Search results for: supervised%20classification

Authors: Sandra Figueiredo, Alexandra Pereira, Ana Oliveira, Idia Brito, Ivaniltan Jones, Joana Moreira, Madalena Silva, Maria Paraíba, Milene Silva, Tânia Pinho

Abstract:

In the present society, we are facing behaviours mainly in young individuals that might be considered trends of culture or psychopathology. Both contexts are challenges for Education, Psychology and Health. This paper examines nine case studies specifically in Educational Psychology with the main goal to identify and define phenomena contexts in school culture, the psychopathology involved and to present a psychological intervention for each case. The research was conducted by university students in the period of March 2017-June 2017, in Portugal, and the childhood was focused. The case studies explored the cyberbullying; the bullying - victims and bullies’ perspectives; the obsessive compulsive disorder; perception and inclusion of children from homoparental families; inclusion of foreign students in the higher education system; blindness and the inclusion in physical curricular activities; influence of doc-reality and media in attitudes and self-esteem; and the morningness and eveningness types learning in the same school timetables. The university students were supervised during their research analysis and two methods were available for the intervention research study: the meta-analysis and the empirical study. In the second phase, the pedagogical intervention was designed for the different educational contexts in analysis, especially concerning the school environments. The evidence of literature and the empirical studies showed new trends of school’ behaviours and educational disturbances that require further research and effective (and adequate to age, gender, nationality and culture) pedagogical instruments. Respecting the instruments, on the one hand, to identify behaviors, habits or pathologies and highlight the role and training of teachers, psychologists and health professionals, on the other hand, to promote the early intervention and to enhance healthy child development and orientation of the families. To respond to both milestones, this paper present nine pedagogical techniques and measures that will be discussed on their impact concerning advances for the psychological and educational intervention, centered in the individual and in the new generations of family’ cultures.

Keywords: behaviour, culture trends, educational intervention, psychopathology, obsessive compulsive disorder, cyberbullying, bullying, homoparental families, sleep influence, blindness and sports at school, inclusion of foreign students, media influence in behaviour

Procedia PDF Downloads 180

Authors: Bjornar Kjellstadli, Shaher A. I. Shalfawi

Abstract:

The aim of this study was to investigate the effect of strength training Cluster set-method compared to traditional set-method 30 m sprinting time and maximum strength in squats and bench-press. Thirteen Physical Education students, 7 males and 6 females between the age of 19-28 years old were recruited. The students were random divided in three groups. Traditional set group (TSG) consist of 2 males and 2 females aged (±SD) (22.3 ± 1.5 years), body mass (79.2 ± 15.4 kg) and height (177.5 ± 11.3 cm). Cluster set group (CSG) consist of 3 males and 2 females aged (22.4 ± 3.29 years), body mass (81.0 ± 24.0 kg) and height (179.2 ± 11.8 cm) and a control group (CG) consist of 2 males and 2 females aged (21.5 ± 2.4 years), body mass (82.1 ± 17.4 kg) and height (175.5 ± 6.7 cm). The intervention consisted of performing squat and bench press at 70% of 1RM (twice a week) for 8 weeks using 10 repetition and 4 sets. Two types of strength-training methods were used , cluster set (CS) where the participants (CSG) performed 2 reps 5 times with a 10 s recovery in between reps and 50 s recovery between sets, and traditional set (TS) where the participants (TSG) performed 10 reps each set with 90 s recovery in between sets. The pre-tests and post-tests conducted were 1 RM in both squats and bench press, and 10 and 30 m sprint time. The 1RM test were performed with Eleiko XF barbell (20 kg), Eleiko weight plates, rack and bench from Hammerstrength. The speed test was measured with the Brower speed trap II testing system (Brower Timing Systems, Utah, USA). The participants received an individualized training program based on the pre-test of the 1RM. In addition, a mid-term test of 1RM was carried out to adjust training intensity. Each training session were supervised by the researchers. Beast sensors (Milano, Italy) were also used to monitor and quantify the training load for the participants. All groups had a statistical significant improvement in bench press 1RM (TSG 1RM from 56.3 ± 28.9 to 66 ± 28.5 kg; CSG 1RM from 69.8 ± 33.5 to 77.2 ± 34.1 kg and CG 1RM from 67.8 ± 26.6 to 72.2 ± 29.1 kg), whereas only the TSG (1RM from 84.3 ± 26.8 to 114.3 ± 26.5 kg) and CSG (1RM from 100.4 ± 33.9 to 129 ± 35.1 kg) had a statistical significant improvement in Squats 1RM (P < 0.05). However, a between groups examination reveals that there were no marked differences in 1RM squat performance between TSG and CSG (P > 0.05) and both groups had a marked improvements compared to the CG (P < 0.05). On the other hand, no differences between groups were observed in Bench press 1RM. The within groups results indicate that none of the groups had any marked improvement in the distances from 0-10 m and 10-30 m except the CSG which had a notable improvement in the distance from 10-30 m (-0.07 s; P < 0.05). Furthermore, no differences in sprinting abilities were observed between groups. The results from this investigation indicate that traditional set strength training at 70% of 1RM gave close results compared to Cluster set strength training at the same intensity. However, the results indicate that the cluster set had an effect on flying time (10-30 m) indicating that the velocity at which those repetitions were performed could be the explanation factor of this this improvement.

Keywords: physical performance, 1RM, pushing velocity, velocity based training

Procedia PDF Downloads 136

Authors: Asma Omri, Noureddine Benothman, Sofiane Sayahi, Fethi Tlili, Hichem Besbes

Abstract:

Cycling, a popular mode of transportation, can also be perilous due to cyclists' vulnerability to collisions with vehicles and obstacles. This paper presents an innovative cyclist safety system based on radar technology designed to offer real-time collision risk warnings to cyclists. The system incorporates a low-power radar sensor affixed to the bicycle and connected to a microcontroller. It leverages radar point cloud detections, a clustering algorithm, and a supervised classifier. These algorithms are optimized for efficiency to run on the TI’s AWR 1843 BOOST radar, utilizing a coarse classification approach distinguishing between cars, trucks, two-wheeled vehicles, and other objects. To enhance the performance of clustering techniques, we propose a 2-Level clustering approach. This approach builds on the state-of-the-art Density-based spatial clustering of applications with noise (DBSCAN). The objective is to first cluster objects based on their velocity, then refine the analysis by clustering based on position. The initial level identifies groups of objects with similar velocities and movement patterns. The subsequent level refines the analysis by considering the spatial distribution of these objects. The clusters obtained from the first level serve as input for the second level of clustering. Our proposed technique surpasses the classical DBSCAN algorithm in terms of geometrical metrics, including homogeneity, completeness, and V-score. Relevant cluster features are extracted and utilized to classify objects using an SVM classifier. Potential obstacles are identified based on their velocity and proximity to the cyclist. To optimize the system, we used the View of Delft dataset for hyperparameter selection and SVM classifier training. The system's performance was assessed using our collected dataset of radar point clouds synchronized with a camera on an Nvidia Jetson Nano board. The radar-based cyclist safety system is a practical solution that can be easily installed on any bicycle and connected to smartphones or other devices, offering real-time feedback and navigation assistance to cyclists. We conducted experiments to validate the system's feasibility, achieving an impressive 85% accuracy in the classification task. This system has the potential to significantly reduce the number of accidents involving cyclists and enhance their safety on the road.

