Search results for: health improvement network (THIN)

Authors: Uvais Qidwai, Amor Moursi, Mohamed Tahar, Malek Hamad, Hamad Alansi

Abstract:

This paper focuses on the development and implementation of an advanced plant health monitoring system with an AI backbone and IoT sensory network. Our approach involves addressing the critical environmental factors essential for preserving a plant’s well-being, including air temperature, soil moisture, soil temperature, soil conductivity, pH, water levels, and humidity, as well as the presence of essential nutrients like nitrogen, phosphorus, and potassium. Central to our methodology is the utilization of computer vision technology, particularly a night vision camera. The captured data is then compared against a reference database containing different health statuses. This comparative analysis is implemented using an AI deep learning model, which enables us to generate accurate assessments of plant health status. By combining the AI-based decision-making approach, our system aims to provide precise and timely insights into the overall health and well-being of plants, offering a valuable tool for effective plant care and management.

Keywords: deep learning image model, IoT sensing, cloud-based analysis, remote monitoring app, computer vision, fuzzy control

Procedia PDF Downloads 46

Authors: Shidrokh Goudarzi, Wan Haslina Hassan

Abstract:

Heterogeneous wireless networks are converging towards an all-IP network as part of the so-called next-generation network. In this paradigm, different access technologies need to be interconnected; thus, vertical handovers or vertical handoffs are necessary for seamless mobility. In this paper, we conduct a review of existing vertical handover decision-making mechanisms that aim to provide ubiquitous connectivity to mobile users. To offer a systematic comparison, we categorize these vertical handover measurement and decision structures based on their respective methodology and parameters. Subsequently, we analyze several vertical handover approaches in the literature and compare them according to their advantages and weaknesses. The paper compares the algorithms based on the network selection methods, complexity of the technologies used and efficiency in order to introduce our vertical handover decision framework. We find that vertical handovers on heterogeneous wireless networks suffer from the lack of a standard and efficient method to satisfy both user and network quality of service requirements at different levels including architectural, decision-making and protocols. Also, the consolidation of network terminal, cross-layer information, multi packet casting and intelligent network selection algorithm appears to be an optimum solution for achieving seamless service continuity in order to facilitate seamless connectivity.

Keywords: heterogeneous wireless networks, vertical handovers, vertical handover metric, decision-making algorithms

Procedia PDF Downloads 391

Authors: Manal Alhazmi, Artem Mishchenko

Abstract:

A molecular fluids' behavior and interaction with other materials at the nanoscale is a complex process. Nanoscale fluids behave so differently than macroscale fluids and interact with other materials in unique ways. It is, therefore, feasible to understand the molecular behavior of H₂O in such two-dimensional nanoscale systems by studying (CaSO4-2H2O), commonly known as gypsum. In the present study, spectroscopic measurements on a 2D structure of exfoliated gypsum crystals are carried out by Raman and IR spectroscopy. An array of gypsum flakes with thicknesses ranging from 8nm to 100nm were observed and analyzed for their Raman and IR spectrum. Water molecules stretching modes spectra lines were also measured and observed in nanoscale gypsum flakes and compared with those of bulk crystals. CaSO4-2H2O crystals have Raman and infrared bands at 3341 cm-1 resulting from the weak hydrogen bonds between the water molecules. This internal vibration of water molecules, together with external vibrations with other atoms, are responsible for these bands. There is a shift of about 70 cm-1 In the peak position of thin flakes with respect to the bulk crystal, which is a result of the different atomic arrangement from bulk to thin flake on the nano scale. An additional peak was observed in Raman spectra around 2910-3137 cm⁻¹ in thin flakes but is missing in bulk crystal. This additional peak is attributed to a combined mode of water internal (stretching mode at 3394cm⁻¹) and external vibrations. In addition to Raman and infra- red analysis of gypsum 2D structure, electrical measurements were conducted to reveal the water molecules transport behavior in such systems. Electrical capacitance of the fabricated device is measured and found to be (0.0686 *10-12) F, and the calculated dielectric constant (ε) is (12.26).

