Search results for: heart sound classification

Authors: Mani Mofidi, Neda Valizadeh, Ali Hashemaghaee, Mona Hashemaghaee, Soudabeh Shafiee Ardestani

Abstract:

Background: Acute pain and its management remained the most complaint of emergency service admission. Diagnostic and therapeutic procedures add to patients’ pain. Diminishing the pain increases the quality of patient’s feeling and improves the patient-physician relationship. Aim: The aim of this study was to evaluate the outcomes and side effects of opioid administration in emergency patients. Material and Methods: patients admitted to ward II emergency service of Imam Khomeini hospital, who received one of the opioids: morphine, pethidine, methadone or fentanyl as an analgesic were evaluated. Their vital signs and general condition were examined before and after drug injection. Also, patient’s pain experience were recorded as numerical rating score (NRS) before and after analgesic administration. Results: 268 patients were studied. 34 patients were addicted to opioid drugs. Morphine had the highest rate of prescription (86.2%), followed by pethidine (8.5%), methadone (3.3%) and fentanyl (1.68). While initial NRS did not show significant difference between addicted patients and non-addicted ones, NRS decline and its score after drug injection were significantly lower in addicted patients. All patients had slight but statistically significant lower respiratory rate, heart rate, blood pressure and O2 saturation. There was no significant difference between different kind of opioid prescription and its outcomes or side effects. Conclusion: Pain management should be always in physicians’ mind during emergency admissions. It should not be assumed that an addicted patient complaining of pain is malingering to receive drug. Titration of drug and close monitoring must be in the curriculum to prevent any hazardous side effects.

Keywords: numerical rating score, opioid, pain, emergency department

Procedia PDF Downloads 426

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 240

Authors: Felix E. Gbenoba, Opeyemi Dahunsi

Abstract:

Self-instructional materials are at the heart of instructional delivery in Open and Distance Learning (ODL). The success of any ODL institution depends on the availability of instructional materials in quality and quantity. An ODL study material is expected to fully play the teacher plays in the face-to-face learning environment. In Nigeria, efforts to deliver ODL learning materials have been peculiarly challenging. Although researchers are unrelenting in hewing out ways to make ODL delivery in Africa generally and Nigeria in particular, meet the learners’ needs and acceptable global practices, the prospects of integrating instructional media into distance learning courses are largely unexplored. In the present study, we critically examine the prospects of integration of instructional media into ODL courses for pedagogic and other benefits it portends for delivery via the distance learning mode. Although efforts to integrate media in ODL have been recorded before now, the reality has not matched the expectation so far in Nigeria. This does not mean that the existing instructional materials have not produced any significant positive results in improving the overall learning (and teaching) experience in its institutions; it implies that increased integration as suggested here will further improve the experience as well as bring up the new challenges. Obstacles and problems of instructional materials and media development that could have affected the open educational resource initiatives are well established. The first aspect of this paper recalls the revolutionary strides that ODL brought to delivery of education in Nigeria particularly. The other aspect is on what instructional media are, their role, prospects and challenges for ODL in Nigeria; these are examined vis a vis the challenges of development, production and distribution of print instructional materials as the major format of instructional delivery at Nigeria’s only single mode ODL institution, NOUN. In the third aspect, we justify the need and benefits of integrating instructional media into the courses and make recommendations.

Keywords: instructional delivery, instructional media, ODL, media integration, Nigeria, self-instructional materials

Procedia PDF Downloads 385

Authors: Kaoutar Ben Azzou, Hanaa Talei

Abstract:

Human resources is an important department in each organization as it manages the life cycle of employees from recruitment training to retirement or termination of contracts. The recruitment process starts with a job opening, followed by a selection of the best-fit candidates from all applicants. Matching the best profile for a job position requires a manual way of looking at many CVs, which requires hours of work that can sometimes lead to choosing not the best profile. The work presented in this paper aims at reducing the workload of HR personnel by automating the preliminary stages of the candidate screening process, thereby fostering a more streamlined recruitment workflow. This tool introduces an automated system designed to help with the recruitment process by scanning candidates' CVs, extracting pertinent features, and employing machine learning algorithms to decide the most fitting job profile for each candidate. Our work employs natural language processing (NLP) techniques to identify and extract key features from unstructured text extracted from a CV, such as education, work experience, and skills. Subsequently, the system utilizes these features to match candidates with job profiles, leveraging the power of classification algorithms.

Keywords: automated recruitment, candidate screening, machine learning, human resources management

Procedia PDF Downloads 54

Authors: Pornpimol Chaiwuttisak

Abstract:

The study aims to compare the performance of the logistics for Thailand’s wholesale and retail trade industries (except motor vehicles, motorcycle, and stalls) by using data (data envelopment analysis). Thailand Standard Industrial Classification in 2009 (TSIC - 2009) categories that industries into sub-group no. 45: wholesale and retail trade (except for the repair of motor vehicles and motorcycles), sub-group no. 46: wholesale trade (except motor vehicles and motorcycles), and sub-group no. 47: retail trade (except motor vehicles and motorcycles. Data used in the study is collected by the National Statistical Office, Thailand. The study consisted of four input factors include the number of companies, the number of personnel in logistics, the training cost in logistics, and outsourcing logistics management. Output factor includes the percentage of enterprises having inventory management. The results showed that the average relative efficiency of small-sized enterprises equals to 27.87 percent and 49.68 percent for the medium-sized enterprises.

