Search results for: medical decision
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 7108

Search results for: medical decision

4648 Optimizing Pediatric Pneumonia Diagnosis with Lightweight MobileNetV2 and VAE-GAN Techniques in Chest X-Ray Analysis

Authors: Shriya Shukla, Lachin Fernando

Abstract:

Pneumonia, a leading cause of mortality in young children globally, presents significant diagnostic challenges, particularly in resource-limited settings. This study presents an approach to diagnosing pediatric pneumonia using Chest X-Ray (CXR) images, employing a lightweight MobileNetV2 model enhanced with synthetic data augmentation. Addressing the challenge of dataset scarcity and imbalance, the study used a Variational Autoencoder-Generative Adversarial Network (VAE-GAN) to generate synthetic CXR images, improving the representation of normal cases in the pediatric dataset. This approach not only addresses the issues of data imbalance and scarcity prevalent in medical imaging but also provides a more accessible and reliable diagnostic tool for early pneumonia detection. The augmented data improved the model’s accuracy and generalization, achieving an overall accuracy of 95% in pneumonia detection. These findings highlight the efficacy of the MobileNetV2 model, offering a computationally efficient yet robust solution well-suited for resource-constrained environments such as mobile health applications. This study demonstrates the potential of synthetic data augmentation in enhancing medical image analysis for critical conditions like pediatric pneumonia.

Keywords: pneumonia, MobileNetV2, image classification, GAN, VAE, deep learning

Procedia PDF Downloads 107
4647 Prevention of Heart Failure Progression in Patients with Post-Infarction Cardiosclerosis After Coronavirus Infection

Authors: Sujayeva V. A., Karpova I. S., Koslataya O. V., Kolyadko M. G., Russkikh I. I., Vankovich E. A.

Abstract:

Objective: The goal of this study is to develop a method for the prevention of the progression of heart failure (HF) in patients with post-infarction cardiosclerosis who have suffered coronavirus infection. Methods: 135 patients with post-infarction cardiosclerosis were divided into 2 groups: Group I - patients who had suffered COVID-19 - 85 people, and Group II - patients who had not suffered COVID-19 - 50 people. Patients of group I, depending on the level of N-terminal fragment of natriuretic peptide (NTproBNP), were divided into 2 subgroups - subgroup A - with HF - 40 people, subgroup B - without HF - 45 people. All patients underwent a clinical examination, echocardiography, electrocardiotopography in 60 leads, computed angiography of the coronary arteries, heart magnetic resonance imaging, NTproBNP. Results: In the post-Covid period, in patients with post-infarction cardiosclerosis, remodeling of the left ventricle and right parts of the heart, deterioration of the systolic-diastolic function of both ventricles, increased pressure in the pulmonary artery, progression of coronary artery atherosclerosis, and an increase in the size of myocardial fibrosis were revealed. The consequence of these changes was the progression of heart failure. The developed method of medical prevention made it possible to improve the clinical course of coronary artery disease and prevent the progression of chronic heart failure in patients with post-infarction cardiosclerosis. Conclusions: In patients with post-infarction cardiosclerosis who initially had HF, after 1 year, according to laboratory and instrumental data, a slight decrease in its severity was revealed. In patients with post-infarction cardiosclerosis who did not have HF before COVID-19, HF developed 1 year after the coronavirus disease, which may be due to the identified process of myocardial fibrosis, which dictates the need to prevent the development of HF in patients with post-infarction cardiosclerosis, even those who did not initially have HF. The proposed method of medical prevention made it possible to improve the clinical course of coronary artery disease in patients with post-infarction cardiosclerosis after COVID-19, both in persons with and without HF, when included in the study. A method of medical prevention in people with post-infarction cardiosclerosis after COVID-19 infection, including spironolactone, loop diuretics, empagliflozin, sacubitril/valsartan, helped prevent the progression of HF.

Keywords: elderly, myocardial infarction, COVID-19, prevention

Procedia PDF Downloads 15
4646 TALENT GAMING©: The Innovative Methodology to Explore Talents and Empower Teams by Using Board Games

Authors: Susana F. Casla

Abstract:

Talent Gaming is an innovative methodology based on a large research done for years about how table board games can be used to empower teams. This methodology was developed thinking about the efficiency of facilitating team coaching sessions and the importance of bringing out the best of individuals when working as a team. The fact that more senses are involved in playing a board game, linked with the psychological element of space and “permission to play”, help us travel to earlier stages of our life when our authenticity was at its heights. By being focused on playing the board game, the individual does not direct their consciousness in a particular way and is rather focused in winning the board game. By doing this, his or her inner talents and authenticity surfaces and the fact that all the senses are involved impacts enormously his behaviors and attitudes. All of this combined results in an arena where our talents show up and our decision making process is not impacted by other elements, such as appearances, status or hierarchy.

Keywords: talent, team, board game, business psychology, coaching teams at work

Procedia PDF Downloads 367
4645 A Systems-Level Approach towards Transition to Electrical Vehicles

Authors: Mayuri Roy Choudhury, Deepti Paul

Abstract:

Many states in the United States are aiming for high renewable energy targets by the year 2045. In order to achieve this goal, they must do transition to Electrical Vehicles (EVS). We first applied the Multi-Level perspective framework to describe the inter-disciplinary complexities associated with the transition to EVs. Thereafter we addressed these complexities by creating an inter-disciplinary policy framework that uses data science algorithms to create evidence-based policies in favor of EVs. Our policy framework uses a systems level approach as it addresses transitions to EVs from a technology, economic, business and social perspective. By Systems-Level we mean approaching a problem from a multi-disciplinary perspective. Our systems-level approach could be a beneficial decision-making tool to a diverse number of stakeholders such as engineers, entrepreneurs, researchers, and policymakers. In addition, it will add value to the literature of electrical vehicles, sustainable energy, energy economics, and management as well as efficient policymaking.