Keywords: gypsum, infra-red spectroscopy, raman spectroscopy, H₂O behavior

Procedia PDF Downloads 97

Authors: Yair Bleiberg, Michael Werman

Abstract:

Coordinate-based Multi-Layer Perceptrons (MLPs) are known to have difficulty reconstructing high frequencies of the training data. A common solution to this problem is Positional Encoding (PE), which has become quite popular. However, PE has drawbacks. It has high-frequency artifacts and adds another hyper hyperparameter, just like batch normalization and dropout do. We believe that under certain circumstances, PE is not necessary, and a smarter construction of the network architecture together with a smart training method is sufficient to achieve similar results. In this paper, we show that very simple MLPs can quite easily output a frequency when given input of the half-frequency and quarter-frequency. Using this, we design a network architecture in blocks, where the input to each block is the output of the two previous blocks along with the original input. We call this a Fibonacci Network. By training each block on the corresponding frequencies of the signal, we show that Fibonacci Networks can reconstruct arbitrarily high frequencies.

Keywords: neural networks, positional encoding, high frequency intepolation, fully connected

Procedia PDF Downloads 91

Authors: Pin-Ju Juan, Peng-Yu Juan, Yi-Shan Chen

Abstract:

The main purpose of this paper is to present a fuzzy Analytic Network Process (ANP) model for the hostel organizational performance selection. In this article, we created 39 criteria for selecting hostel organizational performance acquired from literature's review and experts method practical investigations, and the methods of fuzzy analytic network process are used to consolidate decision-makers’ assessments about criteria weightings. Finally, we selected organizational performance of a hostel in Taiwan to determine the effectiveness of the proposed evaluation model in this paper.

Keywords: Fuzzy ANP, hostel, organizational performance, strategy management

Procedia PDF Downloads 193

Authors: Shoujia Fang, Guoqing Ding, Xin Chen

Abstract:

The quality of press-fit assembly is closely related to reliability and safety of product. The paper proposed a keypoint detection method based on convolutional neural network to improve the accuracy of keypoint detection in press-fit curve. It would provide an auxiliary basis for judging quality of press-fit assembly. The press-fit curve is a curve of press-fit force and displacement. Both force data and distance data are time-series data. Therefore, one-dimensional convolutional neural network is used to process the press-fit curve. After the obtained press-fit data is filtered, the multi-layer one-dimensional convolutional neural network is used to perform the automatic learning of press-fit curve features, and then sent to the multi-layer perceptron to finally output keypoint of the curve. We used the data of press-fit assembly equipment in the actual production process to train CNN model, and we used different data from the same equipment to evaluate the performance of detection. Compared with the existing research result, the performance of detection was significantly improved. This method can provide a reliable basis for the judgment of press-fit quality.

Keywords: keypoint detection, curve feature, convolutional neural network, press-fit assembly

Procedia PDF Downloads 224

Authors: Eileen Y. Wong, Katherine Jin, Anat Talmon

Abstract:

Background: Help seeking behaviors are highly contingent on socio-cultural factors such as ethnicity. Both Latino and Asian Americans underutilize mental health services compared to their White American counterparts. This difference may be related to the composite of one’s social support system, which includes family cohesion and social networks. Previous studies have found that Latino families are characterized by higher levels of family cohesion and social support, and Asian American families with greater family cohesion exhibit lower levels of help seeking behaviors. While both are broadly considered collectivist communities, within-culture variability is also significant. Therefore, this study aims to investigate the relationship between help seeking behaviors in the two cultures with levels of family cohesion and strength of social network. We also consider such relationships in light of previous traumatic events and diagnoses, particularly post-traumatic stress disorder (PTSD), to understand whether clinically diagnosed individuals differ in their strength of network and help seeking behaviors. Method: An adult sample (N = 2,990) from the National Latino and Asian American Study (NLAAS) provided data on participants’ social network, family cohesion, likelihood of seeking professional help, and DSM-IV diagnoses. T-tests compared Latino American (n = 1,576) and Asian American respondents (n = 1,414) in strength of social network, level of family cohesion, and likelihood of seeking professional help. Linear regression models were used to identify the probability of help-seeking behavior based on ethnicity, PTSD diagnosis, and strength of social network. Results: Help-seeking behavior was significantly associated with family cohesion and strength of social network. It was found that higher frequency of expressing one’s feelings with family significantly predicted lower levels of help-seeking behaviors (β = [-.072], p = .017), while higher frequency of spending free time with family significantly predicted higher levels of help-seeking behaviors (β = [.129], p = .002) in the Asian American sample. Subjective importance of family relations compared to that of one’s peers also significantly predict higher levels of help-seeking behaviors (β = [.095], p = .011) in the Asian American sample. Frequency of sharing one’s problems with relatives significantly predicted higher levels of help-seeking behaviors (β = [.113], p < .01) in the Latino American sample. A PTSD diagnosis did not have any significant moderating effect. Conclusion: Considering the underutilization of mental health services in Latino and Asian American minority groups, it is crucial to understand ways in which help seeking behavior can be encouraged. Our findings suggest that different dimensions within family cohesion and social networks have differential impacts on help-seeking behavior. Given the multifaceted nature of family cohesion and cultural relevance, the implications of our findings for theory and practice will be discussed.

