Search results for: time delay neural network

Authors: Zhang Yuqi

Abstract:

Service facilities are the boosters for the cultivation and development of innovative functions in innovative cluster areas. At the same time, reasonable service facilities planning can better link the internal functional blocks. This paper takes Zhejiang University Zijin Co-Maker Town as the research object, based on the combination of network data mining and field research and verification, combined with the needs of its internal innovative groups. It studies the distribution characteristics and existing problems of service facilities and then proposes a targeted planning suggestion. The main conclusions are as follows: (1) From the perspective of view, the town is rich in general life-supporting services, but lacking of provision targeted and distinctive service facilities for innovative groups; (2) From the perspective of scale structure, small-scale street shops are the main business form, lack of large-scale service center; (3) From the perspective of spatial structure, service facilities layout of each functional block is too fragile to fit the characteristics of 2aggregation- distribution' of innovation and entrepreneurial activities; (4) The goal of optimizing service facilities planning should be guided for fostering function of innovation and entrepreneurship and meet the actual needs of the innovation and entrepreneurial groups.

Keywords: the cultivation of innovative function, Zhejiang University Zijin Co-Maker Town, service facilities, network data mining, space optimization advice

Procedia PDF Downloads 116

Authors: Sašo Pečnik, Borut Žalik

Abstract:

This paper presents a real-time visualization technique and filtering of classified LiDAR point clouds. The visualization is capable of displaying filtered information organized in layers by the classification attribute saved within LiDAR data sets. We explain the used data structure and data management, which enables real-time presentation of layered LiDAR data. Real-time visualization is achieved with LOD optimization based on the distance from the observer without loss of quality. The filtering process is done in two steps and is entirely executed on the GPU and implemented using programmable shaders.

Keywords: filtering, graphics, level-of-details, LiDAR, real-time visualization

Procedia PDF Downloads 308

Authors: V. S. S. Kumar, B. Vikram, G. C. S. Reddy

Abstract:

Time and cost are the two critical objectives of construction project management and are not independent but intricately related. Trade-off between project duration and cost are extensively discussed during project scheduling because of practical relevance. Generally when the project duration is compressed, the project calls for an increase in labor and more productive equipments, which increases the cost. Thus, the construction time-cost optimization is defined as a process to identify suitable construction activities for speeding up to attain the best possible savings in both time and cost. As there is hidden tradeoff relationship between project time and cost, it might be difficult to predict whether the total cost would increase or decrease as a result of compressing the schedule. Different combinations of duration and cost for the activities associated with the project determine the best set in the time-cost optimization. Therefore, the contractors need to select the best combination of time and cost to perform each activity, all of which will ultimately determine the project duration and cost. In this paper, the fuzzy set theory is used to model the uncertainties in the project environment for time-cost trade off analysis.

Keywords: fuzzy sets, uncertainty, qualitative factors, decision making

Procedia PDF Downloads 652

Authors: T. Manesh, Abdalla A. Alameen, M. Mohemmed Sha, A. Mohamed Mustaq Ahmed

Abstract:

Email and instant messaging applications are foremost and extensively used electronic communication methods in this era of information explosion. These applications are generally used for exchange of information using several frontend applications from various service providers by its users. Almost all such communications are now secured using SSL or TLS security over HTTP communication. At the same time, it is also noted that cyber criminals and terrorists have started exchanging information using these methods. Since communication is encrypted end-to-end, tracing significant forensic details and actual content of messages are found to be unattended and severe challenges by available forensic tools. These challenges seriously affect in procuring substantial evidences against such criminals from their working environments. This paper presents a vibrant forensic exploration and architectural framework which not only decrypts any communication or network session but also reconstructs actual message contents of email as well as instant messaging applications. The framework can be effectively used in proxy servers and individual computers and it aims to perform forensic reconstruction followed by analysis of webmail and ICQ messaging applications. This forensic framework exhibits a versatile nature as it is equipped with high speed packet capturing hardware, a well-designed packet manipulating algorithm. It regenerates message contents over regular as well as SSL encrypted SMTP, POP3 and IMAP protocols and catalyzes forensic presentation procedure for prosecution of cyber criminals by producing solid evidences of their actual communication as per court of law of specific countries.

