial for the maintenance of a healthy sense of taste and odor, while Calcium is critical for strong bones and teeth, blood coagulation, and muscle tightening and relaxation. Magnesium is needed to build enzymes and antioxidants and also for healthy bones, while Potassium is needed to maintain water balance, muscle movement, and nerve impulses. It functions in conjunction with Na to regulate blood pressure.

Keywords: Solojo cowpea, underutilized legumes, protein isolates, BS, DAS, ungerminated

Procedia PDF Downloads 56

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of the flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on the spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts, as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with an attention mechanism. In previous works on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work, with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on the presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: machine learning, classification and regression, gene circuit design, bidirectional transformers

Procedia PDF Downloads 59

Authors: Sugandha Asthana, Geetika Vajpayee, Pratibha Kumari, Shanthy Sundaram

Abstract:

An economically important disease of wheat in North Western region of India is Karnal Bunt caused by smut fungus Tilletia indica. This fungal pathogen spreads by air, soil and seed borne sporodia at the time of flowering, which ultimately leads to partial bunting of wheat kernels with fishy odor and taste to wheat flour. It has very serious effects due to quarantine measures which have to be applied for grain exports. Chemical fungicides such as mercurial compounds and Propiconazole applied to the control of Karnal bunt have been only partially successful. Considering the harmful effects of chemical fungicides on man as well as environment, many countries are developing biological control as the superior substitute to chemical control. Repeated use of fungicides can be responsible for the development of resistance in fungal pathogens against certain chemical compounds. The present investigation is based on the isolation and evaluation of antifungal properties of some isolated (from natural manure) and commercial bacterial strains against Tilletia indica. Total 23 bacterial isolates were obtained and antagonistic activity of all isolates and commercial bacterial strains (Bacillus subtilis MTCC8601, Bacillus pumilus MTCC 8743, Pseudomonas aeruginosa) were tested against T. indica by dual culture plate assay (pour plate and streak plate). Test for the production of antifungal volatile organic compounds (VOCs) by antagonistic bacteria was done by sealed plate method. Amongst all s1, s3, s5, and B. subtilis showed more than 80% inhibition. Production of extracellular hydrolytic enzymes such as protease, beta 1, 4 glucanase, HCN and ammonia was studied for confirmation of antifungal activity. s1, s3, s5 and B. subtilis were found to be the best for protease activity and s5 and B. subtilis for beta 1, 4 glucanase activity. Bacillus subtilis was significantly effective for HCN whereas s3, s5 and Bacillus subtilis for ammonia production. Isolates were identified as Pseudomonas aeruginosa (s1) and B. licheniformis (s3, s5) by various biochemical assays and confirmed by16s rRNA sequencing. Use of microorganisms or their secretions as biocontrol agents to avoid plant diseases is ecologically safe and may offer long term of protection to crop. The above study reports the promising effects of these strains in better pathogen free crop production and quality maintenance as well as prevention of the excessive use of synthetic fungicides.

Keywords: antagonistic, antifungal, biocontrol, Karnal bunt

Procedia PDF Downloads 281

Authors: Abdelhadi Lotfi, Abdelkader Benyettou

Abstract:

In this work, a training algorithm for probabilistic neural networks (PNN) is presented. The algorithm addresses one of the major drawbacks of PNN, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number consisting of the most representative samples of the training set. This is done without affecting the overall architecture of the network. Performance of the network is compared against performance of standard PNN for different databases from the UCI database repository. Results show an important gain in network size and performance.

Keywords: classification, probabilistic neural networks, network optimization, pattern recognition

Procedia PDF Downloads 260

Authors: Likith Reddy Pinninti, Fredrik Ribsskog Staven, Leslie Robert Noble, Jorge Manuel de Oliveira Fernandes, Deepti Manjari Patel, Torstein Kristensen

Abstract:

