Search results for: weights identify

Authors: Farzad Sharifi, Raziyeh Shamsi

Abstract:

In this paper, we obtain the projection of inefficient units in data envelopment analysis (DEA) in the case of stochastic inputs and outputs using the multi-objective programming (MOP) structure. In some problems, the inputs might be stochastic while the outputs are deterministic, and vice versa. In such cases, we propose molti-objective DEA-R model, because in some cases (e.g., when unnecessary and irrational weights by the BCC model reduces the efficiency score), an efficient DMU is introduced as inefficient by the BCC model, whereas the DMU is considered efficient by the DEA-R model. In some other case, only the ratio of stochastic data may be available (e.g; the ratio of stochastic inputs to stochastic outputs). Thus, we provide multi objective DEA model without explicit outputs and prove that in-put oriented MOP DEA-R model in the invariable return to scale case can be replacing by MOP- DEA model without explicit outputs in the variable return to scale and vice versa. Using the interactive methods for solving the proposed model, yields a projection corresponding to the viewpoint of the DM and the analyst, which is nearer to reality and more practical. Finally, an application is provided.

Keywords: DEA, MOLP, STOCHASTIC, DEA-R

Procedia PDF Downloads 376

Authors: Rosida A. Razak, Mohamad Shanudin Zakaria

Abstract:

The fundamental issues in ICT Governance (ICTG) implementation for Malaysian Public Sector (MPS) is how ICT be applied to support improvements in productivity, management effectiveness and the quality of services offered to its citizens. Our main concern is to develop and adopt a common definition and framework to illustrate how ICTG can be used to better align ICT with government’s operations and strategic focus. In particular, we want to identify and categorize factors that drive a successful ICTG process. This paper presents the results of an exploratory study to identify, validate and refine such Critical Success Factors (CSFs) and confirmed seven CSFs and nineteen sub-factors as influential factors that fit MPS after further validated and refined. The Delphi method applied in validation and refining process before being endorsed as appropriate for MPS. The identified CSFs reflect the focus areas that need to be considered strategically to strengthen ICT Governance implementation and ensure business success.

Keywords: IT governance, critical success factors, productivity, CSFs

Procedia PDF Downloads 247

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

Most well-known classifiers, including the decision tree algorithm, can make predictions on balanced datasets efficiently. However, the decision tree algorithm tends to be biased towards imbalanced datasets because of the skewness of the distribution of such datasets. To overcome this problem, this study proposes a weighted decision tree algorithm that aims to remove the bias toward the majority class and prevents the reduction of majority observations in imbalance datasets classification. The proposed weighted decision tree algorithm was tested on three imbalanced datasets- cancer dataset, german credit dataset, and banknote dataset. The specificity, sensitivity, and accuracy metrics were used to evaluate the performance of the proposed decision tree algorithm on the datasets. The evaluation results show that for some of the weights of our proposed decision tree, the specificity, sensitivity, and accuracy metrics gave better results compared to that of the ID3 decision tree and decision tree induced with minority entropy for all three datasets.

Keywords: data mining, decision tree, classification, imbalance dataset

Procedia PDF Downloads 94

Authors: Ali Asghar Saki, Sayed Ali Hosseini Siyar, Abbass Ashoori

Abstract:

This study was conducted to evaluate the effect of Echinacea purpurea on the expression of cyclooxygenase-2 (COX-2), interleukin-17F (IL-17F) in seven-day-old broiler chickens. Four groups were fed with concentration of 0 g/kg, 5 g/kg, 10 g/kg and 20 g/kg from the root of E. purpurea in the basal diet and two other groups were only fed with the basal diet for 21 days. At the 28^th day, lipopolysaccharide (LPS, 2 mg/kg diet) was injected in four groups and the basal diet group was injected by saline as control. The chickens’ spleen RNA expression was measured for the COX-2 and IL-17F genes by Real-Time PCR. The results have shown that chickens which were fed E. purpurea had a lower COX-2 and IL-17F mRNA expression. The chickens who have received LPS only, lymphocyte was lower than other treatments. Vital organ weights were not significantly different, but body weight loss was recovered by dietary herbs inclusion. The results of this study have shown the positive effect of an anti-inflammatory herb to prevent the undesirable effect of inflammation.