Keywords: 2-level clustering, coarse classification, cyclist safety, warning system based on radar technology

Procedia PDF Downloads 44

Authors: Leif Inge Tjelta, Gerd Lise Nordbotten, Cathrine Nyhus Hagum, Merete Hagen Helland

Abstract:

Overweight and obesity can lead to numerous health problems, and inactive people are more often overweight and obese compared to physically active people. Even a moderate weight loss can improve cardiovascular and endocrine disease risk factors. The aim of the study was to examine to what extent overweight and obese adults starting up with two weekly intensive running sessions had an increase in aerobic capacity, reduction in BMI and waist circumference and changes in body composition after 33 weeks of training. An additional aim was to see if there were differences between participants who, in addition to training, also received lifestyle modification education, including practical cooking (nutritional guidance and training group (NTG =32)) compared to those who were not given any nutritional guidance (training group (TG=40)). 72 participants (49 women), mean age of 46.1 ( ± 10.4) were included. Inclusion Criteria: Previous untrained and inactive adults in all age groups, BMI ≥ 25, desire to become fitter and reduce their BMI. The two weekly supervised training sessions consisted of 10 min warm up followed by 20 to 21 min effective interval running where the participants’ heart rate were between 82 and 92% of hearth rate maximum. The sessions were completed with ten minutes whole body strength training. Measures of BMI, waist circumference (WC) and 3000m running time were performed at the start of the project (T1), after 15 weeks (T2) and at the end of the project (T3). Measurements of fat percentage, muscle mass, and visceral fat were performed at T1 and T3. Twelve participants (9 women) from both groups, who all scored around average on the 3000 m pre-test, were chosen to do a VO₂max test at T1 and T3. The NTG were given ten theoretical sessions (80 minutes each) and eight practical cooking sessions (140 minutes each). There was a significant reduction in bout groups for WC and BMI from T1 to T2. There was not found any further reduction from T2 to T3. Although not significant, NTG reduced their WC more than TG. For both groups, the percentage reduction in WC was similar to the reduction in BMI. There was a decrease in fat percentage in both groups from pre-test to post-test, whereas, for muscle mass, a small, but insignificant increase was observed for both groups. There was a decrease in 3000m running time for both groups from T1 to T2 as well as from T2 to T3. The difference between T2 and T3 was not statistically significant. The 12 participants who tested VO₂max had an increase of 2.86 ( ± 3.84) mlkg⁻¹ min⁻¹ in VO₂max and 3:02 min (± 2:01 min) reduction in running time over 3000 m from T1 until T3. There was a strong, negative correlation between the two variables. The study shows that two intensive running session in 33 weeks can increase aerobic fitness and reduce BMI, WC and fat percent in inactive adults. Cost guidance in addition to training will give additional effect.

Keywords: interval training, nutritional guidance, fitness, BMI

Procedia PDF Downloads 119

Authors: Anup Anand Deshmukh, Catherine Soladie, Renaud Seguier

Abstract:

Emotion plays a key role in many applications like healthcare, to gather patients’ emotional behavior. Unlike typical ASR (Automated Speech Recognition) problems which focus on 'what was said', it is equally important to understand 'how it was said.' There are certain emotions which are given more importance due to their effectiveness in understanding human feelings. In this paper, we propose an approach that models human stress from audio signals. The research challenge in speech emotion detection is finding the appropriate set of acoustic features corresponding to an emotion. Another difficulty lies in defining the very meaning of emotion and being able to categorize it in a precise manner. Supervised Machine Learning models, including state of the art Deep Learning classification methods, rely on the availability of clean and labelled data. One of the problems in affective computation is the limited amount of annotated data. The existing labelled emotions datasets are highly subjective to the perception of the annotator. We address the first issue of feature selection by exploiting the use of traditional MFCC (Mel-Frequency Cepstral Coefficients) features in Convolutional Neural Network. Our proposed Emo-CNN (Emotion-CNN) architecture treats speech representations in a manner similar to how CNN’s treat images in a vision problem. Our experiments show that Emo-CNN consistently and significantly outperforms the popular existing methods over multiple datasets. It achieves 90.2% categorical accuracy on the Emo-DB dataset. We claim that Emo-CNN is robust to speaker variations and environmental distortions. The proposed approach achieves 85.5% speaker-dependant categorical accuracy for SAVEE (Surrey Audio-Visual Expressed Emotion) dataset, beating the existing CNN based approach by 10.2%. To tackle the second problem of subjectivity in stress labels, we use Lovheim’s cube, which is a 3-dimensional projection of emotions. Monoamine neurotransmitters are a type of chemical messengers in the brain that transmits signals on perceiving emotions. The cube aims at explaining the relationship between these neurotransmitters and the positions of emotions in 3D space. The learnt emotion representations from the Emo-CNN are mapped to the cube using three component PCA (Principal Component Analysis) which is then used to model human stress. This proposed approach not only circumvents the need for labelled stress data but also complies with the psychological theory of emotions given by Lovheim’s cube. We believe that this work is the first step towards creating a connection between Artificial Intelligence and the chemistry of human emotions.

Keywords: deep learning, brain chemistry, emotion perception, Lovheim's cube

Procedia PDF Downloads 123

Authors: Olena Kavats, Dmitry Khramov, Kateryna Sergieieva, Vladimir Vasyliev, Iurii Kavats

Abstract:

Geoinformation technologies of space agromonitoring are a means of operative decision making support in the tasks of managing the agricultural sector of the economy. Existing technologies use satellite images in the optical range of electromagnetic spectrum. Time series of optical images often contain gaps due to the presence of clouds and haze. A geoinformation technology is created. It allows to fill gaps in time series of optical images (Sentinel-2, Landsat-8, PROBA-V, MODIS) with radar survey data (Sentinel-1) and use information about agrometeorological conditions of the growing season for individual monitoring years. The technology allows to perform crop classification and mapping for spring-summer (winter and spring crops) and autumn-winter (winter crops) periods of vegetation, monitoring the dynamics of crop state seasonal changes, crop yield forecasting. Crop classification is based on supervised classification algorithms, takes into account the peculiarities of crop growth at different vegetation stages (dates of sowing, emergence, active vegetation, and harvesting) and agriculture land state characteristics (row spacing, seedling density, etc.). A catalog of samples of the main agricultural crops (Ukraine) is created and crop spectral signatures are calculated with the preliminary removal of row spacing, cloud cover, and cloud shadows in order to construct time series of crop growth characteristics. The obtained data is used in grain crop growth tracking and in timely detection of growth trends deviations from reference samples of a given crop for a selected date. Statistical models of crop yield forecast are created in the forms of linear and nonlinear interconnections between crop yield indicators and crop state characteristics (temperature, precipitation, vegetation indices, etc.). Predicted values of grain crop yield are evaluated with an accuracy up to 95%. The developed technology was used for agricultural areas monitoring in a number of Great Britain and Ukraine regions using EOS Crop Monitoring Platform (https://crop-monitoring.eos.com). The obtained results allow to conclude that joint use of Sentinel-1 and Sentinel-2 images improve separation of winter crops (rapeseed, wheat, barley) in the early stages of vegetation (October-December). It allows to separate successfully the soybean, corn, and sunflower sowing areas that are quite similar in their spectral characteristics.

