Search results for: multi-layer perception neural networks
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 5671

Search results for: multi-layer perception neural networks

4231 Fast Prototyping of Precise, Flexible, Multiplexed, Printed Electrochemical Enzyme-Linked Immunosorbent Assay System for Point-of-Care Biomarker Quantification

Authors: Zahrasadat Hosseini, Jie Yuan

Abstract:

Point-of-care (POC) diagnostic devices based on lab-on-a-chip (LOC) technology have the potential to revolutionize medical diagnostics. However, the development of an ideal microfluidic system based on LOC technology for diagnostics purposes requires overcoming several obstacles, such as improving sensitivity, selectivity, portability, cost-effectiveness, and prototyping methods. While numerous studies have introduced technologies and systems that advance these criteria, existing systems still have limitations. Electrochemical enzyme-linked immunosorbent assay (e-ELISA) in a LOC device offers numerous advantages, including enhanced sensitivity, decreased turnaround time, minimized sample and analyte consumption, reduced cost, disposability, and suitability for miniaturization, integration, and multiplexing. In this study, we present a novel design and fabrication method for a microfluidic diagnostic platform that integrates screen-printed electrochemical carbon/silver chloride electrodes on flexible printed circuit boards with flexible, multilayer, polydimethylsiloxane (PDMS) microfluidic networks to accurately manipulate and pre-immobilize analytes for performing electrochemical enzyme-linked immunosorbent assay (e-ELISA) for multiplexed quantification of blood serum biomarkers. We further demonstrate fast, cost-effective prototyping, as well as accurate and reliable detection performance of this device for quantification of interleukin-6-spiked samples through electrochemical analytics methods. We anticipate that our invention represents a significant step towards the development of user-friendly, portable, medical-grade, POC diagnostic devices.

Keywords: lab-on-a-chip, point-of-care diagnostics, electrochemical ELISA, biomarker quantification, fast prototyping

Procedia PDF Downloads 66
4230 Fast Prototyping of Precise, Flexible, Multiplexed, Printed Electrochemical Enzyme-Linked Immunosorbent Assay Platform for Point-of-Care Biomarker Quantification

Authors: Zahrasadat Hosseini, Jie Yuan

Abstract:

Point-of-care (POC) diagnostic devices based on lab-on-a-chip (LOC) technology have the potential to revolutionize medical diagnostics. However, the development of an ideal microfluidic system based on LOC technology for diagnostics purposes requires overcoming several obstacles, such as improving sensitivity, selectivity, portability, cost-effectiveness, and prototyping methods. While numerous studies have introduced technologies and systems that advance these criteria, existing systems still have limitations. Electrochemical enzyme-linked immunosorbent assay (e-ELISA) in a LOC device offers numerous advantages, including enhanced sensitivity, decreased turnaround time, minimized sample and analyte consumption, reduced cost, disposability, and suitability for miniaturization, integration, and multiplexing. In this study, we present a novel design and fabrication method for a microfluidic diagnostic platform that integrates screen-printed electrochemical carbon/silver chloride electrodes on flexible printed circuit boards with flexible, multilayer, polydimethylsiloxane (PDMS) microfluidic networks to accurately manipulate and pre-immobilize analytes for performing electrochemical enzyme-linked immunosorbent assay (e-ELISA) for multiplexed quantification of blood serum biomarkers. We further demonstrate fast, cost-effective prototyping, as well as accurate and reliable detection performance of this device for quantification of interleukin-6-spiked samples through electrochemical analytics methods. We anticipate that our invention represents a significant step towards the development of user-friendly, portable, medical-grade POC diagnostic devices.

Keywords: lab-on-a-chip, point-of-care diagnostics, electrochemical ELISA, biomarker quantification, fast prototyping

Procedia PDF Downloads 68
4229 University Coordinating Council Office: Perceived and Expected Roles and Performances

Authors: Pitsanu Poonpetpun

Abstract:

This research paper consisted of three objectives: 1) to investigate actual perception of Suan Sunandha Rajabhat University’s members towards roles and performances of the Coordinating Council Office under the University Council; 2) to investigate expectation of Suan Sunandha Rajabhat University’s members towards roles and performances of the Coordinating Council Office under the University Council; and 3) to compare actual perception and expectation of Suan Sunandha Rajabhat University’s members towards roles and performances of the Coordinating Council Office under the University Council. A total of 316 samples from the population of the members of Suan Sunandha Rajabhat University were selected by use of the simple random sampling technique. Descriptive statistics and Dependent T- Test for paired samples were used, where the Dependent T- Test was for an analysis of a comparison of actual perception and expectation of Suan Sunandha Rajabhat University’s members towards roles and performances of the Coordinating Council Office under the University Council. The findings unveiled significantly high levels for the following roles: [i] appropriately circulating agendas and meeting files before time; [ii] preparing appropriate amount and quality of audio- visual equipment for meetings; [iii] compiling and keeping up-to-date documents; [iv] coordinating and working on linking all useful information to serve for the university uses for strategic policing; and [v] preparing appropriate meeting venues.

