Search results for: maximum likelihood classification

Authors: Natalia Bustos Sierra, Katrien Tersago

Abstract:

It is currently proven that both extremes of temperature are associated with increased mortality and that air pollution is associated with temperature. This relationship is complex, and in countries with important seasonal variations in weather such as Belgium, some effects can appear as non-significant when the analysis is done over the entire year. We, therefore, analyzed the effect of short-term outdoor air pollution exposure on cardiovascular mortality during the warmer and colder months separately. We used daily cardiovascular deaths from acute cardiovascular diagnostics according to the International Classification of Diseases, 10th Revision (ICD-10: I20-I24, I44-I49, I50, I60-I66) during the period 2008-2013. The environmental data were population-weighted concentrations of particulates with an aerodynamic diameter less than 10 µm (PM₁₀) and less than 2.5 µm (PM₂.₅) (daily average), nitrogen dioxide (NO₂) (daily maximum of the hourly average) and ozone (O₃) (daily maximum of the 8-hour running mean). A Generalized linear model was applied adjusting for the confounding effect of season, temperature, dew point temperature, the day of the week, public holidays and the incidence of influenza-like illness (ILI) per 100,000 inhabitants. The relative risks (RR) were calculated for an increase of one interquartile range (IQR) of the air pollutant (μg/m³). These were presented for the four hottest months (June, July, August, September) and coldest months (November, December, January, February) in Belgium. We applied both individual lag model and unconstrained distributed lag model methods. The cumulative effect of a four-day exposure (day of exposure and three consecutive days) was calculated from the unconstrained distributed lag model. The IQR for PM₁₀, PM₂.₅, NO₂, and O₃ were respectively 8.2, 6.9, 12.9 and 25.5 µg/m³ during warm months and 18.8, 17.6, 18.4 and 27.8 µg/m³ during cold months. The association with CV mortality was statistically significant for the four pollutants during warm months and only for NO₂ during cold months. During the warm months, the cumulative effect of an IQR increase of ozone for the age groups 25-64, 65-84 and 85+ was 1.066 (95%CI: 1.002-1.135), 1.041 (1.008-1.075) and 1.036 (1.013-1.058) respectively. The cumulative effect of an IQR increase of NO₂ for the age group 65-84 was 1.066 (1.020-1.114) during warm months and 1.096 (1.030-1.166) during cold months. The cumulative effect of an IQR increase of PM₁₀ during warm months reached 1.046 (1.011-1.082) and 1.038 (1.015-1.063) for the age groups 65-84 and 85+ respectively. Similar results were observed for PM₂.₅. The short-term effect of air pollution on cardiovascular mortality is greater during warm months for lower pollutant concentrations compared to cold months. Spending more time outside during warm months increases population exposure to air pollution and can, therefore, be a confounding factor for this association. Age can also affect the length of time spent outdoors and the type of physical activity exercised. This study supports the deleterious effect of air pollution on cardiovascular mortality (CV) which varies according to season and age groups in Belgium. Public health measures should, therefore, be adapted to seasonality.

Keywords: air pollution, cardiovascular, mortality, season

Procedia PDF Downloads 148

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 126

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 89

Authors: Yo-Sheng Lin, Chien-Chin Wang, Yun-Wen Lin, Chien-Yo Lee

Abstract:

A wide band power amplifier (PA) for 60 GHz and 77 GHz direct-conversion transceiver using standard 90 nm CMOS technology is reported. The PA comprises a cascode input stage with a wide band T-type input-matching network and inductive interconnection and load, followed by a common-source (CS) gain stage and a CS output stage. To increase the saturated output power (PSAT) and power-added efficiency (PAE), the output stage adopts a two-way power dividing and combining architecture. Instead of the area-consumed Wilkinson power divider and combiner, miniature low-loss transmission-line inductors are used at the input and output terminals of each of the output stages for wide band input and output impedance matching to 100 ohm. This in turn results in further PSAT and PAE enhancement. The PA consumes 92.2 mW and achieves maximum power gain (S21) of 23.3 dB at 56 GHz, and S21 of 21.7 dB and 14 dB, respectively, at 60 GHz and 77 GHz. In addition, the PA achieves excellent saturated output power (PSAT) of 10.6 dB and maximum power added efficiency (PAE) of 12.3% at 60 GHz. At 77 GHz, the PA achieves excellent PSAT of 10.4 dB and maximum PAE of 6%. These results demonstrate the proposed wide band PA architecture is very promising for 60 GHz wireless personal local network (WPAN) and 77 GHz automobile radar systems.