Keywords: DEA, wholesales and retails, logistics, Thailand

Procedia PDF Downloads 414

Authors: Flaurence Benjamain, Michel Casperance

Abstract:

We present in this paper, first, a comparative study of three mathematical theories to achieve the fusion of information sources. This study aims to identify the characteristics inherent in theories of possibilities, belief functions (DST) and plausible and paradoxical reasoning to establish a strategy of choice that allows us to adopt the most appropriate theory to solve a problem of fusion in order, taking into account the acquired information and imperfections that accompany them. Using the new theory of plausible and paradoxical reasoning, also called Dezert-Smarandache Theory (DSmT), to fuse information multi-sources needs, at first step, the generation of the composites events witch is, in general, difficult. Thus, we present in this paper a new approach to construct pertinent paradoxical classes based on gray levels histograms, which also allows to reduce the cardinality of the hyper-powerset. Secondly, we developed a new technique for order and coding generalized focal elements. This method is exploited, in particular, to calculate the cardinality of Dezert and Smarandache. Then, we give an experimentation of classification of a remote sensing image that illustrates the given methods and we compared the result obtained by the DSmT with that resulting from the use of the DST and theory of possibilities.

Keywords: segmentation, image, approach, vision computing

Procedia PDF Downloads 272

Authors: Emmanuel Nikiema

Abstract:

This paper examines article incorporation in Mauritian Creole, a French Lexifier Creole which exhibits three forms of article incorporation as illustrated in (1-3). While various analyses of article incorporation have been proposed in the literature, fewer studies have explored the motivation of this widespread phenomenon in Mauritian Creole (MC) as opposed to other French Lexifier Creoles spoken in the Caribbean. For example, Mauritian Creole exhibits 4 times more CV incorporation than Haitian Creole, and 40 times more than Reunion Creole. (1) Consonantal type (C): loraz ‘thunder storm’, lete ‘summer’, zwazo ‘bird’, nide ‘idea’. (2) Syllabic type (CV): lapo ‘skin’, liku ‘neck’, ledo ‘back’, leker ‘heart’, diber ‘butter’. (3) Bi-consonantal (CVC): delo ‘water’, dizef ‘egg’, lizye ‘eye’, dilwil ‘oil’. The goal of this study is twofold: 1) uncover the rules governing the three types of article incorporation in MC, and 2) account for its remarkable occurrence in MC as opposed to its quasi-absence in Reunion Creole. We have collected a corpus of over 700 cases and organized it into three categories (C; CV and CVC). For example, there are 471 examples of CV incorporation in MC against 112 in Haitian Creole and only 12 in Reunion Creole. Two questions can be raised: 1) what is the motivation and distribution of the three types of incorporation in MC, and 2) how can one account for the high volume of incorporation in MC as opposed to its quasi-absence in Reunion Creole? We suggest that article incorporation in MC is related to the structure of nouns in Bantou languages. While previous authors have largely used population settlement data in the colonies during the Creole formation period to justify their analyses, we propose an account based on the syntactic structure of Bantou nouns. This analysis will shed light on the contribution of African languages to the formation of MC, and on to why MC has exhibited more article incorporation cases than any other French Lexifier Creole.

Keywords: article incorporation, creole languages, description, phonology

Procedia PDF Downloads 108

Authors: Jamal Almatawah, Hamad Matar, Abdulsalam Altemeemi

Abstract:

The World Health Organization (WHO) has recognized environmental noise as harmful pollution that causes adverse psychosocial and physiologic effects on human health. The motor vehicle is considered to be one of the main source of noise pollution. It is a universal phenomenon, and it has grown to the point that it has become a major concern for both the public and policymakers. The aim of this paper, therefore, is to investigate the Traffic noise levels and the contributing factors that affect its level, such as traffic volume, heavy-vehicle Speed and other metrological factors in Ishbiliyah as a sample of a residential area in Kuwait. Three types of roads were selected in Ishbiliyah expressway, major arterial and collector street. The other source of noise that interferes the traffic noise has also been considered in this study. Traffic noise level is measured and analyzed using the Bruel & Kjaer outdoor sound level meter 2250-L (2250 Light). The Count-Cam2 Video Camera has been used to collect the peak and off-peak traffic count. Ambient Weather WM-5 Handheld Weather Station is used for metrological factors such as temperature, humidity and wind speed. Also, the spot speed was obtained using the radar speed: Decatur Genesis model GHD-KPH. All the measurement has been detected at the same time (simultaneously). The results showed that the traffic noise level is over the allowable limit on all types of roads. The average equivalent noise level (LAeq) for the Expressway, Major arterial and Collector Street was 74.3 dB(A), 70.47 dB(A) and 60.84 dB(A), respectively. In addition, a Positive Correlation coefficient between the traffic noise versus traffic volume and between traffic noise versus 85th percentile speed was obtained. However, there was no significant relation and Metrological factors. Abnormal vehicle noise due to poor maintenance or user-enhanced exhaust noise was found to be one of the highest factors that affected the overall traffic noise reading.

