Search results for: unsupervised

Authors: Souhir Chelly, Asma Ben Cheikh, Hela Ghali, Salwa Khefacha, Lamine Dhidah, Mohamed Ben Rejeb, Houyem Said Latiri

Abstract:

The hospital risk management department is firstly involved in the methodological analysis of grade zero sterilization incidents. The system is based on a subsequent analysis process in compliance with the ongoing requirements of the Haute Autorité de santé (HAS) for a reactive approach to risk, allowing to identify failures and start the appropriate preventive and corrective measures. The use of the association of litigation and risk management (ALARM) method makes easier the grade zero analysis and brings to light the team or institutional, organizational, temporal, individual factors representative of undesirable effects. Two main factors come out again from this analysis, pre-disinfection step of the emergency block unsupervised instrumentalist intern was poorly done since she did not remove the battery from micro air motor. At the sterilization unit, the worker who was not supervised by the nurse did the conditioning of the motor without having checked it if it still contained the battery. The main cause is that the management of human resources was inadequate at both levels, the instrumental trainee in the block who was not supervised by his supervisor and the worker of the sterilization unit who was not supervised by the responsible nurse. There is a lack of research help, advice, and collaboration. The difficulties encountered during this type of analysis are multiple. The first is based on its necessary acceptance by the various actors of care involved, which should not perceive it as a tool leading to individual punishment, but rather as a means to improve their practices.

Keywords: ALARM (Association of Litigation and Risk Management Method), incident, risk management, sterilization

Procedia PDF Downloads 193

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 95

Authors: Bouayachi Ali, Alikouss Saida, Baroudi Zouhir, Zerhouni Youssef, Zouhair Mohammed, El Idrissi Assia, Essalhi Mourad

Abstract:

The world-class Imiter silver deposit is located on the northern flank of the Precambrian Imiter buttonhole. This deposit is formed by epithermal veins hosted in the sandstone-pelite formations of the lower complex and in the basic conglomerates of the upper complex, these veins are controlled by a regional scale fault cluster, oriented N70°E to N90°E. The present work on the contribution of remote sensing on the geological mapping of the Imiter buttonhole and application to the mineralized structures of the Principal Corps B3. Mapping on satellite images is a very important tool in mineral prospecting. It allows the localization of the zones of interest in order to orientate the field missions by helping the localization of the major structures which facilitates the interpretation, the programming and the orientation of the mining works. The predictive map also allows for the correction of field mapping work, especially the direction and dimensions of structures such as dykes, corridors or scrapings. The use of a series of processing such as SAM, PCA, MNF and unsupervised and supervised classification on a Landsat 8 satellite image of the study area allowed us to highlight the main facies of the Imite area. To improve the exploration research, we used another processing that allows to realize a spatial distribution of the alteration mineral indices, and the application of several filters on the different bands to have lineament maps.

Keywords: principal corps B3, teledetection, Landsat 8, Imiter II, silver mineralization, lineaments

Procedia PDF Downloads 67

Authors: Ouafa Amira, Jiangshe Zhang

Abstract:

Clustering is an unsupervised machine learning technique; its aim is to extract the data structures, in which similar data objects are grouped in the same cluster, whereas dissimilar objects are grouped in different clusters. Clustering methods are widely utilized in different fields, such as: image processing, computer vision , and pattern recognition, etc. Fuzzy c-means clustering (fcm) is one of the most well known fuzzy clustering methods. It is based on solving an optimization problem, in which a minimization of a given cost function has been studied. This minimization aims to decrease the dissimilarity inside clusters, where the dissimilarity here is measured by the distances between data objects and cluster centers. The degree of belonging of a data point in a cluster is measured by a membership function which is included in the interval [0, 1]. In fcm clustering, the membership degree is constrained with the condition that the sum of a data object’s memberships in all clusters must be equal to one. This constraint can cause several problems, specially when our data objects are included in a noisy space. Regularization approach took a part in fuzzy c-means clustering technique. This process introduces an additional information in order to solve an ill-posed optimization problem. In this study, we focus on regularization by relative entropy approach, where in our optimization problem we aim to minimize the dissimilarity inside clusters. Finding an appropriate membership degree to each data object is our objective, because an appropriate membership degree leads to an accurate clustering result. Our clustering results in synthetic data sets, gaussian based data sets, and real world data sets show that our proposed model achieves a good accuracy.

Keywords: clustering, fuzzy c-means, regularization, relative entropy

Procedia PDF Downloads 239

Authors: Samuel Munaf, Kevin Swingler, Franz Brülisauer, Anthony O’Hare, George Gunn, Aaron Reeves

Abstract:

Web scraping and text mining are popular computer science methods deployed by public health researchers to augment traditional epidemiological surveillance. However, within veterinary disease surveillance, such techniques are still in the early stages of development and have not yet been fully utilised. This study presents an exploration into the utility of incorporating internet-based data to better understand the smallholder farming communities within Scotland by using online text extraction and the subsequent mining of this data. Web scraping of the livestock fora was conducted in conjunction with text mining of the data in search of common themes, words, and topics found within the text. Results from bi-grams and topic modelling uncover four main topics of interest within the data pertaining to aspects of livestock husbandry: feeding, breeding, slaughter, and disposal. These topics were found amongst both the poultry and pig sub-forums. Topic modeling appears to be a useful method of unsupervised classification regarding this form of data, as it has produced clusters that relate to biosecurity and animal welfare. Internet data can be a very effective tool in aiding traditional veterinary surveillance methods, but the requirement for human validation of said data is crucial. This opens avenues of research via the incorporation of other dynamic social media data, namely Twitter and Facebook/Meta, in addition to time series analysis to highlight temporal patterns.