Keywords: 60 GHz, 77 GHz, PA, WPAN, automotive radar

Procedia PDF Downloads 564

Authors: Muhammad Zaman, Guohua Fang, Muhammad Saifullah,

Abstract:

The presented study emphasize at an optimal model to compare past and future optimal hydropower generation. In order to get maximum benefits from the Xin’anjiang hydropower station a model is developed. A Particle Swarm Optimization (PSO) has purposed and past and future water flow is used to get the maximum benefits from future water resources in this study. The results revealed that the future hydropower generation is more than the past generation. This paper gives us idea that what could we get in the past using optimal method of electricity generation and what can we get in the future using this technique.

Keywords: PSO, future water resources, optimization, Xin’anjiang,

Procedia PDF Downloads 422

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 95

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 276

Authors: A. Ramalho, L. Romeiro, R. Ventura, A. Suleman

Abstract:

A real-time path planning framework for Unmanned Air Vehicles, and in particular multi-rotors is proposed. The framework is designed to provide feasible trajectories from the current UAV position to a goal state, taking into account constraints such as obstacle avoidance, problem kinematics, and vehicle limitations such as maximum speed and maximum acceleration. The framework computes feasible paths online, allowing to avoid new, unknown, dynamic obstacles without fully re-computing the trajectory. These features are achieved using an iterative process in which the robot computes and optimizes the trajectory while performing the mission objectives. A first trajectory is computed using a modified Rapidly-Exploring Random Tree (RRT) algorithm, that provides trajectories that respect a maximum curvature constraint. The trajectory optimization is accomplished using the Interior Point Optimizer (IPOPT) as a solver. The framework has proven to be able to compute a trajectory and optimize to a locally optimal with computational efficiency making it feasible for real-time operations.

Keywords: interior point optimization, multi-rotors, online path planning, rapidly exploring random trees, trajectory optimization

Procedia PDF Downloads 125

Authors: Mehdi Ghatus

Abstract:

Two simple apparatus based on the hammer and anvil principle have been constructed and used to study the microstructure and micro-hardness characteristics of some AL-base alloys. Foils with thicknesses arranging from 20 µm up to 600 µm have been obtained. The cooling rate was estimated to be in the range 10^4 - 10^5 K/sec. Microstructure study of rapidly quenched Al-30% Si foils indicated that with decreasing the foil thickness the size of primary Si crystallites decreases in the whole investigated range (0.64-0.15 mm). However, the volume fraction of the primary Si crystals in the structure remained constant down to thickness the primary Si volume fraction started to decrease. Rapid quenching of Al- 14-16% Cu showed single phase cell structure. In foils up to 0.55 mm with decreasing the foil thickness the cell size decreases and micro-hardness increases particularly in foils below 0.3 mm in thickness. Isochronal annealing of theses foils show that the highly supersaturated Al-14-16% Cu solid solution decomposes readily at relatively low temperature and short time intervals. The maximum hardness is obtained after annealing at 100 °C for 30 minutes. However with decreasing the Cu content of the foils the precipitation process is largely delayed. Eight hours of annealing at 100 °C was not enough to achieve the maximum hardness in Al-4% Cu thin foils. The achieved hardness value was more than twice of the maximum hardness obtained in articles of similar composition but conventionally aged.

