Search results for: optimal reaction network

Authors: Mohammad Reza Rahimi Khoygani, Reza Ghasemi

Abstract:

In this paper, designing direct adaptive neural controller is applied for a class of a nonlinear pendulum dynamic system. The radial basis function (RBF) is used for the Neural network (NN). The adaptive neural controller is robust in presence of external and internal uncertainties. Both the effectiveness of the controller and robustness against disturbances are the merits of this paper. The promising performance of the proposed controllers investigates in simulation results.

Keywords: adaptive control, pendulum dynamical system, nonlinear control, adaptive neural controller, nonlinear dynamical, neural network, RBF, driven pendulum, position control

Procedia PDF Downloads 664

Authors: Farzaneh Sasanpour, Saeed Amini Varaki

Abstract:

Resilience is an important goal for cities as urban areas face an increasing range of challenges in the 21st century; therefore, according to the characteristics of risks, adopting an approach that responds to sensitive conditions in the risk management process is the resilience of cities. In the meantime, most of the resilience assessments have dealt with natural hazards and less attention has been paid to pandemics.In the covid-19 pandemic, the country of Iran and especially the metropolis of Tehran, was not immune from the crisis caused by its effects and consequences and faced many challenges. One of the methods that can increase the resilience of Tehran's metropolis against possible crises in the future is future studies. This research is practical in terms of type. The general pattern of the research will be descriptive-analytical and from the point of view that it is trying to communicate between the components and provide urban resilience indicators with pandemic crises and explain the scenarios, its future studies method is exploratory. In order to extract and determine the key factors and driving forces effective on the resilience of Tehran's urban areas against pandemic crises (Covid-19), the method of structural analysis of mutual effects and Micmac software was used. Therefore, the primary factors and variables affecting the resilience of Tehran's urban areas were set in 5 main factors, including physical-infrastructural (transportation, spatial and physical organization, streets and roads, multi-purpose development) with 39 variables based on mutual effects analysis. Finally, key factors and variables in five main areas, including managerial-institutional with five variables; Technology (intelligence) with 3 variables; economic with 2 variables; socio-cultural with 3 variables; and physical infrastructure, were categorized with 7 variables. These factors and variables have been used as key factors and effective driving forces on the resilience of Tehran's urban areas against pandemic crises (Covid-19), in explaining and developing scenarios. In order to develop the scenarios for the resilience of Tehran's urban areas against pandemic crises (Covid-19), intuitive logic, scenario planning as one of the future research methods and the Global Business Network (GBN) model were used. Finally, four scenarios have been drawn and selected with a creative method using the metaphor of weather conditions, which is indicative of the general outline of the conditions of the metropolis of Tehran in that situation. Therefore, the scenarios of Tehran metropolis were obtained in the form of four scenarios: 1- solar scenario (optimal governance and management leading in smart technology) 2- cloud scenario (optimal governance and management following in intelligent technology) 3- dark scenario (optimal governance and management Unfavorable leader in intelligence technology) 4- Storm scenario (unfavorable governance and management of follower in intelligence technology). The solar scenario shows the best situation and the stormy scenario shows the worst situation for the Tehran metropolis. According to the findings obtained in this research, city managers can, in order to achieve a better tomorrow for the metropolis of Tehran, in all the factors and components of urban resilience against pandemic crises by using future research methods, a coherent picture with the long-term horizon of 2050, from the path Provide urban resilience movement and platforms for upgrading and increasing the capacity to deal with the crisis. To create the necessary platforms for the realization, development and evolution of the urban areas of Tehran in a way that guarantees long-term balance and stability in all dimensions and levels.

Keywords: future research, resilience, crisis, pandemic, covid-19, Tehran

Procedia PDF Downloads 65

Authors: Ibrahim Watad, Ibrahim Abdulhalim

Abstract:

Conventional spectroscopic surface plasmon resonance (SPR) sensors are widely used, both in fundamental research and environmental monitoring as well as healthcare diagnostics. However, they still lack the low limit of detection (LOD) and there still a place for improvement. SPR conventional sensors are based on the detection of a dip in the reflectivity spectrum which is relatively wide. To improve the performance of these sensors, many techniques and methods proposed either to reduce the width of the dip or to increase the sensitivity. Together with that, profiting from the sharp jump in the phase spectrum under SPR, several works suggested the extraction of the phase of the reflected wave. However, existing phase measurement setups are in general more complicated compared to the conventional setups, require more stability and are very sensitive to external vibrations and noises. In this study, a simple polarimetric technique for phase extraction under SPR is presented, followed by a theoretical error analysis and an experimental verification. The advantages of the proposed technique upon existing techniques will be elaborated, together with conclusions regarding the best polarimetric function, and its corresponding optimal metal layer range of thicknesses to use under the conventional Kretschmann-Raether configuration.

