Search results for: heart sound classification

Authors: Manik Sharma, Ganapathy Krishnamurthi

Abstract:

The cost of some drugs and medical treatments has risen in recent years, that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. If successful, we could dramatically improve the industry's ability to model cellular images according to their relevant biology. In turn, greatly decreasing the cost of treatments and ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model.

Keywords: cellular images, genetic perturbations, deep-learning, explainability

Procedia PDF Downloads 97

Authors: Kavyadevi N., Kaviya G., Gowsalya P., Janani M., Mohanraj S.

Abstract:

Hevea brasiliensis, also known as the rubber tree, is one of the foremost assets of crops in the world. One of the most significant advantages of the Rubber Plant in terms of air oxygenation is its capacity to reduce the likelihood of an individual developing respiratory allergies like asthma. To construct such a system that can properly identify crop diseases and pests and then create a database of insecticides for each pest and disease, we must first give treatment for the illness that has been detected. We shall primarily examine three major leaf diseases since they are economically deficient in this article, which is Bird's eye spot, algal spot and powdery mildew. And the recommended work focuses on disease identification on rubber tree leaves. It will be accomplished by employing one of the superior algorithms. Input, Preprocessing, Image Segmentation, Extraction Feature, and Classification will be followed by the processing technique. We will use time-consuming procedures that they use to detect the sickness. As a consequence, the main ailments, underlying causes, and signs and symptoms of diseases that harm the rubber tree are covered in this study.

Keywords: image processing, python, convolution neural network (CNN), machine learning

Procedia PDF Downloads 64

Authors: Benghenia Hadj Abd El Kader

Abstract:

Sleep apnea events as obstructive, central, mixed or hypopnea are characterized by frequent breathing cessations or reduction in upper airflow during sleep. An advanced method for analyzing the patterning of biomedical signals to recognize obstructive sleep apnea and hypopnea is presented. In the aim to extract characteristic parameters, which will be used for classifying the above stated (obstructive, central, mixed) sleep apnea and hypopnea, the proposed method is based first on the analysis of polysomnography signals such as electrocardiogram signal (ECG) and electromyogram (EMG), then classification of the (obstructive, central, mixed) sleep apnea and hypopnea. The analysis is carried out using the wavelet transform technique in order to extract characteristic parameters whereas classification is carried out by applying the SVM (support vector machine) technique. The obtained results show good recognition rates using characteristic parameters.

Keywords: obstructive, central, mixed, sleep apnea, hypopnea, ECG, EMG, wavelet transform, SVM classifier

Procedia PDF Downloads 362

Authors: Amine Ben Slama, Aymen Mouelhi, Sondes Manoubi, Chiraz Mbarek, Hedi Trabelsi, Mounir Sayadi, Farhat Fnaiech

Abstract:

Vertigo is a sensation of feeling off balance; the cause of this symptom is very difficult to interpret and needs a complementary exam. Generally, vertigo is caused by an ear problem. Some of the most common causes include: benign paroxysmal positional vertigo (BPPV), Meniere's disease and vestibular neuritis (VN). In clinical practice, different tests of videonystagmographic (VNG) technique are used to detect the presence of vestibular neuritis (VN). The topographical diagnosis of this disease presents a large diversity in its characteristics that confirm a mixture of problems for usual etiological analysis methods. In this study, a vestibular neuritis analysis method is proposed with videonystagmography (VNG) applications using an estimation of pupil movements in the case of an uncontrolled motion to obtain an efficient and reliable diagnosis results. First, an estimation of the pupil displacement vectors using with Hough Transform (HT) is performed to approximate the location of pupil region. Then, temporal and frequency features are computed from the rotation angle variation of the pupil motion. Finally, optimized features are selected using Fisher criterion evaluation for discrimination and classification of the VN disease.Experimental results are analyzed using two categories: normal and pathologic. By classifying the reduced features using the Support Vector Machine (SVM), 94% is achieved as classification accuracy. Compared to recent studies, the proposed expert system is extremely helpful and highly effective to resolve the problem of VNG analysis and provide an accurate diagnostic for medical devices.

Keywords: nystagmus, vestibular neuritis, videonystagmographic system, VNG, Fisher criterion, support vector machine, SVM

Procedia PDF Downloads 129

Authors: Fernanda M. Assef, Maria Teresinha A. Steiner

Abstract:

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.

Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines

Procedia PDF Downloads 92

Authors: Samet Aktaş, Nurtekin Erkmen, Faruk Guven, Halil Taskin

Abstract:

This study aimed to determine the effects of 3 versus 3 small-sided games (SSG) with different recovery times on soma physiological parameters in soccer players. Twelve soccer players from Regional Amateur League volunteered for this study (mean±SD age, 20.50±2.43 years; height, 177.73±4.13 cm; weight, 70.83±8.38 kg). Subjects were performing soccer training for five days per week. The protocol of the study was approved by the local ethic committee in School of Physical Education and Sport, Selcuk University. The subjects were divided into teams with 3 players according to Yo-Yo Intermittent Recovery Test. The field dimension was 26 m wide and 34 m in length. Subjects performed two times in a random order a series of 3 bouts of 3-a-side SSGs with 3 min and 5 min recovery durations. In SSGs, each set were performed with 6 min duration. The percent of maximal heart rate (% HRmax), blood lactate concentration (LA) and Rated Perceived Exertion (RPE) scale points were collected before the SSGs and at the end of each set. Data were analyzed by analysis of variance (ANOVA) with repeated measures. Significant differences were found between %HRmax in before SSG and 1st set, 2nd set, and 3rd set in both SSG with 3 min recovery duration and SSG with 5 min recovery duration (p<0.05). Means of %HRmax in SSG with 3 min recovery duration at both 1st and 2nd sets were significantly higher than SSG with 5 min recovery duration (p<0.05). No significant difference was found between sets of either SSGs in terms of LA (p>0.05). LA in SSG with 3 min recovery duration was higher than SSG with 5 min recovery duration at 2nd sets (p<0.05). RPE in soccer players was not different between SSGs (p>0.05).In conclusion, this study demonstrates that exercise intensity in SSG with 3 min recovery durations is higher than SSG with 5 min recovery durations.

Keywords: small-sided games, soccer, heart rate, lactate

Procedia PDF Downloads 452

Authors: Heramb Somthankar, Anujoy Chakraborty

Abstract:

This paper presents a classification study on yield prediction in semiconductor production using machine learning approaches. A complicated semiconductor production process is generally monitored continuously by signals acquired from sensors and measurement sites. A monitoring system contains a variety of signals, all of which contain useful information, irrelevant information, and noise. In the case of each signal being considered a feature, "Feature Selection" is used to find the most relevant signals. The open-source UCI SECOM Dataset provides 1567 such samples, out of which 104 fail in quality assurance. Feature extraction and selection are performed on the dataset, and useful signals were considered for further study. Afterward, common machine learning algorithms were employed to predict whether the signal yields pass or fail. The most relevant algorithm is selected for prediction based on the accuracy and loss of the ML model.

Keywords: deep learning, feature extraction, feature selection, machine learning classification algorithms, semiconductor production monitoring, signal processing, time-series analysis

Procedia PDF Downloads 98

Authors: Walid Al-Qerem, Ruba Zumot

Abstract:

Background: The rise of obesity among children and adolescents remains a primary challenge for healthcare providers globally and in the Middle East. The aim of the present study is to determine the prevalence of obesity among 5-20 years old Jordanians based on CDC criteria. Method: A total of 5722 Jordanians (37% males; 63% females) aged 5-20 years data were retrieved from the Jordanian Ministry of Health electronic database (Hakeem). As per the CDC selection criteria, the chosen data pertains exclusively to healthy Jordanian children and adolescents who are medically sound, not suffering from health conditions, and not undergoing any treatments that could hinder normal growth patterns, such as severe infection, chronic kidney disease (CKD), Down’s syndrome, attention deficit hyperactivity disorder, cancer, heart disease, lung disease, cystic fibrosis, Crohn’s disease, type 1 diabetes, hormonal disturbances, any stress-related conditions, hormonal therapy such as corticosteroids, Growth hormones (GHS) or gonadotropin-releasing hormone agonists, insulin, and amphetamines or any other stimulants. In addition, participants with missing or invalid data values for anthropometric measurements were excluded from the study. Weight for age and body mass index for age were analyzed comparatively for Jordanian children and adolescents against the international growth standards. The Z-score for each record was computed based on CDC equations. As per CDC classifications, BMI for age percentiles, values ≥85th and < 95th are classified as overweight, and value at ≥ 95th is classified as obesity. Results: The average age of the evaluated sample was 12.33 ±4.39 years (10.79 ±3.39 for males and 13.23 ± 4.66 for females). The mean weight for males and females were 33.16±14.17 Kg and 133.54±17.17 cm for males, 43.86 ±18.82 Kg, and 142.19±18.35 for females, while for BMI the mean was for boys and girls 17.81±3.88 and 20.52±5.03 respectively. The results indicated that based on CDC criteria, 8.9% of males were classified as children/adolescents with overweight, and 9.7% were classified as children/adolescents with obesity, while in females, 17.8% were classified as children/adolescents with overweight and 10.2% were classified as children/adolescents with obesity. Discussion: The high prevalence of obesity reported in the present study emphasizes the importance of applying different strategies to prevent childhood obesity, including encouraging physical activity, promoting healthier food options, and behavioral changes. Conclusion: The results presented in this study indicated the high prevalence of overweight/obesity among Jordanian adolescents and children, which must be tagged by healthcare planners and providers.