Keywords: aluminum, hardness, alloys, quenched aluminum

Procedia PDF Downloads 414

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 131

Authors: Salahud Din, Saima Masood, Hafsa Zaneb, Habib-Ur Rehman, Imad Khan, Muqader Shah

Abstract:

The present study was carried out on the gross anatomy, biometery and radiographic analysis of tarsal bones in twenty specimens of adult chinkara (Gazella bennettii). The desired bones were collected from the graveyards present in the locality of the different safari parks and zoos in Pakistan. To observe the edges and articulations between the bones, the radiographic images were acquired in craniocaudals and mediolateral views of the intact limbs. The gross and radiographic studies of the tarsus of adult Chinkara were carried out in University of Veterinary and Animal Sciences, Lahore, Pakistan. The tarsus of chinkara comprised of five bones both grossly and radiographically, settled in three transverse rows: tibial and fibular tarsal in the proximal, central and fourth fused tarsal in the middle row, the first, second and third fused tarsal in the distal row. The fibular tarsal was the largest and longest bone of the hock, situated on the lateral side and had a bulbous tuber calcis 'point of the hock' at the proximal extremity which projects upward and backward. The average maximum height and breadth for fibular tarsal was 5.61 ± 0.23 cm and 2.06 ± 0.13 cm, respectively. The tibial tarsal bones were the 2nd largest bone of the proximal row and lie on the medial side of the tarsus bears trochlea at either end. The average maximum height and breadth for tibial tarsal was 2.79 ± 0.05 cm and 1.74 ± 0.01 cm, respectively. The central and the fourth tarsals were fused to form a large bone which extends across the entire width of the tarsus and articulates with all bones of the tarsus. A nutrient foramen was present in the center of the non auricular area, more prominent on the ventral surface. The average maximum height and breadth for central and fourth fused tarsal was 1.51 ± 0.13 cm and 2.08 ± 0.07 cm, respectively. The first tarsal was a quadrilateral piece of bone placed on the poteriomedial surface of the hock. The greatest length and maximum breadth of the first tarsal was 0.94 ± 0.01 cm and 1.01 ± 0.01 cm, respectively. The second and third fused tarsal bone resembles the central but was smaller and triangular in outline. It was situated between the central above and the large metatarsal bone below. The greatest length and maximum breadth of second and third fused tarsal was 0.98 ± 0.01 cm and 1.49 ± 0.01 cm.

Keywords: chinkara, morphometry, radiography, tarsal bone

Procedia PDF Downloads 152

Authors: T. N. Goh, M. Hashmi, O. Hussain

Abstract:

Temporomandibular joint (TMJ) dysfunction (TMD) is a condition that may affect patients via restricted mouth opening, significant pain during normal functioning, and/or reproducible joint noise. TMD includes myofascial pain, TMJ functional derangements (internal derangement, dislocation), and TMJ degenerative/inflammatory joint disease. Internal derangement (ID) is the most common cause of TMD-related clicking and locking. These patients are managed in a stepwise approach, from patient education (homecare advice and analgesia), splint therapy, physiotherapy, botulinum toxin treatment, to arthrocentesis. Arthrotomy is offered when the aforementioned treatment options fail to alleviate symptoms and improve quality of life. The aim of this prospective study was to review the outcomes of jaw joint open surgery in TMD patients. Patients who presented from 2015-2022 at the Oral and Maxillofacial Surgery Department in the Doncaster NHS Foundation Trust, UK, with a Wilkes classification of III -V were included. These patients underwent either i) discopexy with bone-anchoring suture (9); ii) intrapositional temporalis flap (ITF) with bone-anchoring suture (3); iii) eminoplasty and discopexy with suturing to the capsule (3); iii) discectomy + ITF with bone-anchoring suture (1); iv) discoplasty + bone-anchoring suture (1); v) ITF (1). Maximum incisal opening (MIO) was assessed pre-operatively and at each follow-up. Pain score, determined via the visual analogue scale (VAS, with 0 being no pain and 10 being the worst pain), was also recorded. A total of 18 eligible patients were identified with a mean age of 45 (range 22 - 79), of which 16 were female. The patients were scored by Wilkes Classification as III (14), IV (1), or V (4). Twelve patients had anterior disc displacement without reduction (66%) and six had degenerative/arthritic changes (33%) to the TMJ. The open joint procedure resulted in an increase in MIO and reduction in pain VAS and for the majority of patients, across all Wilkes Classifications. Pre-procedural MIO was 22.9 ± 7.4 mm and VAS was 7.8 ± 1.5. At three months post-procedure there was an increase in MIO to 34.4 ± 10.4 mm (p < 0.01) and a decrease in the VAS to 1.5 ± 2.9 (p < 0.01). Three patients were lost to follow-up prior to six months. Six were discharged at six month review and five patients were discharged at 12 months review as they were asymptomatic with good mouth opening. Four patients are still attending for annual botulinum toxin treatment. Two patients (Wilkes III and V) subsequently underwent TMJ replacement (11%). One of these patients (Wilkes III) had improvement initially to MIO of 40 mm, but subsequently relapsed to less than 20 mm due to lack of compliance with jaw rehabilitation device post-operatively. Clinical improvements in 89% of patients within the study group were found, with a return to near normal MIO range and reduced pain score. Intraoperatively, the operator found bone-anchoring suture used for discopexy/discoplasty more secure than the soft tissue anchoring suturing technique.