Keywords: coordinating council office of the university council, expected role, perceived role, performances of duties

Procedia PDF Downloads 280
4228 The Effect of Speech-Shaped Noise and Speaker’s Voice Quality on First-Grade Children’s Speech Perception and Listening Comprehension

Authors: I. Schiller, D. Morsomme, A. Remacle

Abstract:

Children’s ability to process spoken language develops until the late teenage years. At school, where efficient spoken language processing is key to academic achievement, listening conditions are often unfavorable. High background noise and poor teacher’s voice represent typical sources of interference. It can be assumed that these factors particularly affect primary school children, because their language and literacy skills are still low. While it is generally accepted that background noise and impaired voice impede spoken language processing, there is an increasing need for analyzing impacts within specific linguistic areas. Against this background, the aim of the study was to investigate the effect of speech-shaped noise and imitated dysphonic voice on first-grade primary school children’s speech perception and sentence comprehension. Via headphones, 5 to 6-year-old children, recruited within the French-speaking community of Belgium, listened to and performed a minimal-pair discrimination task and a sentence-picture matching task. Stimuli were randomly presented according to four experimental conditions: (1) normal voice / no noise, (2) normal voice / noise, (3) impaired voice / no noise, and (4) impaired voice / noise. The primary outcome measure was task score. How did performance vary with respect to listening condition? Preliminary results will be presented with respect to speech perception and sentence comprehension and carefully interpreted in the light of past findings. This study helps to support our understanding of children’s language processing skills under adverse conditions. Results shall serve as a starting point for probing new measures to optimize children’s learning environment.

Keywords: impaired voice, sentence comprehension, speech perception, speech-shaped noise, spoken language processing

Procedia PDF Downloads 173
4227 An Integrated Research of Airline Sponsorship

Authors: Stephen W. Wang

Abstract:

This research aims to explore the multi-faceted structure of airline passengers’ perception of airline sponsorship, and its impact on airline passengers and even consumers on airline brand preferences and brand equity. The connotation of this research is mainly divided into two parts. The first part of the research focuses on exploring the connotation and sub-dimensions of “air passengers’ perception of airline sponsorship”; the second part of the research focuses on integrating “air passengers’ perception on the multi-factor aspect of the corporate sponsorship, “brand transfer theory” and “brand theory”, explores the influence of airlines’ commitment to corporate sponsorship activities on the brand equity and brand preferences of airline passengers, and on passengers’ subsequent behavioral intentions . In addition, in order to clarify the differences between different types of corporate sponsorship activities and events in terms of "air passengers' perception of airline corporate sponsorship activities", brand transfer, brand preference, brand equity and behavioral intentions, this research also focuses on moderating effects of corporate sponsorship events. With the apply of multi-group structural equation model, it is hoped that the effectiveness of the sponsorship activities of airline companies will be improved. In terms of theoretical and practical implications, the aviation industry can follow the results of this research to understand which corporate sponsorship perceptions have a greater impact on consumers, which has important practical significance. The second part of the research project, from the consumer's point of view, understands whether airline corporate sponsorship activities influence behavioral intentions through brand transfer and brand recognition. Through the analysis of the intermediary effect of brand transfer, brand preference and brand equity, the results of this research can provide a more complete and powerful explanation for “why” airlines’ commitment to corporate sponsorship activities can affect airline passengers’ purchase intentions, which will help fill in the gap of the theoretical and practical research on "airline corporate sponsorship", and has its theoretical significance.