Keywords: forensics, network sessions, packet reconstruction, packet reordering

Procedia PDF Downloads 344

Authors: Tak-Chung Fu, Ying-Kit Hung, Fu-Lai Chung

Abstract:

In the field of time series data mining, the concept of the Perceptually Important Point (PIP) identification process is first introduced in 2001. This process originally works for financial time series pattern matching and it is then found suitable for time series dimensionality reduction and representation. Its strength is on preserving the overall shape of the time series by identifying the salient points in it. With the rise of Big Data, time series data contributes a major proportion, especially on the data which generates by sensors in the Internet of Things (IoT) environment. According to the nature of PIP identification and the successful cases, it is worth to further explore the opportunity to apply PIP in time series ‘Big Data’. However, the performance of PIP identification is always considered as the limitation when dealing with ‘Big’ time series data. In this paper, two distributed versions of PIP identification based on the Specialized Binary (SB) Tree are proposed. The proposed approaches solve the bottleneck when running the PIP identification process in a standalone computer. Improvement in term of speed is obtained by the distributed versions.

Keywords: distributed computing, performance analysis, Perceptually Important Point identification, time series data mining

Procedia PDF Downloads 435

Authors: Magaji Zainab Musa, Nordin M. A. Rahman, Julaily Aida Jusoh

Abstract:

This paper discusses the formal specification of web services applications for digital reference services (WSDRS). Digital reference service involves a user requesting for help from a reference librarian and a reference librarian responding to the request of a user all by electronic means. In most cases users do not get satisfied while using digital reference service due to delay of response of the librarians. Another may be due to no response or due to librarian giving an irrelevant solution to the problem submitted by the user. WDSRS is an informal model that claims to reduce the problems of digital reference services in libraries. It uses web services technology to provide efficient way of satisfying users’ need in the reference section of libraries. But informal model is in natural language which is inconsistent and ambiguous that may cause difficulties to the developers of the system. In order to solve this problem we decided to convert the informal specifications into formal specifications. This is supposed to reduce the overall development time and cost. Formal specification can be used to provide an unambiguous and precise supplement to natural language descriptions. It can be rigorously validated and verified leading to the early detection of specification errors. We use Z language to develop the formal model and verify it with Z/EVES theorem prover tool.

Keywords: formal, specifications, web services, digital reference services

Procedia PDF Downloads 376

Authors: Evangelos Kaisar, Anika Tabassum, Taraneh Ardalan, Majed Al-Ghandour

Abstract:

The economy of any country is dependent on its ability to accommodate the movement and delivery of goods. The demand for goods movement and services increases truck traffic on highways and inside the cities. The livability of most cities is directly affected by the congestion and environmental impacts of trucks, which are the backbone of the urban freight system. Better operation of heavy vehicles on highways and arterials could lead to the network’s efficiency and reliability. In many cases, roundabouts can respond better than at-level intersections to enable traffic operations with increased safety for both cars and heavy vehicles. Recently emerged, the concept of turbo-roundabout is a viable alternative to the two-lane roundabout aiming to improve traffic efficiency. The primary objective of this study is to evaluate the operation and performance level of an at-grade intersection, a conventional two-lane roundabout, and a basic turbo roundabout for freight movements. To analyze and evaluate the performances of the signalized intersections and the roundabouts, micro simulation models were developed PTV VISSIM. The networks chosen for this analysis in this study are to experiment and evaluate changes in the performance of the movement of vehicles with different geometric and flow scenarios. There are several scenarios that were examined when attempting to assess the impacts of various geometric designs on vehicle movements. The overall traffic efficiency depends on the geometric layout of the intersections, which consists of traffic congestion rate, hourly volume, frequency of heavy vehicles, type of road, and the ratio of major-street versus side-street traffic. The traffic performance was determined by evaluating the delay time, number of stops, and queue length of each intersection for varying truck percentages. The results indicate that turbo-roundabouts can replace signalized intersections and two-lane roundabouts only when the traffic demand is low, even with high truck volume. More specifically, it is clear that two-lane roundabouts are seen to have shorter queue lengths compared to signalized intersections and turbo-roundabouts. For instance, considering the scenario where the volume is highest, and the truck movement and left turn movement are maximum, the signalized intersection has 3 times, and the turbo-roundabout has 5 times longer queue length than a two-lane roundabout in major roads. Similarly, on minor roads, signalized intersections and turbo-roundabouts have 11 times longer queue lengths than two-lane roundabouts for the same scenario. As explained from all the developed scenarios, while the traffic demand lowers, the queue lengths of turbo-roundabouts shorten. This proves that turbo roundabouts perform well for low and medium traffic demand. The results indicate that turbo-roundabouts can replace signalized intersections and two-lane roundabouts only when the traffic demand is low, even with high truck volume. Finally, this study provides recommendations on the conditions under which different intersections perform better than each other.