Keywords: bone anchoring suture, open temporomandibular joint surgery, temporomandibular joint, temporomandibular joint dysfunction

Procedia PDF Downloads 95

Authors: I. Ahmad, A. Hannan, S. Ahmad, M. Asif, M. F. Nawaz, M. A. Tanvir, M. F. Azhar

Abstract:

During this research, a comprehensive survey of tree growing areas of Faisalabad district of Pakistan was conducted to observe the symptoms, spectrum, occurrence and severity of A. nilotica and E. camaldulensis decline. Objective of current research was to investigate specific fungal pathogens involved in decline of A. nilotica and E. camaldulensis. For this purpose, infected roots, bark, neck portion, stem, branches, leaves and infected soils were collected to identify associated fungi. Potato dextrose agar (PDA) and Czepak dox agar media were used for isolations. Identification of isolated fungi was done microscopically and different fungi were identified. During survey of urban locations of Faisalabad, disease incidence on Kikar and Eucalyptus was recorded as 3.9-7.9% and 2.6-7.1% respectively. Survey of Agroforest zones of Faisalabad revealed decline incidence on kikar 7.5% from Sargodha road while on Satiana and Jhang road it was not planted. In eucalyptus trees, 4%, 8% and 0% disease incidence was observed on Jhang road, Sargodha road and Satiana road respectively. The maximum fungus isolated from the kikar tree was Drechslera australiensis (5.00%) from the stem part. Aspergillus flavus also gave the maximum value of (3.05%) from the bark. Alternaria alternata gave the maximum value of (2.05%) from leaves. Rhizopus and Mucor spp. were recorded minimum as compared to the Drechslera, Alternaria and Aspergillus. The maximum fungus isolated from the Eucalyptus tree was Armillaria luteobubalina (5.00%) from the stem part. The other fungi isolated were Macrophamina phaseolina and A. niger.

Keywords: decline, frequency of mycoflora, A. nilotica and E. camaldulensis, Drechslera australiensis, Armillaria luteobubalina

Procedia PDF Downloads 353

Authors: Haider Karar, Saghir Ahmad, Amjad Ali, Ibrar Ul Haq

Abstract:

The experiment was conducted at Cotton Research Station, Multan to study the impact of weather factors and red cotton bug (RCB) on cotton boll disease yielded yellowish lint during 2012. The population on RCB along with abiotic factors was recorded during three consecutive years i.e. 2012, 2013, and 2014. Along with population of RCB and abiotic factors, the number of unopened/opened cotton bolls (UOB), percent yellowish lint (YL) and whitish lint (WL) were also recorded. The data revealed that the population per plant of RCB remain 0.50 and 0.34 during years 2012, 2013 but increased during 2014 i.e. 3.21 per plant. The number of UOB were more i.e. 13.43% in 2012 with YL 76.30 and WL 23.70% when average maximum temperature 34.73◦C, minimum temperature 22.83◦C, RH 77.43% and 11.08 mm rainfall. Similarly in 2013 the number of UOB were less i.e. 0.34 per plant with YL 1.48 and WL 99.53 per plant when average maximum temperature 34.60◦C, minimum temperature 23.37◦C, RH 73.01% and 9.95 mm rainfall. During 2014 RCB population per plant was 3.22 with no UOB and YL was 0.00% and WL was 100% when average maximum temperature 23.70◦C, minimum temperature 23.18◦C, RH 71.67% and 4.55 mm rainfall. So it is concluded that the cotton bolls disease was more during 2012 due to more rainfall and more percent RH. The RCB may be the carrier of boll rot disease pathogen during more rainfall.

Keywords: red cotton bug, cotton, weather factors, years

Procedia PDF Downloads 329

Authors: Ansoné Human, Nantes Kirsten, Tanja Verster, Willem D. Schutte

Abstract:

Every year the telecommunications industry suffers huge losses due to fraud. Mobile fraud, or generally, telecommunications fraud is the utilisation of telecommunication products or services to acquire money illegally from or failing to pay a telecommunication company. A South African telecommunication operator developed two internal fraud scorecards to mitigate future risks of application fraud events. The scorecards aim to predict the likelihood of an application being fraudulent and surprise fraudsters before they surprise the telecommunication operator by identifying fraud at the time of application. The scorecards are utilised in the vetting process to evaluate the applicant in terms of the fraud risk the applicant would present to the telecommunication operator. Telecommunication providers can utilise these scorecards to profile customers, as well as isolate fraudulent and/or high-risk applicants. We provide the complete methodology utilised in the development of the scorecards. Furthermore, a Determination and Discrimination (DD) ratio is provided in the methodology to select the most influential variables from a group of related variables. Throughout the development of these scorecards, the following was revealed regarding fraudulent cases and fraudster behaviour within the telecommunications industry: Fraudsters typically target high-value handsets. Furthermore, debit order dates scheduled for the end of the month have the highest fraud probability. The fraudsters target specific stores. Applicants who acquire an expensive package and receive a medium-income, as well as applicants who obtain an expensive package and receive a high income, have higher fraud percentages. If one month prior to application, the status of an account is already in arrears (two months or more), the applicant has a high probability of fraud. The applicants with the highest average spend on calls have a higher probability of fraud. If the amount collected changes from month to month, the likelihood of fraud is higher. Lastly, young and middle-aged applicants have an increased probability of being targeted by fraudsters than other ages.

Keywords: application fraud scorecard, predictive modeling, regression, telecommunications

Procedia PDF Downloads 103

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 370

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 160

Authors: Lotfi Farah, Nadir Farah, Zaiem Kamar

Abstract:

This paper achieves a maximum power point tracking (MPPT) controller using a high-efficiency reduced rules neuro-fuzzy inference system (HE2RNF) for a 100 kW stand-alone photovoltaic (PV) system connected to the grid. The suggested HE2RNF based MPPT seeks the optimal duty cycle for the boost DC-DC converter, making the designed PV system working at the maximum power point (MPP), then transferring this power to the grid via a three levels voltage source converter (VSC). PV current variation and voltage variation are chosen as HE2RNF-based MPPT controller inputs. By using these inputs with the duty cycle as the only single output, a six rules ANFIS is generated. The high performance of the proposed HE2RNF numerically in the MATLAB/Simulink environment is shown. The 0.006% steady-state error, 0.006s of tracking time, and 0.088s of starting time prove the robustness of this six reduced rules against the widely used twenty-five ones.