Keywords: geoinformation technology, crop classification, crop yield prediction, agricultural monitoring, EOS Crop Monitoring Platform

Procedia PDF Downloads 400

Authors: Lela Gadrani, Mariam Tsitsagi

Abstract:

Human is a part of the urban landscape and responsible for it. Urbanization of cities includes the longest phase; thus none of the environment ever undergoes such anthropogenic impact as the area of large cities. The post-Soviet period is very interesting in terms of scientific research. The changes that have occurred in the cities since the collapse of the Soviet Union have not yet been analyzed best to our knowledge. In this context, the aim of this paper is to analyze the changes in the land use of the three large cities of Georgia (Tbilisi, Kutaisi, Batumi). Tbilisi as a capital city, Batumi as a port city, and Kutaisi as a former industrial center. Data used during the research process are conventionally divided into satellite and supporting materials. For this purpose, the largest topographic maps (1:10 000) of all three cities were analyzed, Tbilisi General Plans (1896, 1924), Tbilisi and Kutaisi historical maps. The main emphasis was placed on the classification of Landsat images. In this case, we have classified the images LULC (LandUse / LandCover) of all three cities taken in 1987 and 2016 using the supervised and unsupervised methods. All the procedures were performed in the programs: Arc GIS 10.3.1 and ENVI 5.0. In each classification we have singled out the following classes: built-up area, water bodies, agricultural lands, green cover and bare soil, and calculated the areas occupied by them. In order to check the validity of the obtained results, additionally we used the higher resolution images of CORONA and Sentinel. Ultimately we identified the changes that took place in the land use in the post-Soviet period in the above cities. According to the results, a large wave of changes touched Tbilisi and Batumi, though in different periods. It turned out that in the case of Tbilisi, the area of developed territory has increased by 13.9% compared to the 1987 data, which is certainly happening at the expense of agricultural land and green cover, in particular, the area of agricultural lands has decreased by 4.97%; and the green cover by 5.67%. It should be noted that Batumi has obviously overtaken the country's capital in terms of development. With the unaided eye it is clear that in comparison with other regions of Georgia, everything is different in Batumi. In fact, Batumi is an unofficial summer capital of Georgia. Undoubtedly, Batumi’s development is very important both in economic and social terms. However, there is a danger that in the uneven conditions of urban development, we will eventually get a developed center - Batumi, and multiple underdeveloped peripheries around it. Analysis of the changes in the land use is of utmost importance not only for quantitative evaluation of the changes already implemented, but for future modeling and prognosis of urban development. Raster data containing the classes of land use is an integral part of the city's prognostic models.

Keywords: analysis, geo information system, remote sensing, LULC

Procedia PDF Downloads 426

Authors: Monika Rani, Claudio Marchesi, Stefania Federici, Laura E. Depero

Abstract:

Degradation of the aquatic environment by plastic litter, especially microplastics (MPs), i.e., any water-insoluble solid plastic particle with the longest dimension in the range 1µm and 1000 µm (=1 mm) size, is an unfortunate indication of the advancement of the Anthropocene age on Earth. Microplastics formed due to natural weathering processes are termed as secondary microplastics, while when these are synthesized in industries, they are called primary microplastics. Their presence from the highest peaks to the deepest points in oceans explored and their resistance to biological and chemical decay has adversely affected the environment, especially marine life. Even though the presence of MPs in the marine environment is well-reported, a legitimate and authentic analytical technique to sample, analyze, and quantify the MPs is still under progress and testing stages. Among the characterization techniques, vibrational spectroscopic techniques are largely adopted in the field of polymers. And the ongoing miniaturization of these methods is on the way to revolutionize the plastic recycling industry. In this scenario, the capability and the feasibility of a miniaturized near-infrared (MicroNIR) spectroscopy combined with chemometrics tools for qualitative and quantitative analysis of urban plastic waste collected from a recycling plant and microplastic mixture fragmented in the lab were investigated. Based on the Resin Identification Code, 250 plastic samples were used for macroplastic analysis and to set up a library of polymers. Subsequently, MicroNIR spectra were analysed through the application of multivariate modelling. Principal Components Analysis (PCA) was used as an unsupervised tool to find trends within the data. After the exploratory PCA analysis, a supervised classification tool was applied in order to distinguish the different plastic classes, and a database containing the NIR spectra of polymers was made. For the microplastic analysis, the three most abundant polymers in the plastic litter, PE, PP, PS, were mechanically fragmented in the laboratory to micron size. The distinctive arrangement of blends of these three microplastics was prepared in line with a designed ternary composition plot. After the PCA exploratory analysis, a quantitative model Partial Least Squares Regression (PLSR) allowed to predict the percentage of microplastics in the mixtures. With a complete dataset of 63 compositions, PLS was calibrated with 42 data-points. The model was used to predict the composition of 21 unknown mixtures of the test set. The advantage of the consolidated NIR Chemometric approach lies in the quick evaluation of whether the sample is macro or micro, contaminated, coloured or not, and with no sample pre-treatment. The technique can be utilized with bigger example volumes and even considers an on-site evaluation and in this manner satisfies the need for a high-throughput strategy.

Keywords: chemometrics, microNIR, microplastics, urban plastic waste

Procedia PDF Downloads 130

Authors: Nguyen J. M., Lucas G., Ruan S., Digonnet H., Antonioli D.

Abstract:

Introduction: Deep Learning (DL) is a very powerful tool for analyzing image data. But for tabular data, it cannot compete with machine learning methods like XGBoost. The research question becomes: can tabular data be transformed into images that can be analyzed by simple CNNs (Convolutional Neuron Networks)? Will DL be the absolute tool for data classification? All current solutions consist in repositioning the variables in a 2x2 matrix using their correlation proximity. In doing so, it obtains an image whose pixels are the variables. We implement a technology, DeepNIC, that offers the possibility of obtaining an image for each variable, which can be analyzed by simple CNNs. Material and method: The 'ROP' (Regression OPtimized) model is a binary and atypical decision tree whose nodes are managed by a new artificial neuron, the Neurop. By positioning an artificial neuron in each node of the decision trees, it is possible to make an adjustment on a theoretically infinite number of variables at each node. From this new decision tree whose nodes are artificial neurons, we created the concept of a 'Random Forest of Perfect Trees' (RFPT), which disobeys Breiman's concepts by assembling very large numbers of small trees with no classification errors. From the results of the RFPT, we developed a family of 10 statistical information criteria, Nguyen Information Criterion (NICs), which evaluates in 3 dimensions the predictive quality of a variable: Performance, Complexity and Multiplicity of solution. A NIC is a probability that can be transformed into a grey level. The value of a NIC depends essentially on 2 super parameters used in Neurops. By varying these 2 super parameters, we obtain a 2x2 matrix of probabilities for each NIC. We can combine these 10 NICs with the functions AND, OR, and XOR. The total number of combinations is greater than 100,000. In total, we obtain for each variable an image of at least 1166x1167 pixels. The intensity of the pixels is proportional to the probability of the associated NIC. The color depends on the associated NIC. This image actually contains considerable information about the ability of the variable to make the prediction of Y, depending on the presence or absence of other variables. A basic CNNs model was trained for supervised classification. Results: The first results are impressive. Using the GSE22513 public data (Omic data set of markers of Taxane Sensitivity in Breast Cancer), DEEPNic outperformed other statistical methods, including XGBoost. We still need to generalize the comparison on several databases. Conclusion: The ability to transform any tabular variable into an image offers the possibility of merging image and tabular information in the same format. This opens up great perspectives in the analysis of metadata.