Keywords: family cohesion, social networks, Asian American, Latino American, help-seeking behavior

Procedia PDF Downloads 63

Authors: Eveline Muika Kabongo, Peter Delobelle, Ferdinand Mukumbang, Edward Nicol

Abstract:

Introduction: Studies have been conducted to establish the effect of the MomConnect program in South Africa, but these studies did not focus on the stakeholders' and implementers' perspectives and the underlying program theory of the MomConnect initiative program. We strived to obtain stakeholders’ perspectives and assumptions on the MomConnect program and develop an initial program theory (IPT) of how the MomConnect initiative was expected to work. Methods: A realist-informed explanatory design used. The interviewer was performed with 10 key informants selected purposively among MomConnect key informants at the a national level of NDoH South Africa. The interview was done via zoom and lasted for 30 to 60 minutes. Introduction and abduction inferencing approaches were applied. The deductive and inductive approaches were performed during the analysis. ICAMO hereustic framework was used to analysed the data in order to get key informants expectations on how the MomConnect will work or not. Results: We developed three folk’s theories illustrating how the key informants’ expected the MomConnect to work. These theories showed that the MomConnect intended to provide users with health information and education that will empower and motivate them with knowledge which will allow the improvement of health services delivery among HCPs and improvement of the uptake of MCH services among pregnant women and mothers and decrease the rate of maternal and child mortality in the country. The lack of an updated mechanism to link women to the outcome was an issue. Another problem enlightened was the introduction of the WhatsApp program instead of SMS messaging, which was free of charge to women. Conclusion: The Folk’s theory developed from this study provided an insight into how the MomConnect was expected to work and what did not work. The folk’s theory will be merged with information from candidate theories on synthesis review and document review to develop our initial program theory of the MomConnect initiative.

Keywords: mHealth, MomConnect program, realist evaluation, maternal and child health, maternal and child health services, introduction, theory-driven

Procedia PDF Downloads 187

Authors: Said Rabah Azzam, Andrew Graham

Abstract:

Fragmentation of packets caused by encryption applied on the network layer of the IOS model in Internet Protocol version 4 (IPv4) networks as well as the possibility of using fragmentation and Access Control Lists (ACLs) as a method of restricting network access to certain hosts or areas of a network.Using default settings, fragmentation is expected to occur and each fragment to be reassembled at the other end. If this does not occur then a high number of ICMP messages should be generated back towards the source host indicating that the packet is too large and that it needs to be made smaller. This result is also expected when the MTU is changed for certain links between devices.When using ACLs and packet fragments to restrict access to hosts or network segments it is possible that ACLs cannot be set up in this way. If ACLs cannot be setup to allow only fragments then it is a limitation of the hardware’s firmware holding back this particular method. If the ACL on the restricted switch can be set up in such a way to allow only fragments then a connection that forces packets to fragment should be allowed to pass through the ACL. This should then make a network connection to the destination machine allowing data to be sent to and from the destination machine. ICMP messages from the restricted access switch and host should also be blocked from being sent back across the link which will be shown in an SSH session into the switch.