Keywords: traffic noise, residential area, pollution, vehicle noise

Procedia PDF Downloads 64

Authors: P. Serrão, E. Costa, A. Ribeiro, V. Infante

Abstract:

The characteristic sonority of the Portuguese guitar is in great part what makes Fado so distinguishable from other traditional song styles. The Portuguese guitar is a pear-shaped plucked chordophone with six courses of double strings. This study compares the two types of plain strings available for Portuguese guitar and used by the musicians. One is stainless steel spring wire, the other is high carbon spring steel (music wire). Some musicians mention noticeable differences in sound quality between these two string materials, such as a little more brightness and sustain in the steel strings. Experimental tests were performed to characterize string tension at pitch; mechanical strength and tuning stability using the universal testing machine; dimensional control and chemical composition analysis using the scanning electron microscope. The string dynamical behaviour characterization experiments, including frequency response, inharmonicity, transient response, damping phenomena and were made in a monochord test set-up designed and built in-house. Damping factor was determined for the fundamental frequency. As musicians are able to detect very small damping differences, an accurate a characterization of the damping phenomena for all harmonics was necessary. With that purpose, another improved monochord was set and a new system identification methodology applied. Due to the complexity of this task several adjustments were necessary until obtaining good experimental data. In a few cases, dynamical tests were repeated to detect any evolution in damping parameters after break-in period when according to players experience a new string sounds gradually less dull until reaching the typically brilliant timbre. Finally, each set of strings was played on one guitar by a distinguished player and recorded. The recordings which include individual notes, scales, chords and a study piece, will be analysed to potentially characterize timbre variations.

Keywords: damping factor, music wire, portuguese guitar, string dynamics

Procedia PDF Downloads 550

Authors: Amit Keshav, Alok Sharma, Bidyut Mazumdar

Abstract:

Colocasia esculenta leaves and roots are widely used in Asian countries, such as, India, Srilanka and Pakistan, as food and feed material. The root is high in carbohydrates and rich in zinc. The leaves and stalks are often traditionally preserved to be eaten in dry season. Leaf juice is stimulant, expectorant, astringent, appetizer, and otalgia. Looking at the medicinal uses of the plant leaves; phytochemicals were extracted from the plant leaves and were characterized using Fourier-transform infrared spectroscopy (FTIR) to find the functional groups. Phytochemical analysis of Colocasia esculenta (L.) leaf was studied using three solvents (methanol, chloroform, and ethanol) with soxhlet apparatus. Powder of the leaves was employed to obtain the extracts, which was qualitatively and quantitatively analyzed for phytochemical content using standard methods. Phytochemical constituents were abundant in the leave extract. Leaf was found to have various phytochemicals such as alkaloids, glycosides, flavonoids, terpenoids, saponins, oxalates and phenols etc., which could have lot of medicinal benefits such as reducing headache, treatment of congestive heart failure, prevent oxidative cell damage etc. These phytochemicals were identified using UV spectrophotometer and results were presented. In order to find the antioxidant activity of the extract, DPPH (2,2-diphenyl-1-picrylhydrazyl) method was employed using ascorbic acid as standard. DPPH scavenging activity of ascorbic acid was found to be 84%, whereas for ethanol it was observed to be 78.92%, for methanol: 76.46% and for chloroform: 72.46%. Looking at the high antioxidant activity, Colocasia esculenta may be recommended for medicinal applications. The characterizations of functional groups were analyzed using FTIR spectroscopy.

Keywords: antioxidant activity, Colocasia esculenta, leaves, characterization, FTIR

Procedia PDF Downloads 234

Authors: Amit Verma, Simranjeet Kaur, Sandeep Kaur

Abstract:

Test Case Prioritization (TCP) has gained wide spread acceptance as it often results in good quality software free from defects. Due to the increase in rate of faults in software traditional techniques for prioritization results in increased cost and time. Main challenge in TCP is difficulty in manually validate the priorities of different test cases due to large size of test suites and no more emphasis are made to make the TCP process automate. The objective of this paper is to detect the priorities of different test cases using an artificial neural network which helps to predict the correct priorities with the help of back propagation algorithm. In our proposed work one such method is implemented in which priorities are assigned to different test cases based on their frequency. After assigning the priorities ANN predicts whether correct priority is assigned to every test case or not otherwise it generates the interrupt when wrong priority is assigned. In order to classify the different priority test cases classifiers are used. Proposed algorithm is very effective as it reduces the complexity with robust efficiency and makes the process automated to prioritize the test cases.

Keywords: test case prioritization, classification, artificial neural networks, TF-IDF

Procedia PDF Downloads 393

Authors: Wael M. El-Deeb

Abstract:

The aim of this study was to assess the pathophysiological importance of lipid profile, acute phase proteins, proinflammatory cytokines and oxidative stress markers in sheep with pneumonic pasteurellosis. Blood samples were collected from 36 Pasteurellamultocida-infected sheep, together with 20 healthy controls. Samples for bacteriological examination (nasal swabs, bronchoalveolar lavage) were collected from all animals and subjected to bacteriological examinations. Moreover, heart blood and lung samples were collected from the dead pneumonic sheep and subjected also to bacteriological examinations. A lipid profile was determined, along with a blood picture and other biochemical parameters. The acute phase proteins (fibrinogen, haptoglobin, serum amyloid A), the proinflammatory cytokine tumour necrosis factor-alpha, interleukins (IL-1α, IL-1β, IL-6), interferon-gamma and the oxidative stress markers malondialdehyde, super oxide dismutase, glutathione and catalase were also measured. The examined biochemical parameters were increased in the pneumonic sheep, except for cholesterol and high-density lipoprotein cholesterol (HDL-c), which were significantly lower than control group. Acute phase proteins and cytokines were significantly higher in the pneumonic sheep when compared to the healthy sheep. There was a significant increase in the levels of malondialdehyde; however, a significant decrease in the levels of super oxide dismutase, glutathione and catalase was observed. The present study shed the light on the possible pathphysiological role of lipid profile, acute phase proteins (APPs), proinflammatory cytokines and oxidative stress markers in pneumonic pasteurelosis in sheep.