Keywords: tabular data, CNNs, NICs, DeepNICs, random forest of perfect trees, classification

Procedia PDF Downloads 70

Authors: Bolysbek Utelbayev, Tasmagambetova Aigerim, Toktasyn Raila, Markayev Yergali, Myrzakhanov Maxat

Abstract:

Intensive development of secondary processes of destructive processing of crude oil has led to the occurrence of oil refining factories resources of C2-C4 hydrocarbons. Except for oil gases also contain basically C2-C4 hydrocarbon gases where some of the amounts are burned. All these data has induced interest to the study of producing alkylate from hydrocarbons С2-С4 which being as components of motor fuels. The purpose of this work was studying transformation propane-propene, butane-butene fractions at the presence of the ruthenium-chromic support catalyst whereas the carrier is served pillar - structural montmorillonite containing in native bentonite clay. In this work is considered condition and structure of the bentonite clay from the South-Kazakhstan area of the Republic Kazakhstan. For preparation rhodium support catalyst (0,5-1,0 mass. % Rh) was used chloride of rhodium-RhCl3∙3H2O, as a carrier was used modified bentonite clay. For modifying natural clay to pillar structural form were used polyhydroxy complexes of chromium. To aqueous solution of chloride chromium gradually flowed the solution of sodium hydroxide at gradual hashing up to pH~3-4. The concentration of chloride chromium was paid off proceeding from calculation 5-30 mmole Cr3+ per gram clay. Suspension bentonite (~1,0 mass. %) received by intensive washing it in water during 4 h, pH-water extract of clay makes -8-9. The acidity of environment supervised by means of digital pH meter OP-208/1. In order to prevent coagulation of a solution polyhydroxy complexes of chromium, it was slowly added to a suspension of clay. "Reserve of basicity" Cr3+:/OH-allowing to prevent coagulation chloride of rhodium made 1/3. After endurance processed suspensions of clay during 24 h, a deposit was washed by water and condensed. The sample, after separate from a liquid phase, dried at first at the room temperature, and then at 110°C (2h) with the subsequent rise the temperature up to 180°C (4h). After cooling the firm mass was pounded to a powder, it was shifted infractions with the certain sizes of particles. Fractions of particles modifying clay in the further were impregnated with an aqueous solution with rhodium-RhCl3∙3H2O (0,5-1,0 mаss % Rh ). Obtained pillar structural bentonite approaches heat resistance and its porous structure above the 773K. Pillar structural bentonite was used for preparation 1.0% Ru/Carrier (modifying bentonite) support catalysts where is realised alkylation of C2-C4 hydrocarbons. The process of alkylation is carried out at a partial pressure of hydrogen 0.5-1.0MPa. Outcome 2.2.4 three methyl pentane and 2.2.3 trimethylpentane achieved 40%. At alkylation butane-butene mixture outcome of the isooctane is achieved 60%. In this condition of studying the ethene is not undergoing to alkylation.

Keywords: alkylation, butene, pillar structure, ruthenium catalyst

Procedia PDF Downloads 370

Authors: Rajesh Ranjan, Marimuthu Palaniswami, A. A. Hashmi

Abstract:

With the changing lifestyle and environment around us, the prevalence of the critical and incurable disease has proliferated. One such condition is the neurological disorder which is rampant among the old age population and is increasing at an unstoppable rate. Most of the neurological disorder patients suffer from some movement disorder affecting the movement of their body parts. Tremor is the most common movement disorder which is prevalent in such patients that infect the upper or lower limbs or both extremities. The tremor symptoms are commonly visible in Parkinson’s disease patient, and it can also be a pure tremor (essential tremor). The patients suffering from tremor face enormous trouble in performing the daily activity, and they always need a caretaker for assistance. In the clinics, the assessment of tremor is done through a manual clinical rating task such as Unified Parkinson’s disease rating scale which is time taking and cumbersome. Neurologists have also affirmed a challenge in differentiating a Parkinsonian tremor with the pure tremor which is essential in providing an accurate diagnosis. Therefore, there is a need to develop a monitoring and assistive tool for the tremor patient that keep on checking their health condition by coordinating them with the clinicians and caretakers for early diagnosis and assistance in performing the daily activity. In our research, we focus on developing a system for automatic classification of tremor which can accurately differentiate the pure tremor from the Parkinsonian tremor using a wearable accelerometer-based device, so that adequate diagnosis can be provided to the correct patient. In this research, a study was conducted in the neuro-clinic to assess the upper wrist movement of the patient suffering from Pure (Essential) tremor and Parkinsonian tremor using a wearable accelerometer-based device. Four tasks were designed in accordance with Unified Parkinson’s disease motor rating scale which is used to assess the rest, postural, intentional and action tremor in such patient. Various features such as time-frequency domain, wavelet-based and fast-Fourier transform based cross-correlation were extracted from the tri-axial signal which was used as input feature vector space for the different supervised and unsupervised learning tools for quantification of severity of tremor. A minimum covariance maximum correlation energy comparison index was also developed which was used as the input feature for various classification tools for distinguishing the PT and ET tremor types. An automatic system for efficient classification of tremor was developed using feature extraction methods, and superior performance was achieved using K-nearest neighbors and Support Vector Machine classifiers respectively.

Keywords: machine learning approach for neurological disorder assessment, automatic classification of tremor types, feature extraction method for tremor classification, neurological movement disorder, parkinsonian tremor, essential tremor

Procedia PDF Downloads 129

Authors: Mariam Begadze

Abstract:

Separation of Powers (SOP) has often been the most frequently posed objection against the judicial enforcement of socio-economic rights. Although a lot has been written to refute those, very rarely has it been assessed what effect the current practice of social rights adjudication has had on the construction of SOP doctrine in specific jurisdictions. Colombia is an appropriate case-study on this question. The notion of collaborative SOP in the 1991 Constitution has affected the court’s conception of its role. On the other hand, the trends in the jurisprudence have further shaped the collaborative notion of SOP. Other institutional characteristics of the Colombian constitutional law have played its share role as well. Tutela action, particularly flexible and fast judicial action for individuals has placed the judiciary in a more confrontational relation vis-à-vis the political branches. Later interventions through abstract review of austerity measures further contributed to that development. Logically, the court’s activism in this sphere has attracted attacks from political branches, which have turned out to be unsuccessful precisely due to court’s outreach to the middle-class, whose direct reliance on the court has turned into its direct democratic legitimacy. Only later have the structural judgments attempted to revive the collaborative notion behind SOP doctrine. However, the court-supervised monitoring process of implementation has itself manifested fluctuations in the mode of collaboration, moving into more managerial supervision recently. This is not surprising considering the highly dysfunctional political system in Colombia, where distrust seems to be the default starting point in the interaction of the branches. The paper aims to answer the question, what the appropriate judicial tools are to realize the collaborative notion of SOP in a context where the court has to strike a balance between the strong executive and the weak and largely dysfunctional legislative branch. If the recurrent abuse lies in the indifference and inaction of legislative branches to engage with political issues seriously, what are the tools in the court’s hands to activate the political process? The answer to this question partly lies in the court’s other strand of jurisprudence, in which it combines substantive objections with procedural ones concerning the operation of the legislative branch. The primary example is the decision on value-added tax on basic goods, in which the court invalidated the law based on the absence of sufficient deliberation in Congress on the question of the bills’ implications on the equity and progressiveness of the entire taxing system. The decision led to Congressional rejection of an identical bill based on the arguments put forward by the court. The case perhaps is the best illustration of the collaborative notion of SOP, in which the court refrains from categorical pronouncements, while does its bit for activating political process. This also legitimizes the court’s activism based on its role to counter the most perilous abuse in the Colombian context – failure of the political system to seriously engage with serious political questions.