Keywords: CDC, obesity, childhood, Jordan

Procedia PDF Downloads 43

Authors: Nermeen El Kashef, Yasser Fouad, Khaled Mahar

Abstract:

No AI-complete system can model the human brain or behavior, without looking at the totality of the whole situation and incorporating a combination of senses. This paper proposes a Pattern Recognition model based on Simulation of Chemical Senses (SCS) for separation and classification of sign language. The model based on human taste controlling strategy. The main idea of the introduced model is motivated by the facts that the tongue cluster input substance into its basic tastes first, and then the brain recognizes its flavor. To implement this strategy, two level architecture is proposed (this is inspired from taste system). The separation-level of the architecture focuses on hand posture cluster, while the classification-level of the architecture to recognizes the sign language. The efficiency of proposed model is demonstrated experimentally by recognizing American Sign Language (ASL) data set. The recognition accuracy obtained for numbers of ASL is 92.9 percent.

Keywords: artificial intelligence, biocybernetics, gustatory system, sign language recognition, taste sense

Procedia PDF Downloads 280

Authors: Zainuddin Zakaria, Sun Woh Lye

Abstract:

Despite the continuous advancements in automated conflict resolution tools, there is still a low rate of adoption of automation from Air Traffic Control Officers (ATCOs). Trust or acceptance in these tools and conformance to the individual ATCO preferences in strategy execution for conflict resolution are two key factors that impact their use. This paper proposes a methodology to unearth and classify ATCO conflict resolution strategies from simulator data of trained and qualified ATCOs. The methodology involves the extraction of ATCO executive control actions and the establishment of a system of strategy resolution classification based on ATCO radar commands and prevailing flight parameters in deconflicting a pair of aircraft. Six main strategies used to handle various categories of conflict were identified and discussed. It was found that ATCOs were about twice more likely to choose only vertical maneuvers in conflict resolution compared to horizontal maneuvers or a combination of both vertical and horizontal maneuvers.

Keywords: air traffic control strategies, conflict resolution, simulator data, strategy classification system

Procedia PDF Downloads 136

Authors: Ketevan Janashia, Tamar Tsibadze, Levan Tvildiani, Nikoloz Invia, Elguja Kubaneishvili, Vasili Kukhianidze, George Ramishvili

Abstract:

This study considers the possible effects of geomagnetic activity (GMA) on humans situated on Earth by performing experiments concerning specific sensitive reactions in humans in both: natural conditions during different GMA and by the simulation of different GMA in the lab. The measurements of autonomic nervous system (ANS) responses to different GMA via measuring the heart rate variability (HRV) indices and stress index (SI) and their comparison with the K-index of GMA have been presented and discussed. The results of experiments indicate an intensification of the sympathetic part of the ANS as a stress reaction of the human organism when it is exposed to high level of GMA as natural as well as in simulated conditions. Aim: We tested the hypothesis whether the GMF when disturbed can have effects on human ANS causing specific sensitive stress-reactions depending on the initial type of ANS. Methods: The study focuses on the effects of different GMA on ANS by comparing of HRV indices and stress index (SI) of n= 78, 18-24 years old healthy male volunteers. Experiments were performed as natural conditions on days of low (K= 1-3) and high (K= 5-7) GMA as well as in the lab by the simulation of different GMA using the device of geomagnetic storm (GMS) compensation and simulation. Results: In comparison with days of low GMA (K=1-3) the initial values of HRV shifted towards the intensification of the sympathetic part (SP) of the ANS during days of GMSs (K=5-7) with statistical significance p-values: HR (heart rate, p= 0.001), SDNN (Standard deviation of all Normal to Normal intervals, p= 0.0001), RMSSD (The square root of the arithmetical mean of the sum of the squares of differences between adjacent NN intervals, p= 0.0001). In comparison with conditions during GMSs compensation mode (K= 0, B= 0-5nT), the ANS balance was observed to shift during exposure to simulated GMSs with intensities in the range of natural GMSs (K= 7, B= 200nT). However, the initial values of the ANS resulted in different dynamics in its variation depending of GMA level. In the case of initial balanced regulation type (HR > 80) significant intensification of SP was observed with p-values: HR (p= 0.0001), SDNN (p= 0.047), RMSSD (p= 0.28), LF/HF (p=0.03), SI (p= 0.02); while in the case of initial parasympathetic regulation type (HR < 80), an insignificant shift to the intensification of the parasympathetic part (PP) was observed. Conclusions: The results indicate an intensification of SP as a stress reaction of the human organism when it is exposed to high level of GMA in both natural and simulated conditions.