Keywords: airline, sponsorship, brand image transfer, brand preference

Procedia PDF Downloads 11
4226 Understanding Social Networks in Community's Coping Capacity with Floods: A Case Study of a Community in Cambodia

Authors: Ourn Vimoil, Kallaya Suntornvongsagul

Abstract:

Cambodia is considered as one of the most disaster prone countries in South East Asia, and most of natural disasters are related to floods. Cambodia, a developing country, faces significant impacts from floods, such as environmental, social, and economic losses. Using data accessed from focus group discussions and field surveys with villagers in Ba Baong commune, prey Veng province, Cambodia, the research would like to examine roles of social networks in raising community’s coping capacity with floods. The findings indicate that social capital play crucial roles in three stages of floods, namely preparedness, response, and recovery to overcome the crisis. People shared their information and resources, and extent their assistances to one another in order to adapt to floods. The study contribute to policy makers, national and international agencies working on this issue to pay attention on social networks as one factors to accelerate flood coping capacity at community level.

Keywords: social network, community, coping capacity, flood, Cambodia

Procedia PDF Downloads 351
4225 A Network-Theorical Perspective on Music Analysis

Authors: Alberto Alcalá-Alvarez, Pablo Padilla-Longoria

Abstract:

The present paper describes a framework for constructing mathematical networks encoding relevant musical information from a music score for structural analysis. These graphs englobe statistical information about music elements such as notes, chords, rhythms, intervals, etc., and the relations among them, and so become helpful in visualizing and understanding important stylistic features of a music fragment. In order to build such networks, musical data is parsed out of a digital symbolic music file. This data undergoes different analytical procedures from Graph Theory, such as measuring the centrality of nodes, community detection, and entropy calculation. The resulting networks reflect important structural characteristics of the fragment in question: predominant elements, connectivity between them, and complexity of the information contained in it. Music pieces in different styles are analyzed, and the results are contrasted with the traditional analysis outcome in order to show the consistency and potential utility of this method for music analysis.

Keywords: computational musicology, mathematical music modelling, music analysis, style classification

Procedia PDF Downloads 81
4224 Mechanical Characterization of Banana by Inverse Analysis Method Combined with Indentation Test

Authors: Juan F. P. Ramírez, Jésica A. L. Isaza, Benjamín A. Rojano

Abstract:

This study proposes a novel use of a method to determine the mechanical properties of fruits by the use of the indentation tests. The method combines experimental results with a numerical finite elements model. The results presented correspond to a simplified numerical modeling of banana. The banana was assumed as one-layer material with an isotropic linear elastic mechanical behavior, the Young’s modulus found is 0.3Mpa. The method will be extended to multilayer models in further studies.

Keywords: finite element method, fruits, inverse analysis, mechanical properties

Procedia PDF Downloads 339
4223 Structural and Functional Correlates of Reaction Time Variability in a Large Sample of Healthy Adolescents and Adolescents with ADHD Symptoms

Authors: Laura O’Halloran, Zhipeng Cao, Clare M. Kelly, Hugh Garavan, Robert Whelan

Abstract:

Reaction time (RT) variability on cognitive tasks provides the index of the efficiency of executive control processes (e.g. attention and inhibitory control) and is considered to be a hallmark of clinical disorders, such as attention-deficit disorder (ADHD). Increased RT variability is associated with structural and functional brain differences in children and adults with various clinical disorders, as well as poorer task performance accuracy. Furthermore, the strength of functional connectivity across various brain networks, such as the negative relationship between the task-negative default mode network and task-positive attentional networks, has been found to reflect differences in RT variability. Although RT variability may provide an index of attentional efficiency, as well as being a useful indicator of neurological impairment, the brain substrates associated with RT variability remain relatively poorly defined, particularly in a healthy sample. Method: Firstly, we used the intra-individual coefficient of variation (ICV) as an index of RT variability from “Go” responses on the Stop Signal Task. We then examined the functional and structural neural correlates of ICV in a large sample of 14-year old healthy adolescents (n=1719). Of these, a subset had elevated symptoms of ADHD (n=80) and was compared to a matched non-symptomatic control group (n=80). The relationship between brain activity during successful and unsuccessful inhibitions and gray matter volume were compared with the ICV. A mediation analysis was conducted to examine if specific brain regions mediated the relationship between ADHD symptoms and ICV. Lastly, we looked at functional connectivity across various brain networks and quantified both positive and negative correlations during “Go” responses on the Stop Signal Task. Results: The brain data revealed that higher ICV was associated with increased structural and functional brain activation in the precentral gyrus in the whole sample and in adolescents with ADHD symptoms. Lower ICV was associated with lower activation in the anterior cingulate cortex (ACC) and medial frontal gyrus in the whole sample and in the control group. Furthermore, our results indicated that activation in the precentral gyrus (Broadman Area 4) mediated the relationship between ADHD symptoms and behavioural ICV. Conclusion: This is the first study first to investigate the functional and structural correlates of ICV collectively in a large adolescent sample. Our findings demonstrate a concurrent increase in brain structure and function within task-active prefrontal networks as a function of increased RT variability. Furthermore, structural and functional brain activation patterns in the ACC, and medial frontal gyrus plays a role-optimizing top-down control in order to maintain task performance. Our results also evidenced clear differences in brain morphometry between adolescents with symptoms of ADHD but without clinical diagnosis and typically developing controls. Our findings shed light on specific functional and structural brain regions that are implicated in ICV and yield insights into effective cognitive control in healthy individuals and in clinical groups.