Keywords: veterinary epidemiology, disease surveillance, infodemiology, infoveillance, smallholding, social media, web scraping, sentiment analysis, geolocation, text mining, NLP

Procedia PDF Downloads 61

Authors: A. Shirazibeheshti, T. Radwan, A. Ettefaghian, G. Wilson, C. Luca, Farbod Khanizadeh

Abstract:

Anticholinergic medication has been associated with events such as falls, delirium, and cognitive impairment in older patients. To further assess this, anticholinergic burden scores have been developed to quantify risk. A risk model based on clustering was deployed in a healthcare management system to cluster patients into multiple risk groups according to anticholinergic burden scores of multiple medicines prescribed to patients to facilitate clinical decision-making. To do so, anticholinergic burden scores of drugs were extracted from the literature, which categorizes the risk on a scale of 1 to 3. Given the patients’ prescription data on the healthcare database, a weighted anticholinergic risk score was derived per patient based on the prescription of multiple anticholinergic drugs. This study was conducted on over 300,000 records of patients currently registered with a major regional UK-based healthcare provider. The weighted risk scores were used as inputs to an unsupervised learning algorithm (mean-shift clustering) that groups patients into clusters that represent different levels of anticholinergic risk. To further evaluate the performance of the model, any association between the average risk score within each group and other factors such as socioeconomic status (i.e., Index of Multiple Deprivation) and an index of health and disability were investigated. The clustering identifies a group of 15 patients at the highest risk from multiple anticholinergic medication. Our findings also show that this group of patients is located within more deprived areas of London compared to the population of other risk groups. Furthermore, the prescription of anticholinergic medicines is more skewed to female than male patients, indicating that females are more at risk from this kind of multiple medications. The risk may be monitored and controlled in well artificial intelligence-equipped healthcare management systems.

Keywords: anticholinergic medicines, clustering, deprivation, socioeconomic status

Procedia PDF Downloads 168

Authors: Usman Ahmed Khan

Abstract:

Urbanization directly affects the existing infrastructure, landscape modification, environmental contamination, and traffic pollution, especially if there is a lack of urban planning. Recently, the rapid urban sprawl has resulted in less developed green areas and has devastating environmental consequences. This study was aimed to study the past urban expansion rates and measure LST from satellite data. The land use land cover (LULC) maps of years 1996, 2010, 2013, and 2017 were generated using landsat satellite images. Four main classes, i.e., water, urban, bare land, and vegetation, were identified using unsupervised classification with iterative self-organizing data analysis (isodata) technique. The LST from satellite thermal data can be derived from different procedures: atmospheric, radiometric calibrations and surface emissivity corrections, classification of spatial changeability in land-cover. Different methods and formulas were used in the algorithm that successfully retrieves the land surface temperature to help us study the thermal environment of the ground surface. To verify the algorithm, the land surface temperature and the near-air temperature were compared. The results showed that, From 1996-2017, urban areas increased to about a considerable increase of about 48%. Few areas of the city also shown in a reduction in LST from the year 1996-2017 that actually began their transitional phase from rural to urban LULC. The mean temperature of the city increased averagely about 1ºC each year in the month of October. The green and vegetative areas witnessed a decrease in the area while a higher number of pixels increased in urban class.

Keywords: LST, LULC, isodata, urbanization

Procedia PDF Downloads 75

Authors: Qingsong Xiong, Cheng Yuan, Qingzhao Kong, Haibei Xiong

Abstract:

Deep-learning-driven approaches based on vibration responses have attracted larger attention in rapid structural condition assessment while obtaining sufficient measured training data with corresponding labels is relevantly costly and even inaccessible in practical engineering. This study proposes an integrated label propagation network for structural condition assessment, which is able to diffuse the labels from continuously-generating measurements by intact structure to those of missing labels of damage scenarios. The integrated network is embedded with damage-sensitive features extraction by deep autoencoder and pseudo-labels propagation by optimized fuzzy clustering, the architecture and mechanism which are elaborated. With a sophisticated network design and specified strategies for improving performance, the present network achieves to extends the superiority of self-supervised representation learning, unsupervised fuzzy clustering and supervised classification algorithms into an integration aiming at assessing damage conditions. Both numerical simulations and full-scale laboratory shaking table tests of a two-story building structure were conducted to validate its capability of detecting post-earthquake damage. The identifying accuracy of a present network was 0.95 in numerical validations and an average 0.86 in laboratory case studies, respectively. It should be noted that the whole training procedure of all involved models in the network stringently doesn’t rely upon any labeled data of damage scenarios but only several samples of intact structure, which indicates a significant superiority in model adaptability and feasible applicability in practice.