Keywords: fragmentation, encryption, security, switch

Procedia PDF Downloads 330

Authors: Yi Yang

Abstract:

In the era of 'Internet plus', the rapid development of webcast has posed new challenges to the intellectual property law. Meanwhile, traditional copyright protection has also exposed the existing theoretical imbalance in webcast. Through the analysis of the outstanding problems in the copyright protection of the network live broadcast, this paper points out that the main causes of the problems are the unclear nature of the copyright of the network live broadcast, the copyright protection system of the game network live broadcast has not yet been constructed, and the copyright infringement of the pan entertainment live broadcast is mostly, and so on. Based on the current practice, this paper puts forward the specific thinking of the protection path of online live broadcast copyright. First of all, to provide a reasonable judicial solution for a large number of online live copyright cases, we need to integrate the right scope and regulatory behavior of broadcasting right and information network communication right. Secondly, in order to protect the rights of network anchors, the webcast should be regarded as works. Thirdly, in order to protect the copyright of webcast and prevent the infringement of copyright by webcast, the webcast platform will be used as an intermediary to provide solutions for solving the judicial dilemma. In the era of 'Internet plus', it is a theoretical attempt to explore the protection and method of copyright protection on webcast, which has positive guiding significance for judicial practice.

Keywords: 'Internet Plus' era, webcast, copyright, protection dilemma

Procedia PDF Downloads 107

Authors: Rama Krishna Supramanian, Marzuki Isahak, Noran Naqiah Hairi

Abstract:

Noise-induced hearing loss (NIHL) is one of the highest recorded occupational diseases, despite being preventable. Hearing Conservation Program (HCP) is designed to protect workers hearing and prevent them from developing hearing impairment due to occupational noise exposures. However, there is still a lack of evidence regarding the effectiveness of this program. The purpose of this study was to determine the effectiveness of a Hearing Conservation Program (HCP) in preventing or reducing audiometric threshold changes among vector control workers. This study adopts a cluster randomized controlled trial study design, with district health offices as the unit of randomization. Nine district health offices were randomly selected and 183 vector control workers were randomized to intervention or control group. The intervention included a safety and health policy, noise exposure assessment, noise control, distribution of appropriate hearing protection devices, training and education program and audiometric testing. The control group only underwent audiometric testing. Audiometric threshold changes observed in the intervention group showed improvement in the hearing threshold level for all frequencies except 500 Hz and 8000 Hz for the left ear. The hearing threshold changes range from 1.4 dB to 5.2 dB with largest improvement at higher frequencies mainly 4000 Hz and 6000 Hz. Meanwhile for the right ear, the mean hearing threshold level remained similar at 4000 Hz and 6000 Hz after 3 months of intervention. The Hearing Conservation Program (HCP) is effective in preserving the hearing of vector control workers involved in fogging activity as well as increasing their knowledge, attitude and practice towards noise-induced hearing loss (NIHL).

Keywords: adult, hearing conservation program, noise-induced hearing loss, vector control worker

Procedia PDF Downloads 158

Authors: Sobhy Fathy A. Hashesh

Abstract:

The study was carried out in the High School Classes of Andalus Private Schools, boys section, using control and experimental groups that were randomly assigned. The study investigated the effect of Al-Andalus Improvement Model (AIM) on the development of students’ skills acquiring. The society of the study composed of Al-Andalus Private Schools, high school students, boys Section (N=700), while the sample of the study composed of four randomly assigned groups two groups of teachers (N=16) and two groups of students (N=42) with one experimental group and one control group for teachers and their students respectively. The study followed the quantitative and qualitative approaches in collecting and analyzing data to investigate the study hypotheses. Results of the study revealed that there were significant statistical differences in teachers’ performances and students' skills acquiring for the favor of the experimental groups and there was a strong correlation between the teachers performances and the students skills acquiring. The study recommended the implementation of the AIM model for the sake of teachers performances and students’ learning outcomes.

Keywords: AIM, improvement model, Classera, Al-Andalus Improvement Model.