Keywords: ADHD, fMRI, reaction-time variability, default mode, functional connectivity

Procedia PDF Downloads 238
4222 Programmed Speech to Text Summarization Using Graph-Based Algorithm

Authors: Hamsini Pulugurtha, P. V. S. L. Jagadamba

Abstract:

Programmed Speech to Text and Text Summarization Using Graph-based Algorithms can be utilized in gatherings to get the short depiction of the gathering for future reference. This gives signature check utilizing Siamese neural organization to confirm the personality of the client and convert the client gave sound record which is in English into English text utilizing the discourse acknowledgment bundle given in python. At times just the outline of the gathering is required, the answer for this text rundown. Thus, the record is then summed up utilizing the regular language preparing approaches, for example, solo extractive text outline calculations

Keywords: Siamese neural network, English speech, English text, natural language processing, unsupervised extractive text summarization

Procedia PDF Downloads 191
4221 Review: Wavelet New Tool for Path Loss Prediction

Authors: Danladi Ali, Abdullahi Mukaila

Abstract:

In this work, GSM signal strength (power) was monitored in an indoor environment. Samples of the GSM signal strength was measured on mobile equipment (ME). One-dimensional multilevel wavelet is used to predict the fading phenomenon of the GSM signal measured and neural network clustering to determine the average power received in the study area. The wavelet prediction revealed that the GSM signal is attenuated due to the fast fading phenomenon which fades about 7 times faster than the radio wavelength while the neural network clustering determined that -75dBm appeared more frequently followed by -85dBm. The work revealed that significant part of the signal measured is dominated by weak signal and the signal followed more of Rayleigh than Gaussian distribution. This confirmed the wavelet prediction.

Keywords: decomposition, clustering, propagation, model, wavelet, signal strength and spectral efficiency

Procedia PDF Downloads 434
4220 RF Propagation Analysis in Outdoor Environments Using RSSI Measurements Applied in ZigBee Sensor Networks

Authors: Teles de Sales Bezerra, Saulo Aislan da Silva Eleuterio, José Anderson Rodrigues de Souza, Jeronimo Silva Rocha

Abstract:

Propagation in radio frequency is a constant concern in the application of Wireless Sensor Networks (WSN), the behavior of an environment determines how good the quality of signal reception. The objective of this paper is to analyze the behavior of a WSN in an environment for agriculture where environmental variables are present and correlate the capture of values received signal strength (RSSI) with a propagation model.

Keywords: propagation, WSN, agriculture, quality

Procedia PDF Downloads 737
4219 Affirming Students’ Attention and Perceptions on Prezi Presentation via Eye Tracking System

Authors: Mona Masood, Norshazlina Shaik Othman

Abstract:

The purpose of this study was to investigate graduate students’ visual attention and perceptions of a Prezi presentation. Ten post-graduate master students were presented with a Prezi presentation at the Centre for Instructional Technology and Multimedia, Universiti Sains Malaysia (USM). The eye movement indicators such as dwell time, average fixation on the areas of interests, heat maps and focus maps were abstracted to indicate the students’ visual attention. Descriptive statistics was employed to analyze the students’ perception of the Prezi presentation in terms of text, slide design, images, layout and overall presentation. The result revealed that the students paid more attention to the text followed by the images and sub heading presented through the Prezi presentation.