Keywords: broiler chickens, Echinacea purporea, gene expression, lipopolysaccharide

Procedia PDF Downloads 200

Authors: Saad M. Howladar, Mike Dennett

Abstract:

The effect of salinity (0-200 mMNaCl) on wheat growth (leaf and tiller numbers, and fresh and dry weights) underseed soaking (6 and 24 hs) insalicylic acid (SA) was investigated. The impact of salinity was less pronounced in salt tolerant cultivars (Sakha 93 and S24) than Paragon and S24. Chlorophyll content was increased as a response to salinity stress. It was raised in 100 mMNaCl more than 200 mMNaCl. The same trend was found in 24 hs soaking, except chlorophyll content in Paragon and S24 under 200 mMNaCl was more than 100 mMNaCl. SA application induced a positive effect on growth parameters in some cultivars, particularly Paragon under saline and non-saline condition. Soaking for 6 hs was more effective than 24 hs soaking, especially in Paragon and Sakha 93. SA supply caused a slight effect on chlorophyll content but this was not significant and there was no significant difference between both soaking hs. The effect of SA on growth parameters and chlorophyll content depends on cultivar genotype and SA concentration.

Keywords: salinity, salicylic acid, growth parameters, chlorophyll content, wheat cultivars

Procedia PDF Downloads 517

Authors: A. A. Omonori, K. T. Alade, A. F. Lawal

Abstract:

This research was conducted to identify the causes of project abandonment in Nigeria and the effect it has on the host community. The aim of the research was to identify the causes and effects of project failure and abandonment. Project abandonment is a major course of concern in the country as different projects fail and are abandoned at various levels. These projects do not fulfill the purpose for which they were initiated. This is the absolute definition of failure and hence the selection of the Ajaokuta Steel Project as an interesting case study and a typical example of project failure and abandonment. This has been done by conducting field study through the administration of questionnaires. This study was carried out on the Ajaokuta Steel Project to investigate the causes of the abandonment of the project and the effects it has had on the people of Ajaokuta community. Qualitative method of data analysis was used to analyze the findings through frequency tables and ranking. This study brought to light the major factors that led to the abandonment of the Ajaokuta Steel Project. The effects the abandonment of the project has had on the immediate community were identified and recommendations made to prevent the menace of Project abandonment.

Keywords: abandonment, case-study, Nigeria, project

Procedia PDF Downloads 320

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 216

Authors: Elizabeth Stojanovski

Abstract:

Associations between life events and various forms of cancers have been identified. The purpose of a recent random-effects meta-analysis was to identify studies that examined the association between adverse events associated with changes to financial status including decreased income and breast cancer risk. The same association was studied in four separate studies which displayed traits that were not consistent between studies such as the study design, location and time frame. It was of interest to pool information from various studies to help identify characteristics that differentiated study results. Two random-effects Bayesian meta-analysis models are proposed to combine the reported estimates of the described studies. The proposed models allow major sources of variation to be taken into account, including study level characteristics, between study variance, and within study variance and illustrate the ease with which uncertainty can be incorporated using a hierarchical Bayesian modelling approach.

Keywords: random-effects, meta-analysis, Bayesian, variation

Procedia PDF Downloads 130

Authors: Mashood C., Abdul Vahid K., Ashique C. K.

Abstract:

The technology is growing beyond human expectation. Internet is one of very sophisticated product of the information technology. It has various advantages like connecting the world, simplifying the difficult tasks done in past etc. Simultaneously it has demerits also; that is lack of authenticity and internet addiction. To find out the problems of internet addiction, a study conducted among the Postgraduate students of Pondicherry University and collected 454 samples. The study strictly focused to identify the internet addiction among students, influence and interdependence of personality on internet addiction among first years and second years. To evaluate this, we used two major analysis, these are Confirmatory Factor Analysis (CFA) to predict the internet addiction with the observed data and Logistic Regression to identify the difference between first years and second years in the case of internet addiction. Before applying to the core analysis, the data applied to some preliminary tests to check the model fit. The empirical findings shows that , the students of Pondicherry University are very much addicted to the internet, But there is no such huge difference between first years and second years in case of internet addiction.