Keywords: acute phase proteins, sheep, pasteurella, interleukins, stress

Procedia PDF Downloads 389

Authors: Migena Ceyhan, Zeynep Orhan, Dimitrios Karras

Abstract:

People in modern societies are continuously sharing their experiences, emotions, and thoughts in different areas of life. The information reaches almost everyone in real-time and can have an important impact in shaping people’s way of living. This phenomenon is very well recognized and advantageously used by the market representatives, trying to earn the most from this means. Given the abundance of information, people and organizations are looking for efficient tools that filter the countless data into important information, ready to analyze. This paper is a modest contribution in this field, describing the process of automatically classifying social media comments in the Turkish language into positive or negative. Once data is gathered and preprocessed, feature sets of selected single words or groups of words are build according to the characteristics of language used in the texts. These features are used later to train, and test a system according to different machine learning algorithms (Naïve Bayes, Sequential Minimal Optimization, J48, and Bayesian Linear Regression). The resultant high accuracies can be important feedback for decision-makers to improve the business strategies accordingly.

Keywords: feature selection, machine learning, natural language processing, sentiment analysis, social media reviews

Procedia PDF Downloads 145

Authors: Sher Muhammad, Mirza Muhammad Waqar

Abstract:

It is necessary to monitor and identify mangroves types and spatial extent near coastal areas because it plays an important role in coastal ecosystem and environmental protection. This research aims at identifying and mapping mangroves types along Karachi coast ranging from 24.79 to 24.85 degree in latitude and 66.91 to 66.97 degree in longitude using hyperspectral remote sensing data and techniques. Image acquired during February, 2012 through Hyperion sensor have been used for this research. Image preprocessing includes geometric and radiometric correction followed by Minimum Noise Fraction (MNF) and Pixel Purity Index (PPI). The output of MNF and PPI has been analyzed by visualizing it in n-dimensions for end-member extraction. Well-distributed clusters on the n-dimensional scatter plot have been selected with the region of interest (ROI) tool as end members. These end members have been used as an input for classification techniques applied to identify and map mangroves species including Spectral Angle Mapper (SAM), Spectral Feature Fitting (SFF), and Spectral Information Diversion (SID). Only two types of mangroves namely Avicennia Marina (white mangroves) and Avicennia Germinans (black mangroves) have been observed throughout the study area.

Keywords: mangrove, hyperspectral, hyperion, SAM, SFF, SID

Procedia PDF Downloads 361

Authors: Abegunde Linda, Adedeji Oluwatayo, Tope-Ajayi Opeyemi

Abstract:

Maize constitutes a major agrarian production for use by the vast population but despite its economic importance, it has not been produced to meet the economic needs of the country. Achieving optimum yield in maize can meaningfully be supported by land suitability analysis in order to guarantee self-sufficiency for future production optimization. This study examines land suitability for maize production through the analysis of the physic-chemical variations in soil properties over space using a Geographic Information System (GIS) framework. Physic-chemical parameters of importance selected include slope, landuse, and physical and chemical properties of the soil. Landsat imagery was used to categorize the landuse, Shuttle Radar Topographic Mapping (SRTM) generated the slope and soil samples were analyzed for its physical and chemical components. Suitability was categorized into highly, moderately and marginally suitable based on Food and Agricultural Organisation (FAO) classification using the Analytical Hierarchy Process (AHP) technique of GIS. This result can be used by small scale farmers for efficient decision making in the allocation of land for maize production.

Keywords: AHP, GIS, MCE, suitability, Zea mays

Procedia PDF Downloads 395

Authors: Nadya Inda Syartanti

Abstract:

This research aims to identify, classify, and analyze descriptively the aspects of grammatical and lexical cohesion in the speech text of Japan’s Prime Minister Shinzo Abe entitled Nihon wa Modotte kimashita delivered in Washington DC, the United States on February 23, 2013, as a research data source. The method used is qualitative research, which uses descriptions through words that are applied by analyzing aspects of grammatical and lexical cohesion proposed by Halliday and Hasan (1976). The aspects of grammatical cohesion consist of references (personal, demonstrative, interrogative pronouns), substitution, ellipsis, and conjunction. In contrast, lexical cohesion consists of reiteration (repetition, synonym, antonym, hyponym, meronym) and collocation. Data classification is based on the 6 aspects of the cohesion. Through some aspects of cohesion, this research tries to find out the frequency of using grammatical and lexical cohesion in Shinzo Abe's speech text entitled Nihon wa Modotte kimashita. The results of this research are expected to help overcome the difficulty of understanding speech texts in Japanese. Therefore, this research can be a reference for learners, researchers, and anyone who is interested in the field of discourse analysis.