Keywords: Colombian constitutional court, judicial review, separation of powers, social rights

Procedia PDF Downloads 77

Authors: Ran Goldblatt, Nicholas Jones, Jennifer Mannix, Brad Bottoms

Abstract:

Accurate, complete, and up-to-date geospatial information is the foundation of successful disaster management. When the 2010 Haiti Earthquake struck, accurate and timely information on the distribution of critical infrastructure was essential for the disaster response community for effective search and rescue operations. Existing geospatial datasets such as Google Maps did not have comprehensive coverage of these features. In the days following the earthquake, many organizations released high-resolution satellite imagery, catalyzing a worldwide effort to map Haiti and support the recovery operations. Of these organizations, OpenStreetMap (OSM), a collaborative project to create a free editable map of the world, used the imagery to support volunteers to digitize roads, buildings, and other features, creating the most detailed map of Haiti in existence in just a few weeks. However, large portions of the island are still not fully covered by OSM. There is an increasing need for a tool to automatically identify which areas in Haiti, as well as in other countries vulnerable to disasters, that are not fully mapped. The objective of this project is to leverage different types of remote sensing measurements, together with machine learning approaches, in order to identify geographical areas where OSM coverage of building footprints is incomplete. Several remote sensing measures and derived products were assessed as potential predictors of OSM building footprints coverage, including: intensity of light emitted at night (based on VIIRS measurements), spectral indices derived from Sentinel-2 satellite (normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), soil-adjusted vegetation index (SAVI), urban index (UI)), surface texture (based on Sentinel-1 SAR measurements)), elevation and slope. Additional remote sensing derived products, such as Hansen Global Forest Change, DLR`s Global Urban Footprint (GUF), and World Settlement Footprint (WSF), were also evaluated as predictors, as well as OSM street and road network (including junctions). Using a supervised classification with a random forest classifier resulted in the prediction of 89% of the variation of OSM building footprint area in a given cell. These predictions allowed for the identification of cells that are predicted to be covered but are actually not mapped yet. With these results, this methodology could be adapted to any location to assist with preparing for future disastrous events and assure that essential geospatial information is available to support the response and recovery efforts during and following major disasters.

Keywords: disaster management, Haiti, machine learning, OpenStreetMap, remote sensing

Procedia PDF Downloads 98

Authors: Halkiopoulos Constantinos, Koutsopoulou Ioanna, Gkintoni Evgenia, Antonopoulou Hera

Abstract:

Immunization appears to be an essential part of health care service in times of pandemics such as covid-19 and aims not only to protect the health of the population but also the health and sustainability of the economies of the countries affected. It is reported that more than 3.44 billion doses have been administered so far, which accounts for 45 doses for 100 people. Vaccination programs in various countries have been promoted and accepted by people differently and therefore they proceeded in different ways and speed; most countries directing them towards people with vulnerable chronic or recent health statuses. Large scale restriction measures or lockdown, personal protection measures such as masks and gloves and a decrease in leisure and sports activities were also implemented around the world as part of the protection health strategies against the covid-19 pandemic. This research aims to present an analysis based on variations on people’s attitudes towards vaccination based on demographic, social and epidemiological characteristics, and health status on the one hand and perception of health, health satisfaction, pain, and quality of life on the other hand. 1500 Greek e-consumers participated in the research, mainly through social media who took part in an online-based survey voluntarily. The questionnaires included demographic, social and medical characteristics of the participants, and questions asking people’s willingness to be vaccinated and their opinion on whether there should be a vaccine against covid-19. Other stressor factors were also reported in the questionnaires and participants’ loss of someone close due to covid-19, or staying at home quarantine due to being infected from covid-19. WHOQUOL-BREF and GLOBAL PSYCHOTRAUMA SCREEN- GPS were used with kind permission from WHO and from the International Society for Traumatic Stress Studies in this study. Attitudes towards vaccination varied significantly related to aging, level of education, health status and consumer behavior. Health professionals’ attitudes also varied in relation to age, level of education, profession, health status and consumer needs. Vaccines have been the most common technological aid of human civilization so far in the fight against viruses. The results of this study can be used for health managers and digital marketers of pharmaceutical companies and also other staff involved in vaccination programs and for designing health policy immunization strategies during pandemics in order to achieve positive attitudes towards vaccination and larger populations being vaccinated in shorter periods of time after the break out of pandemic. Health staff needs to be trained, aided and supervised to go through with vaccination programs and to be protected through vaccination programs themselves. Feedback in each country’s vaccination program, short backs, deficiencies and delays should be addressed and worked out.

Keywords: consumer behavior, cognitive models, vaccination policy, pandemic, Covid-19, Greece

Procedia PDF Downloads 155

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 112

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 85

Authors: Nicholas Anderson, Steven Petersen, Tom Bates, Val Anderson

Abstract:

Under the multiple-use management regime established in the United States for federally owned lands, government agencies have come under pressure from commercial apiaries to grant permits for the summer pasturing of honeybees on government lands. Federal agencies have struggled to integrate honeybees into their management plans and have little information to make regulations that resolve how many colonies should be allowed in a single location and at what distance sets of hives should be placed. Many conservation groups have voiced their concerns regarding the introduction of honeybees to these natural lands, as they may outcompete and displace native pollinating species. Assessing the quality of an area in regard to its floral resources, pollen, and nectar can be important when attempting to create regulations for the integration of commercial honeybee operations into a native ecosystem. Areas with greater floral resources may be able to support larger numbers of honeybee colonies, while poorer resource areas may be less resilient to introduced disturbances. Attempts are made in this study to determine flower cover using high resolution drone imagery to help assess the floral resource availability to pollinators in high elevation, tall forb communities. This knowledge will help in determining the potential that different areas may have for honeybee pasturing and honey production. Roughly 700 images were captured at 23m above ground level using a drone equipped with a Sony QX1 RGB 20-megapixel camera. These images were stitched together using Pix4D, resulting in a 60m diameter high-resolution mosaic of a tall forb meadow. Using the program ENVI, a supervised maximum likelihood classification was conducted to calculate the percentage of total flower cover and flower cover by color (blue, white, and yellow). A complete vegetation inventory was taken on site, and the major flowers contributing to each color class were noted. An accuracy assessment was performed on the classification yielding an 89% overall accuracy and a Kappa Statistic of 0.855. With this level of accuracy, drones provide an affordable and time efficient method for the assessment of floral cover in large areas. The proximal step of this project will now be to determine the average pollen and nectar loads carried by each flower species. The addition of this knowledge will result in a quantifiable method of measuring pollen and nectar resources of entire landscapes. This information will not only help land managers determine stocking rates for honeybees on public lands but also has applications in the agricultural setting, aiding producers in the determination of the number of honeybee colonies necessary for proper pollination of fruit and nut crops.