Keywords: internet addiction, students, Pondicherry University, empirical study

Procedia PDF Downloads 436

Authors: Petar Dobrev

Abstract:

There is no agreed-upon definition of firm quality. While profitability and stock performance often qualify as popular proxies of quality, in this project, we aim to identify quality without relying on a firm’s financial statements or stock returns as selection criteria. Instead, we use firm-level data on management practices across small to medium-sized U.S. manufacturing firms from the World Management Survey (WMS) to measure firm quality. Each firm in the WMS dataset is assigned a mean management score from 0 to 5, with higher scores identifying better-managed firms. This management score serves as our proxy for firm quality and is the sole criteria we use to separate firms into portfolios comprised of high-quality and low-quality firms. We define high-quality (low-quality) firms as those firms with a management score of one standard deviation above (below) the mean. To study whether this proxy for firm quality can identify better-performing firms, we link this data to Compustat and The Center for Research in Security Prices (CRSP) to obtain firm-level data on financial performance and monthly stock returns, respectively. We find that from 1999 to 2019 (our sample data period), firms in the high-quality portfolio are consistently more profitable — higher operating profitability and return on equity compared to low-quality firms. In addition, high-quality firms also exhibit a lower risk of bankruptcy — a higher Altman Z-score. Next, we test whether the stocks of the firms in the high-quality portfolio earn superior risk-adjusted excess returns. We regress the monthly excess returns on each portfolio on the Fama-French 3-factor, 4-factor, and 5-factor models, the betting-against-beta factor, and the quality-minus-junk factor. We find no statistically significant differences in excess returns between both portfolios, suggesting that stocks of high-quality (well managed) firms do not earn superior risk-adjusted returns compared to low-quality (poorly managed) firms. In short, our proxy for firm quality, the WMS management score, can identify firms with superior financial performance (higher profitability and reduced risk of bankruptcy). However, our management proxy cannot identify stocks that earn superior risk-adjusted returns, suggesting no statistically significant relationship between managerial quality and stock performance.

Keywords: excess stock returns, management, profitability, quality

Procedia PDF Downloads 69

Authors: Gopi Ram, Durbadal Mandal, Rajib Kar, Sakti Prasad Ghoshal

Abstract:

A design problem of non-uniform circular antenna arrays for maximum reduction of both the side lobe level (SLL) and first null beam width (FNBW) is dealt with. This problem is modeled as a simple optimization problem. The method of Firefly algorithm (FFA) is used to determine an optimal set of current excitation weights and antenna inter-element separations that provide radiation pattern with maximum SLL reduction and much improvement on FNBW as well. Circular array antenna laid on x-y plane is assumed. FFA is applied on circular arrays of 8-, 10-, and 12- elements. Various simulation results are presented and hence performances of side lobe and FNBW are analyzed. Experimental results show considerable reductions of both the SLL and FNBW with respect to those of the uniform case and some standard algorithms GA, PSO, and SA applied to the same problem.

Keywords: circular arrays, first null beam width, side lobe level, FFA

Procedia PDF Downloads 225

Authors: Zikiou Nadia, Lahdir Mourad, Ameur Soltane

Abstract:

In this paper, we propose an effective method for image compression based on SVM Regression (SVR), with three different kernels, and biorthogonal 2D Discrete Wavelet Transform. SVM regression could learn dependency from training data and compressed using fewer training points (support vectors) to represent the original data and eliminate the redundancy. Biorthogonal wavelet has been used to transform the image and the coefficients acquired are then trained with different kernels SVM (Gaussian, Polynomial, and Linear). Run-length and Arithmetic coders are used to encode the support vectors and its corresponding weights, obtained from the SVM regression. The peak signal noise ratio (PSNR) and their compression ratios of several test images, compressed with our algorithm, with different kernels are presented. Compared with other kernels, Gaussian kernel achieves better image quality. Experimental results show that the compression performance of our method gains much improvement.