Keywords: autoencoder, condition assessment, fuzzy clustering, label propagation

Procedia PDF Downloads 67

Authors: Donghwan Lee, Gichun Cha, Jooyoung Park, Junkyeong Kim, Seunghee Park

Abstract:

3D shape models of the existing structure are required for many purposes such as safety and operation management. The traditional 3D modeling methods are based on manual or semi-automatic reconstruction from close-range images. It occasions great expense and time consuming. The Terrestrial Laser Scanner (TLS) is a common survey technique to measure quickly and accurately a 3D shape model. This TLS is used to a construction site and cultural heritage management. However there are many limits to process a TLS point cloud, because the raw point cloud is massive volume data. So the capability of carrying out useful analyses is also limited with unstructured 3-D point. Thus, segmentation becomes an essential step whenever grouping of points with common attributes is required. In this paper, members segmentation algorithm was presented to separate a raw point cloud which includes only 3D coordinates. This paper presents a clustering approach based on a fuzzy method for this objective. The Fuzzy C-Means (FCM) is reviewed and used in combination with a similarity-driven cluster merging method. It is applied to the point cloud acquired with Lecia Scan Station C10/C5 at the test bed. The test-bed was a bridge which connects between 1st and 2nd engineering building in Sungkyunkwan University in Korea. It is about 32m long and 2m wide. This bridge was used as pedestrian between two buildings. The 3D point cloud of the test-bed was constructed by a measurement of the TLS. This data was divided by segmentation algorithm for each member. Experimental analyses of the results from the proposed unsupervised segmentation process are shown to be promising. It can be processed to manage configuration each member, because of the segmentation process of point cloud.

Keywords: fuzzy c-means (FCM), point cloud, segmentation, terrestrial laser scanner (TLS)

Procedia PDF Downloads 204

Authors: Cheng Zeng, George Michailidis, Hitoshi Iyatomi, Leo L. Duan

Abstract:

The conditional density characterizes the distribution of a response variable y given other predictor x and plays a key role in many statistical tasks, including classification and outlier detection. Although there has been abundant work on the problem of Conditional Density Estimation (CDE) for a low-dimensional response in the presence of a high-dimensional predictor, little work has been done for a high-dimensional response such as images. The promising performance of normalizing flow (NF) neural networks in unconditional density estimation acts as a motivating starting point. In this work, the authors extend NF neural networks when external x is present. Specifically, they use the NF to parameterize a one-to-one transform between a high-dimensional y and a latent z that comprises two components [zₚ, zₙ]. The zₚ component is a low-dimensional subvector obtained from the posterior distribution of an elementary predictive model for x, such as logistic/linear regression. The zₙ component is a high-dimensional independent Gaussian vector, which explains the variations in y not or less related to x. Unlike existing CDE methods, the proposed approach coined Augmented Posterior CDE (AP-CDE) only requires a simple modification of the common normalizing flow framework while significantly improving the interpretation of the latent component since zₚ represents a supervised dimension reduction. In image analytics applications, AP-CDE shows good separation of 𝑥-related variations due to factors such as lighting condition and subject id from the other random variations. Further, the experiments show that an unconditional NF neural network based on an unsupervised model of z, such as a Gaussian mixture, fails to generate interpretable results.

Keywords: conditional density estimation, image generation, normalizing flow, supervised dimension reduction

Procedia PDF Downloads 62

Authors: Maryam Zarabian, Hector Guzman, Pedro Pereira-Almao, Abraham Fapojuwo

Abstract:

Dry reforming of methane (DRM) has sparked significant industrial and scientific interest not only as a viable alternative for addressing the environmental concerns of two main contributors of the greenhouse effect, i.e., carbon dioxide (CO₂) and methane (CH₄), but also produces syngas, i.e., a mixture of hydrogen (H₂) and carbon monoxide (CO) utilized by a wide range of downstream processes as a feedstock for other chemical productions. In this study, we develop an AI-enable syngas production model to tackle the problem of achieving an equivalent H₂/CO ratio [1:1] with respect to the most efficient conversion. Firstly, the unsupervised density-based spatial clustering of applications with noise (DBSAN) algorithm removes outlier data points from the original experimental dataset. Then, random forest (RF) and deep neural network (DNN) models employ the error-free dataset to predict the DRM results. DNN models inherently would not be able to obtain accurate predictions without a huge dataset. To cope with this limitation, we employ reusing pre-trained layers’ approaches such as transfer learning and greedy layer-wise pretraining. Compared to the other deep models (i.e., pure deep model and transferred deep model), the greedy layer-wise pre-trained deep model provides the most accurate prediction as well as similar accuracy to the RF model with R² values 1.00, 0.999, 0.999, 0.999, 0.999, and 0.999 for the total outlet flow, H₂/CO ratio, H₂ yield, CO yield, CH₄ conversion, and CO₂ conversion outputs, respectively.

Keywords: artificial intelligence, dry reforming of methane, artificial neural network, deep learning, machine learning, transfer learning, greedy layer-wise pretraining

Procedia PDF Downloads 57

Authors: Seyedamir Makinejadsanij

Abstract:

One of the most important factors in the production of quality steel is to know the exact weight of steel in the steelmaking area. In this study, a calculation method is presented to estimate the exact weight of the melt as well as the objects transported by the overhead crane. Iran Alloy Steel Company's steelmaking area has three 90-ton cranes, which are responsible for transferring the ladles and ladle caps between 34 areas in the melt shop. Each crane is equipped with a Disomat Tersus weighing system that calculates and displays real-time weight. The moving object has a variable weight due to swinging, and the weighing system has an error of about +-5%. This means that when the object is moving by a crane, which weighs about 80 tons, the device (Disomat Tersus system) calculates about 4 tons more or 4 tons less, and this is the biggest problem in calculating a real weight. The k-means algorithm is an unsupervised clustering method that was used here. The best result was obtained by considering 3 centers. Compared to the normal average(one) or two, four, five, and six centers, the best answer is with 3 centers, which is logically due to the elimination of noise above and below the real weight. Every day, the standard weight is moved with working cranes to test and calibrate cranes. The results are shown that the accuracy is about 40 kilos per 60 tons (standard weight). As a result, with this method, the accuracy of moving weight is calculated as 99.95%. K-means is used to calculate the exact mean of objects. The stopping criterion of the algorithm is also the number of 1000 repetitions or not moving the points between the clusters. As a result of the implementation of this system, the crane operator does not stop while moving objects and continues his activity regardless of weight calculations. Also, production speed increased, and human error decreased.