Keywords: autonomic nervous system, device of magneto compensation/simulation, geomagnetic storms, heart rate variability

Procedia PDF Downloads 131

Authors: Rami Qaoud, Alkama Djamal

Abstract:

When we ask about the impact of rising architectural façade in improving the terms physical urban ambiance inside the free space for urban fabric. Considered as bringing back life and culture values and civilization to these cities. And This will be the theme of this search. Where we have conducted the study about the relationship that connects the empty and full of in the urban fabric in terms of the density construction and the architectural elevation of its façade to street view. In this framework, we adopted in the methodology of this research the technical field experience. And according to three types of Street engineering(H≥2W, H=W, H≤0.5W). Where we conducted a field to raise the values of the physical ambiance according to three main axes of ambiance. The first axe 1 - Thermal ambiance. Where the temperature values were collected, relative humidity, wind speed, temperature of surfaces (the outer wall-ground). The second axe 2- Visual ambiance. Where we took the values of natural lighting levels during the daytime. The third axe 3- Acoustic ambiance . Where we take sound values during the entire day. That experience, which lasted for three consecutive days, and through six stations of measuring, where it has been one measuring station for each type of the street engineering and in two different way street. Through the obtained results and with the comparison of those values. We noticed the difference between this values and the three type of street engineering. Where the difference the calorific values of air equal 4 ° C , in terms of the visual ambiance the difference in the direct lighting natural periods amounted six hours between the three types of street engineering. As well in terms of sound ambience, registered a difference in values of up 15 (db) between the three types. This difference in values indicates The impact of rising architectural façade in improving the physical urban ambiance within the free field - street- for urban fabric.

Keywords: street, physical urban ambience, rising architectural façade, urban fabric

Procedia PDF Downloads 279

Authors: Razak Zakariya, Fazliana Mustajap, Lenny Sharinee Sakai

Abstract:

A sediment map is quite important in the marine environment. The sediment itself contains thousands of information that can be used for other research. This study was conducted by using a multibeam echo sounder Reson T20 on 15 August 2020 at the Karang Sela (coral reef area) at Pulau Bidong. The study aims to identify the sediment type around the coral reef by using bathymetry and backscatter data. The sediment in the study area was collected as ground truthing data to verify the classification of the seabed. A dry sieving method was used to analyze the sediment sample by using a sieve shaker. PDS 2000 software was used for data acquisition, and Qimera QPS version 2.4.5 was used for processing the bathymetry data. Meanwhile, FMGT QPS version 7.10 processes the backscatter data. Then, backscatter data were analyzed by using the maximum likelihood classification tool in ArcGIS version 10.8 software. The result identified three types of sediments around the coral which were very coarse sand, coarse sand, and medium sand.

Keywords: sediment type, MBES echo sounder, backscatter, ArcGIS

Procedia PDF Downloads 71

Authors: S. M. Giripunje, Mohit Kumar

Abstract:

Acoustic energy that exists in our everyday life and environment have been overlooked as a green energy that can be extracted, generated, and consumed without any significant negative impact to the environment. The harvested energy can be used to enable new technology like wireless sensor networks. Technological developments in the realization of truly autonomous MEMS devices and energy storage systems have made acoustic energy harvesting (AEH) an increasingly viable technology. AEH is the process of converting high and continuous acoustic waves from the environment into electrical energy by using an acoustic transducer or resonator. AEH is not popular as other types of energy harvesting methods since sound waves have lower energy density and such energy can only be harvested in very noisy environment. However, the energy requirements for certain applications are also correspondingly low and also there is a necessity to observe the noise to reduce noise pollution. So the ability to reclaim acoustic energy and store it in a usable electrical form enables a novel means of supplying power to relatively low power devices. A quarter-wavelength straight-tube acoustic resonator as an acoustic energy harvester is introduced with polyvinylidene fluoride (PVDF) and PVDF doped with ZnO nanoparticles, piezoelectric cantilever beams placed inside the resonator. When the resonator is excited by an incident acoustic wave at its first acoustic eigen frequency, an amplified acoustic resonant standing wave is developed inside the resonator. The acoustic pressure gradient of the amplified standing wave then drives the vibration motion of the PVDF piezoelectric beams, generating electricity due to the direct piezoelectric effect. In order to maximize the amount of the harvested energy, each PVDF and PVDF-ZnO piezoelectric beam has been designed to have the same structural eigen frequency as the acoustic eigen frequency of the resonator. With a single PVDF beam placed inside the resonator, the harvested voltage and power become the maximum near the resonator tube open inlet where the largest acoustic pressure gradient vibrates the PVDF beam. As the beam is moved to the resonator tube closed end, the voltage and power gradually decrease due to the decreased acoustic pressure gradient. Multiple piezoelectric beams PVDF and PVDF-ZnO have been placed inside the resonator with two different configurations: the aligned and zigzag configurations. With the zigzag configuration which has the more open path for acoustic air particle motions, the significant increases in the harvested voltage and power have been observed. Due to the interruption of acoustic air particle motion caused by the beams, it is found that placing PVDF beams near the closed tube end is not beneficial. The total output voltage of the piezoelectric beams increases linearly as the incident sound pressure increases. This study therefore reveals that the proposed technique used to harvest sound wave energy has great potential of converting free energy into useful energy.