Keywords: At-grade intersection, simulation, turbo-roundabout, two-lane roundabout

Procedia PDF Downloads 150

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 249

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 189

Authors: Smaran Manchala

Abstract:

Homomorphic Encryption (HE) enables computations on encrypted data without requiring decryption, mitigating data vulnerability during processing. Usable Fully Homomorphic Encryption (FHE) could revolutionize secure data operations across cloud computing, AI training, and healthcare, providing both privacy and functionality, however, the computational inefficiency of schemes like Cheon-Kim-Kim-Song (CKKS) hinders their widespread practical use. This study focuses on optimizing CKKS for faster matrix operations through the implementation of vector computation parallelization and GPU acceleration. The variable effects of vector parallelization on GPUs were explored, recognizing that while parallelization typically accelerates operations, it could introduce overhead that results in slower runtimes, especially in smaller, less computationally demanding operations. To assess performance, two neural network models, MLPN and CNN—were tested on the MNIST dataset using both ARM and x86-64 architectures, with CNN chosen for its higher computational demands. Each test was repeated 1,000 times, and outliers were removed via Z-score analysis to measure the effect of vector parallelization on CKKS performance. Model accuracy was also evaluated under CKKS encryption to ensure optimizations did not compromise results. According to the results of the trail runs, applying vector parallelization had a 2.63X efficiency increase overall with a 1.83X performance increase for x86-64 over ARM architecture. Overall, these results suggest that the application of vector parallelization in tandem with GPU acceleration significantly improves the efficiency of CKKS even while accounting for vector parallelization overhead, providing impact in future zero trust operations.

Keywords: CKKS scheme, runtime efficiency, fully homomorphic encryption (FHE), GPU acceleration, vector parallelization

Procedia PDF Downloads 23

Authors: Alshaimaa Abdelwahab, Allegra Cattani, Caroline Floccia

Abstract:

Assessing children’s language is fundamental for changing their developmental outcome as it gives a chance for a quick and early intervention with the suitable planning and monitoring program. The importance of language assessment lies in helping to find the right test fit for purpose, in addition to achievement and proficiency. This study examines the validity of a new Arabic assessment tool, the Arabic Communicative Development Inventory ‘Arabic CDI’. It assesses the development of language in Arabic children in different Arabic countries, allowing to detect children with language delay. A concurrent validity is set to compare the Arabic CDI to the Arabic Language test. Twenty-three typically developing Egyptian healthy children and their mothers participated in this study. Their age is 24 months (+ or -) two weeks. The sample included 13 males and 10 females. Mothers completed the Arabic CDI either before or after the Arabic Language Test was conducted with the child. The score for comprehension in the Arabic CDI (M= 52.7, SD= 9.7) and words understood in the Arabic Language Test (M= 59.6, SD= 12.5) were strongly and positively correlated (r= .62, p= .002). At the same time, the scores for production in the Arabic CDI (M= 38.4, SD= 14.8) and words expressed in the Arabic Language Test (M= 52.1, SD= 16.3) were also strongly and positively correlated (r= .82, p= .000). The new Arabic CDI is an adequate tool for assessing the development of comprehension and production at Arabic children. In addition, it could be used for detecting children with language impairment. Standardization of the Arabic CDI across 18 different Arabic dialects in children aged 8 to 30 months is underway.