Keywords: k-means, overhead crane, melt weight, weight estimation, swing problem

Procedia PDF Downloads 58

Authors: Bassem Nassar, Wessam Hussein, Medhat Mokhtar

Abstract:

The crucial concern of satellite operations is to ensure the health and safety of satellites. The worst case in this perspective is probably the loss of a mission but the more common interruption of satellite functionality can result in compromised mission objectives. All the data acquiring from the spacecraft are known as Telemetry (TM), which contains the wealth information related to the health of all its subsystems. Each single item of information is contained in a telemetry parameter, which represents a time-variant property (i.e. a status or a measurement) to be checked. As a consequence, there is a continuous improvement of TM monitoring systems in order to reduce the time required to respond to changes in a satellite's state of health. A fast conception of the current state of the satellite is thus very important in order to respond to occurring failures. Statistical multivariate latent techniques are one of the vital learning tools that are used to tackle the aforementioned problem coherently. Information extraction from such rich data sources using advanced statistical methodologies is a challenging task due to the massive volume of data. To solve this problem, in this paper, we present a proposed unsupervised learning algorithm based on Principle Component Analysis (PCA) technique. The algorithm is particularly applied on an actual remote sensing spacecraft. Data from the Attitude Determination and Control System (ADCS) was acquired under two operation conditions: normal and faulty states. The models were built and tested under these conditions and the results shows that the algorithm could successfully differentiate between these operations conditions. Furthermore, the algorithm provides competent information in prediction as well as adding more insight and physical interpretation to the ADCS operation.

Keywords: space telemetry monitoring, multivariate analysis, PCA algorithm, space operations

Procedia PDF Downloads 388

Authors: Javier De La Torre Costa, Belen Rubio Ballester, Martina Maier, Paul F. M. J. Verschure

Abstract:

After a stroke, a great number of patients experience persistent motor impairments such as hemiparesis or weakness in one entire side of the body. As a result, the lack of use of the paretic limb might be one of the main contributors to functional loss after clinical discharge. We aim to reverse this cycle by promoting the use of the paretic limb during activities of daily living (ADLs). To do so, we describe the key components of a system that is composed of a wearable bracelet (i.e., a smartwatch) and a mobile phone, designed to bring a set of neurorehabilitation principles that promote acquisition, retention and generalization of skills to the home of the patient. A fundamental question is whether the loss in motor function derived from learned–non–use may emerge as a consequence of decision–making processes for motor optimization. Our system is based on well-established rehabilitation strategies that aim to reverse this behaviour by increasing the reward associated with action execution as well as implicitly reducing the expected cost associated with the use of the paretic limb, following the notion of the reinforcement–induced movement therapy (RIMT). Here we validate an accelerometer–based measure of arm use, and its capacity to discriminate different activities that require increasing movement of the arm. We also show how the system can act as a personalized assistant by providing specific goals and adjusting them depending on the performance of the patients. The usability and acceptance of the device as a rehabilitation tool is tested using a battery of self–reported and objective measurements obtained from acute/subacute patients and healthy controls. We believe that an extension of these technologies will allow for the deployment of unsupervised rehabilitation paradigms during and beyond the hospitalization time.

Keywords: stroke, wearables, learned non use, hemiparesis, ADLs

Procedia PDF Downloads 178

Authors: Ismail Elkhrachy

Abstract:

Determination of land use changing is an important component of regional planning for applications ranging from urban fringe change detection to monitoring change detection of land use. This data are very useful for natural resources management.On the other hand, the technologies and methods of change detection also have evolved dramatically during past 20 years. So it has been well recognized that the change detection had become the best methods for researching dynamic change of land use by multi-temporal remotely-sensed data. The objective of this paper is to assess, evaluate and monitor land use change surrounding the area of Najran city, Kingdom of Saudi Arabia (KSA) using Landsat images (June 23, 2009) and ETM+ image(June. 21, 2014). The post-classification change detection technique was applied. At last,two-time subset images of Najran city are compared on a pixel-by-pixel basis using the post-classification comparison method and the from-to change matrix is produced, the land use change information obtained.Three classes were obtained, urban, bare land and agricultural land from unsupervised classification method by using Erdas Imagine and ArcGIS software. Accuracy assessment of classification has been performed before calculating change detection for study area. The obtained accuracy is between 61% to 87% percent for all the classes. Change detection analysis shows that rapid growth in urban area has been increased by 73.2%, the agricultural area has been decreased by 10.5 % and barren area reduced by 7% between 2009 and 2014. The quantitative study indicated that the area of urban class has unchanged by 58.2 km〗^2, gained 70.3 〖km〗^2 and lost 16 〖km〗^2. For bare land class 586.4〖km〗^2 has unchanged, 53.2〖km〗^2 has gained and 101.5〖km〗^2 has lost. While agriculture area class, 20.2〖km〗^2 has unchanged, 31.2〖km〗^2 has gained and 37.2〖km〗^2 has lost.