Keywords: transition, electrical vehicles, systems-level, algorithms

Procedia PDF Downloads 222
4644 Multi-Criteria Goal Programming Model for Sustainable Development of India

Authors: Irfan Ali, Srikant Gupta, Aquil Ahmed

Abstract:

Every country needs a sustainable development (SD) for its economic growth by forming suitable policies and initiative programs for the development of different sectors of the country. This paper is comprised of modeling and optimization of different sectors of India that form a multi-criterion model. In this paper, we developed a fractional goal programming (FGP) model that helps in providing the efficient allocation of resources simultaneously by achieving the sustainable goals in gross domestic product (GDP), electricity consumption (EC) and greenhouse gasses (GHG) emission by the year 2030. Also, a weighted model of FGP is presented to obtain varying solution according to the priorities set by the policy maker for achieving future goals of GDP growth, EC, and GHG emission. The presented models provide a useful insight to the decision makers for implementing strategies in a different sector.

Keywords: sustainable and economic development, multi-objective fractional programming, fuzzy goal programming, weighted fuzzy goal programming

Procedia PDF Downloads 220
4643 Potentially Inappropriate Prescribing in Elderly Population

Authors: Ajit Kumar Sah, Rajesh Kumar Jha, Phoolgen Sah, Dev Kumar Shah

Abstract:

Older individuals often suffer from multiple systemic diseases and are particularly more vulnerable to potentially inappropriate medicine prescribing. Inappropriate medication can cause serious medical problem for the elderly. The purpose of this study was to determine the prevalence of potentially inappropriate medicine (PIM) prescribing in older Nepalese patients in a medicine outpatient department. Beers’ criteria are the most widely used tools to assess PIM to elderly patients. Prospective observational analysis of drugs prescribed in medicine out-patient department (OPD) of a hospital of Bharatpur, Chitwan, Nepal during November 2011 to October 2012 to 869 older adults aged 65 years and above. The use of potentially inappropriate medications (PIM) in elderly patients was analyzed using Beers Criteria updated to 2013. In the 869 patients included the average number of drugs prescribed per prescription was 5.56. The most commonly used drugs were atenolol (24.3%), amlodipine (23.16%), paracetamol (17.6%), salbutamol (15.72%) and vitamin B complex (13.26%). The total number of medications prescribed was 4833. At least one instance of PIM was experienced by approximately 26.3% of patients when evaluated using the Beers criteria. Potentially inappropriate medications are highly prevalent among older patients attending medical OPD and are associated with a number of medications prescribed. Further research is warranted to study the impact of PIMs towards health-related outcomes in these elderly.

Keywords: Beers criteria, elderly, polypharmacy, potentially inappropriate medicines

Procedia PDF Downloads 562
4642 Effect of Low-Intensity Laser on Severe Tinnitus in Idiopathic Sudden Hearing Loss Patients

Authors: Z. Mowafy Emam Mowafy, Ahmed R. Sayed, M. El Sayed Mohmmed Hassan

Abstract:

Purpose: to evaluate the effect of low intensity laser on severe tinnitus in idiopathic sudden hearing loss patients. Methods of evaluation (Visual analogue scale and tinnitus handicap inventory scale):- Thirty patients who had unilateral tinnitus with sensorineural hearing loss were participated in the study. Subjects aged from 40 to 50 were randomly divided into two equal groups: group (A): composed of 15 patients who received the routine medical care (Systemic steroids) in addition to the low-intensity laser therapy (LILT) while group (B): composed of 15 patients who received only the routine medical care. Continuous 632.8nm He-Ne laser was used with 5mW power for 15 min\day, 3 days per week for 3 months. Results and conclusion: Results showed that application of the LILT had a valuable effect on severe tinnitus in idiopathic sudden hearing loss patients as evidenced by the highly decreased visual analogue scale and tinnitus handicap inventory scale.

Keywords: idiopathic sudden hearing loss, low intensity laser, tinnitus, tinnitus handicap inventory scale and visual analogue scale

Procedia PDF Downloads 389
4641 Insight-Based Evaluation of a Map-Based Dashboard

Authors: Anna Fredriksson Häägg, Charlotte Weil, Niklas Rönnberg

Abstract:

Map-based dashboards are used for data exploration every day. The present study used an insight-based methodology for evaluating a map-based dashboard that presents research findings of water management and ecosystem services in the Amazon. In addition to analyzing the insights gained from using the dashboard, the evaluation method was compared to standardized questionnaires and task-based evaluations. The result suggests that the dashboard enabled the participants to gain domain-relevant, complex insights regarding the topic presented. Furthermore, the insight-based analysis highlighted unexpected insights and hypotheses regarding causes and potential adaptation strategies for remediation. Although time- and resource-consuming, the insight-based methodology was shown to have the potential of thoroughly analyzing how end users can utilize map-based dashboards for data exploration and decision making. Finally, the insight-based methodology is argued to evaluate tools in scenarios more similar to real-life usage compared to task-based evaluation methods.