Keywords: cohesion, grammatical cohesion, lexical cohesion, speech text, Shinzo Abe

Procedia PDF Downloads 160

Authors: Qianwei Cheng, A. K. M. Mahbubur Rahman, Anis Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, M. Ashraful Amin, Ryosuke Shibasaki, Moinul Zaber

Abstract:

Thomas Friedman, in his famous book, argued that the world in this 21st century is flat and will continue to be flatter. This is attributed to rapid globalization and the interdependence of humanity that engendered tremendous in-flow of human migration towards the urban spaces. In order to keep the urban environment sustainable, policy makers need to plan based on extensive analysis of the urban environment. With the advent of high definition satellite images, high resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding urban space lies in useful categorization of the space that is usable for data collection, analysis, and visualization. In this paper, we propose a pragmatic categorization method that is readily usable for machine analysis and show applicability of the methodology on a developing world setting. Categorization to plan sustainable urban spaces should encompass the buildings and their surroundings. However, the state-of-the-art is mostly dominated by classification of building structures, building types, etc. and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh, where the surrounding environment is crucial for the categorization. Moreover, these categorizations propose small-scale classifications, which give limited information, have poor scalability and are slow to compute in real time. Our proposed method is divided into two steps-categorization and automation. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50 km × 50 km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently a map was drawn. The categorization is based broadly on two dimensions-the state of urbanization and the architectural form of urban environment. Consequently, the urban space is divided into four categories: 1) highly informal area; 2) moderately informal area; 3) moderately formal area; and 4) highly formal area. In total, sixteen sub-categories were identified. For semantic segmentation and automatic categorization, Google’s DeeplabV3+ model was used. The model uses Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate larger context. Image encompassing 70% of the urban space was used to train the model, and the remaining 30% was used for testing and validation. The model is able to segment with 75% accuracy and 60% Mean Intersection over Union (mIoU). In this paper, we propose a pragmatic categorization method that is readily applicable for automatic use in both developing and developed world context. The method can be augmented for real-time socio-economic comparative analysis among cities. It can be an essential tool for the policy makers to plan future sustainable urban spaces.

Keywords: semantic segmentation, urban environment, deep learning, urban building, classification

Procedia PDF Downloads 188

Authors: Hamdi Amroun, Yacine Benziani, Mehdi Ammi

Abstract:

In this paper, we want to determine whether the accurate prediction of nicotine concentration can be obtained by using a network of smart objects and an e-cigarette. The approach consists of, first, the recognition of factors influencing smoking cessation such as physical activity recognition and participant’s behaviors (using both smartphone and smartwatch), then the prediction of the configuration of the e-cigarette (in terms of nicotine concentration, power, and resistance of e-cigarette). The study uses a network of commonly connected objects; a smartwatch, a smartphone, and an e-cigarette transported by the participants during an uncontrolled experiment. The data obtained from sensors carried in the three devices were trained by a Long short-term memory algorithm (LSTM). Results show that our LSTM-based model allows predicting the configuration of the e-cigarette in terms of nicotine concentration, power, and resistance with a root mean square error percentage of 12.9%, 9.15%, and 11.84%, respectively. This study can help to better control consumption of nicotine and offer an intelligent configuration of the e-cigarette to users.

Keywords: Iot, activity recognition, automatic classification, unconstrained environment

Procedia PDF Downloads 223

Authors: Lingxia Li, Frédéric Schnell, Shuzhe Ding, Solène Le Douairon Lahaye

Abstract:

Background: The prevalence of cardiovascular diseases (CVD) in different triathlon sports disciplines has not been determined. Purpose: The present study aimed to determine the prevalence of CVD in world-class triathletes according to their sex, sports disciplines (aquathlon, duathlon, triathlon…), and formats (short/medium, long, and ultra-long distance). Methods: Male and female elite athletes from eleven triathlon sport disciplines, ranked in the internationally yearly top 10 between 2006 and 2019, were included. The athlete’s name was associated in a Google search with selected key terms related to heart disease and/or cardiac abnormalities. The prevalence and the hazard function of the variation were calculated, and the differences were then compared. Results: From 1329 athletes (male 639, female 690), 13 cases of CVD (0.98%, 95% CI: [0.45-1.51]) were identified, and the mean age of their occurrence was 29±6 years. Although no sex differences were found in each sport discipline/format (p > 0.05), severe outcomes (sudden cardiac arrest/death and those who had to stop their sports practice) were only observed in males. Short-distance triathlon (5.08%, 95% CI: [1.12-9.05]) was more affected than other disciplines in short/medium, long, and ultra-long formats. The prevalence of CVD in athletes who participated in multi-type of sports disciplines (4.14%, 95% CI: [1.14-7.15]) was higher than in those who participated in one type (0.52%, 95% CI: [0.10-0.93]) (p = 0.0004). Conclusion: Athletes in short-distance triathlon were more affected than other disciplines in short/medium, long and ultra-long formats. Athletes who participate in short/medium distances and those who participate in multi-type of sports disciplines should be closely monitored regardless of sex.