Keywords: PV, MPPT, ANFIS, HE2RNF-based MPPT controller, VSC, grid connection

Procedia PDF Downloads 167

Authors: Suganiya Rama Rao, Yoon-Yen Yow, Thor-Seng Liew, Shyamala Ratnayeke

Abstract:

Invasive snails in the genus Pomacea have spread across Southeast Asia including Peninsular Malaysia. Apart from significant economic costs to wetland crops, very little is known about the snails’ effects on native species, and wetland function through their alteration of macrophyte communities. This study was conducted to establish diagnostic characteristics of Pomacea species in the Malaysian environment using genetic and morphological criteria. Snails were collected from eight localities in northern and central regions of Peninsular Malaysia. The mitochondrial COI gene of 52 adult snails was amplified and sequenced. Maximum likelihood analysis was used to analyse species identity and assess phylogenetic relationships among snails from different geographic locations. Shells of the two species were compared using geometric morphometric analysis and covariance analyses. Shell height accounted for most of the observed variation between P. canaliculata and P. maculata, with the latter possessing a smaller mean ratio of shell height: aperture height (p < 0.0001) and shell height to shell width (give p < 0.0001). Genomic and phylogenetic analysis demonstrated the presence of two monophyletic taxa, P. canaliculata and P. maculata, in Peninsular Malaysia samples. P. maculata co-occurred with P. canaliculata in 5 localities, but samples from 3 localities contained only P. canaliculata. This study is the first to confirm the presence of two of the most invasive species of Pomacea in Peninsular Malaysia using a genomic approach. P. canaliculata appears to be the more widespread species. Despite statistical differences, both quantitative and qualitative morphological characteristics demonstrate much interspecific overlap and intraspecific variability; thus morphology alone cannot reliably verify species identity. Molecular techniques for distinguishing between these two highly invasive Pomacea species are needed to understand their specific ecological niches and develop effective protocols for their management.

Keywords: Pomacea canaliculata, Pomacea maculata, invasive species, phylog enetic analysis, geometric morphometric analysis

Procedia PDF Downloads 246

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 112

Authors: Nguyen Thu Huong, Nguyen Quang Bau

Abstract:

The Hall Coefficient (HC) and the Magnetoresistance (MR) have been studied in two-dimensional systems. The HC and the MR in Rectangular Quantum Wire (RQW) subjected to a crossed DC electric field and magnetic field in the presence of a Strong Electromagnetic Wave (EMW) characterized by electric field are studied in this work. Using the quantum kinetic equation for electrons interacting with optical phonons, we obtain the analytic expressions for the HC and the MR with a dependence on magnetic field, EMW frequency, temperatures of systems and the length characteristic parameters of RQW. These expressions are different from those obtained for bulk semiconductors and cylindrical quantum wires. The analytical results are applied to GaAs/GaAs/Al. For this material, MR depends on the ratio of the EMW frequency to the cyclotron frequency. Indeed, MR reaches a minimum at the ratio 5/4, and when this ratio increases, it tends towards a saturation value. The HC can take negative or positive values. Each curve has one maximum and one minimum. When magnetic field increases, the HC is negative, achieves a minimum value and then increases suddenly to a maximum with a positive value. This phenomenon differs from the one observed in cylindrical quantum wire, which does not have maximum and minimum values.

Keywords: hall coefficient, rectangular quantum wires, electron-optical phonon interaction, quantum kinetic equation

Procedia PDF Downloads 466

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 91

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 304

Authors: Tasir Khan, Yejuan Wang

Abstract:

The study of extreme rainfall events is very important for flood management in river basins and the design of water conservancy infrastructure. Evaluation of quantiles of annual maximum rainfall (AMRF) is required in different environmental fields, agriculture operations, renewable energy sources, climatology, and the design of different structures. Therefore, the annual maximum rainfall (AMRF) was performed at different stations in Pakistan. Multiple probability distributions, log normal (LN), generalized extreme value (GEV), Gumbel (max), and Pearson type3 (P3) were used to find out the most appropriate distributions in different stations. The L moments method was used to evaluate the distribution parameters. Anderson darling test, Kolmogorov- Smirnov test, and chi-square test showed that two distributions, namely GUM (max) and LN, were the best appropriate distributions. The quantile estimate of a multi-parameter PD offers extreme rainfall through a specific location and is therefore important for decision-makers and planners who design and construct different structures. This result provides an indication of these multi-parameter distribution consequences for the study of sites and peak flow prediction and the design of hydrological maps. Therefore, this discovery can support hydraulic structure and flood management.