Keywords: land use, remote sensing, change detection, satellite images, image classification

Procedia PDF Downloads 499

Authors: Chahrazed Zouaoui

Abstract:

In recent years, the volume of geospatial information is increasing due to the evolution of communication technologies and information, this information is presented often by geographic information systems (GIS) and stored on of spatial databases (BDS). The classical data mining revealed a weakness in knowledge extraction at these enormous amounts of data due to the particularity of these spatial entities, which are characterized by the interdependence between them (1st law of geography). This gave rise to spatial data mining. Spatial data mining is a process of analyzing geographic data, which allows the extraction of knowledge and spatial relationships from geospatial data, including methods of this process we distinguish the monothematic and thematic, geo- Clustering is one of the main tasks of spatial data mining, which is registered in the part of the monothematic method. It includes geo-spatial entities similar in the same class and it affects more dissimilar to the different classes. In other words, maximize intra-class similarity and minimize inter similarity classes. Taking account of the particularity of geo-spatial data. Two approaches to geo-clustering exist, the dynamic processing of data involves applying algorithms designed for the direct treatment of spatial data, and the approach based on the spatial data pre-processing, which consists of applying clustering algorithms classic pre-processed data (by integration of spatial relationships). This approach (based on pre-treatment) is quite complex in different cases, so the search for approximate solutions involves the use of approximation algorithms, including the algorithms we are interested in dedicated approaches (clustering methods for partitioning and methods for density) and approaching bees (biomimetic approach), our study is proposed to design very significant to this problem, using different algorithms for automatically detecting geo-spatial neighborhood in order to implement the method of geo- clustering by pre-treatment, and the application of the bees algorithm to this problem for the first time in the field of geo-spatial.

Keywords: mining, GIS, geo-clustering, neighborhood

Procedia PDF Downloads 355

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system

Procedia PDF Downloads 125

Authors: Donatella Giuliani

Abstract:

In this research, we propose an unsupervised grayscale image segmentation method based on a combination of the Firefly Algorithm and the Gaussian Mixture Model. Firstly, the Firefly Algorithm has been applied in a histogram-based research of cluster means. The Firefly Algorithm is a stochastic global optimization technique, centered on the flashing characteristics of fireflies. In this context it has been performed to determine the number of clusters and the related cluster means in a histogram-based segmentation approach. Successively these means are used in the initialization step for the parameter estimation of a Gaussian Mixture Model. The parametric probability density function of a Gaussian Mixture Model is represented as a weighted sum of Gaussian component densities, whose parameters are evaluated applying the iterative Expectation-Maximization technique. The coefficients of the linear super-position of Gaussians can be thought as prior probabilities of each component. Applying the Bayes rule, the posterior probabilities of the grayscale intensities have been evaluated, therefore their maxima are used to assign each pixel to the clusters, according to their gray-level values. The proposed approach appears fairly solid and reliable when applied even to complex grayscale images. The validation has been performed by using different standard measures, more precisely: the Root Mean Square Error (RMSE), the Structural Content (SC), the Normalized Correlation Coefficient (NK) and the Davies-Bouldin (DB) index. The achieved results have strongly confirmed the robustness of this gray scale segmentation method based on a metaheuristic algorithm. Another noteworthy advantage of this methodology is due to the use of maxima of responsibilities for the pixel assignment that implies a consistent reduction of the computational costs.

Keywords: clustering images, firefly algorithm, Gaussian mixture model, meta heuristic algorithm, image segmentation

Procedia PDF Downloads 188

Authors: Abdesselem Dakhli, Wajdi Bellil, Chokri Ben Amar

Abstract:

DNA Barcode, a short mitochondrial DNA fragment, made up of three subunits; a phosphate group, sugar and nucleic bases (A, T, C, and G). They provide good sources of information needed to classify living species. Such intuition has been confirmed by many experimental results. Species classification with DNA Barcode sequences has been studied by several researchers. The classification problem assigns unknown species to known ones by analyzing their Barcode. This task has to be supported with reliable methods and algorithms. To analyze species regions or entire genomes, it becomes necessary to use similarity sequence methods. A large set of sequences can be simultaneously compared using Multiple Sequence Alignment which is known to be NP-complete. To make this type of analysis feasible, heuristics, like progressive alignment, have been developed. Another tool for similarity search against a database of sequences is BLAST, which outputs shorter regions of high similarity between a query sequence and matched sequences in the database. However, all these methods are still computationally very expensive and require significant computational infrastructure. Our goal is to build predictive models that are highly accurate and interpretable. This method permits to avoid the complex problem of form and structure in different classes of organisms. On empirical data and their classification performances are compared with other methods. Our system consists of three phases. The first is called transformation, which is composed of three steps; Electron-Ion Interaction Pseudopotential (EIIP) for the codification of DNA Barcodes, Fourier Transform and Power Spectrum Signal Processing. The second is called approximation, which is empowered by the use of Multi Llibrary Wavelet Neural Networks (MLWNN).The third is called the classification of DNA Barcodes, which is realized by applying the algorithm of hierarchical classification.

Keywords: DNA barcode, electron-ion interaction pseudopotential, Multi Library Wavelet Neural Networks (MLWNN)

Procedia PDF Downloads 284

Authors: Jeff Chak-Fu Wong, Tony Chun Yin Yip

Abstract:

The transition from secondary school to university seems exciting for many first-year students but can be more challenging than expected. Enabling instructors to know students’ learning habits and styles enhances their understanding of the students’ learning backgrounds, allows teachers to provide better support for their students, and has therefore high potential to improve teaching quality and learning, especially in any mathematics-related courses. The aim of this research is to collect students’ data using online surveys, to analyze students’ factors using learning analytics and educational data mining and to discover the characteristics of the students at risk of falling behind in their studies based on students’ previous academic backgrounds and collected data. In this paper, we use correlation-based distance methods and mutual information for measuring student factor relationships. We then develop a factor network using the Minimum Spanning Tree method and consider further study for analyzing the topological properties of these networks using social network analysis tools. Under the framework of mutual information, two graph-based feature filtering methods, i.e., unsupervised and supervised infinite feature selection algorithms, are used to analyze the results for students’ data to rank and select the appropriate subsets of features and yield effective results in identifying the factors affecting students at risk of failing. This discovered knowledge may help students as well as instructors enhance educational quality by finding out possible under-performers at the beginning of the first semester and applying more special attention to them in order to help in their learning process and improve their learning outcomes.