Understanding fish behavior is essential to improve animal welfare in aquaculture research. Behavioral traits can have a strong influence on fish health and habituation. To identify the genes and biological pathways responsible for lumpfish behavior, we performed an experiment to understand the interspecies relationship (mutualism) between the lumpfish and salmon. Also, we tested the correlation between the gene expression data vs. observational/physiological data to know the essential genes that trigger stress and swimming behavior in lumpfish. After the de novo assembly of the brain transcriptome, all the samples were individually mapped to the available lumpfish (Cyclopterus lumpus L.) primary genome assembly (fCycLum1.pri, GCF_009769545.1). Out of ~16749 genes expressed in brain samples, we found 267 genes to be statistically significant (P > 0.05) found only in odor and control (1), model and control (41) and salmon and control (225) groups. However, genes with |LogFC| ≥0.5 were found to be only eight; these are considered as differentially expressed genes (DEG’s). Though, we are unable to find the differential genes related to the behavioral traits from RNA-Seq data analysis. From the correlation analysis, between the gene expression data vs. observational/physiological data (serotonin (5HT), dopamine (DA), 3,4-Dihydroxyphenylacetic acid (DOPAC), 5-hydroxy indole acetic acid (5-HIAA), Noradrenaline (NORAD)). We found 2495 genes found to be significant (P > 0.05) and among these, 1587 genes are positively correlated with the Noradrenaline (NORAD) hormone group. This suggests that Noradrenaline is triggering the change in pigmentation and skin color in lumpfish. Genes related to behavioral traits like rhythmic, locomotory, feeding, visual, pigmentation, stress, response to other organisms, taxis, dopamine synthesis and other neurotransmitter synthesis-related genes were obtained from the correlation analysis. In KEGG pathway enrichment analysis, we find important pathways, like the calcium signaling pathway and adrenergic signaling in cardiomyocytes, both involved in cell signaling, behavior, emotion, and stress. Calcium is an essential signaling molecule in the brain cells; it could affect the behavior of fish. Our results suggest that changes in calcium homeostasis and adrenergic receptor binding activity lead to changes in fish behavior during stress.

Keywords: behavior, De novo, lumpfish, salmon

Procedia PDF Downloads 172

Authors: Allen A. Espinosa, Arlyne C. Marasigan, Janir T. Datukan

Abstract:

The study explored how students visualize the states and classifications of matter using scientific models. It also identified misconceptions of students in using scientific models. In general, high percentage of students was able to use scientific models correctly and only a little misconception was identified. From the result of the study, a teaching framework was formulated wherein scientific models should be employed in classroom instruction to visualize abstract concepts in chemistry and for better conceptual understanding.

Keywords: visual conception, scientific models, mental models, states of matter, classification of matter

Procedia PDF Downloads 397

Authors: Valdir Moura, Raniele dos Anjos de Souza, Fernando Gomes de Souza, Jose Vagner da Silva, Jerry Adriani Johann

Abstract:

The estimate of the Area of Land to be planted with annual crops and its stratification by the municipality are important variables in crop forecast. Nowadays in Brazil, these information’s are obtained by the Brazilian Institute of Geography and Statistics (IBGE) and published under the report Assessment of the Agricultural Production. Due to the high cloud cover in the main crop growing season (October to March) it is difficult to acquire good orbital images. Thus, one alternative is to work with remote sensing data from dates before the crop growing season. This work presents the use of multitemporal Landsat data gathered on July and September (before the summer growing season) in order to estimate the area of land to be planted with summer crops in an area of São Paulo State, Brazil. Geographic Information Systems (GIS) and digital image processing techniques were applied for the treatment of the available data. Supervised and non-supervised classifications were used for data in digital number and reflectance formats and the multitemporal Normalized Difference Vegetation Index (NDVI) images. The objective was to discriminate the tracts with higher probability to become planted with summer crops. Classification accuracies were evaluated using a sampling system developed basically for this study region. The estimated areas were corrected using the error matrix derived from these evaluations. The classification techniques presented an excellent level according to the kappa index. The proportion of crops stratified by municipalities was derived by a field work during the crop growing season. These proportion coefficients were applied onto the area of land to be planted with summer crops (derived from Landsat data). Thus, it was possible to derive the area of each summer crop by the municipality. The discrepancies between official statistics and our results were attributed to the sampling and the stratification procedures. Nevertheless, this methodology can be improved in order to provide good crop area estimates using remote sensing data, despite the cloud cover during the growing season.

Keywords: area intended for summer culture, estimated area planted, agriculture, Landsat, planting schedule

Procedia PDF Downloads 150

Authors: Djamila Benhaddouche, Abdelkader Benyettou

Abstract:

In this paper, we used data mining to extract biomedical knowledge. In general, complex biomedical data collected in studies of populations are treated by statistical methods, although they are robust, they are not sufficient in themselves to harness the potential wealth of data. For that you used in step two learning algorithms: the Decision Trees and Support Vector Machine (SVM). These supervised classification methods are used to make the diagnosis of thyroid disease. In this context, we propose to promote the study and use of symbolic data mining techniques.

Keywords: biomedical data, learning, classifier, algorithms decision tree, knowledge extraction

Procedia PDF Downloads 556