Keywords: image compression, 2D discrete wavelet transform (DWT-2D), support vector regression (SVR), SVM Kernels, run-length, arithmetic coding

Procedia PDF Downloads 352

Authors: Ranajoy Bhattcharyya

Abstract:

We estimate international product cycles as shifting product spaces by using 1976 to 2010 UN Comtrade data on all differentiated tradable products in all countries. We use a product space approach to identify the representative product baskets of high-, middle and low-income countries and then use these baskets to identify the patterns of change in comparative advantage of countries over time. We find evidence of a product cycle in two senses: First, high-, middle- and low-income countries differ in comparative advantage, and high-income products migrate to the middle-income basket. A similar pattern is observed for middle- and low-income countries. Our estimation of the lag shows that middle-income countries tend to quickly take up the products of high-income countries, but low-income countries take a longer time absorbing these products. Thus, the gap between low- and middle-income countries is considerably higher than that between middle- and high-income nations.

Keywords: product cycle, comparative advantage, representative product basket, ex-post data

Procedia PDF Downloads 380

Authors: Rafael Felipe Guatura da Silva, José Luis Gomes da Silva, Luiz Antonio, Ferreira Perrone de Brito

Abstract:

Noise can cause serious damage to human health, such as hearing loss, stress, irritability, fatigue, and others. Aviation is a place where your entire process should be work out with the utmost attention and commitment of human resources, thus the need to study the effects of noise in this sector, as aeronautical noise levels are high. This study aimed to evaluate the impact of noise pollution on the performance of professionals regarding the fatigue generated by aeronautical noise and time to noise exposure. The methodology used consists of measurements of sound pressure levels at 42 points of the aerodrome. The selected points are located inside the hangars and outside the airfield hangars. All points chosen are close to the professionals' work areas, seeking to identify the sound pressure levels to which they submitted. The other part of the research used the principle on the application of a self-report questionnaire to a sample of 207 people working inside the aerodrome. The 207 professionals surveyed consist of aircraft mechanics, pilots, maintenance managers, and administrative professionals. The questionnaire was intended to evaluate the knowledge that professionals have about health risks caused by sound exposure as well as to identify diseases that professionals have, and that may be associated with exposure to high levels of sound pressure. Preliminary results identify points with sound pressure levels of up to 91.7 dB, thus highlighting the need for the use of personal protective equipment that reduces noise exposure. It was also identified a large number of professionals who are bothered by the sound exposure and approximately 25% of professionals interviewed reported having a hearing disorder.

Keywords: aeronautical noise, fatigue, noise and health, noise management

Procedia PDF Downloads 118

Authors: Marcos Bosques-Perez, Walter Izquierdo, Harold Martin, Liangdon Deng, Josue Rodriguez, Thony Yan, Mercedes Cabrerizo, Armando Barreto, Naphtali Rishe, Malek Adjouadi

Abstract:

Aerial imagery is a powerful tool when it comes to analyzing temporal changes in ecosystems and extracting valuable information from the observed scene. It allows us to identify and assess various elements such as objects, structures, textures, waterways, and shadows. To extract meaningful information, multispectral cameras capture data across different wavelength bands of the electromagnetic spectrum. In this study, the collected multispectral aerial images were subjected to principal component analysis (PCA) to identify independent and uncorrelated components or features that extend beyond the visible spectrum captured in standard RGB images. The results demonstrate that these principal components contain unique characteristics specific to certain wavebands, enabling effective object identification and image segmentation.

Keywords: big data, image processing, multispectral, principal component analysis

Procedia PDF Downloads 131

Authors: Anum Ali, Kashaf ad Dooja, Asif Saleem

Abstract:

The future smart cities trend will be towards Internet of Things (IoT); IoT creates dynamic connections in a ubiquitous manner. Smart cities offer ease and flexibility for daily life matters. By using small devices that are connected to cloud servers based on IoT, network traffic between these devices is growing exponentially, whose security is a concerned issue, since ratio of cyber attack may make the network traffic vulnerable. This paper discusses the latest machine learning approaches in related work further to tackle the increasing rate of cyber attacks, machine learning algorithm is applied to IoT-based network traffic data. The proposed algorithm train itself on data and identify different sections of devices interaction by using supervised learning which is considered as a classifier related to a specific IoT device class. The simulation results clearly identify the attacks and produce fewer false detections.