Keywords: acoustic energy, acoustic resonator, energy harvester, eigenfrequency, polyvinylidene fluoride (PVDF)

Procedia PDF Downloads 368

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

By the evolvement in technology, the way of expressing opinions switched the direction to the digital world. The domain of politics as one of the hottest topics of opinion mining research merged together with the behavior analysis for affiliation determination in text which constitutes the subject of this paper. This study aims to classify the text in news/blogs either as Republican or Democrat with the minimum number of features. As an initial set, 68 features which 64 are constituted by Linguistic Inquiry and Word Count (LIWC) features are tested against 14 benchmark classification algorithms. In the later experiments, the dimensions of the feature vector reduced based on the 7 feature selection algorithms. The results show that Decision Tree, Rule Induction and M5 Rule classifiers when used with SVM and IGR feature selection algorithms performed the best up to 82.5% accuracy on a given dataset. Further tests on a single feature and the linguistic based feature sets showed the similar results. The feature “function” as an aggregate feature of the linguistic category, is obtained as the most differentiating feature among the 68 features with 81% accuracy by itself in classifying articles either as Republican or Democrat.

Keywords: feature selection, LIWC, machine learning, politics

Procedia PDF Downloads 373

Authors: Kasra Majbouri Yazdi, Adel Majbouri Yazdi, Saeid Khodayi, Jingyu Hou, Wanlei Zhou, Saeed Saedy

Abstract:

Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.

Keywords: clustering, fake news detection, feature selection, machine learning, social media, support vector machine

Procedia PDF Downloads 165

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 116

Authors: Samad Lotfollahzadeh

Abstract:

Escherichia coli (E.coli) is the most isolated bacteria from blood circulation of septicemic calves. Given the prevalence of septicemia in animals and its economic importance in veterinary practice, better understanding of changes in clinical signs following disease, may contribute to early detection of the disorder. The present study has been carried out to detect changes of clinical signs in induced sepsis in calves with E.coli. Colisepticemia has been induced in 10 twenty-day old healthy Holstein- Frisian calves with intravenous injection of 1.5 X 109 colony forming units (cfu) of O111: H8 strain of E.coli. Clinical signs including rectal temperature, heart rate, respiratory rate, shock, appetite, sucking reflex, feces consistency, general behavior, dehydration and standing ability were recorded in experimental calves during 24 hours after induction of colisepticemia. Blood culture was also carried out from calves four times during the experiment. ANOVA with repeated measure is used to see changes of calves’ clinical signs to experimental colisepticemia, and values of P≤ 0.05 was considered statistically significant. Mean values of rectal temperature and heart rate as well as median values of respiratory rate, appetite, suckling reflex, standing ability and feces consistency of experimental calves increased significantly during the study (P<0.05). In the present study, median value of shock score was not significantly increased in experimental calves (P> 0.05). The results of present study showed that total score of clinical signs in calves with experimental colisepticemia increased significantly, although the score of some clinical signs such as shock did not change significantly.

Keywords: calves, clinical signs scoring, E. coli O111:H8, experimental colisepticemia

Procedia PDF Downloads 364

Authors: Peifei Zhu, Zisheng Li, Yasuki Kakishita, Mayumi Suzuki, Tomoaki Chono

Abstract:

Segmentation of left ventricle (LV) from cardiac ultrasound images provides a quantitative functional analysis of the heart to diagnose disease. Active Shape Model (ASM) is a widely used approach for LV segmentation but suffers from the drawback that initialization of the shape model is not sufficiently close to the target, especially when dealing with abnormal shapes in disease. In this work, a two-step framework is proposed to improve the accuracy and speed of the model-based segmentation. Firstly, a robust and efficient detector based on Hough forest is proposed to localize cardiac feature points, and such points are used to predict the initial fitting of the LV shape model. Secondly, to achieve more accurate and detailed segmentation, ASM is applied to further fit the LV shape model to the cardiac ultrasound image. The performance of the proposed method is evaluated on a dataset of 800 cardiac ultrasound images that are mostly of abnormal shapes. The proposed method is compared to several combinations of ASM and existing initialization methods. The experiment results demonstrate that the accuracy of feature point detection for initialization was improved by 40% compared to the existing methods. Moreover, the proposed method significantly reduces the number of necessary ASM fitting loops, thus speeding up the whole segmentation process. Therefore, the proposed method is able to achieve more accurate and efficient segmentation results and is applicable to unusual shapes of heart with cardiac diseases, such as left atrial enlargement.