Keywords: Arabic CDI, assessing children, language development, language impairment

Procedia PDF Downloads 470

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 274

Authors: Leo Latasch, Mario Di Gennaro

Abstract:

Introduction: The goal of this project was to increase the resilience of the population as well as rescue organizations to make both quality and time-related improvements in handling crises. A helper network was created for this purpose. Methods: Social questions regarding the structure and purpose of helper networks were considered - specifically with regard to helper motivation, the level of commitment and collaboration between populations and agencies. The exchange of information, the coordinated use of volunteers, and the distribution of available resources will be ensured through defined communication and cooperation routines. Helper smartphones will also be used provide a picture of the situation on the ground. Results: The helper network was established and deployed based on the RESIBES information technology system. It consists of a service platform, a web portal and a smartphone app. The service platform is the central element for collaboration between the various rescue organizations, as well as for persons, associations, and companies from the population offering voluntary aid. The platform was used for: Registering helpers and resources and then requesting and assigning it in case of a disaster. These services allow the population's resources to be organized. The service platform also allows for a secure data exchange between services and external systems. Conclusions: The social and technical work priorities have allowed us to cover a full cycle of advance structural work, gaining an overview, damage management, evaluation, and feedback on experiences. This cycle allows experiences gained while handling the crisis to feed back into the cycle and improve preparations and management strategies.

Keywords: coordination, disaster, resilience, volunteers

Procedia PDF Downloads 142

Authors: Stefan Andersson, Balram Panjwani, Bernd Wittgens, Jan Erik Olsen

Abstract:

Polycyclic Aromatic hydrocarbons are organic compounds consisting of only hydrogen and carbon aromatic rings. PAH are neutral, non-polar molecules that are produced due to incomplete combustion of organic matter. These compounds are carcinogenic and interact with biological nucleophiles to inhibit the normal metabolic functions of the cells. Norways, the most important sources of PAH pollution is considered to be aluminum plants, the metallurgical industry, offshore oil activity, transport, and wood burning. Stricter governmental regulations regarding emissions to the outer and internal environment combined with increased awareness of the potential health effects have motivated Norwegian metal industries to increase their efforts to reduce emissions considerably. One of the objective of the ongoing industry and Norwegian research council supported "SCORE" project is to reduce potential PAH emissions from an off gas stream of a ferroalloy furnace through controlled combustion. In a dedicated combustion chamber. The sizing and configuration of the combustion chamber depends on the combined properties of the bulk gas stream and the properties of the PAH itself. In order to achieve efficient and complete combustion the residence time and minimum temperature need to be optimized. For this design approach reliable kinetic data of the individual PAH-species and/or groups thereof are necessary. However, kinetic data on the combustion of PAH are difficult to obtain and there is only a limited number of studies. The paper presents an evaluation of the kinetic data for some of the PAH obtained from literature. In the present study, the oxidation is modelled for pure PAH and also for PAH mixed with process gas. Using a perfectly stirred reactor modelling approach the oxidation is modelled including advanced reaction kinetics to study influence of residence time and temperature on the conversion of PAH to CO2 and water. A Chemical Reactor Network (CRN) approach is developed to understand the oxidation of PAH inside the combustion chamber. Chemical reactor network modeling has been found to be a valuable tool in the evaluation of oxidation behavior of PAH under various conditions.

Keywords: PAH, PSR, energy recovery, ferro alloy furnace

Procedia PDF Downloads 273

Authors: Hamad Aljassmi, Sangwon Han

Abstract:

Various solutions for preventing construction defects have been suggested. However, a construction company may have difficulties adopting all these suggestions due to financial and practical constraints. Based on this recognition, this paper aims to identify the most significant defect causes and formulate their defect generation mechanism in order to help a construction company to set priorities of its defect prevention strategies. For this goal, we conducted a questionnaire survey of 106 industry professionals and identified five most significant causes including: (1) organizational culture, (2) time pressure and constraints, (3) workplace quality system, (4) financial constraints upon operational expenses and (5) inadequate employee training or learning opportunities.