Keywords: visual analytics, dashboard, insight-based evaluation, geographic visualization

Procedia PDF Downloads 113
4640 Computational Model of Human Cardiopulmonary System

Authors: Julian Thrash, Douglas Folk, Michael Ciracy, Audrey C. Tseng, Kristen M. Stromsodt, Amber Younggren, Christopher Maciolek

Abstract:

The cardiopulmonary system is comprised of the heart, lungs, and many dynamic feedback mechanisms that control its function based on a multitude of variables. The next generation of cardiopulmonary medical devices will involve adaptive control and smart pacing techniques. However, testing these smart devices on living systems may be unethical and exceedingly expensive. As a solution, a comprehensive computational model of the cardiopulmonary system was implemented in Simulink. The model contains over 240 state variables and over 100 equations previously described in a series of published articles. Simulink was chosen because of its ease of introducing machine learning elements. Initial results indicate that physiologically correct waveforms of pressures and volumes were obtained in the simulation. With the development of a comprehensive computational model, we hope to pioneer the future of predictive medicine by applying our research towards the initial stages of smart devices. After validation, we will introduce and train reinforcement learning agents using the cardiopulmonary model to assist in adaptive control system design. With our cardiopulmonary model, we will accelerate the design and testing of smart and adaptive medical devices to better serve those with cardiovascular disease.

Keywords: adaptive control, cardiopulmonary, computational model, machine learning, predictive medicine

Procedia PDF Downloads 175
4639 A Memetic Algorithm for an Energy-Costs-Aware Flexible Job-Shop Scheduling Problem

Authors: Christian Böning, Henrik Prinzhorn, Eric C. Hund, Malte Stonis

Abstract:

In this article, the flexible job-shop scheduling problem is extended by consideration of energy costs which arise owing to the power peak, and further decision variables such as work in process and throughput time are incorporated into the objective function. This enables a production plan to be simultaneously optimized in respect of the real arising energy and logistics costs. The energy-costs-aware flexible job-shop scheduling problem (EFJSP) which arises is described mathematically, and a memetic algorithm (MA) is presented as a solution. In the MA, the evolutionary process is supplemented with a local search. Furthermore, repair procedures are used in order to rectify any infeasible solutions that have arisen in the evolutionary process. The potential for lowering the real arising costs of a production plan through consideration of energy consumption levels is highlighted.

Keywords: energy costs, flexible job-shop scheduling, memetic algorithm, power peak

Procedia PDF Downloads 341
4638 The Relationship between Eating Disorders (Anorexia and Bulimia Nervosa) with Some of the Demographic Factors among University Students

Authors: Shima Hashemi, Firoozeh Ghazanfari

Abstract:

Introduction: Eating disorder is a psychiatric disorder that is increasingly growing. This study aimed to determine the relationship between eating disorders (anorexia and bulimia nervosa) with some of the demographic factors among Lorestan University of Medical Sciences students. Materials and Methods: This study is a cross-sectional and descriptive study that was done at Lorestan University of Medical Sciences in 2019. Four hundred fifty students were studied by stratified and cluster sampling methods. For gathering data, we use the standard questionnaire Eating Attitudes Test EAT (26). Data were analyzed using statistical software SPSS. Results: According to the results, 144 (32%) males and 305 (67.8%) females were studied. 88.7% were single, and 8.9% were married. In the anorexia nervosa group, the results showed that there was a significant meaning between demographic information, and the number of family members, marital status, BMI, level of education, family income, father and mother education, as well as in the bulimia nervosa group, there was no significant meaning with any demographic information (p>0.05). Conclusion: Anorexia and bulimia nervosa are two known types of eating disorders, and some demographic factors can be effective in causing or aggravating these disorders.

Keywords: eating disorder, anorexia nervosa, bulimia nervosa, students

Procedia PDF Downloads 95
4637 Hybrid Fuzzy Weighted K-Nearest Neighbor to Predict Hospital Readmission for Diabetic Patients

Authors: Soha A. Bahanshal, Byung G. Kim

Abstract:

Identification of patients at high risk for hospital readmission is of crucial importance for quality health care and cost reduction. Predicting hospital readmissions among diabetic patients has been of great interest to many researchers and health decision makers. We build a prediction model to predict hospital readmission for diabetic patients within 30 days of discharge. The core of the prediction model is a modified k Nearest Neighbor called Hybrid Fuzzy Weighted k Nearest Neighbor algorithm. The prediction is performed on a patient dataset which consists of more than 70,000 patients with 50 attributes. We applied data preprocessing using different techniques in order to handle data imbalance and to fuzzify the data to suit the prediction algorithm. The model so far achieved classification accuracy of 80% compared to other models that only use k Nearest Neighbor.

Keywords: machine learning, prediction, classification, hybrid fuzzy weighted k-nearest neighbor, diabetic hospital readmission

Procedia PDF Downloads 181
4636 Successful Management of a Boy with Mild Persistent Asthma: A Longitudinal Case

Authors: A. Lubis, L. Setiawati, A. R. Setyoningrum, A. Suryawan, Irwanto

Abstract:

Asthma is a condition that causing chronic health problems in children. In addition to basic therapy against disease, we must try to reduce the impact of chronic health problems and also optimize their medical aspect of growth and development. A boy with mild asthma attack frequent episode did not showed any improvement with medical treatment and his asthma control test was 11. From radiologic examination he got hyperaerated lung and billateral sinusitis maxillaris; skin test results were house dust, food and pet allergy; an overweight body; bad school grades; psychological and environmental problem. We followed and evaluated this boy in 6 months, treated holistically. Even we could not do much on environmental but no more psychological and school problems, his on a good bodyweight and his asthma control test was 22. A case of a child with mild asthma attack frequent episode was reported. Asthma clinical course show no significant improvement when other predisposing factor is not well-controlled and a child’s growth and development may be affected. Improving condition of the patient can be created with the help of loving and caring way of nurturing from the parents and supportive peer group. Therefore, continuous and consistent monitoring is required because prognosis of asthma is generally good when regularly and properly controlled.