Keywords: IoT, traffic security, deep learning, classification

Procedia PDF Downloads 123

Authors: Hazem Al-Mofleh, John Daniels, Joseph McKean

Abstract:

Within geostatistics research, effective estimation of the variogram points has been examined, particularly in developing robust alternatives. The parametric fit of these variogram points which eventually defines the kriging weights, however, has not received the same attention from a robust perspective. This paper proposes the use of the non-linear Wilcoxon norm over weighted non-linear least squares as a robust variogram fitting alternative. First, we introduce the concept of variogram estimation and fitting. Then, as an alternative to non-linear weighted least squares, we discuss the non-linear Wilcoxon estimator. Next, the robustness properties of the non-linear Wilcoxon are demonstrated using a contaminated spatial data set. Finally, under simulated conditions, increasing levels of contaminated spatial processes have their variograms points estimated and fit. In the fitting of these variogram points, both non-linear Weighted Least Squares and non-linear Wilcoxon fits are examined for efficiency. At all levels of contamination (including 0%), using a robust estimation and robust fitting procedure, the non-weighted Wilcoxon outperforms weighted Least Squares.

Keywords: non-linear wilcoxon, robust estimation, variogram estimation, wilcoxon norm

Procedia PDF Downloads 428

Authors: Giulio Rosati, Luciano Sappia, Rossana Madrid, Noemi Rozlòsnik

Abstract:

The addition of PEG of different molecular weights has important effects on the physical, electrical and electrochemical properties of iron(III)-tosylate doped PEDOT. This particular polymer can be easily spin coated over plastic discs, optimizing thickness and uniformity of the PEDOT-PEG films. The conductivity and morphological analysis of the hybrid PEDOT-PEG polymer by 4-point probe (4PP), 12-point probe (12PP), and conductive AFM (C-AFM) show strong effects of the PEG doping. Moreover, the conductive films kinetics at the nanoscale, in response to different bias voltages, change radically depending on the PEG molecular weight. The hybrid conductive films show also interesting electrochemical properties, making the PEDOT PEG doping appealing for biosensing applications both for EIS-based and amperometric affinity/catalytic biosensors.

Keywords: atomic force microscopy, biosensors, four-point probe, nano-films, PEDOT

Procedia PDF Downloads 309

Authors: Vadivel Ayyasamy

Abstract:

The present approach deals with the identification of Emotions and classification of Emotional patterns at Phrase-level with respect to Positive and Negative Orientation. The proposed approach considers emotion triggered terms, its co-occurrence terms and also associated sentences for recognizing emotions. The proposed approach uses Part of Speech Tagging and Emotion Actifiers for classification. Here sentence patterns are broken into phrases and Neuro-Fuzzy model is used to classify which results in 16 patterns of emotional phrases. Suitable intensities are assigned for capturing the degree of emotion contents that exist in semantics of patterns. These emotional phrases are assigned weights which supports in deciding the Positive and Negative Orientation of emotions. The approach uses web documents for experimental purpose and the proposed classification approach performs well and achieves good F-Scores.

Keywords: emotions, sentences, phrases, classification, patterns, fuzzy, positive orientation, negative orientation

Procedia PDF Downloads 350

Authors: Sana Ridene, Soumaya Sayeb, Houda Helali, Mohammed Ben Hassen

Abstract:

Nonwoven structures have a range of applications which include Medical, filtration, geotextile and recently this unconventional fabric is finding a niche in fashion apparel. In this paper, a modified form of Vangheluwe rheological model is used to describe the mechanical behavior of nonwovens fabrics in uniaxial tension. This model is an association in parallel of three Maxwell elements characterized by damping coefficients η1, η2 and η3 and E1, E2, E3 elastic modulus and a nonlinear spring C. The model is verified experimentally with two types of nonwovens (50% viscose /50% Polyester) and (40% viscose/60% Polyester) and a range of three square weights values. Comparative analysis of the theoretical model and the experimental results of tensile test proofs a high correlation between them. The proposed model can fairly well replicate the behavior of nonwoven fabrics during relaxation and sample traction. This allowed us to predict the mechanical behavior in tension and relaxation of fabrics starting only from their technical parameters (composition and weight).