Keywords: defect, quality, failure, risk

Procedia PDF Downloads 627

Authors: Eric Kumar, Erica Cochran, Zhiang Zhang, Wei Liang, Ronak Mody

Abstract:

The objective of this article was to create a modelling framework that exposes the marginal costs of shifting workloads across geographically distributed data-centers. Geographical distribution of internet services helps to optimize their performance for localized end users with lowered communications times and increased availability. However, due to the geographical and temporal effects, the physical embodiments of a service's data center infrastructure can vary greatly. In this work, we first identify that the sources of variances in the physical infrastructure primarily stem from local weather conditions, specific user traffic profiles, energy sources, and the types of IT hardware available at the time of deployment. Second, we create a traffic simulator that indicates the IT load at each data-center in the set as an approximator for user traffic profiles. Third, we implement a framework that quantifies the global level energy demands using building energy models and the traffic profiles. The results of the model provide a time series of energy demands that can be used for further life cycle analysis of internet services.

Keywords: data-centers, energy, life cycle, network simulation

Procedia PDF Downloads 147

Authors: Walid Tawfik, W. Askam Farooq, Sultan F. Alqhtani

Abstract:

Quantum dots (QDots) are nanometer-sized crystals, less than 10 nm, comprise a semiconductor or metallic materials and contain from 100 - 100,000 atoms in each crystal. QDots play an important role in many applications; light emitting devices (LEDs), solar cells, drug delivery, and optical computers. In the current research, a fundamental wavelength of Nd:YAG laser was applied to analyse the impurities in homemade cadmium selenide (CdSe) QDots through laser-induced plasma (LIPS) technique. The CdSe QDots were fabricated by using hot-solution decomposition method where a mixture of Cd precursor and trioctylphosphine oxide (TOPO) is prepared at concentrations of TOPO under controlled temperatures 200-350ºC. By applying laser energy of 15 mJ, at frequency 10 Hz, and delay time 500 ns, LIPS spectra of CdSe QDots samples were observed. The qualitative LIPS analysis for CdSe QDs revealed that the sample contains Cd, Te, Se, H, P, Ar, O, Ni, C, Al and He impurities. These observed results gave precise details of the impurities present in the QDs sample. These impurities are important for future work at which controlling the impurity contents in the QDs samples may improve the physical, optical and electrical properties of the QDs used for solar cell application.

Keywords: cadmium selenide, TOPO, LIPS spectroscopy, quantum dots

Procedia PDF Downloads 143

Authors: Roberta Martino, Viviana Ventre

Abstract:

Every day we face choices whose consequences are deferred in time. These types of choices are the intertemporal choices and play an important role in the social, economic, and financial world. The Discounted Utility Model is the mathematical model of reference to calculate the utility of intertemporal prospects. The discount rate is the main element of the model as it describes how the individual perceives the indeterminacy of subsequent periods. Empirical evidence has shown a discrepancy between the behavior expected from the predictions of the model and the effective choices made from the decision makers. In particular, the term temporal inconsistency indicates those choices that do not remain optimal with the passage of time. This phenomenon has been described with hyperbolic models of the discount rate which, unlike the linear or exponential nature assumed by the discounted utility model, is not constant over time. This paper explores the problem of inconsistency by tracing the decision-making process through the concept of impatience. The degree of impatience and the degree of decrease of impatience are two parameters that allow to quantify the weight of emotional factors and cognitive limitations during the evaluation and selection of alternatives. In fact, although the theory assumes perfectly rational decision makers, behavioral finance and cognitive psychology have made it possible to understand that distortions in the decision-making process and emotional influence have an inevitable impact on the decision-making process. The degree to which impatience is diminished is the focus of the first part of the study. By comparing consistent and inconsistent preferences over time, it was possible to verify that some anomalies in the discounted utility model are a result of the combination of cognitive bias and emotional factors. In particular: the delay effect and the interval effect are compared through the concept of misperception of time; starting from psychological considerations, a criterion is proposed to identify the causes of the magnitude effect that considers the differences in outcomes rather than their ratio; the sign effect is analyzed by integrating in the evaluation of prospects with negative outcomes the psychological aspects of loss aversion provided by Prospect Theory. An experiment implemented confirms three findings: the greatest variation in the degree of decrease in impatience corresponds to shorter intervals close to the present; the greatest variation in the degree of impatience occurs for outcomes of lower magnitude; the variation in the degree of impatience is greatest for negative outcomes. The experimental phase was implemented with the construction of the hyperbolic factor through the administration of questionnaires constructed for each anomaly. This work formalizes the underlying causes of the discrepancy between the discounted utility model and the empirical evidence of preference reversal.