Keywords: plasmonics, polarimetry, thin films, optical sensors

Procedia PDF Downloads 395

Authors: Rafael Marinho de Andrade, Elcio Hideti Shiguemori, Rafael Duarte Coelho dos Santos

Abstract:

Relying on computer vision, many clever things are possible in order to make the world safer and optimized on resource management, especially considering time and attention as manageable resources, once the modern world is very abundant in cameras from inside our pockets to above our heads while crossing the streets. Thus, automated solutions based on computer vision techniques to detect, react, or even prevent relevant events such as robbery, car crashes and traffic jams can be accomplished and implemented for the sake of both logistical and surveillance improvements. In this paper, we present an approach for vehicles’ abnormal behaviors detection from highway footages, in which the vectorial data of the vehicles’ displacement are extracted directly from surveillance cameras footage through object detection and tracking with a deep convolutional neural network and inserted into a long-short term memory neural network for behavior classification. The results show that the classifications of behaviors are consistent and the same principles may be applied to other trackable objects and scenarios as well.

Keywords: artificial intelligence, behavior detection, computer vision, convolutional neural networks, LSTM, highway footage

Procedia PDF Downloads 160

Authors: Mustafa Al-Refai

Abstract:

This paper presents the optimal design and simulation of a grid-connected Photovoltaic (PV) system to supply electric power to meet the energy demand by Electrical Department in University of Tripoli Libya. Solar radiation is the key factor determining electricity produced by photovoltaic (PV) systems. This paper is designed to develop a novel method to calculate the solar photovoltaic generation capacity on the basis of Mean Global Solar Radiation data available for Tripoli Libya and finally develop a system design of possible plant capacity for the available roof area. MatLab/Simulink Programming tools and monthly average solar radiation data are used for this design and simulation. The specifications of equipments are provided based on the availability of the components in the market. Simulation results and analyses are presented to validate the proposed system configuration.

Keywords: photovoltaic (PV), grid, Simulink, solar energy, power plant, solar irradiation

Procedia PDF Downloads 293

Authors: Andrée-Anne Parent, Alain-Steve Comtois

Abstract:

The Antarctica environment can be a great challenge for human exploration. Explorers need to be focused on the task and require the physical abilities to succeed and survive in complete autonomy in this hostile environment. The aim of this study was to observe cognitive performance and physiological stress with a biomarker (cortisol) and hand grip strength during an expedition in Antarctica. A total of 6 explorers were in complete autonomous exploration on the Forbidden Plateau in Antarctica to reach unknown summits during a 30 day period. The Stroop Test, a simple reaction time, and mood scale (PANAS) tests were performed every week during the expedition. Saliva samples were taken before sailing to Antarctica, the first day on the continent, after the mission on the continent and on the boat return trip. Furthermore, hair samples were taken before and after the expedition. The results were analyzed with SPSS using ANOVA repeated measures. The Stroop and mood scale results are presented in the following order: 1) before sailing to Antarctica, 2) the first day on the continent, 3) after the mission on the continent and 4) on the boat return trip. No significant difference was observed with the Stroop (759±166 ms, 850±114 ms, 772±179 ms and 833±105 ms, respectively) and the PANAS (39.5 ±5.7, 40.5±5, 41.8±6.9, 37.3±5.8 positive emotions, and 17.5±2.3, 18.2±5, 18.3±8.6, 15.8±5.4 negative emotions, respectively) (p>0.05). However, there appears to be an improvement at the end of the second week. Furthermore, the simple reaction time was significantly lower at the end of the second week, a moment where important decisions were taken about the mission, vs the week before (416±39 ms vs 459.8±39 ms respectively; p=0.030). Furthermore, the saliva cortisol was not significantly different (p>0.05) possibly due to important variations and seemed to reach a peak on the first day on the continent. However, the cortisol from the hair pre and post expedition increased significantly (2.4±0.5 pg/mg pre-expedition and 16.7±9.2 pg/mg post-expedition, p=0.013) showing important stress during the expedition. Moreover, no significant difference was observed on the grip strength except between after the mission on the continent and after the boat return trip (91.5±21 kg vs 85±19 kg, p=0.20). In conclusion, the cognitive performance does not seem to be affected during the expedition. Furthermore, it seems to increase for specific important events where the crew seemed to focus on the present task. The physiological stress does not seem to change significantly at specific moments, however, a global pre-post mission measure can be important and for this reason, for long-term missions, a pre-expedition baseline measure is important for crewmembers.