Keywords: mechanical behavior, tensile strength, relaxation, rheological model

Procedia PDF Downloads 379

Authors: Krishna Pal Singh, Shailendra Kumar Gupta, Olaf Wolkenhauer

Abstract:

Background: Our study aimed to identify common genes and potential targets across the four diseases, which include rheumatoid arthritis, melanoma metastasis, ulcerative colitis, and Crohn’s disease. We used a network and systems biology approach to identify the hub gene, which can act as a potential target for all four disease conditions. The regulatory network was extracted from the PPI using the MCODE module present in Cytoscape. Our objective was to investigate the significance of hub genes in these diseases using gene ontology and KEGG pathway enrichment analysis. Methods: Our methodology involved collecting disease gene-related information from DisGeNET databases and performing protein-protein interaction (PPI) network and core genes screening. We then conducted gene ontology and KEGG pathway enrichment analysis. Results: We found that IL6 plays a critical role in all disease conditions and in different pathways that can be associated with the development of all four diseases. Conclusions: The theoretical importance of our research is that we employed various systems and structural biology techniques to identify a crucial protein that could serve as a promising target for treating multiple diseases. Our data collection and analysis procedures involved rigorous scrutiny, ensuring high-quality results. Our conclusion is that IL6 plays a significant role in all four diseases, and it can act as a potential target for treating them. Our findings may have important implications for the development of novel therapeutic interventions for these diseases.

Keywords: melanoma metastasis, rheumatoid arthritis, inflammatory bowel diseases, integrated bioinformatics analysis

Procedia PDF Downloads 54

Authors: Ahmad Alsolami, Darren Mundy, Manuel Hernandez-Perez

Abstract:

Social media networks, such as Twitter, offer the perfect opportunity to either positively or negatively affect political attitudes on large audiences. The existence of influential users who have developed a reputation for their knowledge and experience of specific topics is a major factor contributing to this impact. Therefore, knowledge of the mechanisms to identify influential users on social media is vital for understanding their effect on their audience. The concept of the influential user is related to the concept of opinion leaders' to indicate that ideas first flow from mass media to opinion leaders and then to the rest of the population. Hence, the objective of this research was to provide reliable and accurate structural mechanisms to identify influential users, which could be applied to different platforms, places, and subjects. Twitter was selected as the platform of interest, and Saudi Arabia as the context for the investigation. These were selected because Saudi Arabia has a large number of Twitter users, some of whom are considerably active in setting agendas and disseminating ideas. The study considered the scientific methods that have been used to identify public opinion leaders before, utilizing metrics software on Twitter. The key findings propose multiple novel metrics to compare Twitter influencers, including the number of followers, social authority and the use of political hashtags, and four secondary filtering measures. Thus, using ratio and percentage calculations to classify the most influential users, Twitter accounts were filtered, analyzed and included. The structured approach is used as a mechanism to explore the top ten influencers on Twitter from the political domain in Saudi Arabia.

Keywords: Twitter, influencers, structured mechanism, Saudi Arabia

Procedia PDF Downloads 94

Authors: Hilalah Alturkistani, Alaa AlFaadhel, Nora AlJahani, Fatiha Djebbar

Abstract:

Cloud computing is one of the most widely used technology which provides opportunities and services to government entities, large companies, and standard users. However, cybersecurity risk management studies of cloud computing and resiliency approaches are lacking. This paper proposes resilient cloud cybersecurity risk assessment and management tailored specifically, to Dropbox with two approaches:1) technical-based solution motivated by a cybersecurity risk assessment of cloud services, and 2)a target personnel-based solution guided by cybersecurity-related survey among employees to identify their knowledge that qualifies them withstand to any cyberattack. The proposed work attempts to identify cloud vulnerabilities, assess threats and detect high risk components, to finally propose appropriate safeguards such as failure predicting and removing, redundancy or load balancing techniques for quick recovery and return to pre-attack state if failure happens.