Keywords: decreasing impatience, discount utility model, hyperbolic discount, hyperbolic factor, impatience

Procedia PDF Downloads 103

Authors: A. Assad, T. Zayed

Abstract:

Water networks (WNs) are responsible of providing adequate amounts of safe, high quality, water to the public. As other critical infrastructure systems, WNs are subjected to deterioration which increases the number of breaks and leaks and lower water quality. In Canada, 35% of water assets require critical attention and there is a significant gap between the needed and the implemented investments. Thus, the need for efficient rehabilitation programs is becoming more urgent given the paradigm of aging infrastructure and tight budget. The first step towards developing such programs is to formulate a Performance Index that reflects the current condition of water assets along with its criticality. While numerous studies in the literature have focused on various aspects of condition assessment and reliability, limited efforts have investigated the criticality of such components. Critical water mains are those whose failure cause significant economic, environmental or social impacts on a community. Inclusion of criticality in computing the performance index will serve as a prioritizing tool for the optimum allocating of the available resources and budget. In this study, several social, economic, and environmental factors that dictate the criticality of a water pipelines have been elicited from analyzing the literature. Expert opinions were sought to provide pairwise comparisons of the importance of such factors. Subsequently, Fuzzy Logic along with Analytical Network Process (ANP) was utilized to calculate the weights of several criteria factors. Multi Attribute Utility Theories (MAUT) was then employed to integrate the aforementioned weights with the attribute values of several pipelines in Montreal WN. The result is a criticality index, 0-1, that quantifies the severity of the consequence of failure of each pipeline. A novel contribution of this approach is that it accounts for both the interdependency between criteria factors as well as the inherited uncertainties in calculating the criticality. The practical value of the current study is represented by the automated tool, Excel-MATLAB, which can be used by the utility managers and decision makers in planning for future maintenance and rehabilitation activities where high-level efficiency in use of materials and time resources is required.

Keywords: water networks, criticality assessment, asset management, fuzzy analytical network process

Procedia PDF Downloads 147

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 75

Authors: Redouane Larbi Boufeniza, Jing-Jia Luo

Abstract:

This study assesses the suitability of deep learning (DL) for downscaling sea surface temperature (SST) over the Mediterranean Sea in the context of seasonal forecasting. We design a set of experiments that compare different DL configurations and deploy the best-performing architecture to downscale one-month lead forecasts of June–September (JJAS) SST from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0) for the period of 1982–2020. We have also introduced predictors over a larger area to include information about the main large-scale circulations that drive SST over the Mediterranean Sea region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results showed that the convolutional neural network (CNN)-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme SST spatial patterns. Besides, the CNN-based downscaling yields a much more accurate forecast of extreme SST and spell indicators and reduces the significant relevant biases exhibited by the raw model predictions. Moreover, our results show that the CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of the Mediterranean Sea. The results demonstrate the potential usefulness of CNN in downscaling seasonal SST predictions over the Mediterranean Sea, particularly in providing improved forecast products.