Keywords: honeybee, flower, pollinator, remote sensing

Procedia PDF Downloads 106

Authors: Sardorbek Numonov, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Dongeun Choi, Byung-Woo Hong

Abstract:

The detection of curvilinear structures often plays an important role in the analysis of images. In particular, it is considered as a crucial step for the diagnosis of chronic respiratory diseases to localize the fissures in chest CT imagery where the lung is divided into five lobes by the fissures that are characterized by linear features in appearance. However, the characteristic linear features for the fissures are often shown to be subtle due to the high intensity variability, pathological deformation or image noise involved in the imaging procedure, which leads to the uncertainty in the quantification of anatomical or functional properties of the lung. Thus, it is desired to enhance the linear features present in the chest CT images so that the distinctiveness in the delineation of the lobe is improved. We propose a recursive diffusion process that prefers coherent features based on the analysis of structure tensor in an anisotropic manner. The local image features associated with certain scales and directions can be characterized by the eigenanalysis of the structure tensor that is often regularized via isotropic diffusion filters. However, the isotropic diffusion filters involved in the computation of the structure tensor generally blur geometrically significant structure of the features leading to the degradation of the characteristic power in the feature space. Thus, it is required to take into consideration of local structure of the feature in scale and direction when computing the structure tensor. We apply an anisotropic diffusion in consideration of scale and direction of the features in the computation of the structure tensor that subsequently provides the geometrical structure of the features by its eigenanalysis that determines the shape of the anisotropic diffusion kernel. The recursive application of the anisotropic diffusion with the kernel the shape of which is derived from the structure tensor leading to the anisotropic scale-space where the geometrical features are preserved via the eigenanalysis of the structure tensor computed from the diffused image. The recursive interaction between the anisotropic diffusion based on the geometry-driven kernels and the computation of the structure tensor that determines the shape of the diffusion kernels yields a scale-space where geometrical properties of the image structure are effectively characterized. We apply our recursive anisotropic diffusion algorithm to the detection of curvilinear structure in the chest CT imagery where the fissures present curvilinear features and define the boundary of lobes. It is shown that our algorithm yields precise detection of the fissures while overcoming the subtlety in defining the characteristic linear features. The quantitative evaluation demonstrates the robustness and effectiveness of the proposed algorithm for the detection of fissures in the chest CT in terms of the false positive and the true positive measures. The receiver operating characteristic curves indicate the potential of our algorithm as a segmentation tool in the clinical environment. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: anisotropic diffusion, chest CT imagery, chronic respiratory disease, curvilinear structure, fissure detection, structure tensor

Procedia PDF Downloads 206

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 37

Authors: A. Bortkiewcz, A. Dudarewicz, P. Małecki, M. Kłaczyński, T. Wszołek, Małgorzata Pawlaczyk-Łuszczyńska

Abstract:

Low-frequency noise (LFN) has been recognized as a special environmental pollutant. It is usually considered a broadband noise with the dominant content of low frequencies from 10 Hz to 250 Hz. A growing body of data shows that LFN differs in nature from other environmental noises, which are at comparable levels but not dominated by low-frequency components. The primary and most frequent adverse effect of LFN exposure is annoyance. Moreover, some recent investigations showed that LFN at relatively low A-weighted sound pressure levels (40−45 dB) occurring in office-like areas could adversely affect the mental performance, especially of high-sensitive subjects. It is well documented that high-frequency noise disturbs various types of human functions; however, there is very little data on the impact of LFN on well-being and health, including the cardiovascular system. Heart rate variability (HRV) is a sensitive marker of autonomic regulation of the circulatory system. Walker and co-workers found that LFN has a significantly more negative impact on cardiovascular response than exposure to high-frequency noise and that changes in HRV parameters resulting from LFN exposure tend to persist over time. The negative reactions of the cardiovascular system in response to LFN generated by wind turbines (20-200 Hz) were confirmed by Chiu. The scientific aim of the study is to assess the relationship between the spectral-temporal characteristics of LFN and the activity of the autonomic nervous system, considering the subjective assessment of annoyance, sensitivity to this type of noise, and cognitive and general health status. The study will be conducted in 20 male students in a special, acoustically prepared, constantly supervised room. Each person will be tested 4 times (4 sessions), under conditions of non-exposure (sham) and exposure to noise of wind turbines recorded at a distance of 250 meters from the turbine with different frequencies and frequency ranges: acoustic band 20 Hz-20 kHz, infrasound band 5-20 Hz, acoustic band + infrasound band. The order of sessions of the experiment will be randomly selected. Each session will last 1 h. There will be a 2-3 days break between sessions to exclude the possibility of the earlier session influencing the results of the next one. Before the first exposure, a questionnaire will be conducted on noise sensitivity, general health status using the GHQ questionnaire, hearing organ status and sociodemographic data. Before each of the 4 exposures, subjects will complete a brief questionnaire on their mood and sleep quality the night before the test. After the test, the subjects will be asked about any discomfort and subjective symptoms during the exposure. Before the test begins, Holter ECG monitoring equipment will be installed. HRV will be analyzed from the ECG recordings, including time and frequency domain parameters. The tests will always be performed in the morning (9-12) to avoid the influence of diurnal rhythm on HRV results. Students will perform psychological tests 15 minutes before the end of the test (Vienna Test System).

Keywords: neurovegetative control, heart rate variability (HRV), cognitive processes, low frequency noise

Procedia PDF Downloads 45

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: electrical disaggregation, DTW, general appliance modeling, event detection

Procedia PDF Downloads 43

Authors: Mara Aparecida De Castilho Lopes. Maria Eliza Mattosinho Bernardes

Abstract:

The education of deaf individuals in Brazil is grounded in the bilingual approach, which presupposes Brazilian Sign Language (Libras) as the first language for these students. In this perspective, Portuguese should be taught as a second language in its written form, ensuring that deaf students also have access to various academic subjects in sign language. Brazilian legislation (Federal Decree No. 5626 of 2005) mandates the teaching of Brazilian Sign Language in university teacher training programs, but there is no pre-established minimum workload. As a result, there is a significant disparity in the teaching and quality of teacher education across the Brazilian territory. Added to this fact is the general lack of awareness within society regarding the linguistic status of Libras, leading to a shortage of competent teachers for its use and instruction, particularly in higher education. Recently, Federal Law No. 14191 of 2021 established bilingual education for the deaf as a mode of instruction, indicating the need for adjustments in teacher training within higher education teacher preparation programs. Given this context, the objective of the present study was to analyze the teaching proposals for Brazilian Sign Language for students in teacher training programs at public universities in Brazil, presenting alternatives to overcome the current models and academic pathways of teaching and learning. In addition to analyzing Brazilian teaching models, an analysis of a continuing education model for teachers in a French institution was also conducted - considering the historical Franco-Brazilian path of deaf education in Brazil. The analysis of the current teacher training model for deaf education in Brazil revealed that initial exposure to sign language and its linguistic structure is not sufficient to provide future teachers with opportunities to reflect on bilingual teaching methods and practices, as seen in other definitions of bilingualism - bilingual education for proficient listeners in two oral languages. As a result, a training proposal was developed for an experimental interdisciplinary course, integrating the curriculum of an initial and continuing teacher training program alongside the Alfredo Bossi Chair at the University of São Paulo. This proposal is structured into three disciplines, which constitute consecutive moments in teacher education: Fundamental Aspects of Brazilian Sign Language, Bilingual Teaching Methodology, and Teaching Investigation Project - interdisciplinary engagement in the field of deafness. The last offered discipline represents an interdisciplinary supervised internship proposal, considering the multi-professional context that constitutes deaf education within a bilingual approach. In interdisciplinary work within the field of deafness, dialogue between teachers and other professionals who work with deaf students from different perspectives - teachers, speech therapists, and sign language interpreters - is frequently necessary. Through alternative avenues, these actions aim to direct the linguistic development of deaf students within their learning processes. Based on the innovative curriculum proposal described here, the intention is to contribute to the enhancement of teacher education in Brazil, with the goal of ensuring bilingual education for deaf students.