Keywords: cardiovascular diseases, sudden cardiac death, triathlon sport disciplines, world-class athletes

Procedia PDF Downloads 149

Authors: Ahmed Kamil Hasan Al-Ali, Bouchra Senadji, Ganesh Naik

Abstract:

We propose a system to real environmental noise and channel mismatch for forensic speaker verification systems. This method is based on suppressing various types of real environmental noise by using independent component analysis (ICA) algorithm. The enhanced speech signal is applied to mel frequency cepstral coefficients (MFCC) or MFCC feature warping to extract the essential characteristics of the speech signal. Channel effects are reduced using an intermediate vector (i-vector) and probabilistic linear discriminant analysis (PLDA) approach for classification. The proposed algorithm is evaluated by using an Australian forensic voice comparison database, combined with car, street and home noises from QUT-NOISE at a signal to noise ratio (SNR) ranging from -10 dB to 10 dB. Experimental results indicate that the MFCC feature warping-ICA achieves a reduction in equal error rate about (48.22%, 44.66%, and 50.07%) over using MFCC feature warping when the test speech signals are corrupted with random sessions of street, car, and home noises at -10 dB SNR.

Keywords: noisy forensic speaker verification, ICA algorithm, MFCC, MFCC feature warping

Procedia PDF Downloads 406

Authors: Mais Haj Qasem, Maen M. Al Assaf, Ali Rodan

Abstract:

Parallel hybrid storage systems consist of a hierarchy of different storage devices that vary in terms of data reading speed performance. As we ascend in the hierarchy, data reading speed becomes faster. Thus, migrating the application’ important data that will be accessed in the near future to the uppermost level will reduce the application I/O waiting time; hence, reducing its execution elapsed time. In this research, we implement trace-driven two-levels parallel hybrid storage system prototype that consists of HDDs and SSDs. The prototype uses data mining techniques to classify application’ data in order to determine its near future data accesses in parallel with the its on-demand request. The important data (i.e. the data that the application will access in the near future) are continuously migrated to the uppermost level of the hierarchy. Our simulation results show that our data migration approach integrated with data mining techniques reduces the application execution elapsed time when using variety of traces in at least to 22%.

Keywords: hybrid storage system, data mining, recurrent neural network, support vector machine

Procedia PDF Downloads 306

Authors: Ni Luh Putu Harta Wedari

Abstract:

Background: Clostridium difficile has two main virulence factors, namely TcdA and TcdB. TcdA encoded by the tcdA gene acts as an enterotoxin, pro-inflammatory and fluid accumulation, while TcdB encoded by the tcdB gene is cytotoxic, causes disruption of the actin cytoskeleton, and causes disruption of tight junctions in colon cells. This study aims to explore the relationship between the tcdA and tcdB genes and the duration of diarrhea in elderly patients. Method: This research was an observational analytic with a prospective cross-sectional with samples of elderly diarrhea patients who met the inclusion criteria in Denpasar City health service facilities from 1 December 2022 until 30 June 2023, and then their feces were analyzed using the real-time PCR method. Results: In this study, 40 elderly diarrhea patients met the inclusion criteria and in accordance with the minimum sample size, 28 (70%) men and 12 (30%) women. 5 patients (12.5%) had a history of azithromycin, 4 (10%) levofloxacin, 17 (42.5%) ciprofloxacin, 8 (20%) metronidazole, 1 (2.5%) cefoperazone, 5 (12, 5%) doxycycline. Comorbids, namely 13 (32.5%) type II diabetes mellitus, 4 (10%) chronic kidney disease, 10 (25%) malignancies, 7 (17.5%) urinary tract infections, 3 (7.5%) %) immunocompromised, 2 (5%) cardiac heart failure, and 1 (2.5%) acute on chronic kidney disease. The overall diarrhea duration average was 5 days. 8 samples (20%) were positive for 16s rRNA, and there was no significant difference in diarrhea duration with negative samples (p=0.166). The relationship between the tcdA gene and the duration of diarrhea could not be performed because all samples were negative. Likewise, relationship analysis between the coexistence of tcdA and tcdB could not be performed. There was no significant difference between tcdB positive 3 (7.5%) and negative with diarrhea duration (p=0.739). Conclusion: There is no significant relationship between the presence of the 16s rRNA and tcdB C. difficile genes with the duration of diarrhea in elderly patients.

Keywords: clostridium, difficile, diarrhea, elderly, tcdA, tcdB

Procedia PDF Downloads 84

Authors: Rauza Sukma Rita, Katsuya Dezaki, Yuko Maejima, Toshihiko Yada

Abstract:

Oxytocin is a nine-amino acid peptide synthesized in the paraventricular nucleus (PVN) and supraoptic nucleus (SON) of the hypothalamus. Oxytocin promotes contraction of the uterus during birth and milk ejection during breast feeding. Although oxytocin receptors are found predominantly in the breasts and uterus of females, many tissues and organs express oxytocin receptors, including the pituitary, heart, kidney, thymus, vascular endothelium, adipocytes, osteoblasts, adrenal gland, pancreatic islets, and many cell lines. On the other hand, in pancreatic islets, oxytocin receptors are expressed in both α-cells and β-cells with stronger expression in α- cells. However, to our knowledge there are no reports yet about the effect of oxytocin on cytosolic calcium reaction on α and β-cell. This study aims to investigate the effect of oxytocin on α-cells and β-cells and its oscillation pattern. Islet of Langerhans from wild type mice were isolated by collagenase digestion. Isolated and dissociated single cells either α-cells or β-cells on coverslips were mounted in an open chamber and superfused in HKRB. Cytosolic concentration ([Ca2+]i) in single cells were measured by fura-2 microfluorimetry. After measurement of [Ca2+]i, α-cells were identified by subsequent immunocytochemical staining using an anti-glucagon antiserum. In β-cells, the [Ca2+]i increase in response to oxytocin was observed only under 8.3 mM glucose condition, whereas in α-cells, [Ca2+]i an increase induced by oxytocin was observed in both 2.8 mM and 8.3 mM glucose. The oscillation incidence was induced more frequently in β-cells compared to α-cells. In conclusion, the present study demonstrated that oxytocin directly interacts with both α-cells and β-cells and induces increase of [Ca2+]i and its specific patterns.