Keywords: Mediterranean Sea, sea surface temperature, seasonal forecasting, downscaling, deep learning

Procedia PDF Downloads 76

Authors: Shadrack Mambo, Karim Djouani, Yskandar Hamam, Barend van Wyk, Patrick Siarry

Abstract:

This paper discusses the current trends in medical image registration techniques and addresses the need to provide a solid theoretical foundation for research endeavours. Methodological analysis and synthesis of quality literature was done, providing a platform for developing a good foundation for research study in this field which is crucial in understanding the existing levels of knowledge. Research on medical image registration techniques assists clinical and medical practitioners in diagnosis of tumours and lesion in anatomical organs, thereby enhancing fast and accurate curative treatment of patients. Literature review aims to provide a solid theoretical foundation for research endeavours in image registration techniques. Developing a solid foundation for a research study is possible through a methodological analysis and synthesis of existing contributions. Out of these considerations, the aim of this paper is to enhance the scientific community’s understanding of the current status of research in medical image registration techniques and also communicate to them, the contribution of this research in the field of image processing. The gaps identified in current techniques can be closed by use of artificial neural networks that form learning systems designed to minimise error function. The paper also suggests several areas of future research in the image registration.

Keywords: image registration techniques, medical images, neural networks, optimisaztion, transformation

Procedia PDF Downloads 178

Authors: S. M. Dash, K. B. Lua, T. T. Lim

Abstract:

This paper presents results of numerical and experimental studies on a two-dimensional (2D) flapping elliptic airfoil in a forward flight condition at Reynolds number of 5000. The study is motivated from an earlier investigation which shows that the deterioration in thrust performance of a sinusoidal heaving and pitching 2D (NACA0012) airfoil at high flapping frequency can be recovered by changing the effective angle of attack profile to square wave, sawtooth, or cosine wave shape. To better understand why such modifications lead to superior thrust performance, we take a closer look at the transient aerodynamic force behavior of an airfoil when the effective angle of attack profile changes gradually from a generic smooth trapezoidal profile to a sinusoid shape by modifying the base length of the trapezoid. The choice of using a smooth trapezoidal profile is to avoid the infinite acceleration condition encountered in the square wave profile. Our results show that the enhancement in the time-averaged thrust performance at high flapping frequency can be attributed to the delay and reduction in the drag producing valley region in the transient thrust force coefficient when the effective angle of attack profile changes from sinusoidal to trapezoidal.

Keywords: two-dimensional flapping airfoil, thrust performance, effective angle of attack, CFD, experiments

Procedia PDF Downloads 358

Authors: Xiang Shijie, Zhou Dong, Tian Dan

Abstract:

Speaker recognition is a crucial task in the field of speech processing, aimed at identifying individuals based on their vocal characteristics. However, existing speaker recognition methods face numerous challenges. Traditional methods primarily rely on audio signals, which often suffer from limitations in noisy environments, variations in speaking style, and insufficient sample sizes. Additionally, relying solely on audio features can sometimes fail to capture the unique identity of the speaker comprehensively, impacting recognition accuracy. To address these issues, we propose a multi-modal network architecture that simultaneously processes both audio and text signals. By gradually integrating audio and text features, we leverage the strengths of both modalities to enhance the robustness and accuracy of speaker recognition. Our experiments demonstrate significant improvements with this multi-modal approach, particularly in complex environments, where recognition performance has been notably enhanced. Our research not only highlights the limitations of current speaker recognition methods but also showcases the effectiveness of multi-modal fusion techniques in overcoming these limitations, providing valuable insights for future research.

Keywords: feature fusion, memory network, multimodal input, speaker recognition

Procedia PDF Downloads 33

Authors: Chuan Yang, Jing Bie, Zhong Wang, Panagiotis Psimoulis

Abstract:

Contemporary studies investigating the association between the spatial configuration of the urban network and economic activities at the street level were mostly conducted within space syntax conceptual framework. These findings supported the theory of 'movement economy' and demonstrated the impact of street configuration on the distribution of pedestrian movement and land-use shaping, especially retail activities. However, the effects varied between different urban contexts. In this paper, the relationship between economic activity distribution and the urban configurational characters was examined at the segment level. In the study area, three kinds of neighbourhood types, urban, suburban, and rural neighbourhood, were included. And among all neighbourhoods, three kinds of urban network form, 'tree-like', grid, and organic pattern, were recognised. To investigate the nested effects of urban configuration measured by space syntax approach and urban context, multilevel zero-inflated negative binomial (ZINB) regression models were constructed. Additionally, considering the spatial autocorrelation, spatial lag was also concluded in the model as an independent variable. The random effect ZINB model shows superiority over the ZINB model or multilevel linear (ML) model in the explanation of economic activities pattern shaping over the urban environment. And after adjusting for the neighbourhood type and network form effects, connectivity and syntax centrality significantly affect economic activities clustering. The comparison between accumulative and new established economic activities illustrated the different preferences for economic activity location choice.