Keywords: Antarctica, cognitive performance, expedition, physiological adaptation, reaction time

Procedia PDF Downloads 239

Authors: Bingquan Shen

Abstract:

Convolutional Neural Networks (CNN) have demonstrated their effectiveness in synthesizing 3D views of object instances at various viewpoints. Given the problem where one have limited viewpoints of a particular object for classification, we present a pose normalization architecture to transform the object to existing viewpoints in the training dataset before classification to yield better classification performance. We have demonstrated that this Pose Normalization Network (PNN) can capture the style of the target object and is able to re-render it to a desired viewpoint. Moreover, we have shown that the PNN improves the classification result for the 3D chairs dataset and ShapeNet airplanes dataset when given only images at limited viewpoint, as compared to a CNN baseline.

Keywords: convolutional neural networks, object classification, pose normalization, viewpoint invariant

Procedia PDF Downloads 346

Authors: Hala Zaghloul, Taymoor Nazmy

Abstract:

One of the great challenges of the 21st century is to build a robot that can perceive and act within its environment and communicate with people, while also exhibiting the cognitive capabilities that lead to performance like that of people. The Pulse Coupled Neural Network, PCNN, is a relative new ANN model that derived from a neural mammal model with a great potential in the area of image processing as well as target recognition, feature extraction, speech recognition, combinatorial optimization, compressed encoding. PCNN has unique feature among other types of neural network, which make it a candid to be an important approach for perceiving in cognitive systems. This work show and emphasis on the potentials of PCNN to perform different tasks related to image processing. The main drawback or the obstacle that prevent the direct implementation of such technique, is the need to find away to control the PCNN parameters toward perform a specific task. This paper will evaluate the performance of PCNN standard model for processing images with different properties, and select the important parameters that give a significant result, also, the approaches towards find a way for the adaptation of the PCNN parameters to perform a specific task.

Keywords: cognitive system, image processing, segmentation, PCNN kernels

Procedia PDF Downloads 272

Authors: KumarShashvat, ArshpreetKaur, RajeshKumar, Raman Chadha

Abstract:

Wireless sensor networks have principal characteristic of having restricted energy and with limitation that energy of the nodes cannot be replenished. To increase the lifetime in this scenario WSN route for data transmission is opted such that utilization of energy along the selected route is negligible. For this energy efficient network, dandy infrastructure is needed because it impinges the network lifespan. Clustering is a technique in which nodes are grouped into disjoints and non–overlapping sets. In this technique data is collected at the cluster head. In this paper, Adaptive-PSO algorithm is proposed which forms energy aware clusters by minimizing the cost of locating the cluster head. The main concern is of the suitability of the swarms by adjusting the learning parameters of PSO. Particle Swarm Optimization converges quickly at the beginning stage of the search but during the course of time, it becomes stable and may be trapped in local optima. In suggested network model swarms are given the intelligence of the spiders which makes them capable enough to avoid earlier convergence and also help them to escape from the local optima. Comparison analysis with traditional PSO shows that new algorithm considerably enhances the performance where multi-dimensional functions are taken into consideration.

Keywords: Particle Swarm Optimization, adaptive – PSO, comparison between PSO and A-PSO, energy efficient clustering

Procedia PDF Downloads 242

Authors: Tayyaba Hussain, Sobia Jangsher, Saqib Ali, Saqib Ejaz

Abstract:

Unmanned Aerial vehicles (UAV’s) have gained great popularity due to their remoteness, ease of deployment and high maneuverability in different applications like real-time surveillance, image capturing, weather atmospheric studies, disaster site monitoring and mapping. These applications can involve a real-time communication with the ground station. However, altitude and mobility possess a few challenges for the communication. UAV’s at high altitude usually require more transmit power. One possible solution can be with the use of multi hops (UAV’s acting as relays) and exploiting the mobility pattern of the UAV’s. In this paper, we studied a relay (UAV’s acting as relays) selection for a reliable transmission to a destination UAV. We exploit the mobility information of the UAV’s to propose a Mobility-Aware Relay Selection (MARS) algorithm with the objective of giving improved data rates. The results are compared with Non Mobility-Aware relay selection scheme and optimal values. Numerical results show that our proposed MARS algorithm gives 6% better achievable data rates for the mobile UAV’s as compared with Non MobilityAware relay selection scheme. On average a decrease of 20.2% in data rate is achieved with MARS as compared with SDP solver in Yalmip.

Keywords: mobility aware, relay selection, time division multiple acess, unmanned aerial vehicle

Procedia PDF Downloads 232

Authors: Samia Dardouri, Ridha Bouallegue

Abstract:

Scheduling is the process of dynamically allocating physical resources to User Equipment (UE) based on scheduling algorithms implemented at the LTE base station. Various algorithms have been proposed by network researchers as the implementation of scheduling algorithm which represents an open issue in Long Term Evolution (LTE) standard. This paper makes an attempt to study and compare the performance of PF, MLWDF and EXP/PF scheduling algorithms. The evaluation is considered for a single cell with interference scenario for different flows such as Best effort, Video and VoIP in a pedestrian and vehicular environment using the LTE-Sim network simulator. The comparative study is conducted in terms of system throughput, fairness index, delay, packet loss ratio (PLR) and total cell spectral efficiency.