Keywords: α-cells, β-cells, cytosolic calcium concentration, oscillation, oxytocin

Procedia PDF Downloads 190

Authors: Payel Datta, Abhishek Das, Abhishek Roychoudhury, Dhiman Chattopadhyay, Tanushyam Chattopadhyay

Abstract:

Machine learning (ML) and deep learning (DL) is most predominantly used in image/video processing, natural language processing (NLP), audio and speech recognition but not that much used in system performance evaluation. In this paper, authors are going to describe the architecture of an abstraction layer constructed using ML/DL to detect the system failure. This proposed system is used to detect the system failure by evaluating the performance metrics of an IoT service deployment under constrained infrastructure environment. This system has been tested on the manually annotated data set containing different metrics of the system, like number of threads, throughput, average response time, CPU usage, memory usage, network input/output captured in different hardware environments like edge (atom based gateway) and cloud (AWS EC2). The main challenge of developing such system is that the accuracy of classification should be 100% as the error in the system has an impact on the degradation of the service performance and thus consequently affect the reliability and high availability which is mandatory for an IoT system. Proposed ML/DL classifiers work with 100% accuracy for the data set of nearly 4,000 samples captured within the organization.

Keywords: machine learning, system performance, performance metrics, IoT, edge

Procedia PDF Downloads 193

Authors: Ladda Leungratanamart, Seree Chadcham

Abstract:

Fluid intelligence declines along with age, but it can be developed. For this reason, increasing fluid intelligence in young adults can be possible. This study examined the effects of a two-month treadmill exercise program on fluid intelligence. The researcher designed a treadmill exercise program to promote cardiorespiratory fitness. Thirty-eight healthy voluntary students from the Boromarajonani College of Nursing, Chon Buri were assigned randomly to an exercise group (n=18) and a control group (n=20). The experiment consisted of three sessions: The baseline session consisted of measuring the VO₂max, electroencephalogram and behavioral response during performed the Raven Progressive Matrices (RPM) test, a measure of fluid intelligence. For the exercise session, an experimental group exercises using treadmill training at 60 % to 80 % maximum heart rate for 30 mins, three times per week, whereas the control group did not exercise. For the following two sessions, each participant was measured the same as baseline testing. The data were analyzed using the t-test to examine whether there is significant difference between the means of the two groups. The results showed that the mean VO₂ max in the experimental group were significantly more than the control group (p<.05), suggesting a two-month treadmill exercise program can improve fluid intelligence. When comparing the behavioral data, it was found that experimental group performed RPM test more accurately and faster than the control group. Neuroelectric data indicated a significant increase in percentages of alpha band ERD (%ERD) at P3 and Pz compared to the pre-exercise condition and the control group. These data suggest that a two-month treadmill exercise program can contribute to the development of cardiorespiratory fitness which influences an increase fluid intelligence. Exercise involved in cortical activation in difference brain areas.

Keywords: treadmill exercise, fluid intelligence, raven progressive matrices test, alpha band

Procedia PDF Downloads 348

Authors: Caio Marcelo Nunes, Anderson da Silva Soares, Gustavo Teodoro Laureano, Clarimar Jose Coelho

Abstract:

This paper presents a methodology to pixel recognition in aerial images using fuzzy $c$-means algorithm. This algorithm is a alternative to recognize areas considering uncertainties and inaccuracies. Traditional clustering technics are used in recognizing of multispectral images of earth's surface. This technics recognize well-defined borders that can be easily discretized. However, in the real world there are many areas with uncertainties and inaccuracies which can be mapped by clustering algorithms that use fuzzy sets. The methodology presents in this work is applied to multispectral images obtained from Landsat-5/TM satellite. The pixels are joined using the $c$-means algorithm. After, a classification process identify the types of surface according the patterns obtained from spectral response of image surface. The classes considered are, exposed soil, moist soil, vegetation, turbid water and clean water. The results obtained shows that the fuzzy clustering identify the real type of the earth's surface.

Keywords: aerial images, fuzzy clustering, image processing, pattern recognition

Procedia PDF Downloads 480

Authors: Austin Jiang, Richard M. Salmon, Nicholas W. Morrell, Wei Li

Abstract:

BMP10 is highly expressed in the developing heart and plays essential roles in cardiogenesis. BMP10 deletion in mice results in embryonic lethality due to impaired cardiac development. In adults, BMP10 expression is restricted to the right atrium, though ventricular hypertrophy is accompanied by increased BMP10 expression in a rat hypertension model. However, reports of BMP10 activity in the circulation are inconclusive. In particular it is not known whether in vivo secreted BMP10 is active or whether additional factors are required to achieve its bioactivity. It has been shown that high-affinity binding of the BMP10 prodomain to the mature ligand inhibits BMP10 signaling activity in C2C12 cells, and it was proposed that prodomain-bound BMP10 (pBMP10) complex is latent. In this study, we demonstrated that the BMP10 prodomain did not inhibit BMP10 signaling activity in multiple endothelial cells, and that recombinant human pBMP10 complex, expressed in mammalian cells and purified under native conditions, was fully active. In addition, both BMP10 in human plasma and BMP10 secreted from the mouse right atrium were fully active. Finally, we confirmed that active BMP10 secreted from mouse right atrium was in the prodomain-bound form. Our data suggest that circulating BMP10 in adults is fully active and that the reported vascular quiescence function of BMP10 in vivo is due to the direct activity of pBMP10 and does not require an additional activation step. Moreover, being an active ligand, recombinant pBMP10 may have therapeutic potential as an endothelial-selective BMP ligand, in conditions characterized by loss of BMP9/10 signaling.