Keywords: eye tracking, Prezi, visual attention, visual perception

Procedia PDF Downloads 423
4218 Multimodal Data Fusion Techniques in Audiovisual Speech Recognition

Authors: Hadeer M. Sayed, Hesham E. El Deeb, Shereen A. Taie

Abstract:

In the big data era, we are facing a diversity of datasets from different sources in different domains that describe a single life event. These datasets consist of multiple modalities, each of which has a different representation, distribution, scale, and density. Multimodal fusion is the concept of integrating information from multiple modalities in a joint representation with the goal of predicting an outcome through a classification task or regression task. In this paper, multimodal fusion techniques are classified into two main classes: model-agnostic techniques and model-based approaches. It provides a comprehensive study of recent research in each class and outlines the benefits and limitations of each of them. Furthermore, the audiovisual speech recognition task is expressed as a case study of multimodal data fusion approaches, and the open issues through the limitations of the current studies are presented. This paper can be considered a powerful guide for interested researchers in the field of multimodal data fusion and audiovisual speech recognition particularly.

Keywords: multimodal data, data fusion, audio-visual speech recognition, neural networks

Procedia PDF Downloads 92
4217 Identifying Network Subgraph-Associated Essential Genes in Molecular Networks

Authors: Efendi Zaenudin, Chien-Hung Huang, Ka-Lok Ng

Abstract:

Essential genes play an important role in the survival of an organism. It has been shown that cancer-associated essential genes are genes necessary for cancer cell proliferation, where these genes are potential therapeutic targets. Also, it was demonstrated that mutations of the cancer-associated essential genes give rise to the resistance of immunotherapy for patients with tumors. In the present study, we focus on studying the biological effects of the essential genes from a network perspective. We hypothesize that one can analyze a biological molecular network by decomposing it into both three-node and four-node digraphs (subgraphs). These network subgraphs encode the regulatory interaction information among the network’s genetic elements. In this study, the frequency of occurrence of the subgraph-associated essential genes in a molecular network was quantified by using the statistical parameter, odds ratio. Biological effects of subgraph-associated essential genes are discussed. In summary, the subgraph approach provides a systematic method for analyzing molecular networks and it can capture useful biological information for biomedical research.

Keywords: biological molecular networks, essential genes, graph theory, network subgraphs

Procedia PDF Downloads 140
4216 Reliability-Simulation of Composite Tubular Structure under Pressure by Finite Elements Methods

Authors: Abdelkader Hocine, Abdelhakim Maizia

Abstract:

The exponential growth of reinforced fibers composite materials use has prompted researchers to step up their work on the prediction of their reliability. Owing to differences between the properties of the materials used for the composite, the manufacturing processes, the load combinations and types of environment, the prediction of the reliability of composite materials has become a primary task. Through failure criteria, TSAI-WU and the maximum stress, the reliability of multilayer tubular structures under pressure is the subject of this paper, where the failure probability of is estimated by the method of Monte Carlo.

Keywords: composite, design, monte carlo, tubular structure, reliability

Procedia PDF Downloads 442
4215 An Empirical Study on the Impact of Peace in Tourists' Country of Origin on Their Travel Behavior

Authors: Claudia Seabra, Elisabeth Kastenholz, José Luís Abrantes, Manuel Reis

Abstract:

In a world of increasing mobility and global risks, terrorism has, in a perverse way, capitalized on contemporaneous society’s growing interest in travel to explore a world whose national boundaries and distances have decreased. Terrorists have identified the modern tourist flows originated from the economically more developed countries as new appealing targets so as to: i) call attention to the causes they defend and ii) destroy a country’s foundations of tourism, with the final aim of disrupting the economic and consequently social fabric of the affected countries. The present study analyses sensitivity towards risk and travel behaviors in international travel amongst a sample of 600 international tourists from 49 countries travelling by air. Specifically, the sample was segmented according to the Global Peace Index. This index defines country profiles regarding the levels of peace. The indicators used are established over three broad themes: i) ongoing domestic and international conflict; ii) societal safety and security; and iii) militarisation. Tourists were segmented, according to their country of origin, in different levels of peacefulness. Several facets of travel behavior were evaluated, namely motivations, attitude towards trip planning, quality perception and perceived value of the trip. Also factors related with risk perception were evaluated, specifically terrorism risk perception during the trip, unsafety sensation as well as importance attributed to safety in travel. Results contribute to our understanding of the role of previous exposure to the lack of peace and safety at home in the international tourists behaviors, which is further discussed in terms of tourism management and marketing implications which should particularly interest tourism services and destinations more affected by terrorism, war, political turmoil, crime and other safety risks.