Keywords: asthma, chronic health problems, growth, development

Procedia PDF Downloads 226
4635 MCDM Spectrum Handover Models for Cognitive Wireless Networks

Authors: Cesar Hernández, Diego Giral, Fernando Santa

Abstract:

The spectral handoff is important in cognitive wireless networks to ensure an adequate quality of service and performance for secondary user communications. This work proposes a benchmarking of performance of the three spectrum handoff models: VIKOR, SAW and MEW. Four evaluation metrics are used. These metrics are, accumulative average of failed handoffs, accumulative average of handoffs performed, accumulative average of transmission bandwidth and, accumulative average of the transmission delay. As a difference with related work, the performance of the three spectrum handoff models was validated with captured data of spectral occupancy in experiments realized at the GSM frequency band (824 MHz-849 MHz). These data represent the actual behavior of the licensed users for this wireless frequency band. The results of the comparative show that VIKOR Algorithm provides 15.8% performance improvement compared to a SAW Algorithm and, 12.1% better than the MEW Algorithm.

Keywords: cognitive radio, decision making, MEW, SAW, spectrum handoff, VIKOR

Procedia PDF Downloads 433
4634 Multi-Sensor Target Tracking Using Ensemble Learning

Authors: Bhekisipho Twala, Mantepu Masetshaba, Ramapulana Nkoana

Abstract:

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. However, an increasingly controversial question is whether such systems can outperform the single best classifier, and if so, what form of multiple classifiers system yields the most significant benefit. Also, multi-target tracking detection using multiple sensors is an important research field in mobile techniques and military applications. In this paper, several multiple classifiers systems are evaluated in terms of their ability to predict a system’s failure or success for multi-sensor target tracking tasks. The Bristol Eden project dataset is utilised for this task. Experimental and simulation results show that the human activity identification system can fulfill requirements of target tracking due to improved sensors classification performances with multiple classifier systems constructed using boosting achieving higher accuracy rates.

Keywords: single classifier, ensemble learning, multi-target tracking, multiple classifiers

Procedia PDF Downloads 258
4633 A Comparative Study of Malware Detection Techniques Using Machine Learning Methods

Authors: Cristina Vatamanu, Doina Cosovan, Dragos Gavrilut, Henri Luchian

Abstract:

In the past few years, the amount of malicious software increased exponentially and, therefore, machine learning algorithms became instrumental in identifying clean and malware files through semi-automated classification. When working with very large datasets, the major challenge is to reach both a very high malware detection rate and a very low false positive rate. Another challenge is to minimize the time needed for the machine learning algorithm to do so. This paper presents a comparative study between different machine learning techniques such as linear classifiers, ensembles, decision trees or various hybrids thereof. The training dataset consists of approximately 2 million clean files and 200.000 infected files, which is a realistic quantitative mixture. The paper investigates the above mentioned methods with respect to both their performance (detection rate and false positive rate) and their practicability.

Keywords: ensembles, false positives, feature selection, one side class algorithm

Procedia PDF Downloads 287
4632 Fine Needle Aspiration Biopsy of Thyroid Nodules

Authors: Ilirian Laçi, Alketa Spahiu

Abstract:

Big strums of thyroid glandule observed by a simple viewing can be witnessed in everyday life. Medical cabinets evidence patients withpalpablenodes of thyroid glandule, mainly nodes of the size of 10 millimeters. Further, more cases which have resulted in negative under palpation have resulted in positive at ultrasound examination. Therefore, the use of ultrasound for diagnosing has increased the number of patients with nodes of thyroid glandule in the last couple of decades in all countries, Albania included. Thus, there has been evidence of an increased number of patients affected by this pathology, where female patients dominate. Demographically, the capital shows high numbers due to the high population, but of interest is the high incidence of those areas distanced from the sea. While regarding related pathologies, no significant link was evidenced, an element of ancestry was evident in the nodes of the thyroid glandule. When we talk of nodes of the thyroid glandule, we should consider hyperplasia, neoplasia, and inflammatory diseases that cause nodes of the thyroid glandule. This increase parallels the world’s increase of the incidence of thyroid glandule, with malign cases, which are at about 5% and are not depended on size. Given the numbers, with most thyroid glandule nodes being benign, the main objective of the examination of the nodes was the determination of benign and malign cases to avoid undue surgery. Subject of this study were 212 patients that underwent fine-needle aspiration (FNA) under ultrasound guidance at the Medical University Center of Tirana. All the patients came to the Mother Teresa University Hospital from public and private hospitals and other polyclinics. These patients had an ultrasound examination before visiting the Center of Nuclear Medicine for a scintigraph of thyroid glandule in the period September 2016 and September 2017. To correlate, all patients had been examined via ultrasound of the thyroid glandule prior to the scintigraph. The ultrasound included evaluation of the number of nodes, their size, their solid, cystic, or solid-cystic structure, echogenicity according to the gray scale, the presence of calcification, the presence of lymph nodes, the presence of adenopathy, and the correlation of the cytology results from the Laboratory of Pathological Anatomy of Medical University Center of Tirana.

