Pub Date : 2023-09-28DOI: 10.22230/jwsm.2023v6n1a47
Matthew Chernos, Kim Green, Ryan MacDonald
Forest disturbance can alter the hydrologic conditions of a watershed, including the frequency, magnitude, and timing of peak and low flows. Equivalent Clearcut Area (ECA) has been routinely used in watershed assessments to estimate hydrologic alteration due to forest disturbance. ECA analyses typically rely on broad regional assumptions, qualitative observations, and/or expert judgement, making it difficult to provide accurate quantitative estimates of hydrologic change. Process-based hydrological models offer an improved approach since they replicate watershed processes, can simulate land cover and climate change scenarios, and provide quantitative estimates of hydrologic change, including at ungauged points of interest. A workflow using a regionally calibrated hydrological model to investigate forest disturbance and future climate change scenarios is demonstrated. Results are contrasted with ECA-based outputs and emphasize that in addition to the amount of forest disturbance, watershed physical characteristics and the location of disturbance within a watershed influence the hydrologic response. This approach provides forest managers with quantitative outputs that support risk-based forest management decisions and presents a substantial improvement over ECA-based methods. Keywords: hydrological modelling, ECA-based analysis, watershed assessment, forest disturbance, cumulative effects, risk-based forest management
{"title":"Hydrological Modelling to Inform Forest Management: Moving Beyond Equivalent Clearcut Area","authors":"Matthew Chernos, Kim Green, Ryan MacDonald","doi":"10.22230/jwsm.2023v6n1a47","DOIUrl":"https://doi.org/10.22230/jwsm.2023v6n1a47","url":null,"abstract":"Forest disturbance can alter the hydrologic conditions of a watershed, including the frequency, magnitude, and timing of peak and low flows. Equivalent Clearcut Area (ECA) has been routinely used in watershed assessments to estimate hydrologic alteration due to forest disturbance. ECA analyses typically rely on broad regional assumptions, qualitative observations, and/or expert judgement, making it difficult to provide accurate quantitative estimates of hydrologic change. Process-based hydrological models offer an improved approach since they replicate watershed processes, can simulate land cover and climate change scenarios, and provide quantitative estimates of hydrologic change, including at ungauged points of interest. A workflow using a regionally calibrated hydrological model to investigate forest disturbance and future climate change scenarios is demonstrated. Results are contrasted with ECA-based outputs and emphasize that in addition to the amount of forest disturbance, watershed physical characteristics and the location of disturbance within a watershed influence the hydrologic response. This approach provides forest managers with quantitative outputs that support risk-based forest management decisions and presents a substantial improvement over ECA-based methods. Keywords: hydrological modelling, ECA-based analysis, watershed assessment, forest disturbance, cumulative effects, risk-based forest management","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135425171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Customer Churn, an event indicating a customer abandoning an established relation with a business is an important problem researched well, both for academic and commercial interest. Through this work, we propose an improved churn prediction model that emphasizes on an effective data collection pipeline through varied channels capturing explicit and implicit customer footprints. The goal of this paper is to demonstrate the improvement in classifier efficiency using an extended feature set and feature selection algorithms. Prominent features playing a vital role in customer churn are also ranked. The contributions through this paper can be broadly categorized into 3 folds: First, we discuss how popular data mining tools in Hadoop stack help extract several implicit customer interaction metrics including Sales and Clickstream logs generated as a result of customer interaction. Second, through Feature Engineering techniques we verify that some of the new features we propose have a definite impact on customer churn. Finally, we demonstrate how Regularized Logistic Regression, SVM and Gradient Boost Random Forests are the best performing models for predicting customer churn verified through comprehensive cross-validation techniques.