Keywords: hough forest, active shape model, segmentation, cardiac left ventricle

Procedia PDF Downloads 329

Authors: L. Lindsay, S. A. Coleman, D. Kerr, B. J. Taylor, A. Moorhead

Abstract:

Cognitive decline and frailty is apparent in older adults leading to an increased likelihood of the risk of falling. Currently health care professionals have to make professional decisions regarding such risks, and hence make difficult decisions regarding the future welfare of the ageing population. This study uses health data from The Irish Longitudinal Study on Ageing (TILDA), focusing on adults over the age of 50 years, in order to analyse health risk factors and predict the likelihood of falls. This prediction is based on the use of machine learning algorithms whereby health risk factors are used as inputs to predict the likelihood of falling. Initial results show that health risk factors such as long-term health issues contribute to the number of falls. The identification of such health risk factors has the potential to inform health and social care professionals, older people and their family members in order to mitigate daily living risks.

Keywords: classification, falls, health risk factors, machine learning, older adults

Procedia PDF Downloads 132

Authors: Muhammad Ali Sarwar, Muhammad Farooq, Nayab Hassan, Hammad Hassan

Abstract:

Pakistan is highly recognized for its agriculture and is well known for producing substantial amounts of wheat, cotton, and sugarcane. However, some factors contribute to a decline in crop quality and a reduction in overall output. One of the main factors contributing to this decline is the presence of weed and its late detection. This process of detection is manual and demands a detailed inspection to be done by the farmer itself. But by the time detection of weed, the farmer will be able to save its cost and can increase the overall production. The focus of this research is to identify and classify the four main types of weeds (Small-Flowered Cranesbill, Chick Weed, Prickly Acacia, and Black-Grass) that are prevalent in our region’s major crops. In this work, we implemented three different deep learning techniques: YOLO-v5, Inception-v3, and Deep CNN on the same Dataset, and have concluded that deep convolutions neural network performed better with an accuracy of 97.45% for such classification. In relative to the state of the art, our proposed approach yields 2% better results. We devised the architecture in an efficient way such that it can be used in real-time.

Keywords: deep convolution networks, Yolo, machine learning, agriculture

Procedia PDF Downloads 94

Authors: Bushra Zafar, Usman Qamar

Abstract:

Large data sample size and dimensions render the effectiveness of conventional data mining methodologies. A data mining technique are important tools for collection of knowledgeable information from variety of databases and provides supervised learning in the form of classification to design models to describe vital data classes while structure of the classifier is based on class attribute. Classification efficiency and accuracy are often influenced to great extent by noisy and undesirable features in real application data sets. The inherent natures of data set greatly masks its quality analysis and leave us with quite few practical approaches to use. To our knowledge first time, we present a new approach for investigation of structure and quality of datasets by providing a targeted analysis of localization of noisy and irrelevant features of data sets. Machine learning is based primarily on feature selection as pre-processing step which offers us to select few features from number of features as a subset by reducing the space according to certain evaluation criterion. The primary objective of this study is to trim down the scope of the given data sample by searching a small set of important features which may results into good classification performance. For this purpose, a heuristic for wrapper-based feature selection using genetic algorithm and for discriminative feature selection an external classifier are used. Selection of feature based on its number of occurrence in the chosen chromosomes. Sample dataset has been used to demonstrate proposed idea effectively. A proposed method has improved average accuracy of different datasets is about 95%. Experimental results illustrate that proposed algorithm increases the accuracy of prediction of different diseases.

Keywords: data mining, generic algorithm, KNN algorithms, wrapper based feature selection

Procedia PDF Downloads 307

Authors: Aaron Walayat

Abstract:

Protection of the environment in international law has been one of the most developed in the context of international humanitarian law. This paper examines the history of the protection of the environment in times of armed conflict, beginning with the traditional notion of restraint observed in antiquity towards the obligation to protect the environment, examining the treaties and agreements, both binding and non-binding which have contributed to environmental protection in war. The paper begins with a discussion of the ancient concept of restraint. This section examines the social norms in favor of protection of the environment as observed in the Bible, Greco-Roman mythology, and even more contemporary literature. The study of the traditional rejection of total war establishes the social foundation on which the current legal regime has stemmed. The paper then studies the principle of restraint as codified in international humanitarian law. It mainly examines Additional Protocol I of the Geneva Convention of 1949 and existing international law concerning civilian objects and the principles of international humanitarian law in the classification between civilian objects and military objectives. The paper then explores the environment’s classification as both a military objective and as a civilian object as well as explores arguments in favor of the classification of the whole environment as a civilian object. The paper will then discuss the current legal regime surrounding the protection of the environment, discussing some declarations and conventions including the 1868 Declaration of St. Petersburg, the 1907 Hague Convention No. IV, the Geneva Conventions, and the 1976 Environmental Modification Convention. The paper concludes with the outline noting the movement from codification of the principles of restraint into the various treaties, agreements, and declarations of the current regime of international humanitarian law. This paper provides an analysis of the history and significance of the relationship between international humanitarian law as a major contributor to the growing field of international environmental law.