Keywords: terrorism, tourism, safety, risk perception

Procedia PDF Downloads 424
4214 Alloy Design of Single Crystal Ni-base Superalloys by Combined Method of Neural Network and CALPHAD

Authors: Mehdi Montakhabrazlighi, Ercan Balikci

Abstract:

The neural network (NN) method is applied to alloy development of single crystal Ni-base Superalloys with low density and improved mechanical strength. A set of 1200 dataset which includes chemical composition of the alloys, applied stress and temperature as inputs and density and time to rupture as outputs is used for training and testing the network. Thermodynamic phase diagram modeling of the screened alloys is performed with Thermocalc software to model the equilibrium phases and also microsegregation in solidification processing. The model is first trained by 80% of the data and the 20% rest is used to test it. Comparing the predicted values and the experimental ones showed that a well-trained network is capable of accurately predicting the density and time to rupture strength of the Ni-base superalloys. Modeling results is used to determine the effect of alloying elements, stress, temperature and gamma-prime phase volume fraction on rupture strength of the Ni-base superalloys. This approach is in line with the materials genome initiative and integrated computed materials engineering approaches promoted recently with the aim of reducing the cost and time for development of new alloys for critical aerospace components. This work has been funded by TUBITAK under grant number 112M783.

Keywords: neural network, rupture strength, superalloy, thermocalc

Procedia PDF Downloads 299
4213 Assessing the Effectiveness of Machine Learning Algorithms for Cyber Threat Intelligence Discovery from the Darknet

Authors: Azene Zenebe

Abstract:

Deep learning is a subset of machine learning which incorporates techniques for the construction of artificial neural networks and found to be useful for modeling complex problems with large dataset. Deep learning requires a very high power computational and longer time for training. By aggregating computing power, high performance computer (HPC) has emerged as an approach to resolving advanced problems and performing data-driven research activities. Cyber threat intelligence (CIT) is actionable information or insight an organization or individual uses to understand the threats that have, will, or are currently targeting the organization. Results of review of literature will be presented along with results of experimental study that compares the performance of tree-based and function-base machine learning including deep learning algorithms using secondary dataset collected from darknet.

Keywords: deep-learning, cyber security, cyber threat modeling, tree-based machine learning, function-based machine learning, data science

Procedia PDF Downloads 137
4212 Prediction on Housing Price Based on Deep Learning

Authors: Li Yu, Chenlu Jiao, Hongrun Xin, Yan Wang, Kaiyang Wang

Abstract:

In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.

Keywords: deep learning, convolutional neural network, LSTM, housing prediction

Procedia PDF Downloads 292
4211 Improved Rare Species Identification Using Focal Loss Based Deep Learning Models

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation

Procedia PDF Downloads 170
4210 A Genetic Algorithm Based Sleep-Wake up Protocol for Area Coverage in WSNs

Authors: Seyed Mahdi Jameii, Arash Nikdel, Seyed Mohsen Jameii

Abstract:

Energy efficiency is an important issue in the field of Wireless Sensor Networks (WSNs). So, minimizing the energy consumption in this kind of networks should be an essential consideration. Sleep/wake scheduling mechanism is an efficient approach to handling this issue. In this paper, we propose a Genetic Algorithm-based Sleep-Wake up Area Coverage protocol called GA-SWAC. The proposed protocol puts the minimum of nodes in active mode and adjusts the sensing radius of each active node to decrease the energy consumption while maintaining the network’s coverage. The proposed protocol is simulated. The results demonstrate the efficiency of the proposed protocol in terms of coverage ratio, number of active nodes and energy consumption.

Keywords: wireless sensor networks, genetic algorithm, coverage, connectivity

Procedia PDF Downloads 498
4209 Loss Allocation in Radial Distribution Networks for Loads of Composite Types

Authors: Sumit Banerjee, Chandan Kumar Chanda

Abstract:

The paper presents allocation of active power losses and energy losses to consumers connected to radial distribution networks in a deregulated environment for loads of composite types. A detailed comparison among four algorithms, namely quadratic loss allocation, proportional loss allocation, pro rata loss allocation and exact loss allocation methods are presented. Quadratic and proportional loss allocations are based on identifying the active and reactive components of current in each branch and the losses are allocated to each consumer, pro rata loss allocation method is based on the load demand of each consumer and exact loss allocation method is based on the actual contribution of active power loss by each consumer. The effectiveness of the proposed comparison among four algorithms for composite load is demonstrated through an example.