Keywords: LTE, multimedia flows, scheduling algorithms, mobile computing

Procedia PDF Downloads 380

Authors: Lubem Matthew Kwaghkor

Abstract:

Terrorism, which remains one of the largest threats faced by various nations and communities around the world, including Nigeria, is the calculated use of violence to create a general climate of fear in a population to attain particular goals that might be political, religious, or economical. Several terrorist groups are currently active in Nigeria, leading to attacks on both civil and military targets. Among these groups, Boko Haram is the deadliest terrorist group operating majorly in Borno State. The southern part of Borno State in North-Eastern Nigeria has been plagued by terrorism, insurgency, and conflict for several years. Understanding the dynamics of terrorism is crucial for developing effective strategies to mitigate its impact on communities and to facilitate peace-building efforts. This research aims to develop a mathematical model that captures the dynamics of terrorism within the southern part of Borno State, Nigeria, capturing both government and local community intervention strategies as control measures in combating terrorism. A compartmental model of five nonlinear differential equations is formulated. The model analyses show that a feasible solution set of the model exists and is bounded. Stability analyses show that both the terrorism free equilibrium and the terrorism endermic equilibrium are asymptotically stable, making the model to have biological meaning. Optimal control theory will be employed to identify the most effective strategy to prevent or minimize acts of terrorism. The research outcomes are expected to contribute towards enhancing security and stability in Southern Borno State while providing valuable insights for policymakers, security agencies, and researchers. This is an ongoing research.

Keywords: modelling, terrorism, optimal control, susceptible, non-susceptible, community intervention

Procedia PDF Downloads 7

Authors: Carlos A. C. G. Neto, Natan C. G. e Silva , Thaís de O. Costa, Luciana R. B. Gonçalves, Maria V. P. Rocha

Abstract:

β-galactosidases (E.C. 3.2.1.23) are enzymes that have attracted by catalyzing the hydrolysis of lactose and in producing galacto-oligosaccharides by favoring transgalactosylation reactions. These enzymes, when immobilized, can have some enzymatic characteristics substantially improved, and the coating of supports with multifunctional polymers is a promising alternative to enhance the stability of the biocatalysts, among which polyethylenimine (PEI) stands out. PEI has certain properties, such as being a flexible polymer that suits the structure of the enzyme, giving greater stability, especially for multimeric enzymes such as β-galactosidases. Besides that, protects them from environmental variations. The use of chitosan support coated with PEI could improve the catalytic efficiency of β-galactosidase from Kluyveromyces lactis in the transgalactosylation reaction for the production of prebiotics, such as lactulose since this strain is more effective in the hydrolysis reaction. In this context, the aim of the present work was first to develop biocatalysts of β-galactosidase from K. lactis immobilized on chitosan-coated with PEI, determining the immobilization parameters, its operational and thermal stability, and then to apply it in hydrolysis and transgalactolisation reactions to produce lactulose using whey as a substrate. The immobilization of β-galactosidase in chitosan previously functionalized with 0.8% (v/v) glutaraldehyde and then coated with 10% (w/v) PEI solution was evaluated using an enzymatic load of 10 mg protein per gram support. Subsequently, the hydrolysis and transgalactosylation reactions were conducted at 50 °C, 120 RPM for 20 minutes, using whey supplemented with fructose at a ratio of 1:2 lactose/fructose, totaling 200 g/L. Operational stability studies were performed in the same conditions for 10 cycles. Thermal stabilities of biocatalysts were conducted at 50 ºC in 50 mM phosphate buffer, pH 6.6 with 0.1 mM MnCl2. The biocatalyst whose support was coated was named CHI_GLU_PEI_GAL, and the one that was not coated was named CHI_GLU_GAL. The coating of the support with PEI considerably improved the parameters of immobilization. The immobilization yield increased from 56.53% to 97.45%, biocatalyst activity from 38.93 U/g to 95.26 U/g and the efficiency from 3.51% to 6.0% for uncoated and coated support, respectively. The biocatalyst CHI_GLU_PEI_GAL was better than CHI_GLU_GAL in the hydrolysis of lactose and production of lactulose, converting 97.05% of lactose at 5 min of reaction and producing 7.60 g/L lactulose in the same time interval. QUI_GLU_PEI_GAL biocatalyst was stable in the hydrolysis reactions of lactose during the 10 cycles evaluated, converting 73.45% lactose even after the tenth cycle, and in the lactulose production was stable until the fifth cycle evaluated, producing 10.95 g/L lactulose. However, the thermal stability of CHI_GLU_GAL biocatalyst was superior, with a half-life time 6 times higher, probably because the enzyme was immobilized by covalent bonding, which is stronger than adsorption (CHI_GLU_PEI_GAL). Therefore, the strategy of coating the supports with PEI has proven to be effective for the immobilization of β-galactosidase from K. lactis, considerably improving the immobilization parameters, as well as, the catalytic action of the enzyme. Besides that, this process can be economically viable due to the use of an industrial residue as a substrate.