Keywords: students' academic performance, correlation-based distance method, social network analysis, feature selection, graph-based feature filtering method

Procedia PDF Downloads 92

Authors: Mirza Waseem Abbas, Syed Danish Raza

Abstract:

For many countries agriculture is still the major force driving the economy and a critically important socioeconomic sector, despite exceptional industrial development across the globe. In countries like Pakistan, this sector is considered the backbone of the economy, and most of the economic decision making revolves around agricultural outputs and data. Timely and accurate facts and figures about this vital sector hold immense significance and have serious implications for the long-term development of the economy. Therefore, any significant improvements in the statistics and other forms of data regarding agriculture sector are considered important by all policymakers. This is especially true for decision making for the betterment of crops and the agriculture sector in general. Provincial and federal agricultural departments collect data for all cash and non-cash crops and the sector, in general, every year. Traditional data collection for such a large sector i.e. agriculture, being time-consuming, prone to human error and labor-intensive, is slowly but gradually being replaced by remote sensing techniques. For this study, remotely sensed data were used for change detection (machine learning, supervised & unsupervised classification) to assess the increase or decrease in area under agriculture over the last fifteen years due to urbanization. Detailed Landsat Images for the selected agricultural districts were acquired for the year 2000 and compared to images of the same area acquired for the year 2016. Observed differences validated through detailed analysis of the areas show that there was a considerable decrease in vegetation during the last fifteen years in four major agricultural districts of the Punjab province due to urbanization (housing societies).

Keywords: change detection, area estimation, machine learning, urbanization, remote sensing

Procedia PDF Downloads 218

Authors: Christopher B. Obida, George A. Blackburn, James D. Whyatt, Kirk T. Semple

Abstract:

In many regions of the world, especially in developing countries, river network data are outdated or completely absent, yet such information is critical for supporting important functions such as flood mitigation efforts, land use and transportation planning, and the management of water resources. In this study, a method was developed for delineating river networks using Sentinel 1 imagery. Unsupervised classification was applied to multi-temporal Sentinel 1 data to discriminate water bodies from other land covers then the outputs were combined to generate a single persistent water bodies product. A thinning algorithm was then used to delineate river centre lines, which were converted into vector features and built into a topologically structured geometric network. The complex river system of the Niger Delta was used to compare the performance of the Sentinel-based method against alternative freely available water body products from United States Geological Survey, European Space Agency and OpenStreetMap and a river network derived from a Shuttle Rader Topography Mission Digital Elevation Model. From both raster-based and vector-based accuracy assessments, it was found that the Sentinel-based river network products were superior to the comparator data sets by a substantial margin. The geometric river network that was constructed permitted a flow routing analysis which is important for a variety of environmental management and planning applications. The extracted network will potentially be applied for modelling dispersion of hydrocarbon pollutants in Ogoniland, a part of the Niger Delta. The approach developed in this study holds considerable potential for generating up to date, detailed river network data for the many countries where such data are deficient.

Keywords: Sentinel 1, image processing, river delineation, large scale mapping, data comparison, geometric network

Procedia PDF Downloads 108

Authors: Jian-Heng Wu, Bor-Shen Lin

Abstract:

The temperature-salinity relationship is one of the most important characteristics used for identifying water masses in marine research. Temperature-salinity characteristics, however, may change dynamically with respect to the geographic location and is quite sensitive to the depth at the same location. When depth is taken into consideration, however, it is not easy to compare the characteristics of different water masses efficiently for a wide range of areas of the ocean. In this paper, the Gaussian mixture model was proposed to analyze the temperature-salinity-depth characteristics of water masses, based on which comparison between water masses may be conducted. Gaussian mixture model could model the distribution of a random vector and is formulated as the weighting sum for a set of multivariate normal distributions. The temperature-salinity-depth data for different locations are first used to train a set of Gaussian mixture models individually. The distance between two Gaussian mixture models can then be defined as the weighting sum of pairwise Bhattacharyya distances among the Gaussian distributions. Consequently, the distance between two water masses may be measured fast, which allows the automatic and efficient comparison of the water masses for a wide range area. The proposed approach not only can approximate the distribution of temperature, salinity, and depth directly without the prior knowledge for assuming the regression family, but may restrict the complexity by controlling the number of mixtures when the amounts of samples are unevenly distributed. In addition, it is critical for knowledge discovery in marine research to represent, manage and share the temperature-salinity-depth characteristics flexibly and responsively. The proposed approach has been applied to a real-time visualization system of ocean data, which may facilitate the comparison of water masses by aggregating the data without degrading the discriminating capabilities. This system provides an interface for querying geographic locations with similar temperature-salinity-depth characteristics interactively and for tracking specific patterns of water masses, such as the Kuroshio near Taiwan or those in the South China Sea.