Keywords: composite type, deregulation, loss allocation, radial distribution networks

Procedia PDF Downloads 271
4208 A Review on the Perception of Beşiktaş Public Square

Authors: Neslinur Hizli, Berrak Kirbaş Akyürek

Abstract:

Beşiktaş, one of the historical coastal district of İstanbul, is on the very edge of the radical transformation because of an approaching ‘Beşiktaş Public Square Project’. At this juncture, due its location, presence on the coast, population density and distance to the other centers of the city, the decisions to be taken are critical to whole Istanbul that will be majorly affected from this transformation. As the new project aims to pedestrianize the area by placing the vehicular traffic under the ground, Beşiktaş and its square will change from top to bottom. Among those considerations, through the advantages and disadvantages the perception of the existing conditions of the Beşiktaş play significant role. The motive of this paper is the lack of determination and clarity on the cognition of the Square. After brief analysis on the historical transformation of the area, prominent studies on the criteria of public square are revised. Through cognitive mapping methodology, characteristics of the Square and the public space in general find a place to discuss from individual views. This study aims to discuss and review Beşiktaş Public Square from perspective, mind and behavior of the users. Cognitive map study with thirty subjects (30) is evaluated and categorized upon the five elements that Kevin Lynch defined as the images of the city. The results obtained digitized and represented with tables and graphs. Findings of the research underline the crucial issues on the approaching change in Beşiktaş. Thus, this study may help to develop comprehensive ideas and new suggestions on the Square.

Keywords: Beşiktaş public square, cognitive map, perception, public space

Procedia PDF Downloads 253
4207 Human-Centric Sensor Networks for Comfort and Productivity in Offices: Integrating Environmental, Body Area Network, and Participatory Sensing

Authors: Chenlu Zhang, Wanni Zhang, Florian Schaule

Abstract:

Indoor environment in office buildings directly affects comfort, productivity, health, and well-being of building occupants. Wireless environmental sensor networks have been deployed in many modern offices to monitor and control the indoor environments. However, indoor environmental variables are not strong enough predictors of comfort and productivity levels of every occupant due to personal differences, both physiologically and psychologically. This study proposes human-centric sensor networks that integrate wireless environmental sensors, body area network sensors and participatory sensing technologies to collect data from both environment and human and support building operations. The sensor networks have been tested in one small-size and one medium-size office rooms with 22 participants for five months. Indoor environmental data (e.g., air temperature and relative humidity), physiological data (e.g., skin temperature and Galvani skin response), and physiological responses (e.g., comfort and self-reported productivity levels) were obtained from each participant and his/her workplace. The data results show that: (1) participants have different physiological and physiological responses in the same environmental conditions; (2) physiological variables are more effective predictors of comfort and productivity levels than environmental variables. These results indicate that the human-centric sensor networks can support human-centric building control and improve comfort and productivity in offices.

Keywords: body area network, comfort and productivity, human-centric sensors, internet of things, participatory sensing

Procedia PDF Downloads 126
4206 The Balance between the Two Characters of the Night: A Study on the Nightscape of Pei Ho Street and Yen Chow Street West in Sham Shui Po

Authors: Lei Danyang, Lu Jialiang

Abstract:

As nightlife is getting richer in urban area, urban nightscape has become an increasingly important part of the urban landscape. Understanding urban nightscape from the perspec­tive of pedestrian perception is very important to improve the livability and walkability of a city. The purpose of this study is to analyze the nightscapes of two different urban forms. The research methods are literature investigation and field investigation. From analyzing the lighting, sensory ex­perience, and night activities, this research studies the two streets, Pei Ho Street and Yen Chow Street West in Sham Shui Po. Results revealed that the two streets are on the two extremes of the two characters of the night and a better balance needs to be found between them. Because of the different land usage and stakeholders, the two streets should play different roles in the nightscape, so their balance points are also different. On the one hand, Pei Ho Street, which has a strong commercial atmos­phere, should not only retain its vitality and diversity but also ensure its function of relaxation at night; on the other hand, in Yen Chow Street West, it is necessary to develop its potential of reconnecting people with the darkness of the night while ensur­ing its safety. These findings may not only provide policymak­ers with information to help them improve the nightscape and livability of the Sham Shui Po area but also help bridge the gap between research and design. In the future, more attention should be paid to pedestrian preference and nightscape perception of vulnerable groups.