Procedia PDF Downloads 159

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 312

Authors: M. A. Hassan, M. H. Sakinah, K. Kadirgama, D. Ramasamy, M. M. Noor, M. M. Rahman

Abstract:

Tribological properties that include nanoparticles are an alternative to improve the tribological behaviour of lubricating oil, which has been investigated by many researchers for the past few decades. Various nanostructures can be used as additives for tribological improvement. However, this also depends on the characteristics of the nanoparticles. In this study, tribological investigation was performed to examine the effect of CuO nanoparticles on the tribological behaviour of Syntium 800 SL 10W−30. Three parameters used in the analysis using the wear tester (piston ring) were load, revolutions per minute (rpm), and concentration. The specifications of the nanoparticles, such as size, concentration, hardness, and shape, can affect the tribological behaviour of the lubricant. The friction and wear experiment was conducted using a tribo-tester and the Response Surface Methodology method was used to analyse any improvement of the performance. Therefore, two concentrations of 40 nm nanoparticles were used to conduct the experiments, namely, 0.005 wt % and 0.01 wt % and compared with base oil 0 wt % (control). A water bath sonicator was used to disperse the nanoparticles in base oil, while a tribo-tester was used to measure the coefficient of friction and wear rate. In addition, the thermal properties of the nanolubricant were also measured. The results have shown that the thermal conductivity of the nanolubricant was increased when compared with the base oil. Therefore, the results indicated that CuO nanoparticles had improved the tribological behaviour as well as the thermal properties of the nanolubricant oil.

Keywords: concentration, improvement, tribological, copper (II) oxide, nano lubricant

Procedia PDF Downloads 435

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: distillation, machine learning, neural networks, quantization

Procedia PDF Downloads 320

Authors: Elaine Wong

Abstract:

This research protocol aims to explore and justify the need for nutrition and physical activity intervention to improve health outcomes among SME (Small Medium Enterprise) employees. It was found that the worksite is an ideal and convenient setting for employees to take charge of their health thru active participation in health programmes since they spent a great deal of time at their workplace. This study will examine the impact of both general or/and targeted health interventions in both SME and non-SME companies utilizing the Workplace Health Promotion (WHP) grant over a 12 months period and assessed the improvement in chronic health disease outcomes in Singapore. Random sampling of both non-SME and SME companies will be conducted to undergo health intervention and statistical packages such as Statistical Package for Social Science (SPSS) 25 will be used to examine the impact of both general and targeted interventions on employees who participate and those who do not participate in the intervention and their effects on blood glucose (BG), blood lipid, blood pressure (BP), body mass index (BMI), and body fat percentage. Using focus groups and interviews, the data results will be transcribed to investigate enablers and barriers to workplace health intervention revealed by employees and WHP coordinators that could explain the variation in the health screening results across the organisations. Dietary habits and physical activity levels of the employees participating and not participating in the intervention will be collected before and after intervention to assess any changes in their lifestyle practices. It makes economic sense to study the impact of these interventions on health screening outcomes across various organizations that are existing grant recipients to justify the sustainability of these programmes by the local government. Healthcare policy makers and employers can then tailor appropriate and relevant programmes to manage these escalating chronic health disease conditions which is integral to the competitiveness and productivity of the nation’s workforce.

Keywords: chronic diseases, health screening, nutrition and fitness intervention , workplace health

Procedia PDF Downloads 146

Authors: Riyadh Alsultani, Ali Majdi

Abstract:

It is necessary to develop a design methodology that includes the possibility of seismic events occurring in a region, the vulnerability of the civil hydraulic structure, and the effects of the occurrence hazard on society, environment, and economy in order to evaluate the flood and earthquake risks of coastal bridge networks. This paper presents a design approach for the assessment of the risk and sustainability of coastal bridge networks under time-variant flood-earthquake conditions. The social, environmental, and economic indicators of the network are used to measure its sustainability. These consist of anticipated loss, downtime, energy waste, and carbon dioxide emissions. The design process takes into account the possibility of happening in a set of flood and earthquake scenarios that represent the local seismic activity. Based on the performance of each bridge as determined by fragility assessments, network linkages are measured. The network's connections and bridges' damage statuses after an earthquake scenario determine the network's sustainability and danger. The sustainability measures' temporal volatility and the danger of structural degradation are both highlighted. The method is shown using a transportation network in Baghdad, Iraq.