Keywords: β-galactosidase, immobilization, kluyveromyces lactis, lactulose, polyethylenimine, transgalactosylation reaction, whey

Procedia PDF Downloads 108

Authors: A. A. Okafor, C. H. Achebe, J. L. Chukwuneke, C. G. Ozoegwu

Abstract:

The performance of an engine whose basic design parameters are known can be predicted with the assistance of simulation programs into the less time, cost and near value of actual. This paper presents a comprehensive mathematical model of the performance parameters of four stroke spark ignition engine. The essence of this research work is to develop a mathematical model for the analysis of engine performance parameters of four stroke spark ignition engine before embarking on full scale construction, this will ensure that only optimal parameters are in the design and development of an engine and also allow to check and develop the design of the engine and it’s operation alternatives in an inexpensive way and less time, instead of using experimental method which requires costly research test beds. To achieve this, equations were derived which describe the performance parameters (sfc, thermal efficiency, mep and A/F). The equations were used to simulate and optimize the engine performance of the model for various engine speeds. The optimal values obtained for the developed bivariate mathematical models are: sfc is 0.2833kg/kwh, efficiency is 28.77% and a/f is 20.75.

Keywords: bivariate models, engine performance, injector engine, optimization, performance parameters, simulation, spark ignition

Procedia PDF Downloads 320

Authors: Chothmal

Abstract:

In this paper, we present a route discovery process which uses the signal strength on a link as a parameter of its inclusion in the route discovery method. The proposed signal-to-interference and noise ratio (SINR) based multipath reactive routing protocol is named as SINR-MP protocol. The proposed SINR-MP routing protocols has two following two features: a) SINR-MP protocol selects routes based on the SINR of the links during the route discovery process therefore it select the routes which has long lifetime and low frame error rate for data transmission, and b) SINR-MP protocols route discovery process is multipath which discovers more than one SINR based route between a given source destination pair. The multiple routes selected by our SINR-MP protocol are node-disjoint in nature which increases their robustness against link failures, as failure of one route will not affect the other route. The secondary route is very useful in situations where the primary route is broken because we can now use the secondary route without causing a new route discovery process. Due to this, the network overhead caused by a route discovery process is avoided. This increases the network performance greatly. The proposed SINR-MP routing protocol is implemented in the trail version of network simulator called Qualnet.

Keywords: ad hoc networks, quality of service, video streaming, H.264/SVC, multiple routes, video traces

Procedia PDF Downloads 242

Authors: Senay Yitmen

Abstract:

This research investigated individual’s support and helping intentions towards Syrian refugees in Turkey. This is examined in relation to perceived threat and negative emotions, and also to the perceptions of whether one’s intimate social network (family and friends) considers Syrians a threat (descriptive network norm) and whether this network morally supports Syrian refugees (injunctive norms). A questionnaire study was conducted among Turkish participants (n= 565) and the results showed that perception of threat was associated with negative emotions which, in turn, were related to less support of Syrian refugees. Additionally, descriptive norms moderated the relationship between perceived threat and negative emotions towards Syrian refugees. Furthermore, injunctive norms moderated the relationship between negative emotions and support to Syrian refugees. Specifically, the findings indicate that perceived threat is associated with less support of Syrian refugees through negative emotions when descriptive norms are weak and injunctive norms are strong. Injunctive norms appear to trigger a dilemma over the decision to conform or not to conform: when one has negative emotions as a result of perceived threat, it becomes more difficult to conform to the moral obligation of injunctive norms which is associated with less support of Syrian refugees. Hence, these findings demonstrate that both descriptive and injunctive norms are important and play different roles in individual’s support of Syrian refugees.