Keywords: Hong Kong, pedestrian perception, Sham Shui Po, urban form, urban nightscape

Procedia PDF Downloads 132
4205 Power Grid Line Ampacity Forecasting Based on a Long-Short-Term Memory Neural Network

Authors: Xiang-Yao Zheng, Jen-Cheng Wang, Joe-Air Jiang

Abstract:

Improving the line ampacity while using existing power grids is an important issue that electricity dispatchers are now facing. Using the information provided by the dynamic thermal rating (DTR) of transmission lines, an overhead power grid can operate safely. However, dispatchers usually lack real-time DTR information. Thus, this study proposes a long-short-term memory (LSTM)-based method, which is one of the neural network models. The LSTM-based method predicts the DTR of lines using the weather data provided by Central Weather Bureau (CWB) of Taiwan. The possible thermal bottlenecks at different locations along the line and the margin of line ampacity can be real-time determined by the proposed LSTM-based prediction method. A case study that targets the 345 kV power grid of TaiPower in Taiwan is utilized to examine the performance of the proposed method. The simulation results show that the proposed method is useful to provide the information for the smart grid application in the future.

Keywords: electricity dispatch, line ampacity prediction, dynamic thermal rating, long-short-term memory neural network, smart grid

Procedia PDF Downloads 270
4204 Energy Efficient Clustering with Reliable and Load-Balanced Multipath Routing for Wireless Sensor Networks

Authors: Alamgir Naushad, Ghulam Abbas, Shehzad Ali Shah, Ziaul Haq Abbas

Abstract:

Unlike conventional networks, it is particularly challenging to manage resources efficiently in Wireless Sensor Networks (WSNs) due to their inherent characteristics, such as dynamic network topology and limited bandwidth and battery power. To ensure energy efficiency, this paper presents a routing protocol for WSNs, namely, Enhanced Hybrid Multipath Routing (EHMR), which employs hierarchical clustering and proposes a next hop selection mechanism between nodes according to a maximum residual energy metric together with a minimum hop count. Load-balancing of data traffic over multiple paths is achieved for a better packet delivery ratio and low latency rate. Reliability is ensured in terms of higher data rate and lower end-to-end delay. EHMR also enhances the fast-failure recovery mechanism to recover a failed path. Simulation results demonstrate that EHMR achieves a higher packet delivery ratio, reduced energy consumption per-packet delivery, lower end-to-end latency, and reduced effect of data rate on packet delivery ratio when compared with eminent WSN routing protocols.

Keywords: energy efficiency, load-balancing, hierarchical clustering, multipath routing, wireless sensor networks

Procedia PDF Downloads 64
4203 From Linear to Nonlinear Deterrence: Deterrence for Rising Power

Authors: Farhad Ghasemi

Abstract:

Along with transforming the international system into a complex and chaotic system, the fundamental question arises: how can deterrence be reconstructed conceptually and theoretically in this system model? The deterrence system is much more complex today than it was seven decades ago. This article suggests that the perception of deterrence as a linear system is a fundamental mistake because it does not consider the new dynamics of the international system, including network power dynamics. The author aims to improve this point by focusing on complexity and chaos theories, especially their nonlinearity and cascading failure principles. This article proposes that the perception of deterrence as a linear system is a fundamental mistake, as the new dynamics of the surrounding international system do not take into account. The author recognizes deterrence as a nonlinear system and introduces it as a concept in strategic studies.

Keywords: complexity, international system, deterrence, linear deterrence, nonlinear deterrence

Procedia PDF Downloads 127
4202 The Value and Role of Higher Education in the Police Profession

Authors: Habib Ahmadi, Mohamad Ali Ameri

Abstract:

In this research, the perception and understanding of police officers about the value of higher education have been investigated. A qualitative research approach and phenomenological method were used, and in data analysis, the Claizi method was used. In this research, 17 people with different degrees and occupations were selected by purposive sampling method until saturation and were investigated using a semi-structured interview tool. After the data was collected, recorded, and coded in the Atlas T software, it was formulated in the form of main categories and concepts. The general views of police officers participating in this research show the importance of university education in police jobs(76%). The analysis of participants' experiences led to the identification of seven main categories of the value and role of higher education, including; 1- Improvement of behavior and social skills, 2- Opportunities to improve and improve job performance, 3- Professionalization of police work, 4- Financial motivation, 5- People's satisfaction with police services, 6- Improvement of writing and technical skills Statement, 7- Raising the level of expectation and expectations was misplaced (negative perception). The findings of this study support the positive attitude and professionalism of the educated police. Therefore, considering the change of paradigm in society as well as the change of technologies, more complex organizational designs, and the perception of police officers, it is concluded that the police field needs officers with higher education to enable them to understand the new global environment.

Keywords: lived experience, higher education, police professionalization, perceptions of police officers

Procedia PDF Downloads 74