Keywords: thyroid nodes, fine needle aspiration, ultrasound, scintigraphy

Procedia PDF Downloads 99
4631 Development of a Decision-Making Method by Using Machine Learning Algorithms in the Early Stage of School Building Design

Authors: Rajaian Hoonejani Mohammad, Eshraghi Pegah, Zomorodian Zahra Sadat, Tahsildoost Mohammad

Abstract:

Over the past decade, energy consumption in educational buildings has steadily increased. The purpose of this research is to provide a method to quickly predict the energy consumption of buildings using separate evaluation of zones and decomposing the building to eliminate the complexity of geometry at the early design stage. To produce this framework, machine learning algorithms such as Support vector regression (SVR) and Artificial neural network (ANN) are used to predict energy consumption and thermal comfort metrics in a school as a case. The database consists of more than 55000 samples in three climates of Iran. Cross-validation evaluation and unseen data have been used for validation. In a specific label, cooling energy, it can be said the accuracy of prediction is at least 84% and 89% in SVR and ANN, respectively. The results show that the SVR performed much better than the ANN.

Keywords: early stage of design, energy, thermal comfort, validation, machine learning

Procedia PDF Downloads 66
4630 Malpractice, Even in Conditions of Compliance With the Rules of Dental Ethics

Authors: Saimir Heta, Kers Kapaj, Rialda Xhizdari, Ilma Robo

Abstract:

Despite the existence of different dental specialties, the dentist-patient relationship is unique, in the very fact that the treatment is performed by one doctor and the patient identifies the malpractice presented as part of that doctor's practice; this is in complete contrast to cases of medical treatments where the patient can be presented to a team of doctors, to treat a specific pathology. The rules of dental ethics are almost the same as the rules of medical ethics. The appearance of dental malpractice affects exactly this two-party relationship, created on the basis of professionalism, without deviations in this direction, between the dentist and the patient, but with very narrow individual boundaries, compared to cases of medical malpractice. Main text: Malpractice can have different reasons for its appearance, starting from professional negligence, but also from the lack of professional knowledge of the dentist who undertakes the dental treatment. It should always be seen in perspective that we are not talking about the individual - the dentist who goes to work with the intention of harming their patients. Malpractice can also be a consequence of the impossibility, for anatomical or physiological reasons of the tooth under dental treatment, to realize the predetermined dental treatment plan. On the other hand, the dentist himself is an individual who can be affected by health conditions, or have vices that affect the systemic health of the dentist as an individual, which in these conditions can cause malpractice. So, depending on the reason that led to the appearance of malpractice, the method of treatment from a legal point of view also varies, for the dentist who committed the malpractice, evaluating the latter if the malpractice came under the conditions of applying the rules of dental ethics. Conclusions: The deviation from the predetermined dental plan is the minimum sign of malpractice and the latter should not be definitively related only to cases of difficult dental treatments. The identification of the reason for the appearance of malpractice is the initial element, which makes the difference in the way of its treatment, from a legal point of view, and the involvement of the dentist in the assessment of the malpractice committed, must be based on the legislation in force, which must be said to have their specific changes in different states. Malpractice should be referred to, or included in the lectures or in the continuing education of professionals, because it serves as a method of obtaining professional experience in order not to repeat the same thing several times, by different professionals.

Keywords: dental ethics, malpractice, negligence, legal basis, continuing education, dental treatments

Procedia PDF Downloads 55
4629 Dynamic Route Optimization in Vehicle Adhoc Networks: A Heuristics Routing Protocol

Authors: Rafi Ullah, Shah Muhammad Emaduddin, Taha Jilani

Abstract:

Vehicle Adhoc Networks (VANET) belongs to a special class of Mobile Adhoc Network (MANET) with high mobility. Network is created by road side vehicles equipped with communication devices like GPS and Wifi etc. Since the environment is highly dynamic due to difference in speed and high mobility of vehicles and weak stability of the network connection, it is a challenging task to design an efficient routing protocol for such an unstable environment. Our proposed algorithm uses heuristic for the calculation of optimal path for routing the packet efficiently in collaboration with several other parameters like geographical location, speed, priority, the distance among the vehicles, communication range, and networks congestion. We have incorporated probabilistic, heuristic and machine learning based approach inconsistency with the relay function of the memory buffer to keep the packet moving towards the destination. These parameters when used in collaboration provide us a very strong and admissible heuristics. We have mathematically proved that the proposed technique is efficient for the routing of packets, especially in a medical emergency situation. These networks can be used for medical emergency, security, entertainment and routing purposes.

Keywords: heuristics routing, intelligent routing, VANET, route optimization

Procedia PDF Downloads 171
4628 Long Short-Time Memory Neural Networks for Human Driving Behavior Modelling

Authors: Lu Zhao, Nadir Farhi, Yeltsin Valero, Zoi Christoforou, Nadia Haddadou

Abstract:

In this paper, a long short-term memory (LSTM) neural network model is proposed to replicate simultaneously car-following and lane-changing behaviors in road networks. By combining two kinds of LSTM layers and three input designs of the neural network, six variants of the LSTM model have been created. These models were trained and tested on the NGSIM 101 dataset, and the results were evaluated in terms of longitudinal speed and lateral position, respectively. Then, we compared the LSTM model with a classical car-following model (the intelligent driving model (IDM)) in the part of speed decision. In addition, the LSTM model is compared with a model using classical neural networks. After the comparison, the LSTM model demonstrates higher accuracy than the physical model IDM in terms of car-following behavior and displays better performance with regard to both car-following and lane-changing behavior compared to the classical neural network model.