Keywords: water mass, Gaussian mixture model, data visualization, system framework

Procedia PDF Downloads 103

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 80

Authors: Nathenal Thomas

Abstract:

In the food chain and in many other agricultural products, corn, also known as maize, which goes by the scientific name Zea mays subsp, is a widely produced agricultural product. Corn has the highest adaptability. It comes in many different types, is employed in many different industrial processes, and is more adaptable to different agro-climatic situations. In Ethiopia, maize is among the most widely grown crop. Small-scale corn farming may be a household's only source of food in developing nations like Ethiopia. The aforementioned data demonstrates that the country's requirement for this crop is excessively high, and conversely, the crop's productivity is very low for a variety of reasons. The most damaging disease that greatly contributes to this imbalance between the crop's supply and demand is the corn disease. The failure to diagnose diseases in maize plant until they are too late is one of the most important factors influencing crop output in Ethiopia. This study will aid in the early detection of such diseases and support farmers during the cultivation process, directly affecting the amount of maize produced. The diseases in maize plants, such as northern leaf blight and cercospora leaf spot, have distinct symptoms that are visible. This study aims to detect the most frequent and degrading maize diseases using the most efficiently used subset of machine learning technology, deep learning so, called Image Processing. Deep learning uses networks that can be trained from unlabeled data without supervision (unsupervised). It is a feature that simulates the exercises the human brain goes through when digesting data. Its applications include speech recognition, language translation, object classification, and decision-making. Convolutional Neural Network (CNN) for Image Processing, also known as convent, is a deep learning class that is widely used for image classification, image detection, face recognition, and other problems. it will also use this algorithm as the state-of-the-art for my research to detect maize diseases by photographing maize leaves using a mobile phone.

Keywords: CNN, zea mays subsp, leaf blight, cercospora leaf spot

Procedia PDF Downloads 44

Authors: Samain Sabrin, Joshua Pratt, Joshua Bryk, Maryam Karimi

Abstract:

Globally, extreme heat events have led to a surge in the number of heat-related moralities. These incidents are further exacerbated in high-density population centers due to the Urban Heat Island (UHI) effect. Varieties of anthropogenic activities such as unsupervised land surface modifications, expansion of impervious areas, and lack of use of vegetation are all contributors to an increase in the amount of heat flux trapped by an urban canopy which intensifies the UHI effect. This project aims to propose a systematic approach to measure the impact of air quality and increased temperature based on urban morphology in the selected metropolitan cities. This project will measure the impact of build environment for urban and regional planning using human biometeorological evaluations (mean radiant temperature, Tmrt). We utilized the Rayman model (capable of calculating short and long wave radiation fluxes affecting the human body) to estimate the Tmrt in an urban environment incorporating location and height of buildings and trees as a supplemental tool in urban planning, and street design. Our current results suggest a strong correlation between building height and increased surface temperature in megacities. This model will help with; 1. Quantify the impacts of the built environment and surface properties on surrounding temperature, 2. Identify priority urban neighborhoods by analyzing Tmrt and air quality data at pedestrian level, 3. Characterizing the need for urban green infrastructure or better urban planning- maximizing the cooling benefit from existing Urban Green Infrastructure (UGI), and 4. Developing a hierarchy of streets for new UGI integration and propose new UGI based on site characteristics and cooling potential.

Keywords: air quality, heat mitigation, human-biometeorological indices, increased temperature, mean radiant temperature, radiation flux, sustainable development, thermal comfort, urban canopy, urban planning

Procedia PDF Downloads 106

Authors: Eleni C. Mazarakioti, Anastasios Zotos, Anna-Akrivi Thomatou, Efthimios Kokkotos, Achilleas Kontogeorgos, Athanasios Ladavos, Angelos Patakas

Abstract:

“Gigantes Elefantes” is a particularly dynamic crop of giant beans cultivated in western Macedonia (Greece). This variety of large beans growing in this area and specifically in the regions of Prespes and Kastoria is a protected designation of origin (PDO) species with high nutritional quality. Mislabeling of geographical origin and blending with unidentified samples are common fraudulent practices in Greek food market with financial and possible health consequences. In the last decades, multi-elemental composition analysis has been used in identifying the geographical origin of foods and agricultural products. In an attempt to discriminate the authenticity of Greek beans, multi-elemental analysis (Ag, Al, As, B, Ba, Be, Ca, Cd, Co, Cr, Cs, Cu, Fe, Ga, Ge, K, Li, Mg, Mn, Mo, Na, Nb, Ni, P, Pb, Rb, Re, Se, Sr, Ta, Ti, Tl, U, V, W, Zn, Zr) was performed by inductively coupled plasma mass spectrometry (ICP-MS) on 320 samples of beans, originated from Greece (Prespes and Kastoria), China and Poland. All samples were collected during the autumn of 2021. The obtained data were analysed by principal component analysis (PCA), an unsupervised statistical method, which allows for to reduce of the dimensionality of the enormous datasets. Statistical analysis revealed a clear separation of beans that had been cultivated in Greece compared with those from China and Poland. An adequate discrimination of geographical origin between bean samples originating from the two Greece regions, Prespes and Kastoria, was also evident. Our results suggest that multi-elemental analysis combined with the appropriate multivariate statistical method could be a useful tool for bean’s geographical authentication. Acknowledgment: This research has been financed by the Public Investment Programme/General Secretariat for Research and Innovation, under the call “YPOERGO 3, code 2018SE01300000: project title: ‘Elaboration and implementation of methodology for authenticity and geographical origin assessment of agricultural products.