Keywords: bilingual education, teacher training, historical-cultural approach, interdisciplinary education, inclusive education

Procedia PDF Downloads 55

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: general appliance model, non intrusive load monitoring, events detection, unsupervised techniques;

Procedia PDF Downloads 46

Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca

Abstract:

Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.

Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks

Procedia PDF Downloads 162

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 257

Authors: Nick Toossi, Joseph Hartland

Abstract:

Background: Malawi is an example of a low resource setting which faces a chronic shortage of doctors and other medical staff. This shortfall is made up for by clinical officers (COs), who are para-medicals trained for 4 years. The literature suggests to improve outcomes surgical skills training specifically should be promoted for COs in district and mission hospitals. Accordingly, the primary author was tasked with developing a basic surgical skills teaching package for COs of Mulanje Mission Hospital (MMH), Malawi, as part of a 4th year medical student External Student Selected Component field trip. MMH is a hospital based in the South of Malawi near the base of Mulanje Mountain and works in an extremely isolated environment with some of the poorest communities in the country. Traveling to Malawi the medical student author performed an educational needs assessment to develop and deliver a bespoke basic surgical skills teaching package. Methodology: An initial needs assessment identified the following domains: basic surgical skills (instrument naming & handling, knot tying, suturing principles and suturing techniques) and perineal repair. Five COs took part in a teaching package involving an interactive group simulation session, overseen by senior clinical officers and surgical trainees from the UK. Non-organic and animal models were used for simulation practice. This included the use of surgical skills boards to practice knot tying and ox tongue to simulate perineal repair. All participants spoke and read English. The impact of the session was analysed in two different ways. The first was via a pre and post Single Best Answer test and the second a questionnaire including likert’s scales and free text response questions. Results: There was a positive trend in pre and post test scores on competition of the course. There was increase in the mean confidence of learners before and after the delivery of teaching in basic surgical skills and simulated perineal repair, especially in ‘instrument naming and handling’. Whilst positively received it was discovered that learners desire more frequent surgical skills teaching sessions in order to improve and revise skills. Feedback suggests that the learners were not confident in retaining the skills without regular input. Discussion: Skills and confidence were improved as a result of the teaching provided. Learner's written feedback suggested there was an overall appetite for regular surgical skills teaching in the clinical environment and further opportunities to allow for deliberate self-practice. Surgical mentorship schemes facilitating supervised theatre time among trainees and lead surgeons along with improving access to surgical models/textbooks were some of the simple suggestions to improve surgical skills and confidence among COs. Although, this study is limited by population size it is reflective of the small, isolated and low resource environment in which this healthcare is delivered. This project does suggest that current surgical skills packages used in the UK could be adapted for employment in low resource settings, but it is consistency and sustainability that staff seek above all in their on-going education.

Keywords: clinical officers, education, Malawi, surgical skills

Procedia PDF Downloads 156

Authors: Dan Kanmegne

Abstract:

Africa will become the most populated continent by the end of the century, with around 4 billion inhabitants. Food security and climate changes will become continental issues since agricultural practices depend on climate but also contribute to global emissions and land degradation. Agroforestry has been identified as a cost-efficient and reliable strategy to address these two issues. It is defined as the integrated management of trees and crops/animals in the same land unit. Agroforestry provides benefits in terms of goods (fruits, medicine, wood, etc.) and services (windbreaks, fertility, etc.), and is acknowledged to have a great potential for carbon sequestration; therefore it can be integrated into reduction mechanisms of carbon emissions. Particularly in sub-Saharan Africa, the constraint stands in the lack of information about both areas under agroforestry and the characterization (composition, structure, and management) of each agroforestry system at the country level. This study describes and quantifies “what is where?”, earliest to the quantification of carbon stock in different systems. Remote sensing (RS) is the most efficient approach to map such a dynamic technology as agroforestry since it gives relatively adequate and consistent information over a large area at nearly no cost. RS data fulfill the good practice guidelines of the Intergovernmental Panel On Climate Change (IPCC) that is to be used in carbon estimation. Satellite data are getting more and more accessible, and the archives are growing exponentially. To retrieve useful information to support decision-making out of this large amount of data, satellite data needs to be organized so to ensure fast processing, quick accessibility, and ease of use. A new solution is a data cube, which can be understood as a multi-dimensional stack (space, time, data type) of spatially aligned pixels and used for efficient access and analysis. A data cube for Burkina Faso has been set up from the cooperation project between the international service provider WASCAL and Germany, which provides an accessible exploitation architecture of multi-temporal satellite data. The aim of this study is to map and characterize agroforestry systems using the Burkina Faso earth observation data cube. The approach in its initial stage is based on an unsupervised image classification of a normalized difference vegetation index (NDVI) time series from 2010 to 2018, to stratify the country based on the vegetation. Fifteen strata were identified, and four samples per location were randomly assigned to define the sampling units. For safety reasons, the northern part will not be part of the fieldwork. A total of 52 locations will be visited by the end of the dry season in February-March 2020. The field campaigns will consist of identifying and describing different agroforestry systems and qualitative interviews. A multi-temporal supervised image classification will be done with a random forest algorithm, and the field data will be used for both training the algorithm and accuracy assessment. The expected outputs are (i) map(s) of agroforestry dynamics, (ii) characteristics of different systems (main species, management, area, etc.); (iii) assessment report of Burkina Faso data cube.