Keywords: traffic modeling, neural networks, LSTM, car-following, lane-change

Procedia PDF Downloads 250
4627 Security Risks Assessment: A Conceptualization and Extension of NFC Touch-And-Go Application

Authors: Ku Aina Afiqah Ku Adzman, Manmeet Mahinderjit Singh, Zarul Fitri Zaaba

Abstract:

NFC operates on low-range 13.56 MHz frequency within a distance from 4cm to 10cm, and the applications can be categorized as touch and go, touch and confirm, touch and connect, and touch and explore. NFC applications are vulnerable to various security and privacy attacks such due to its physical nature; unprotected data stored in NFC tag and insecure communication between its applications. This paper aims to determine the likelihood of security risks happening in an NFC technology and application. We present an NFC technology taxonomy covering NFC standards, types of application and various security and privacy attack. Based on observations and the survey presented to evaluate the risk assessment within the touch and go application demonstrates two security attacks that are high risks namely data corruption and DOS attacks. After the risks are determined, risk countermeasures by using AHP is adopted. The guideline and solutions to these two high risks, attacks are later applied to a secure NFC-enabled Smartphone Attendance System.

Keywords: Near Field Communication (NFC), risk assessment, multi-criteria decision making, Analytical Hierarchy Process (AHP)

Procedia PDF Downloads 297
4626 Evaluation of the Architect-Friendliness of LCA-Based Environmental Impact Assessment Tools

Authors: Elke Meex, Elke Knapen, Griet Verbeeck

Abstract:

The focus of sustainable building is gradually shifting from energy efficiency towards the more global environmental impact of building design during all life-cycle stages. In this context, many tools have been developed that use a LCA-approach to assess the environmental impact on a whole building level. Since the building design strongly influences the final environmental performance and the architect plays a key role in the design process, it is important that these tools are adapted to his work method and support the decision making from the early design phase on. Therefore, a comparative evaluation of the degree of architect-friendliness of some LCA tools on building level is made, based on an evaluation framework specifically developed for the architect’s viewpoint. In order to allow comparison of the results, a reference building has been designed, documented for different design phases and entered in all software tools. The evaluation according to the framework shows that the existing tools are not very architect-friendly. Suggestions for improvement are formulated.

Keywords: architect-friendliness, design supportive value, evaluation framework, tool comparison

Procedia PDF Downloads 536
4625 Preliminary Experience in Multiple Green Health Hospital Construction

Authors: Ming-Jyh Chen, Wen-Ming Huang, Yi-Chu Liu, Li-Hui Yang

Abstract:

Introduction: Social responsibility is the key to sustainable organizational development. Under the ground Green Health Hospital Declaration signed by our superintendent, we have launched comprehensive energy conservation management in medical services, the community, and the staff’s life. To execute environment-friendly promotion with robust strategies, we build up a low-carbon medical system and community with smart green public construction promotion as well as intensifying energy conservation education and communication. Purpose/Methods: With the support of the board and the superintendent, we construct an energy management team, commencing with an environment-friendly system, management, education, and ISO 50001 energy management system; we have ameliorated energy performance and energy efficiency and continuing. Results: In the year 2021, we have achieved multiple goals. The energy management system efficiently controls diesel, natural gas, and electricity usage. About 5% of the consumption is saved when compared to the numbers from 2018 and 2021. Our company develops intelligent services and promotes various paperless electronic operations to provide people with a vibrant and environmentally friendly lifestyle. The goal is to save 68.6% on printing and photocopying by reducing 35.15 million sheets of paper yearly. We strengthen the concept of environmental protection classification among colleagues. In the past two years, the amount of resource recycling has reached more than 650 tons, and the resource recycling rate has reached 70%. The annual growth rate of waste recycling is about 28 metric tons. Conclusions: To build a green medical system with “high efficacy, high value, low carbon, low reliance,” energy stewardship, economic prosperity, and social responsibility are our principles when it comes to formulation of energy conservation management strategies, converting limited sources to efficient usage, developing clean energy, and continuing with sustainable energy.

Keywords: energy efficiency, environmental education, green hospital, sustainable development

Procedia PDF Downloads 76
4624 Reservoir Properties Effect on Estimating Initial Gas in Place Using Flowing Material Balance Method

Authors: Yousef S. Kh. S. Hashem

Abstract:

Accurate estimation of initial gas in place (IGIP) plays an important factor in the decision to develop a gas field. One of the methods that are available in the industry to estimate the IGIP is material balance. This method required that the well has to be shut-in while pressure is measured as it builds to average reservoir pressure. Since gas demand is high and shut-in well surveys are very expensive, flowing gas material balance (FGMB) is sometimes used instead of material balance. This work investigated the effect of reservoir properties (pressure, permeability, and reservoir size) on the estimation of IGIP when using FGMB. A gas reservoir simulator that accounts for friction loss, wellbore storage, and the non-Darcy effect was used to simulate 165 different possible causes (3 pressures, 5 reservoir sizes, and 11 permeabilities). Both tubing pressure and bottom-hole pressure were analyzed using FGMB. The results showed that the FGMB method is very sensitive for tied reservoirs (k < 10). Also, it showed which method is best to be used for different reservoir properties. This study can be used as a guideline for the application of the FGMB method.