Keywords: armed conflict, environment, legal regime, restraint

Procedia PDF Downloads 189

Authors: Galal Omer, Onisimo Mutanga, Elfatih M. Abdel-Rahman, Elhadi Adam

Abstract:

Threatened tree species (TTS) play a significant role in ecosystem functioning and services, land use dynamics, and other socio-economic aspects. Such aspects include ecological, economic, livelihood, security-based, and well-being benefits. The development of techniques for mapping and monitoring TTS is thus critical for understanding the functioning of ecosystems. The advent of advanced imaging systems and supervised learning algorithms has provided an opportunity to classify TTS over fragmenting landscape. Recently, vegetation maps have been produced using advanced imaging systems such as WorldView-2 (WV-2) and robust classification algorithms such as support vectors machines (SVM) and artificial neural network (ANN). However, delineation of TTS in a fragmenting landscape using high resolution imagery has widely remained elusive due to the complexity of the species structure and their distribution. Therefore, the objective of the current study was to examine the utility of the advanced WV-2 data for mapping TTS in the fragmenting Dukuduku indigenous forest of South Africa using SVM and ANN classification algorithms. The results showed the robustness of the two machine learning algorithms with an overall accuracy (OA) of 77.00% (total disagreement = 23.00%) for SVM and 75.00% (total disagreement = 25.00%) for ANN using all eight bands of WV-2 (8B). This study concludes that SVM and ANN classification algorithms with WV-2 8B have the potential to classify TTS in the Dukuduku indigenous forest. This study offers relatively accurate information that is important for forest managers to make informed decisions regarding management and conservation protocols of TTS.

Keywords: artificial neural network, threatened tree species, indigenous forest, support vector machines

Procedia PDF Downloads 502

Authors: Youhang Zhou, Weimin Zeng, Qi Xie

Abstract:

Abstract: In order to solve the wear recognition problem of the machine tool guide surface, a new machine tool guide surface recognition method based on the radar-graph barycentre feature is presented in this paper. Firstly, the gray mean value, skewness, projection variance, flat degrees and kurtosis features of the guide surface image data are defined as primary characteristics. Secondly, data Visualization technology based on radar graph is used. The visual barycentre graphical feature is demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology is used, the radar-graph barycentre feature and wear original feature are put into the classifier separately for classification and comparative analysis of classification and experiment results. The calculation and experimental results show that the method based on the radar-graph barycentre feature can detect the guide surface effectively.

Keywords: guide surface, wear defects, feature extraction, data visualization

Procedia PDF Downloads 507

Authors: Gabriel Wainer

Abstract:

Modeling and Simulation methods have been used to better analyze the behavior of complex physical systems, and it is now common to use simulation as a part of the scientific and technological discovery process. M&S advanced thanks to the improvements in computer technology, which, in many cases, resulted in the development of simulation software using ad-hoc techniques. Formal M&S appeared in order to try to improve the development task of very complex simulation systems. Some of these techniques proved to be successful in providing a sound base for the development of discrete-event simulation models, improving the ease of model definition and enhancing the application development tasks; reducing costs and favoring reuse. The DEVS formalism is one of these techniques, which proved to be successful in providing means for modeling while reducing development complexity and costs. DEVS model development is based on a sound theoretical framework. The independence of M&S tasks made possible to run DEVS models on different environments (personal computers, parallel computers, real-time equipment, and distributed simulators) and middleware. We will present a historical perspective of discrete-event M&S methodologies, showing different modeling techniques. We will introduce DEVS origins and general ideas, and compare it with some of these techniques. We will then show the current status of DEVS M&S, and we will discuss a technological perspective to solve current M&S problems (including real-time simulation, interoperability, and model-centered development techniques). We will show some examples of the current use of DEVS, including applications in different fields. We will finally show current open topics in the area, which include advanced methods for centralized, parallel or distributed simulation, the need for real-time modeling techniques, and our view in these fields.