Keywords: agroforestry systems, Burkina Faso, earth observation data cube, multi-temporal image classification

Procedia PDF Downloads 107

Authors: Miroslava Cuperlovic-Culf, Lipu Wang, Ketty Boyle, Nadine Makley, Ian Burton, Anissa Belkaid, Mohamed Touaibia, Marc E. Surrette

Abstract:

Metabolic changes are one of the major factors in the development of a variety of diseases in various species. Metabolism of agricultural plants is altered the following infection with pathogens sometimes contributing to resistance. At the same time, pathogens use metabolites for infection and progression. In humans, metabolism is a hallmark of cancer development for example. Quantified metabolomics data combined with other omics or clinical data and analyzed using various unsupervised and supervised methods can lead to better diagnosis and prognosis. It can also provide information about resistance as well as contribute knowledge of compounds significant for disease progression or prevention. In this work, different methods for metabolomics quantification and analysis from Nuclear Magnetic Resonance (NMR) measurements that are used for investigation of disease development in wheat and human cells will be presented. One-dimensional 1H NMR spectra are used extensively for metabolic profiling due to their high reliability, wide range of applicability, speed, trivial sample preparation and low cost. This presentation will describe a new method for metabolite quantification from NMR data that combines alignment of spectra of standards to sample spectra followed by multivariate linear regression optimization of spectra of assigned metabolites to samples’ spectra. Several different alignment methods were tested and multivariate linear regression result has been compared with other quantification methods. Quantified metabolomics data can be analyzed in the variety of ways and we will present different clustering methods used for phenotype determination, network analysis providing knowledge about the relationships between metabolites through metabolic network as well as biomarker selection providing novel markers. These analysis methods have been utilized for the investigation of fusarium head blight resistance in wheat cultivars as well as analysis of the effect of estrogen receptor and carbonic anhydrase activation and inhibition on breast cancer cell metabolism. Metabolic changes in spikelet’s of wheat cultivars FL62R1, Stettler, MuchMore and Sumai3 following fusarium graminearum infection were explored. Extensive 1D 1H and 2D NMR measurements provided information for detailed metabolite assignment and quantification leading to possible metabolic markers discriminating resistance level in wheat subtypes. Quantification data is compared to results obtained using other published methods. Fusarium infection induced metabolic changes in different wheat varieties are discussed in the context of metabolic network and resistance. Quantitative metabolomics has been used for the investigation of the effect of targeted enzyme inhibition in cancer. In this work, the effect of 17 β -estradiol and ferulic acid on metabolism of ER+ breast cancer cells has been compared to their effect on ER- control cells. The effect of the inhibitors of carbonic anhydrase on the observed metabolic changes resulting from ER activation has also been determined. Metabolic profiles were studied using 1D and 2D metabolomic NMR experiments, combined with the identification and quantification of metabolites, and the annotation of the results is provided in the context of biochemical pathways.

Keywords: metabolic biomarkers, metabolic network, metabolomics, multivariate linear regression, NMR quantification, quantified metabolomics, spectral alignment

Procedia PDF Downloads 315

Authors: David F. Nettleton, Elodie Bugnicourt, Christian Wasiak, Alejandro Rosales

Abstract:

In this presentation, preliminary results are given for the modeling and calibration of two different industrial winding MIMO (Multiple Input Multiple Output) processes using machine learning techniques. In contrast to previous approaches which have typically used ‘black-box’ linear statistical methods together with a definition of the mechanical behavior of the process, we use non-linear machine learning algorithms together with a ‘white-box’ rule induction technique to create a supervised model of the fitting error between the expected and real force measures. The final objective is to build a precise model of the winding process in order to control de-tension of the material being wound in the first case, and the friction of the material passing through the die, in the second case. Case 1, Tension Control of a Winding Process. A plastic web is unwound from a first reel, goes over a traction reel and is rewound on a third reel. The objectives are: (i) to train a model to predict the web tension and (ii) calibration to find the input values which result in a given tension. Case 2, Friction Force Control of a Micro-Pullwinding Process. A core+resin passes through a first die, then two winding units wind an outer layer around the core, and a final pass through a second die. The objectives are: (i) to train a model to predict the friction on die2; (ii) calibration to find the input values which result in a given friction on die2. Different machine learning approaches are tested to build models, Kernel Ridge Regression, Support Vector Regression (with a Radial Basis Function Kernel) and MPART (Rule Induction with continuous value as output). As a previous step, the MPART rule induction algorithm was used to build an explicative model of the error (the difference between expected and real friction on die2). The modeling of the error behavior using explicative rules is used to help improve the overall process model. Once the models are built, the inputs are calibrated by generating Gaussian random numbers for each input (taking into account its mean and standard deviation) and comparing the output to a target (desired) output until a closest fit is found. The results of empirical testing show that a high precision is obtained for the trained models and for the calibration process. The learning step is the slowest part of the process (max. 5 minutes for this data), but this can be done offline just once. The calibration step is much faster and in under one minute obtained a precision error of less than 1x10-3 for both outputs. To summarize, in the present work two processes have been modeled and calibrated. A fast processing time and high precision has been achieved, which can be further improved by using heuristics to guide the Gaussian calibration. Error behavior has been modeled to help improve the overall process understanding. This has relevance for the quick optimal set up of many different industrial processes which use a pull-winding type process to manufacture fibre reinforced plastic parts. Acknowledgements to the Openmind project which is funded by Horizon 2020 European Union funding for Research & Innovation, Grant Agreement number 680820

Keywords: data model, machine learning, industrial winding, calibration

Procedia PDF Downloads 212

Authors: Wei Ji

Abstract:

This study was conducted in the Kansas City metropolitan area of the United States, which has experienced significant urban sprawling in recent decades. The remote sensing of land cover changes in this area spanned over four decades from 1972 through 2010. The project was implemented in two stages: the first stage focused on detection of long-term trends of urban land cover change, while the second one examined how to detect the coupled effects of human impact and climate change on urban landscapes. For the first-stage study, six Landsat images were used with a time interval of about five years for the period from 1972 through 2001. Four major land cover types, built-up land, forestland, non-forest vegetation land, and surface water, were mapped using supervised image classification techniques. The study found that over the three decades the built-up lands in the study area were more than doubled, which was mainly at the expense of non-forest vegetation lands. Surprisingly and interestingly, the area also saw a significant gain in surface water coverage. This observation raised questions: How have human activities and precipitation variation jointly impacted surface water cover during recent decades? How can we detect such coupled impacts through remote sensing analysis? These questions led to the second stage of the study, in which we designed and developed approaches to detecting fine-scale surface waters and analyzing coupled effects of human impact and precipitation variation on the waters. To effectively detect urban landscape changes that might be jointly shaped by precipitation variation, our study proposed “urban wetscapes” (loosely-defined urban wetlands) as a new indicator for remote sensing detection. The study examined whether urban wetscape dynamics was a sensitive indicator of the coupled effects of the two driving forces. To better detect this indicator, a rule-based classification algorithm was developed to identify fine-scale, hidden wetlands that could not be appropriately detected based on their spectral differentiability by a traditional image classification. Three SPOT images for years 1992, 2008, and 2010, respectively were classified with this technique to generate the four types of land cover as described above. The spatial analyses of remotely-sensed wetscape changes were implemented at the scales of metropolitan, watershed, and sub-watershed, as well as based on the size of surface water bodies in order to accurately reveal urban wetscape change trends in relation to the driving forces. The study identified that urban wetscape dynamics varied in trend and magnitude from the metropolitan, watersheds, to sub-watersheds in response to human impacts at different scales. The study also found that increased precipitation in the region in the past decades swelled larger wetlands in particular while generally smaller wetlands decreased mainly due to human development activities. These results confirm that wetscape dynamics can effectively reveal the coupled effects of human impact and climate change on urban landscapes. As such, remote sensing of this indicator provides new insights into the relationships between urban land cover changes and driving forces.

Keywords: urban land cover, human impact, climate change, rule-based classification, across-scale analysis

Procedia PDF Downloads 285