Keywords: flowing material balance, gas reservoir, reserves, gas simulator

Procedia PDF Downloads 147
4623 Design and Implementation of an Effective Machine Learning Approach to Crime Prediction and Prevention

Authors: Ashish Kumar, Kaptan Singh, Amit Saxena

Abstract:

Today, it is believed that crimes have the greatest impact on a person's ability to progress financially and personally. Identifying places where individuals shouldn't go is crucial for preventing crimes and is one of the key considerations. As society and technologies have advanced significantly, so have crimes and the harm they wreak. When there is a concentration of people in one place and changes happen quickly, it is even harder to prevent. Because of this, many crime prevention strategies have been embraced as a component of the development of smart cities in numerous cities. However, crimes can occur anywhere; all that is required is to identify the pattern of their occurrences, which will help to lower the crime rate. In this paper, an analysis related to crime has been done; information related to crimes is collected from all over India that can be accessed from anywhere. The purpose of this paper is to investigate the relationship between several factors and India's crime rate. The review has covered information related to every state of India and their associated regions of the period going in between 2001- 2014. However various classes of violations have a marginally unique scope over the years.

Keywords: K-nearest neighbor, random forest, decision tree, pre-processing

Procedia PDF Downloads 85
4622 A Paradigm Shift in the Cost of Illness of Type 2 Diabetes Mellitus over a Decade in South India: A Prevalence Based Study

Authors: Usha S. Adiga, Sachidanada Adiga

Abstract:

Introduction: Diabetes Mellitus (DM) is one of the most common non-communicable diseases which imposes a large economic burden on the global health-care system. Cost of illness studies in India have assessed the health care cost of DM, but have certain limitations due to lack of standardization of the methods used, improper documentation of data, lack of follow up, etc. The objective of the study was to estimate the cost of illness of uncomplicated versus complicated type 2 diabetes mellitus in Coastal Karnataka, India. The study also aimed to find out the trend of cost of illness of the disease over a decade. Methodology: A prevalence based bottom-up approach study was carried out in two tertiary care hospitals located in Coastal Karnataka after ethical approval. Direct Medical costs like annual laboratory costs, pharmacy cost, consultation charges, hospital bed charges, surgical /intervention costs of 238 diabetics and 340 diabetic patients respectively from two hospitals were obtained from the medical record sections. Patients were divided into six groups, uncomplicated diabetes, diabetic retinopathy(DR), nephropathy(DN), neuropathy(DNeu), diabetic foot(DF), and ischemic heart disease (IHD). Different costs incurred in 2008 and 2017 in these groups were compared, to study the trend of cost of illness. Kruskal Wallis test followed by Dunn’s test were used to compare median costs between the groups and Spearman's correlation test was used for correlation studies. Results: Uncomplicated patients had significantly lower costs (p <0.0001) compared to other groups. Patients with IHD had highest Medical expenses (p < 0.0001), followed by DN and DF (p < 0.0001 ). Annual medical costs incurred were 1.8, 2.76, 2.77, 1.76, and 4.34 times higher in retinopathy, nephropathy, diabetic foot, neuropathy and IHD patients as compared to the cost incurred in managing uncomplicated diabetics. Other costs also showed a similar pattern of rising. A positive correlation was observed between the costs incurred and duration of diabetes, a negative correlation between the glycemic status and cost incurred. The cost incurred in the management of DM in 2017 was found to be elevated 1.4 - 2.7 times when compared to that in 2008. Conclusion: It is evident from the study that the economic burden due to diabetes mellitus is substantial. It poses a significant financial burden on the healthcare system, individual and society as a whole. There is a need for the strategies to achieve optimal glycemic control and operationalize regular and early screening methods for complications so as to reduce the burden of the disease.

Keywords: COI, diabetes mellitus, a bottom up approach, economics

Procedia PDF Downloads 115
4621 Analysis of the Relationship between the Old Days Hospitalized with Economic Lost Top Ten Age Productive Disease in Hospital Inpatient Inche Abdul Moeis Samarinda, Indonesia

Authors: Tri Murti Tugiman, Awalyya Fasha

Abstract:

This research aims to analyze the magnitude of the economic losses incurred as a result of a person suffering from a particular disease of the ten highest in the productive age diseases in Hospitals Inche Abdul Moeis Samarinda. This research was a descriptive survey research and a secondary data analysis. For the analysis of economic losses populations used are all in patients who suffer from the 10 highest diseases in the productive age in hospitals IA Moeis Samarinda in 2011. Sampling was performed by using a stratified random sampling with samples of 77 people. Research results indicate that the direct cost community incurred to obtain medical services in hospitals IA Moeis is IDR 74437520. The amount of indirect costs incurred during service in a community hospital is IDR 10562000. The amount lost due to sickness fee is IDR 5377800. The amount of economic lost people to obtain medical services in hospitals IA Moeis is IDR 90377320. The number of days of hospitalization was as much as 171 respondents throughout the day. This study suggests the economic loss could be prevented by changes in the lifestyle of the people who clean and healthy along with the following insurance.