{"title":"Enhanced feature mining and classifier models to predict customer churn for an E-retailer","authors":"K. B. Subramanya, Arun Kumar Somani","doi":"10.1201/B21822-13","DOIUrl":"https://doi.org/10.1201/B21822-13","url":null,"abstract":"Customer Churn, an event indicating a customer abandoning an established relation with a business is an important problem researched well, both for academic and commercial interest. Through this work, we propose an improved churn prediction model that emphasizes on an effective data collection pipeline through varied channels capturing explicit and implicit customer footprints. The goal of this paper is to demonstrate the improvement in classifier efficiency using an extended feature set and feature selection algorithms. Prominent features playing a vital role in customer churn are also ranked. The contributions through this paper can be broadly categorized into 3 folds: First, we discuss how popular data mining tools in Hadoop stack help extract several implicit customer interaction metrics including Sales and Clickstream logs generated as a result of customer interaction. Second, through Feature Engineering techniques we verify that some of the new features we propose have a definite impact on customer churn. Finally, we demonstrate how Regularized Logistic Regression, SVM and Gradient Boost Random Forests are the best performing models for predicting customer churn verified through comprehensive cross-validation techniques.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"107 1","pages":"531-536"},"PeriodicalIF":0.0,"publicationDate":"2017-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73479404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-06-07DOI: 10.1109/CONFLUENCE.2017.7943199
Michael Opoku Agyeman, W. Zong, T. Kanakis, K. Tong, T. Mak
Recently, an improved surface wave-enabled communication fabric has been proposed to solve the reliability issues of emerging hybrid wired-wireless Network-on-Chip (WiNoC) architectures. Thus, providing a promising solution to the performance and scalability demands of the fast-paced technological growth towards exascale and Big-Data processing on future System-on-Chip (SoC) design. However, WiNoCs tradeoff optimized performance for cost by restricting the number of area and power hungry wireless nodes. Consequently, in this paper, we propose a low-latency adaptive router with a low-complexity single-cycle bypassing mechanism to alleviate the performance degradation due to the slow wired routers in such emerging hybrid NoCs. The proposed router is able to redistribute traffic in the network to alleviate average packet latency at both low and high traffic conditions. As a second contribution the paper presents an experimental evaluation of a practically implemented surface wave communication fabric. By reducing the latency between the wired nodes and wireless nodes the proposed router can improve performance efficiency in terms of average packet delay by an average of 50% in WiNoCs.
{"title":"Towards the practical design of performance-aware resilient wireless NoC architectures","authors":"Michael Opoku Agyeman, W. Zong, T. Kanakis, K. Tong, T. Mak","doi":"10.1109/CONFLUENCE.2017.7943199","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943199","url":null,"abstract":"Recently, an improved surface wave-enabled communication fabric has been proposed to solve the reliability issues of emerging hybrid wired-wireless Network-on-Chip (WiNoC) architectures. Thus, providing a promising solution to the performance and scalability demands of the fast-paced technological growth towards exascale and Big-Data processing on future System-on-Chip (SoC) design. However, WiNoCs tradeoff optimized performance for cost by restricting the number of area and power hungry wireless nodes. Consequently, in this paper, we propose a low-latency adaptive router with a low-complexity single-cycle bypassing mechanism to alleviate the performance degradation due to the slow wired routers in such emerging hybrid NoCs. The proposed router is able to redistribute traffic in the network to alleviate average packet latency at both low and high traffic conditions. As a second contribution the paper presents an experimental evaluation of a practically implemented surface wave communication fabric. By reducing the latency between the wired nodes and wireless nodes the proposed router can improve performance efficiency in terms of average packet delay by an average of 50% in WiNoCs.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"15 1","pages":"479-484"},"PeriodicalIF":0.0,"publicationDate":"2017-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81114870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-13DOI: 10.1109/CONFLUENCE.2017.7943198
T. Kanakis, Michael Opoku Agyeman, Anastasios G. Bakaoukas
Adaptive Virtual MIMO optimized in a single cluster of small cells is shown in this paper to achieve near Shannon channel capacity when operating with partial or no Channel State Information. Although, access links have enormously increased in the recent years, the operational system complexity remains linear regardless of the number of access nodes in the system proposed. Adaptive Virtual MIMO optimized in a single cluster performs a theoretical information spectral efficiency, almost equal to that of the upper bounds of a typical mesh network, up to 43 bits/s/Hz at a SNR of 30dB while the BER performance remains impressively low hitting the 10−6 at an SNR of about 13 dB when the theoretical upper bound of an ideal small cell mesh network achieves the 10−6 at a SNR of 12.5 dB. In addition, in a sub-optimum channel condition, the channel capacity and BER performance of the proposed solution is shown to drastically delay saturation even for the very high SNR.