Keywords: cybersecurity risk management plan, resilient cloud computing, cyberattacks, cybersecurity risk assessment

Procedia PDF Downloads 105

Authors: Nihal Murali, Kunal Gupta, Surekha Bhanot

Abstract:

Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without any hand-engineered features or domain heuristics. In this paper, the standard control problem of line following robot was used as a test-bed, and an ANN controller for the robot was trained on images from a live video feed using Q-learning. A virtual agent was first trained in simulation environment and then deployed onto a robot’s hardware. The robot successfully learns to traverse a wide range of curves and displays excellent generalization ability. Qualitative analysis of the evolution of policies, performance and weights of the network provide insights into the nature and convergence of the learning algorithm.

Keywords: artificial neural networks, q-learning, reinforcement learning, robot learning

Procedia PDF Downloads 349

Authors: Bisola Olumegbon

Abstract:

Globally, there were about 229 million cases of malaria in 2022. The sub-Saharan African region accounted for 92% of the reported cases and 94% of deaths. Nigeria had the highest number of malaria cases and deaths, representing 27% of global cases. This scholarly project was a case study guided by the political determinants of health. Triangulation of data using thematic analysis was used to identify the political determinants of malaria in Nigeria and to understand how the concept of interaction contributes to the persistence of the disease. The analysis involved a deductive and inductive approach based on the literature review and the evidence of political determinants gathered in the data. Participants’ in-depth interviews were used to collect data from frontline personnel. Data triangulation was done using thematic analysis, a method used to identify patterns and themes in qualitative data. The study findings revealed a correlation between political determinants of health and malaria management efforts in Nigeria. Some influencing factors included voting challenges, inadequate funding, lack of health priority from the government, noncompliance among patients, and hurdles to effective communication. The findings suggest a need to deliberately increase dedication to the political agenda, provide sufficient financial resources, enhance communication, and active community involvement to address the persistent malaria endemic effectively. Further study is recommended to identify interventions to address identified factors of political determinants of health to reduce malaria in Nigeria. Such intervention must involve collaboration with diverse stakeholders such as policymakers, healthcare professionals, community leaders, and researchers.

Keywords: malaria, malaria management, health worker, stakeholders, political determinant of health

Procedia PDF Downloads 33

Authors: Tyler Gill, Sophia Daniels

Abstract:

The paper examines how accessing the spatial-temporal constrains of data will help inform policymakers and law enforcement officials. The authors utilize Chicago crime data from 2006-2016 to demonstrate how the Emerging Hot Spot Tool is an ideal hot spot clustering approach to analyze crime data. Traditional approaches include density maps or creating a spatial weights matrix to include the spatial-temporal constrains. This new approach utilizes a space-time implementation of the Getis-Ord Gi* statistic to visualize the data more quickly to make better decisions. The research will help complement socio-cultural research to find key patterns to help frame future policies and evaluate the implementation of prior strategies. Through this analysis, homicide trends and patterns are found more effectively and recommendations for use by non-traditional users of GIS are offered for real life implementation.

Keywords: crime mapping, emerging hot spot analysis, Getis-Ord Gi*, spatial-temporal analysis

Procedia PDF Downloads 217

Authors: N. W. U. D. Chathurani, Shlomo Geva, Vinod Chandran, Proboda Rajapaksha

Abstract:

Selecting an appropriate image representation is the most important factor in implementing an effective Content-Based Image Retrieval (CBIR) system. This paper presents a multi-feature fusion approach for efficient CBIR, based on the distance distribution of features and relative feature weights at the time of query processing. It is a simple yet effective approach, which is free from the effect of features' dimensions, ranges, internal feature normalization and the distance measure. This approach can easily be adopted in any feature combination to improve retrieval quality. The proposed approach is empirically evaluated using two benchmark datasets for image classification (a subset of the Corel dataset and Oliva and Torralba) and compared with existing approaches. The performance of the proposed approach is confirmed with the significantly improved performance in comparison with the independently evaluated baseline of the previously proposed feature fusion approaches.