Keywords: sustainability, Coastal bridge networks, flood-earthquake risk, structural design

Procedia PDF Downloads 87

Authors: P. Kumar, D. Eisenhauer, M. M. K. Yousef, Q. Shi, A. S. G. Khalil, M. R. Saber, C. Becker, T. Pullerits, K. J. Karki

Abstract:

In impedance spectroscopy (IS) the response of a photo-active device is analysed as a function of ac bias. It is widely applied in a broad class of material systems and devices. It gives access to fundamental mechanisms of operation of solar cells. We have implemented a method of IS where we modulate the light instead of the bias. This scheme allows us to analyze not only carrier dynamics but also impedance of device locally. Here, using this scheme, we have measured the frequency-dependent photocurrent response of the thin-film planar and nano-textured Si solar cells using this method. Photocurrent response is measured in range of 50 Hz to 50 kHz. Bode and Nyquist plots are used to determine characteristic lifetime of both the cells. Interestingly, the carrier lifetime of both planar and nano-textured solar cells depend on back and front contact positions. This is due to either heterogeneity of device or contacts are not optimized. The estimated average lifetime is found to be shorter for the nano-textured cell, which could be due to the influence of the textured interface on the carrier relaxation dynamics.

Keywords: carrier lifetime, impedance, nano-textured, photocurrent

Procedia PDF Downloads 229

Authors: Ishtiaq Wahid, Masood Ahmad, Nighat Ayub, Sajad Ali

Abstract:

Lifetime of a wireless sensor network (WSN) is directly proportional to the energy consumption of its constituent nodes. Routing in wireless sensor network is very challenging due its inherit characteristics. In hierarchal routing the sensor filed is divided into clusters. The cluster-heads are selected from each cluster, which forms a hierarchy of nodes. The cluster-heads are used to transmit the data to the base station while other nodes perform the sensing task. In this way the lifetime of the network is increased. In this paper a comparative study of hierarchal routing protocols are conducted. The simulation is done in NS-2 for validation.

Keywords: WSN, cluster, routing, sensor networks

Procedia PDF Downloads 474

Authors: Ali Nadi, Ali Edrissi

Abstract:

Relief demand and transportation links availability is the essential information that is needed for every natural disaster operation. This information is not in hand once a disaster strikes. Relief demand and network condition has been evaluated based on prediction method in related works. Nevertheless, prediction seems to be over or under estimated due to uncertainties and may lead to a failure operation. Therefore, in this paper a stochastic programming model is proposed to evaluate real-time relief demand and network condition at the onset of a natural disaster. To address the time sensitivity of the emergency response, the proposed model uses reinforcement learning for optimization of the total relief assessment time. The proposed model is tested on a real size network problem. The simulation results indicate that the proposed model performs well in the case of collecting real-time information.

Keywords: disaster management, real-time demand, reinforcement learning, relief demand

Procedia PDF Downloads 310

Authors: Rachel M. Lørum, Henrik Eriksson, Frida Smith

Abstract:

Purpose: In recent years, the use of benchmarks for the improvement of healthcare has become increasingly common. There has been an increasing interest in why improvement initiatives so often fail to eliminate the problems they aspire to solve. Benchmarking comes with its fair share of challenges and problems, such as capturing the dynamics and complexities of the care environments, among others. In this study, we demonstrate how learning-oriented, voluntary benchmarks in the complex environment of public healthcare could be designed. Findings: Our four most important findings were the following: first, important organizational learning (OL) regarding the complexity of the service and implications on how to design a benchmark for learning and improvement occurred during the process. Second, participation by a wide range of professionals and stakeholders was crucial for capturing the complexity of people and organizations and increasing the quality of the template. Third, the continuous dialogue between all organizations involved was an important tool for ongoing organizational learning throughout the process. The last important finding was the impact of the facilitator’s role through supporting progress, coordination, and dialogue. Design: We chose participatory design as the research design. Data were derived from written materials such as e-mails, protocols, observational notes, and reflection notes collected during a period of 1.5 years. Originality: Our main contributions are the identification of important strategies, initiatives, and actors to involve when designing voluntary benchmarks for learning and improvement.