Keywords: geographical origin, authenticity, multi-elemental analysis, beans, ICP-MS, PCA

Procedia PDF Downloads 43

Authors: Wanderson Goncalves e Goncalves, José Alberto Silva de Sá

Abstract:

Human actions are a threat to the balance and conservation of the Amazon forest. Therefore the environmental monitoring services play an important role as the preservation and maintenance of this environment. This study classified forest types using data from a forest inventory provided by the 'Florestal e da Biodiversidade do Estado do Pará' (IDEFLOR-BIO), located between the municipalities of Santarém, Juruti and Aveiro, in the state of Pará, Brazil, covering an area approximately of 600,000 hectares, Bands 3, 4 and 5 of the TM-Landsat satellite image, and Self - Organizing Maps. The information from the satellite images was extracted using QGIS software 2.8.1 Wien and was used as a database for training the neural network. The midpoints of each sample of forest inventory have been linked to images. Later the Digital Numbers of the pixels have been extracted, composing the database that fed the training process and testing of the classifier. The neural network was trained to classify two forest types: Rain Forest of Lowland Emerging Canopy (Dbe) and Rain Forest of Lowland Emerging Canopy plus Open with palm trees (Dbe + Abp) in the Mamuru Arapiuns glebes of Pará State, and the number of examples in the training data set was 400, 200 examples for each class (Dbe and Dbe + Abp), and the size of the test data set was 100, with 50 examples for each class (Dbe and Dbe + Abp). Therefore, total mass of data consisted of 500 examples. The classifier was compiled in Orange Data Mining 2.7 Software and was evaluated in terms of the confusion matrix indicators. The results of the classifier were considered satisfactory, and being obtained values of the global accuracy equal to 89% and Kappa coefficient equal to 78% and F1 score equal to 0,88. It evaluated also the efficiency of the classifier by the ROC plot (receiver operating characteristics), obtaining results close to ideal ratings, showing it to be a very good classifier, and demonstrating the potential of this methodology to provide ecosystem services, particularly in anthropogenic areas in the Amazon.

Keywords: artificial neural network, computational intelligence, pattern recognition, unsupervised learning

Procedia PDF Downloads 336

Authors: Swathi Ganesan, Nalinda Somasiri, Rebecca Jeyavadhanam, Gayathri Karthick

Abstract:

The COVID-19 crisis presents a substantial and critical hazard to worldwide health. Since the occurrence of the disease in late January 2020 in the UK, the number of infected people confirmed to acquire the illness has increased tremendously across the country, and the number of individuals affected is undoubtedly considerably high. The purpose of this research is to figure out a predictive machine learning archetypal that could forecast COVID-19 cases within the UK. This study concentrates on the statistical data collected from 31st January 2020 to 31st March 2021 in the United Kingdom. Information on total COVID cases registered, new cases encountered on a daily basis, total death registered, and patients’ death per day due to Coronavirus is collected from World Health Organisation (WHO). Data preprocessing is carried out to identify any missing values, outliers, or anomalies in the dataset. The data is split into 8:2 ratio for training and testing purposes to forecast future new COVID cases. Support Vector Machines (SVM), Random Forests, and linear regression algorithms are chosen to study the model performance in the prediction of new COVID-19 cases. From the evaluation metrics such as r-squared value and mean squared error, the statistical performance of the model in predicting the new COVID cases is evaluated. Random Forest outperformed the other two Machine Learning algorithms with a training accuracy of 99.47% and testing accuracy of 98.26% when n=30. The mean square error obtained for Random Forest is 4.05e11, which is lesser compared to the other predictive models used for this study. From the experimental analysis Random Forest algorithm can perform more effectively and efficiently in predicting the new COVID cases, which could help the health sector to take relevant control measures for the spread of the virus.

Keywords: COVID-19, machine learning, supervised learning, unsupervised learning, linear regression, support vector machine, random forest

Procedia PDF Downloads 85

Authors: Moshe Wasserblat, Jonathan Mamou, Oren Pereg

Abstract:

Natural Language Processing (NLP) has made a major leap in the last few years, in practical integration into medical solutions; for example, extracting clinical concepts from medical texts such as medical condition, medication, treatment, and symptoms. However, training and deploying those models in real environments still demands a large amount of annotated data and NLP/Machine Learning (ML) expertise, which makes this process costly and time-consuming. We present a practical and efficient method for clinical concept extraction that does not require costly labeled data nor ML expertise. The method includes three steps: Step 1- the user injects a large in-domain text corpus (e.g., PubMed). Then, the system builds a contextual model containing vector representations of concepts in the corpus, in an unsupervised manner (e.g., Phrase2Vec). Step 2- the user provides a seed set of terms representing a specific medical concept (e.g., for the concept of the symptoms, the user may provide: ‘dry mouth,’ ‘itchy skin,’ and ‘blurred vision’). Then, the system matches the seed set against the contextual model and extracts the most semantically similar terms (e.g., additional symptoms). The result is a complete set of terms related to the medical concept. Step 3 –in production, there is a need to extract medical concepts from the unseen medical text. The system extracts key-phrases from the new text, then matches them against the complete set of terms from step 2, and the most semantically similar will be annotated with the same medical concept category. As an example, the seed symptom concepts would result in the following annotation: “The patient complaints on fatigue [symptom], dry skin [symptom], and Weight loss [symptom], which can be an early sign for Diabetes.” Our evaluations show promising results for extracting concepts from medical corpora. The method allows medical analysts to easily and efficiently build taxonomies (in step 2) representing their domain-specific concepts, and automatically annotate a large number of texts (in step 3) for classification/summarization of medical reports.

Keywords: clinical concepts, concept expansion, medical records annotation, medical records summarization

Procedia PDF Downloads 102