Keywords: RAMSE, multiple frequency analysis, annual maximum rainfall, L-moments

Procedia PDF Downloads 64

Authors: Mukesh Saran, Ashima Bagaria

Abstract:

Green nanotechnology is the most researched field in the current scenario. Herein we study the synthesis of Zinc and Ferrous nanoparticles using Moringa oleifera leaf extracts. Our protocol using established protocols heat treatment of plant extracts along with the solution of copper sulphate in the ratio of 1:1. The leaf extracts of Moringa oleifera were prepared in deionized water. Copper sulfate solution (1mM) was added to this, and the change in color of the solution was observed indicating the formation of Cu nanoparticles. The as biosynthesized Cu nanoparticles were characterized with the help of Scanning Electron Microscopy (SEM), and Fourier Transforms Infrared Spectroscopy (FTIR). It was observed that the leaf extracts of Moringa oleifera can reduce copper ions into copper nanoparticles within 8 to 10 min of reaction time. The method thus can be used for rapid and eco-friendly biosynthesis of stable copper nanoparticles. Further, we checked their antimicrobial and antioxidant potential, and it was observed that maximum antioxidant activity was observed for the particles prepared using the heating method. The maximum antibacterial activity was observed in Streptomyces grisveus particles and in Triochoderma Reesei for the maximum antifungal activity. At present, we are engaged in studying the anti-inflammatory activities of these as prepared nanoparticles.

Keywords: green synthesis, antibacterial, antioxidant, antifungal, anti-inflammatory

Procedia PDF Downloads 331

Authors: Aleh Meshyk, Anastasiya Vouchak

Abstract:

On the average snow covers Belarus for 75 days in the south-west and 125 days in the north-east. During the cold season snowpack often destroys due to thaws, especially at the beginning and end of winter. Over 50% of thawing days have a positive mean daily temperature, which results in complete snow melting. For instance, in December 10% of thaws occur at 4 С mean daily temperature. Stable snowpack lying for over a month forms in the north-east in the first decade of December but in the south-west in the third decade of December. The cover disappears in March: in the north-east in the last decade but in the south-west in the first decade. This research takes into account that precipitation falling during a cold season could be not only liquid and solid but also a mixed type (about 10-15 % a year). Another important feature of snow cover is its density. In Belarus, the density of freshly fallen snow ranges from 0.08-0.12 g/cm³ in the north-east to 0.12-0.17 g/cm³ in the south-west. Over time, snow settles under its weight and after melting and refreezing. Averaged annual density of snow at the end of January is 0.23-0.28 g/сm³, in February – 0.25-0.30 g/сm³, in March – 0.29-0.36 g/сm³. Sometimes it can be over 0.50 g/сm³ if the snow melts too fast. The density of melting snow saturated with water can reach 0.80 g/сm³. Average maximum of snow depth is 15-33 cm: minimum is in Brest, maximum is in Lyntupy. Maximum registered snow depth ranges within 40-72 cm. The water content in snowpack, as well as its depth and density, reaches its maximum in the second half of February – beginning of March. Spatial distribution of the amount of liquid in snow corresponds to the trend described above, i.e. it increases in the direction from south-west to north-east and on the highlands. Average annual value of maximum water content in snow ranges from 35 mm in the south-west to 80-100 mm in the north-east. The water content in snow is over 80 mm on the central Belarusian highland. In certain years it exceeds 2-3 times the average annual values. Moderate water content in snow (80-95 mm) is characteristic of western highlands. Maximum water content in snow varies over the country from 107 mm (Brest) to 207 mm (Novogrudok). Maximum water content in snow varies significantly in time (in years), which is confirmed by high variation coefficient (Cv). Maximums (0.62-0.69) are in the south and south-west of Belarus. Minimums (0.42-0.46) are in central and north-eastern Belarus where snow cover is more stable. Since 1987 most gauge stations in Belarus have observed a trend to a decrease in water content in snow. It is confirmed by the research. The biggest snow cover forms on the highlands in central and north-eastern Belarus. Novogrudok, Minsk, Volkovysk, and Sventayny highlands are a natural orographic barrier which prevents snow-bringing air masses from penetrating inside the country. The research is based on data from gauge stations in Belarus registered from 1944 to 2014.