Keywords: descriptive norms, emotions, injunctive norms, the perception of threat

Procedia PDF Downloads 183

Authors: Sajida Rasheed, Imran Hashmi, Luiza Campos, Qizhi Zhou, Kim Keu

Abstract:

A quadratic model (p ˂ 0.0001) was developed by using central composite design of 50 experimental runs (42 non-center + 8 center points) to assess efficiency of background chlorine residuals in combating accidental microbial episode in a prototype distribution network (DN) (rig). A known amount of background chlorine residuals were maintained in DN and a required number of bacteria, Escherichia coli K-12 strain were introduced by an injection port in the pipe loop system. Samples were taken at various time intervals at different pipe lengths. Spread plate count was performed to count bacterial number. The model developed was significant. With microbial concentration and time (p ˂ 0.0001), pipe length (p ˂ 0.022), background chlorine residuals (p ˂ 0.07) and time^2 (p ˂ 0.09) as significant factors. The ramp function of variables shows that at the microbial count of 10^6, at 0.76 L/min, and pipe length of 133 meters, a background residual chlorine 0.16 mg/L was enough for complete inactivation of microbial episode in approximately 18 minutes.

Keywords: central composite design (CCD), distribution network, Escherichia coli, residual chlorine

Procedia PDF Downloads 457

Authors: Yu-Ting Tsai, Chiun-Chieh Hsu, Yu-Chun Chu

Abstract:

In recent years, due to the development of wireless network technology, many researchers have devoted to the study of wireless sensor networks. The applications of wireless sensor network mainly use the sensor nodes to collect the required information, and send the information back to the users. Since the sensed area is difficult to reach, there are many restrictions on the design of the sensor nodes, where the most important restriction is the limited energy of sensor nodes. Because of the limited energy, researchers proposed a number of ways to reduce energy consumption and balance the load of sensor nodes in order to increase the network lifetime. In this paper, we proposed the Energy-Balanced Clustering method with Auxiliary Members on Wireless Sensor Networks（EBCAM）based on the cluster routing. The main purpose is to balance the energy consumption on the sensed area and average the distribution of dead nodes in order to avoid excessive energy consumption because of the increasing in transmission distance. In addition, we use the residual energy and average energy consumption of the nodes within the cluster to choose the cluster heads, use the multi hop transmission method to deliver the data, and dynamically adjust the transmission radius according to the load conditions. Finally, we use the auxiliary cluster members to change the delivering path according to the residual energy of the cluster head in order to its load. Finally, we compare the proposed method with the related algorithms via simulated experiments and then analyze the results. It reveals that the proposed method outperforms other algorithms in the numbers of used rounds and the average energy consumption.

Keywords: auxiliary nodes, cluster, load balance, routing algorithm, wireless sensor network

Procedia PDF Downloads 271

Authors: Ksenija Dumičić, Anita Čeh Časni, Berislav Žmuk

Abstract:

The aim of this paper is to select the most accurate forecasting method for predicting the future values of the unemployment rate in selected European countries. In order to do so, several forecasting techniques adequate for forecasting time series with trend component, were selected, namely: double exponential smoothing (also known as Holt`s method) and Holt-Winters` method which accounts for trend and seasonality. The results of the empirical analysis showed that the optimal model for forecasting unemployment rate in Greece was Holt-Winters` additive method. In the case of Spain, according to MAPE, the optimal model was double exponential smoothing model. Furthermore, for Croatia and Italy the best forecasting model for unemployment rate was Holt-Winters` multiplicative model, whereas in the case of Portugal the best model to forecast unemployment rate was Double exponential smoothing model. Our findings are in line with European Commission unemployment rate estimates.

Keywords: European Union countries, exponential smoothing methods, forecast accuracy unemployment rate

Procedia PDF Downloads 365

Authors: Daniel Fulus Fom, Gau Patrick Damulak

Abstract:

In this study, the Autoregressive Fractional Integrated Moving Average (ARFIMA) and Jordan Recurrent Neural Network (JRNN) models were employed to model the forecasting performance of the daily turbidity flow of White Clay Creek (WCC). The two methods were applied to the log difference series of the daily turbidity flow series of WCC. The measurements of error employed to investigate the forecasting performance of the ARFIMA and JRNN models are the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The outcome of the investigation revealed that the forecasting performance of the JRNN technique is better than the forecasting performance of the ARFIMA technique in the mean square error sense. The results of the ARFIMA and JRNN models were obtained by the simulation of the models using MATLAB version 8.03. The significance of using the log difference series rather than the difference series is that the log difference series stabilizes the turbidity flow series than the difference series on the ARFIMA and JRNN.