Keywords: bone morphogenetic protein 10 (BMP10), endothelial cell, signal transduction, transforming growth factor beta (TGF-B)

Procedia PDF Downloads 272

Authors: Ahmed S. Afifi, Ahmed Magdy

Abstract:

Satellite monitoring is an essential tool to study, understand, and map large-scale environmental changes that affect humans, climate, and biodiversity. The Sentinel-1 Synthetic Aperture Radar (SAR) instrument provides a high collection of data in all-weather, short revisit time, and high spatial resolution that can be used effectively in flood management. Floods occur when an overflow of water submerges dry land that requires to be distinguished from flooded areas. In this study, we use global flood mapper (GFM), a new google earth engine application that allows users to quickly map floods using Sentinel-1 SAR. The GFM enables the users to adjust manually the flood map parameters, e.g., the threshold for Z-value for VV and VH bands and the elevation and slope mask threshold. The composite R:G:B image results by coupling the bands of Sentinel-1 (VH:VV:VH) reduces false classification to a large extent compared to using one separate band (e.g., VH polarization band). The flood mapping algorithm in the GFM and the Otsu thresholding are compared with Sentinel-2 optical data. And the results show that the GFM algorithm can overcome the misclassification of a flooded area in An Giang, Vietnam.

Keywords: SAR backscattering, Sentinel-1, flood mapping, disaster

Procedia PDF Downloads 103

Authors: Fatemeh Fallah, Ensieh Lotfali, Leila Azimi, Hannan Khodaei, Maryam Rajabnejad, Nafiseh Abdollahi, Hossein Tayebi, Saham Ansari, Saeedeh Yaghoubi, Abdollah Karimi

Abstract:

Background: Coronavirus disease 2019 (COVID-19) has become a worldwide issue due to its high prevalence and rapid transmission. Fungal infections have been detected in COVID-19 patients, leading to increased morbidity and mortality. Objectives: This study aimed to isolate Aspergillus fumigatus and Mucor spp. on mini-bronchoalveolar lavage samples obtained from children with COVID-19 hospitalized in an Iranian children’s hospital. Methods: A cross-sectional descriptive study was performed on mini-bronchoalveolar lavage samples from children confirmed positive for COVID-19 admitted to ICU with a ventilator from April 2021 to February 2022. Demographic characteristics were recorded, and fungal DNA was extracted from mini-BAL samples taken from children. Nested PCR was made with two primers for Aspergillus fumigatus and Mucor spp. Results: Out of 100 children with COVID-19, all samples were negative for Aspergillus fumigatus; however, 12 cases were positive for BAL PCR for Mucor spp. Among the 12 patients, fever, shortness of breath, cough, and decreased level of consciousness were reported in 8.3% (n: 1), 16.6% (n: 2), 25% (n: 3), and 25% (n: 3), respectively. Most cases (41.7%; n: 5) suffered from heart disease, followed by underlying malignancy (33.4%; n: 4). All positive BAL PCR for Mucor spp. cases had significantly higher chest CT scan scores and spent more time under a ventilator. Conclusions: The identification of COVID-19 with Mucor spp. was observed among 12% (n: 12) of children hospitalized in a COVID-19 ICU. When dealing with pediatric COVID-19 patients, clinicians should consider the differential diagnosis of fungal co-infections and have a low threshold to begin treatment. Moreover, it is highly advisable to take prophylactic measures, such as properly using corticosteroids and shortening the intubation time.

Keywords: aspergillosis, COVID-19 identification, mucormycosis, paediatrics

Procedia PDF Downloads 5

Authors: Fabiola M. Villalobos-Castaldi, Nicolás C. Kemper, Esther Rojas-Krugger, Laura G. Ramírez-Sánchez

Abstract:

This paper presents the classification results about exploring the combination of a motion based approach with a local appearance method to describe the facial motion caused by the muscle contractions and expansions that are presented in facial expressions. The proposed feature extraction method take advantage of the knowledge related to which parts of the face reflects the highest deformations, so we selected 4 specific facial regions at which the appearance descriptor were applied. The most common used approaches for feature extraction are the holistic and the local strategies. In this work we present the results of using a local appearance approach estimating the correlation coefficient to the 4 corresponding landmark-localized facial templates of the expression face related to the neutral face. The results let us to probe how the proposed motion estimation scheme based on the local appearance correlation computation can simply and intuitively measure the motion parameters for some of the most relevant facial regions and how these parameters can be used to recognize facial expressions automatically.

Keywords: facial expression recognition system, feature extraction, local-appearance method, motion-based approach

Procedia PDF Downloads 412