Keywords: modeling and simulation, discrete-event simulation, hybrid systems modeling, parallel and distributed simulation

Procedia PDF Downloads 310

Authors: Aisulu Tileukulova, Zhexebay Dauren

Abstract:

Radar plays an important role because it is widely used in civil and military fields. Target detection is one of the most important radar applications. The accuracy of detecting inconspicuous aerial objects in radar facilities is lower against the background of noise. Convolutional neural networks can be used to improve the recognition of this type of aerial object. The purpose of this work is to develop an algorithm for recognizing aerial objects using convolutional neural networks, as well as training a neural network. In this paper, the structure of a convolutional neural network (CNN) consists of different types of layers: 8 convolutional layers and 3 layers of a fully connected perceptron. ReLU is used as an activation function in convolutional layers, while the last layer uses softmax. It is necessary to form a data set for training a neural network in order to detect a target. We built a Confusion Matrix of the CNN model to measure the effectiveness of our model. The results showed that the accuracy when testing the model was 95.7%. Classification of echo signals using CNN shows high accuracy and significantly speeds up the process of predicting the target.

Keywords: radar, neural network, convolutional neural network, echo signals

Procedia PDF Downloads 335

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 144

Authors: Uswah Khairuddin, Rubiyah Yusof, Nenny Ruthfalydia Rosli

Abstract:

This paper presents a comparative study between k-Nearest Neighbour (k-NN) and Multi-Layer Perceptron Neural Network (MLP-NN) classifier using Genetic Algorithm (GA) as feature selector for wood recognition system. The features have been extracted from the images using Grey Level Co-Occurrence Matrix (GLCM). The use of GA based feature selection is mainly to ensure that the database used for training the features for the wood species pattern classifier consists of only optimized features. The feature selection process is aimed at selecting only the most discriminating features of the wood species to reduce the confusion for the pattern classifier. This feature selection approach maintains the ‘good’ features that minimizes the inter-class distance and maximizes the intra-class distance. Wrapper GA is used with k-NN classifier as fitness evaluator (GA-kNN). The results shows that k-NN is the best choice of classifier because it uses a very simple distance calculation algorithm and classification tasks can be done in a short time with good classification accuracy.

Keywords: feature selection, genetic algorithm, optimization, wood recognition system

Procedia PDF Downloads 532

Authors: Aizati N. A. Daud, Jorieke E. H. Bergman, Wilhelmina S. Kerstjens-Frederikse, Pieter Van Der Vlies, Eelko Hak, Rolf M. F. Berger, Henk Groen, Bob Wilffert

Abstract:

Prenatal use of SRIs was previously associated with Congenital Heart Anomalies (CHA). The aim of the study is to explore whether pharmacogenetics plays a role in this teratogenicity using a gene-environment interaction study. A total of 33 case-mother dyads and 2 mother-only (children deceased) registered in EUROCAT Northern Netherlands were included in a case-only study. Five case-mother dyads and two mothers-only were exposed to SRIs (paroxetine=3, fluoxetine=2, venlafaxine=1, paroxetine and venlafaxine=1) in the first trimester of pregnancy. The remaining 28 case-mother dyads were not exposed to SRIs. Ten genes that encode the enzymes or proteins important in determining fetal exposure to SRIs or its mechanism of action were selected: CYPs (CYP1A2, CYP2C9, CYP2C19, CYP2D6), ABCB1 (placental P-glycoprotein), SLC6A4 (serotonin transporter) and serotonin receptor genes (HTR1A, HTR1B, HTR2A, and HTR3B). All included subjects were genotyped for 58 genetic variations in these ten genes. Logistic regression analyses were performed to determine the interaction odds ratio (OR) between genetic variations and SRIs exposure on the risk of CHA. Due to low phenotype frequencies of CYP450 poor metabolizers among exposed cases, the OR cannot be calculated. For ABCB1, there was no indication of changes in the risk of CHA with any of the ABCB1 SNPs in the children and their mothers. Several genetic variations of the serotonin transporter and receptors (SLC6A4 5-HTTLPR and 5-HTTVNTR, HTR1A rs1364043, HTR1B rs6296 & rs6298, HTR3B rs1176744) were associated with an increased risk of CHA, but with too limited sample size to reach statistical significance. For SLC6A4 genetic variations, the mean genetic scores of the exposed case-mothers tended to be higher than the unexposed mothers (2.5 ± 0.8 and 1.88 ± 0.7, respectively; p=0.061). For SNPs of the serotonin receptors, the mean genetic score for exposed cases (children) tended to be higher than the unexposed cases (3.4 ± 2.2, and 1.9 ± 1.6, respectively; p=0.065). This study might be among the first to explore the potential gene-environment interaction between pharmacogenetic determinants and SRIs use on the risk of CHA. With small sample sizes, it was not possible to find a significant interaction. However, there were indications for a role of serotonin receptor polymorphisms in fetuses exposed to SRIs on fetal risk of CHA which warrants further investigation.

Keywords: gene-environment interaction, heart defects, pharmacogenetics, serotonin reuptake inhibitors, teratogenicity

Procedia PDF Downloads 211