Keywords: auto regressive, mean absolute error, neural network, root square mean error

Procedia PDF Downloads 266

Authors: D. Kumar, S. Kumar, A. G. Memon, R. A. Memon, K. Harijan

Abstract:

A considerable amount of energy is usually lost due to compression of insulation in Heating, ventilation, and air conditioning (HVAC) duct. In this paper, the economic impact of compression of insulation is estimated. Relevant mathematical models were used to estimate the optimal thickness at the points of compression. Furthermore, the payback period is calculated for the optimal thickness at the critical parts of supply air duct (SAD) and return air duct (RAD) considering natural gas (NG) and liquefied petroleum gas (LPG) as fuels for chillier operation. The mathematical model is developed using preliminary data obtained for an HVAC system of a pharmaceutical company. The higher heat gain and cooling loss, due to compression of thermal insulation, is estimated using relevant heat transfer equations. The results reveal that maximum energy savings (ES) in SAD is 34.5 and 40%, while in RAD is 22.9% and 29% for NG and LPG, respectively. Moreover, the minimum payback period (PP) for SAD is 2 and 1.6years, while in RAD is 4.3 and 2.7years for NG and LPG, respectively. The optimum insulation thickness (OIT) corresponding to maximum ES and minimum PP is estimated to be 35 and 42mm for SAD, while 30 and 38mm for RAD in case of NG and LPG, respectively.

Keywords: optimum insulation thickness, life cycle cost analysis, payback period, HVAC system

Procedia PDF Downloads 213

Authors: Kais Manai

Abstract:

The main part of this work focuses on the study of pion/muon separation at low energy using a nuclear Emulsion Cloud Chamber (ECC) made of lead and nuclear emulsion films. The work consists of two parts: particle reconstruction algorithm and a Neural Network that assigns to each reconstructed particle the probability to be a muon or a pion. The pion/muon separation algorithm has been optimized by using a detailed Monte Carlo simulation of the ECC and tested on real data. The algorithm allows to achieve a 60% muon identification efficiency with a pion misidentification smaller than 3%.

Keywords: nuclear emulsion, particle identification, tracking, neural network

Procedia PDF Downloads 496

Authors: Mikheil Kalmakhelidze

Abstract:

Record linkage (RL) problem has become more and more important in recent years due to the growing interest towards big data analysis. The problem can be formulated in a very simple way: Given two entries a and b of a database, decide whether they represent the same object or not. There are two classical deterministic and probabilistic ways of solving the RL problem. Using simple Bayes classifier in many cases produces useful results but sometimes they show to be poor. In recent years several successful approaches have been made towards solving specific RL problems by neural network algorithms including single layer perception, multilayer back propagation network etc. In our work, we model the RL problem for specific dataset of student applications in fuzzy description logic (FDL) where linkage of specific pair (a,b) depends on the truth value of corresponding formula A(a,b) in a canonical FDL model. As a main result, we build neural network for deciding truth value of FDL formulas in a canonical model and thus link RL problem to machine learning. We apply the approach to dataset with 10000 entries and also compare to classical RL solving approaches. The results show to be more accurate than standard probabilistic approach.

Keywords: description logic, fuzzy logic, neural networks, record linkage

Procedia PDF Downloads 269

Authors: Fanqiang Kong, Chending Bian

Abstract:

Sparse unmixing is a promising approach in a semisupervised fashion by assuming that the observed pixels of a hyperspectral image can be expressed in the form of linear combination of only a few pure spectral signatures (end members) in an available spectral library. However, the sparse unmixing problem still remains a great challenge at finding the optimal subset of endmembers for the observed data from a large standard spectral library, without considering the spatial information. Under such circumstances, a sparse unmixing algorithm termed as non-local simultaneous sparse unmixing (NLSSU) is presented. In NLSSU, the non-local simultaneous sparse representation method for endmember selection of sparse unmixing, is used to finding the optimal subset of endmembers for the similar image patch set in the hyperspectral image. And then, the non-local means method, as a regularizer for abundance estimation of sparse unmixing, is used to exploit the abundance image non-local self-similarity. Experimental results on both simulated and real data demonstrate that NLSSU outperforms the other algorithms, with a better spectral unmixing accuracy.

Keywords: hyperspectral unmixing, simultaneous sparse representation, sparse regression, non-local means

Procedia PDF Downloads 242

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 153

Authors: Nazmul Shahadat, Anthony S. Maida

Abstract:

In recent years, hypercomplex inspired neural networks improved deep CNN architectures due to their ability to share weights across input channels and thus improve cohesiveness of representations within the layers. The work described herein studies the effect of replacing existing layers in an Axial Attention ResNet with their quaternion variants that use cross-channel weight sharing to assess the effect on image classification. We expect the quaternion enhancements to produce improved feature maps with more interlinked representations. We experiment with the stem of the network, the bottleneck layer, and the fully connected backend by replacing them with quaternion versions. These modifications lead to novel architectures which yield improved accuracy performance on the ImageNet300k classification dataset. Our baseline networks for comparison were the original real-valued ResNet, the original quaternion-valued ResNet, and the Axial Attention ResNet. Since improvement was observed regardless of which part of the network was modified, there is a promise that this technique may be generally useful in improving classification accuracy for a large class of networks.