Keywords: organizational learning, quality improvement, learning-oriented benchmark, healthcare, patient safety

Procedia PDF Downloads 107

Authors: Zhenzhen Xu, Chunfu Shao, Shengyou Wang, Chunjiao Dong

Abstract:

To improve the satisfaction of residents' travel, this paper analyzes the characteristics and influencing factors of urban residents' travel behavior. First, a Multinominal Logit Model (MNL) model is built to analyze the characteristics of residents' travel behavior, reveal the influence of individual attributes, family attributes and travel characteristics on the choice of travel mode, and identify the significant factors. Then put forward suggestions for policy improvement. Finally, Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) models are introduced to evaluate the policy effect. This paper selects Futian Street in Futian District, Shenzhen City for investigation and research. The results show that gender, age, education, income, number of cars owned, travel purpose, departure time, journey time, travel distance and times all have a significant influence on residents' choice of travel mode. Based on the above results, two policy improvement suggestions are put forward from reducing public transportation and non-motor vehicle travel time, and the policy effect is evaluated. Before the evaluation, the prediction effect of MNL, SVM and MLP models was evaluated. After parameter optimization, it was found that the prediction accuracy of the three models was 72.80%, 71.42%, and 76.42%, respectively. The MLP model with the highest prediction accuracy was selected to evaluate the effect of policy improvement. The results showed that after the implementation of the policy, the proportion of public transportation in plan 1 and plan 2 increased by 14.04% and 9.86%, respectively, while the proportion of private cars decreased by 3.47% and 2.54%, respectively. The proportion of car trips decreased obviously, while the proportion of public transport trips increased. It can be considered that the measures have a positive effect on promoting green trips and improving the satisfaction of urban residents, and can provide a reference for relevant departments to formulate transportation policies.

Keywords: neural network, travel characteristics analysis, transportation choice, travel sharing rate, traffic resource allocation

Procedia PDF Downloads 135

Authors: Jitendra Aswani

Abstract:

In the first section of this study, impact of Global Financial Crisis (GFC) on the synchronization of fourteen Asian Stock Markets (ASM’s) of countries like Hong Kong, India, Thailand, Singapore, Taiwan, Pakistan, Bangladesh, South Korea, Malaysia, Indonesia, Japan, China, Philippines and Sri Lanka, has been analysed using the network science and its metrics like degree of node, clustering coefficient and network density. Then in the second section of this study by introducing the US stock market in existing network and developing a Minimum Spanning Tree (MST) spread of crisis from the US stock market to Asian Stock Markets (ASM) has been explained. Data used for this study is adjusted the closing price of these indices from 6th January, 2000 to 15th September, 2013 which further divided into three sub-periods: Pre, during and post-crisis. Using network analysis, it is found that Asian stock markets become more interdependent during the crisis than pre and post crisis, and also Hong Kong, India, South Korea and Japan are systemic important stock markets in the Asian region. Therefore, failure or shock to any of these systemic important stock markets can cause contagion to another stock market of this region. This study is useful for global investors’ in portfolio management especially during the crisis period and also for policy makers in formulating the financial regulation norms by knowing the connections between the stock markets and how the system of these stock markets changes in crisis period and after that.

Keywords: global financial crisis, Asian stock markets, network science, Kruskal algorithm

Procedia PDF Downloads 419

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 193

Authors: Kaustubh Chakradeo, Michael Delves, Sofya Titarenko

Abstract:

Malaria is a serious disease which affects hundreds of millions of people around the world, each year. If not treated in time, it can be fatal. Despite recent developments in malaria diagnostics, the microscopy method to detect malaria remains the most common. Unfortunately, the accuracy of microscopic diagnostics is dependent on the skill of the microscopist and limits the throughput of malaria diagnosis. With the development of Artificial Intelligence tools and Deep Learning techniques in particular, it is possible to lower the cost, while achieving an overall higher accuracy. In this paper, we present a VGG-based model and compare it with previously developed models for identifying infected cells. Our model surpasses most previously developed models in a range of the accuracy metrics. The model has an advantage of being constructed from a relatively small number of layers. This reduces the computer resources and computational time. Moreover, we test our model on two types of datasets and argue that the currently developed deep-learning-based methods cannot efficiently distinguish between infected and contaminated cells. A more precise study of suspicious regions is required.