Keywords: hospitalized, economic lost, productive age diseases, secondary data analysis

Procedia PDF Downloads 471
4620 Incidence and Risk Factors of Central Venous Associated Infections in a Tunisian Medical Intensive Care Unit

Authors: Ammar Asma, Bouafia Nabiha, Ghammam Rim, Ezzi Olfa, Ben Cheikh Asma, Mahjoub Mohamed, Helali Radhia, Sma Nesrine, Chouchène Imed, Boussarsar Hamadi, Njah Mansour

Abstract:

Background: Central venous catheter associated infections (CVC-AI) are among the serious hospital-acquired infections. The aims of this study are to determine the incidence of CVC-AI, and their risk factors among patients followed in a Tunisian medical intensive care unit (ICU). Materials / Methods: A prospective cohort study conducted between September 15th, 2015 and November 15th, 2016 in an 8-bed medical ICU including all patients admitted for more than 48h. CVC-AI were defined according to CDC of ATLANTA criteria. The enrollment was based on clinical and laboratory diagnosis of CVC-AI. For all subjects, age, sex, underlying diseases, SAPS II score, ICU length of stay, exposure to CVC (number of CVC placed, site of insertion and duration catheterization) were recorded. Risk factors were analyzed by conditional stepwise logistic regression. The p-value of < 0.05 was considered significant. Results: Among 192 eligible patients, 144 patients (75%) had a central venous catheter. Twenty-eight patients (19.4%) had developed CVC-AI with density rate incidence 20.02/1000 CVC-days. Among these infections, 60.7% (n=17) were systemic CVC-AI (with negative blood culture), and 35.7% (n=10) were bloodstream CVC-AI. The mean SAPS II of patients with CVC-AI was 32.76 14.48; their mean Charlson index was 1.77 1.55, their mean duration of catheterization was 15.46 10.81 days and the mean duration of one central line was 5.8+/-3.72 days. Gram-negative bacteria was determined in 53.5 % of CVC-AI (n= 15) dominated by multi-drug resistant Acinetobacter baumani (n=7). Staphylococci were isolated in 3 CVC-AI. Fourteen (50%) patients with CVC-AI died. Univariate analysis identified men (p=0.034), the referral from another hospital department (p=0.03), tobacco (p=0.006), duration of sedation (p=0.003) and the duration of catheterization (p=0), as possible risk factors of CVC-AI. Multivariate analysis showed that independent factors of CVC-AI were, male sex; OR= 5.73, IC 95% [2; 16.46], p=0.001, Ramsay score; OR= 1.57, IC 95% [1.036; 2.38], p=0.033, and duration of catheterization; OR=1.093, IC 95% [1.035; 1.15], p=0.001. Conclusion: In a monocenter cohort, CVC-AI had a high density and is associated with poor outcome. Identifying the risk factors is necessary to find solutions for this major health problem.

Keywords: central venous catheter associated infection, intensive care unit, prospective cohort studies, risk factors

Procedia PDF Downloads 360
4619 Keeping under the Hat or Taking off the Lid: Determinants of Social Enterprise Transparency

Authors: Echo Wang, Andrew Li

Abstract:

Transparency could be defined as the voluntary release of information by institutions that is relevant to their own evaluation. Transparency based on information disclosure is recognised to be vital for the Third Sector, as civil society organisations are under pressure to become more transparent to answer the call for accountability. The growing importance of social enterprises as hybrid organisations emerging from the nexus of the public, the private and the Third Sector makes their transparency a topic worth exploring. However, transparency for social enterprises has not yet been studied: as a new form of organisation that combines non-profit missions with commercial means, it is unclear to both the practical and the academic world if the shift in operational logics from non-profit motives to for-profit pursuits has significantly altered their transparency. This is especially so in China, where informational governance and practices of information disclosure by local governments, industries and civil society are notably different from other countries. This study investigates the transparency-seeking behaviour of social enterprises in Greater China to understand what factors at the organisational level may affect their transparency, measured by their willingness to disclose financial information. We make use of the Survey on the Models and Development Status of Social Enterprises in the Greater China Region (MDSSGCR) conducted in 2015-2016. The sample consists of more than 300 social enterprises from the Mainland, Hong Kong and Taiwan. While most respondents have provided complete answers to most of the questions, there is tremendous variation in the respondents’ demonstrated level of transparency in answering those questions related to the financial aspects of their organisations, such as total revenue, net profit, source of revenue and expense. This has led to a lot of missing data on such variables. In this study, we take missing data as data. Specifically, we use missing values as a proxy for an organisation’s level of transparency. Our dependent variables are constructed from missing data on total revenue, net profit, source of revenue and cost breakdown. In addition, we also take into consideration the quality of answers in coding the dependent variables. For example, to be coded as being transparent, an organization must report the sources of at least 50% of its revenue. We have four groups of predictors of transparency, namely nature of organization, decision making body, funding channel and field of concentration. Furthermore, we control for an organisation’s stage of development, self-identity and region. The results show that social enterprises that are at their later stages of organisational development and are funded by financial means are significantly more transparent than others. There is also some evidence that social enterprises located in the Northeast region in China are less transparent than those located in other regions probably because of local political economy features. On the other hand, the nature of the organisation, the decision-making body and field of concentration do not systematically affect the level of transparency. This study provides in-depth empirical insights into the information disclosure behaviour of social enterprises under specific social context. It does not only reveal important characteristics of Third Sector development in China, but also contributes to the general understanding of hybrid institutions.

Keywords: China, information transparency, organisational behaviour, social enterprise

Procedia PDF Downloads 182