Keywords: space syntax, economic activities, multilevel model, Chinese city

Procedia PDF Downloads 124

Authors: Marcella De Filippo, Delio Colangelo, Luca Farnia

Abstract:

In recent decades, the hyper-competition of tourism scenario has implicated the maturity of many businesses, attributing a central role to innovative processes and their dissemination in the economy of company management. At the same time, it has defined the need for monitoring the application of innovations, in order to govern and improve the performance of companies and destinations. The study aims to analyze and define the innovation in the tourism sector. The research actions have concerned, on the one hand, some in-depth interviews with experts, identifying innovation in terms of process and product, digitalization, sustainability policies and, on the other hand, to evaluate the interaction between these factors, in terms of substitutability and complementarity in management scenarios, in order to identify which one is essential to be competitive in the global scenario. Fuzzy measures and Choquet integral were used to elicit Experts’ preferences. This method allows not only to evaluate the relative importance of each pillar, but also and more interestingly, the level of interaction, ranging from complementarity to substitutability, between pairs of factors. The results of the survey are the following: in terms of Shapley values, Experts assert that Innovation is the most important factor (32.32), followed by digitalization (31.86), Network (20.57) and Sustainability (15.25). In terms of Interaction indices, given the low degree of consensus among experts, the interaction between couples of criteria on average could be ignored; however, it is worth to note that the factors innovations and digitalization are those in which experts express the highest degree of interaction. However for some of them, these factors have a moderate level of complementarity (with a pick of 57.14), and others consider them moderately substitutes (with a pick of -39.58). Another example, although outlier is the interaction between network and digitalization, in which an expert consider them markedly substitutes (-77.08).

Keywords: innovation, business model, tourism, fuzzy

Procedia PDF Downloads 272

Authors: Yanshuang Zhang, Byungho Jeong

Abstract:

There exists some time lag between the consumption of inputs and the production of outputs. This time lag effect should be considered in calculating efficiency of decision making units (DMU). Recently, a couple of DEA models were developed for considering time lag effect in efficiency evaluation of research activities. However, these models can’t discriminate efficient DMUs because of the nature of basic DEA model in which efficiency scores are limited to ‘1’. This problem can be resolved a super-efficiency model. However, a super efficiency model sometimes causes infeasibility problem. This paper suggests an output oriented super-efficiency model for efficiency evaluation under the consideration of time lag effect. A case example using a long term research project is given to compare the suggested model with the MpO model

Keywords: DEA, Super-efficiency, Time Lag, research activities

Procedia PDF Downloads 658

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 240

Authors: Yanshuang Zhang, Byungho Jeong

Abstract:

In many cases, there is a time lag between the consumption of inputs and the production of outputs. This time lag effect should be considered in evaluating the performance of organizations. Recently, a couple of DEA models were developed for considering time lag effect in efficiency evaluation of research activities. Multi-periods input(MpI) and Multi-periods output(MpO) models are integrated models to calculate simple efficiency considering time lag effect. However, these models can’t discriminate efficient DMUs because of the nature of basic DEA model in which efficiency scores are limited to ‘1’. That is, efficient DMUs can’t be discriminated because their efficiency scores are same. Thus, this paper suggests a super-efficiency model for efficiency evaluation under the consideration of time lag effect based on the MpO model. A case example using a long-term research project is given to compare the suggested model with the MpO model.

Keywords: DEA, super-efficiency, time lag, multi-periods input

Procedia PDF Downloads 474

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 155