Keywords: convolution neural network, deep learning, malaria, thin blood smears

Procedia PDF Downloads 124

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 125

Authors: Kornkanok Noulta, Pornsri Pakeyangkoon, Stephen T. Dubas, Pomthong Malakul, Manit Nithithanakul

Abstract:

In recent years, interest in the development of material for tissue engineering application has increased considerably. Poly(High Internal Phase Emulsion) (PolyHIPE) foam is a material that is good candidate for used in tissue engineering application due to its 3D structure and highly porous with interconnected pore. The PolyHIPE was prepared from poly (styrene/ethylene glycol dimethacrylate) through high internal phase emulsion polymerization technique and loaded with hydroxyapatite (HA) to improve biocompatibility. To further increase hydrophilicity of the obtained polyHIPE, layer-by-layer polyelectrolyte multilayers (PEM) technique was used. A surface property of polyHIPE was characterized by contact angle measurement. Morphology and pore size was observed by scanning electron microscope (SEM). The cell viability was revealed by the 3-(4, 5-dimethylthiazol-2-yl)-2, 5-diphenyltetrazolium bromide (MTT) assay technique.

Keywords: polyelectrolyte multilayer thin film, high internal phase emulsion, polyhipe foam, scaffold, tissue engineering

Procedia PDF Downloads 348

Authors: Mahdi Pirmoradian, Olayinka Adigun, Christos Politis

Abstract:

Cooperative spectrum sensing is a crucial challenge in cognitive radio networks. Cooperative sensing can increase the reliability of spectrum hole detection, optimize sensing time and reduce delay in cooperative networks. In this paper, an efficient central capacity optimization algorithm is proposed to minimize cooperative sensing time in a homogenous sensor network using OR decision rule subject to the detection and false alarm probabilities constraints. The evaluation results reveal significant improvement in the sensing time and normalized capacity of the cognitive sensors.

Keywords: cooperative networks, normalized capacity, sensing time

Procedia PDF Downloads 630

Authors: Mohammed Affanuddin H. Siddique, Jayesh S. Shukla, Chetan B. Meshram

Abstract:

The neural networks are one of the power tools of machine learning. After the invention of perceptron in early 1980's, the neural networks and its application have grown rapidly. Neural networks are a technique originally developed for pattern investigation. The structure of a neural network consists of neurons connected through synapse. Here, we have investigated the different algorithms and cost function reduction techniques for optimization of vertical axis wind turbine (VAWT) rotor blades. The aerodynamic force coefficients corresponding to the airfoils are stored in a database along with the airfoil coordinates. A forward propagation neural network is created with the input as aerodynamic coefficients and output as the airfoil co-ordinates. In the proposed algorithm, the hidden layer is incorporated into cost function having linear and non-linear error terms. In this article, it is observed that the ANNs (Artificial Neural Network) can be used for the VAWT’s optimization.

Keywords: VAWT, ANN, optimization, inverse design

Procedia PDF Downloads 319

Authors: Monika Kamocka, Radoslaw Mania

Abstract:

The design of Fiber Metal Laminates - combining thin aluminum sheets and prepreg layers, allows creating a hybrid structure with high strength to weight ratio. This feature makes FMLs very attractive for aerospace industry, where thin-walled structures are commonly used. Nevertheless, those structures are prone to buckling phenomenon. Buckling could occur also under static load as well as dynamic pulse loads. In this paper, the problem of dynamic buckling of open cross-section FML profiles under axial dynamic compression in the form of pulse load of finite duration is investigated. In the numerical model, material properties of FML constituents were assumed as nonlinear elastic-plastic aluminum and linear-elastic glass-fiber-reinforced composite. The influence of pulse shape was investigated. Sinusoidal and rectangular pulse loads of finite duration were compared in two ways, i.e. with respect to magnitude and force pulse. The dynamic critical buckling load was determined based on Budiansky-Hutchinson, Ari Gur, and Simonetta dynamic buckling criteria.

Keywords: dynamic buckling, dynamic stability, Fiber Metal Laminate, Finite Element Method

Procedia PDF Downloads 186