Keywords: axial attention, representational networks, weight sharing, cross-channel correlations, quaternion-enhanced axial attention, deep networks

Procedia PDF Downloads 78

Authors: Pooja Kumbhare

Abstract:

Water is an important resource for the survival of life. The inadequate availability of surface water makes people depend on ground water for fulfilling their needs. However, ground water is generally too hard to satisfy the requirements for domestic as well as industrial applications. Removal of hardness involves various techniques such as lime soda process, ion exchange, reverse osmosis, nano-filtration, distillation, and, evaporation, etc. These techniques have individual problems such as high annual operating cost, sediment formation on membrane, sludge disposal problem, etc. Electrocoagulation (EC) is being explored as modern and cost-effective technology to cope up with the growing demand of high water quality at the consumer end. In general, earlier studies on electrocoagulation for hardness removal are found to deploy batch processes. As batch processes are always inappropriate to deal with large volume of water to be treated, it is essential to develop continuous flow EC process. So, in the present study, an attempt is made to investigate continuous flow EC process for decreasing excessive hardness of bore-well water. The experimental study has been conducted using 12 aluminum electrodes (25cm*10cm, 1cm thick) provided in EC reactor with volume of 8 L. Bore well water sample, collected from a local bore-well (i.e. at – Vishrambag, Sangli; Maharashtra) having average initial hardness of 680 mg/l (Range: 650 – 700 mg/l), was used for the study. Continuous flow electrocoagulation experiments were carried out by varying operating parameters specifically reaction time (Range: 10 – 60 min), voltage (Range: 5 – 20 V), current (Range: 1 – 5A). Based on the experimental study, it is found that hardness removal to the desired extent could be achieved even for continuous flow EC reactor, so the use of it is found promising.

Keywords: hardness, continuous flow EC process, aluminum electrode, optimal operating parameters

Procedia PDF Downloads 177

Authors: Mahdi Mottahedi, Peter Zahn, Armin Lechler, Alexander Verl

Abstract:

Optimal topology of components leads to the maximum stiffness with the minimum material use. For the generation of these topologies, normally algorithms are employed, which tackle manufacturing limitations, at the cost of the optimal result. The global optimum result with penalty factor one, however, cannot be fabricated with conventional methods. In this article, an additive manufacturing method is introduced, in order to enable the production of global topology optimization results. For a benchmark, topology optimization with higher and lower penalty factors are performed. Different algorithms are employed in order to interpret the results of topology optimization with lower factors in many microstructure layers. These layers are then joined to form the final geometry. The algorithms’ benefits are then compared experimentally and numerically for the best interpretation. The findings demonstrate that by implementation of the selected algorithm, the stiffness of the components produced with this method is higher than what could have been produced by conventional techniques.

Keywords: topology optimization, additive manufacturing, 3D-printer, laminated object manufacturing

Procedia PDF Downloads 335

Authors: Alafara A. Baba, Kuranga I. Ayinla, Folahan A. Adekola, Rafiu B. Bale

Abstract:

Due to increasing demands and diverse applications of copper oxide as pigment in ceramics, cuprammonium hydroxide solution for rayon, p-type semi-conductor, dry cell batteries production and as safety disposal of hazardous materials, a study on the hydrometallurgical operations involving leaching, solvent extraction and precipitation for the recovery of copper for producing high grade copper oxide from a Nigerian chalcopyrite ore in chloride media has been examined. At a particular set of experimental parameter with respect to acid concentration, reaction temperature and particle size, the leaching investigation showed that the ore dissolution increases with increasing acid concentration, temperature and decreasing particle diameter at a moderate stirring. The kinetics data has been analyzed and was found to follow diffusion control mechanism. At optimal conditions, the extent of ore dissolution reached 94.3%. The recovery of the total copper from the hydrochloric acid-leached chalcopyrite ore was undertaken by solvent extraction and precipitation techniques, prior to the beneficiation of the purified solution as copper oxide. The purification of the leach liquor was firstly done by precipitation of total iron and manganese using Ca(OH)2 and H2O2 as oxidizer at pH 3.5 and 4.25, respectively. An extraction efficiency of 97.3% total copper was obtained by 0.2 mol/L Dithizone in kerosene at 25±2ºC within 40 minutes, from which ≈98% Cu from loaded organic phase was successfully stripped by 0.1 mol/L HCl solution. The beneficiation of the recovered pure copper solution was carried out by crystallization through alkali addition followed by calcination at 600ºC to obtain high grade copper oxide (Tenorite, CuO: 05-0661). Finally, a simple hydrometallurgical scheme for the operational extraction procedure amenable for industrial utilization and economic sustainability was provided.

Keywords: chalcopyrite ore, Nigeria, copper, copper oxide, solvent extraction

Procedia PDF Downloads 385

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 124