Keywords: feature fusion, image retrieval, membership function, normalization

Procedia PDF Downloads 321

Authors: Ranjith Menon, Abathar Aladi, Hans-Christean Nahser, Maneesh Bhojak, Sacha Nevin, Paul Eldridge

Abstract:

Background: Spontaneous subarachnoid haemorrhage (SAH) accounts for approximately 5% of all strokes. Patients with spontaneous SAH (as shown by CT or lumbar puncture) undergo investigations to identify or exclude an underlying structural cause, typically cerebral aneurysm. However in 10 - 20% of cases, no structural cause is found. This includes more than one imaging modality (intracranial MRA, CTA, 4DCTA and/or DSA) and in some spinal MRI. Objective: To determine; 1) If an underlying structural or vascular cause can be identified in non-aneurysmal SAH patients by comparing different imaging modalities at presentation and at follow-up. 2) If MRI spine in patients with non-aneurysmal SAH reveals an underlying SAH cause. 3)The functional outcome at discharge. Results: We performed a retrospective analysis of all non-traumatic SAH patients admitted to the Walton centre from January 2009 to December 2015. There were 1457 patients with non-traumatic SAH admitted to the Walton centre of whom 21.8% (n=300) patients were diagnosed with non-aneurysmal SAH. Males were 65.6% and females were 43.3%. The presenting symptoms were sudden onset headache (93.6%), the focal neurological deficit (12%), loss of consciousness (10.6%) and others (6%). About 285 patients received 2 modalities of imaging (CTA & DSA), 192 received 3 modalities of imaging (CTA, MRA & DSA) and 137 received MRI spine (51/137 whole spine). The modified Rankin Score at discharge were: mRS 0 = 292 (97.33%), mRS 1-2 = 6, mRS 6 = 1 (cardiac arrest in IHD patient) and unknown in 1. Follow-up imaging at 3 to 6 months in 190 (63.3%) patients did not identify an underlying cause. Conclusion: This retrospective analysis concludes that non-aneurysmal SAH has a good functional outcome. A single imaging modality (CTA (4DCTA) or MRA or DSA) was adequate to exclude an underlying cause of SAH and a delayed imaging failed to identify a cause. Routinely performing MRI spine in this group of patients appears not to be necessary according to this evidence.

Keywords: stroke, non-aneurysmal subarachnoid haemorrhage, neuroimaging, modified rankin score

Procedia PDF Downloads 228

Authors: Osiris Terry, Kenneth Hopkinson, Laura Humphrey

Abstract:

Systematic resampling is the most popularly used resampling method in particle filters. This paper seeks to further the understanding of systematic resampling by defining a formula made up of variables from the sampling equation and the particle weights. The formula is then verified via SPARK, a software verification language. The verified systematic resampling formula states that the minimum/maximum number of possible samples taken of a particle is equal to the floor/ceiling value of particle weight divided by the sampling interval, respectively. This allows for the creation of a randomness spectrum that each resampling method can fall within. Methods on the lower end, e.g., systematic resampling, have less randomness and, thus, are quicker to reach an estimate. Although lower randomness allows for error by having a larger bias towards the size of the weight, having this bias creates vulnerabilities to the noise in the environment, e.g., jamming. Conclusively, this is the first step in characterizing each resampling method. This will allow target-tracking engineers to pick the best resampling method for their environment instead of choosing the most popularly used one.

Keywords: SPARK, software verification, resampling, systematic resampling, particle filter, tracking

Procedia PDF Downloads 51

Authors: Yuhong Zhang, Dan Lu, Chenyang Bu, Peipei Li, Kui Yu, Xindong Wu

Abstract:

The Cross-Lingual Entity Alignment (CLEA) task aims to find the aligned entities that refer to the same identity from two knowledge graphs (KGs) in different languages. It is an effective way to enhance the performance of data mining for KGs with scarce resources. In real-world applications, the neighborhood structures of the same entities in different KGs tend to be non-isomorphic, which makes the representation of entities contain diverse semantic information and then poses a great challenge for CLEA. In this paper, we try to address this challenge from two perspectives. On the one hand, the cross-KG relation completion rules are designed with the alignment constraint of entities and relations to improve the topology isomorphism of two KGs. On the other hand, a representation method combining isomorphic weights is designed to include more isomorphic semantics for counterpart entities, which will benefit the CLEA. Experiments show that our model can improve the isomorphism of two KGs and the alignment performance, especially for two non-isomorphic KGs.

Keywords: knowledge graphs, cross-lingual entity alignment, non-isomorphic, relation completion

Procedia PDF Downloads 96