Keywords: density, depth, snow, water content in snow

Procedia PDF Downloads 146

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 182

Authors: Kulin Dave, Kapil Mohan

Abstract:

Earthquakes are considered to be the most destructive rapid-onset disasters human beings are exposed to. The amount of loss it brings in is sufficient to take careful considerations for designing of structures and facilities. Seismic Hazard Analysis is one such tool which can be used for earthquake resistant design. Ground Response Analysis is one of the most crucial and decisive steps for seismic hazard analysis. Rapar district of Kutch, Gujarat falls in Zone 5 of earthquake zone map of India and thus has high seismicity because of which it is selected for analysis. In total 8 bore-log data were studied at different locations in and around Rapar district. Different soil engineering properties were analyzed and relevant empirical correlations were used to calculate maximum shear modulus (Gmax) and shear wave velocity (Vs) for the soil layers. The soil was modeled using Pressure-Dependent Modified Kodner Zelasko (MKZ) model and the reference curve used for fitting was Seed and Idriss (1970) for sand and Darendeli (2001) for clay. Both Equivalent linear (EL), as well as Non-linear (NL) ground response analysis, has been carried out with Masing Hysteretic Re/Unloading formulation for comparison. Commercially available DEEPSOIL v. 7.0 software is used for this analysis. In this study an attempt is made to quantify ground response regarding generated acceleration time-history at top of the soil column, Response spectra calculation at 5 % damping and Fourier amplitude spectrum calculation. Moreover, the variation of Peak Ground Acceleration (PGA), Maximum Displacement, Maximum Strain (in %), Maximum Stress Ratio, Mobilized Shear Stress with depth is also calculated. From the study, PGA values estimated in rocky strata are nearly same as bedrock motion and marginal amplification is observed in sandy silt and silty clays by both analyses. The NL analysis gives conservative results of maximum displacement as compared to EL analysis. Maximum strain predicted by both studies is very close to each other. And overall NL analysis is more efficient and realistic because it follows the actual hyperbolic stress-strain relationship, considers stiffness degradation and mobilizes stresses generated due to pore water pressure.

Keywords: DEEPSOIL v 7.0, ground response analysis, pressure-dependent modified Kodner Zelasko model, MKZ model, response spectra, shear wave velocity

Procedia PDF Downloads 123

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 496

Authors: ِAbdallah A. A. Shaheen

Abstract:

Gaza Strip faces economic and political issues such as conflict, siege and urbanization; all these have led to an increase in the air pollution over Gaza Strip. In this study, Particulate matter 10 (PM10) concentration over Gaza Strip has been estimated by Landsat Thematic Mapper (TM) and Landsat Enhanced Thematic Mapper Plus (ETM+) data, based on a multispectral algorithm. Simultaneously, in-situ measurements for the corresponding particulate are acquired for selected time period. Landsat and ground data for eleven years are used to develop the algorithm while four years data (2002, 2006, 2010 and 2014) have been used to validate the results of algorithm. The developed algorithm gives highest regression, R coefficient value i.e. 0.86; RMSE value as 9.71 µg/m³; P values as 0. Average validation of algorithm show that calculated PM10 strongly correlates with measured PM10, indicating high efficiency of algorithm for the mapping of PM10 concentration during the years 2000 to 2014. Overall results show increase in minimum, maximum and average yearly PM10 concentrations, also presents similar trend over urban area. The rate of urbanization has been evaluated by supervised classification of the Landsat image. Urban sprawl from year 2000 to 2014 results in a high concentration of PM10 in the study area.

Keywords: PM10, landsat, atmospheric reflectance, Gaza strip, urbanization

Procedia PDF Downloads 236