{"title":"Adaptive virtual MIMO single cluster optimization in a small cell","authors":"T. Kanakis, Michael Opoku Agyeman, Anastasios G. Bakaoukas","doi":"10.1109/CONFLUENCE.2017.7943198","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943198","url":null,"abstract":"Adaptive Virtual MIMO optimized in a single cluster of small cells is shown in this paper to achieve near Shannon channel capacity when operating with partial or no Channel State Information. Although, access links have enormously increased in the recent years, the operational system complexity remains linear regardless of the number of access nodes in the system proposed. Adaptive Virtual MIMO optimized in a single cluster performs a theoretical information spectral efficiency, almost equal to that of the upper bounds of a typical mesh network, up to 43 bits/s/Hz at a SNR of 30dB while the BER performance remains impressively low hitting the 10−6 at an SNR of about 13 dB when the theoretical upper bound of an ideal small cell mesh network achieves the 10−6 at a SNR of 12.5 dB. In addition, in a sub-optimum channel condition, the channel capacity and BER performance of the proposed solution is shown to drastically delay saturation even for the very high SNR.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"28 1","pages":"474-478"},"PeriodicalIF":0.0,"publicationDate":"2017-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82253493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/CONFLUENCE.2017.7943187
Dr. Aleem Ali, Neeta Singh
MANET has acquired a remarkable stake in the arena of wireless communication within a short span of time. That is because of their flexibility, relatively low cost, scalability provided by their dynamic infrastructure. In this paper a Queueing Approach based model is proposed for MANETs to evaluate the performance measures. The node can be considered as a server to serve the arriving packets that reaches to destination node. The packets reaches each node in certain sequence, follow certain statistical distributions, and follow a specific model. M/G/1: ot/FIFO model is formulated for MANET which evaluates some its average waiting times (AWT), Queueing Delay (QD) and response times (RT).
{"title":"Queueing approach based MANET performance analysis","authors":"Dr. Aleem Ali, Neeta Singh","doi":"10.1109/CONFLUENCE.2017.7943187","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943187","url":null,"abstract":"MANET has acquired a remarkable stake in the arena of wireless communication within a short span of time. That is because of their flexibility, relatively low cost, scalability provided by their dynamic infrastructure. In this paper a Queueing Approach based model is proposed for MANETs to evaluate the performance measures. The node can be considered as a server to serve the arriving packets that reaches to destination node. The packets reaches each node in certain sequence, follow certain statistical distributions, and follow a specific model. M/G/1: ot/FIFO model is formulated for MANET which evaluates some its average waiting times (AWT), Queueing Delay (QD) and response times (RT).","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"205 1","pages":"422-424"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80385572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/CONFLUENCE.2017.7943131
Tribhi Kathuria, Ayush Gupta, J. Kumar, Vineet Kumar, K. Rana
Robotic manipulators are used in wide range of industrial applications. These are highly complex, multi-input multi-output and coupled systems requiring efficient control mechanism. This complexity is further enhanced as the number of links is increased. PID control is the most widely employed control scheme in the manufacturing industry but conventional tuning approaches for tuning PID gains do not offer satisfactory results for complex systems like robotic manipulators. This generates the need for advance optimization techniques to carry out the tuning of PID controller for a customized performance index. This paper presents a comparative study of the performances of three such heuristic optimization algorithms, namely. Teacher Learning Based Optimization Algorithm (TLBO), Flower Pollination Optimization Algorithm (FPO) and Genetic Algorithm (GA) for tuning the PID controllers applied to a three link planar rigid robotic manipulator. The trajectory tracking and disturbance rejection performances of the PID controller tuned by these algorithms are considered. The tuning has been done by minimizing the weighted sum of integral absolute error and integral of absolute controller output for path following. Based on the results obtained, it was concluded that TLBO offers superior results.
{"title":"Study of optimization methods for tuning of PID gains for three link manipulator","authors":"Tribhi Kathuria, Ayush Gupta, J. Kumar, Vineet Kumar, K. Rana","doi":"10.1109/CONFLUENCE.2017.7943131","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943131","url":null,"abstract":"Robotic manipulators are used in wide range of industrial applications. These are highly complex, multi-input multi-output and coupled systems requiring efficient control mechanism. This complexity is further enhanced as the number of links is increased. PID control is the most widely employed control scheme in the manufacturing industry but conventional tuning approaches for tuning PID gains do not offer satisfactory results for complex systems like robotic manipulators. This generates the need for advance optimization techniques to carry out the tuning of PID controller for a customized performance index. This paper presents a comparative study of the performances of three such heuristic optimization algorithms, namely. Teacher Learning Based Optimization Algorithm (TLBO), Flower Pollination Optimization Algorithm (FPO) and Genetic Algorithm (GA) for tuning the PID controllers applied to a three link planar rigid robotic manipulator. The trajectory tracking and disturbance rejection performances of the PID controller tuned by these algorithms are considered. The tuning has been done by minimizing the weighted sum of integral absolute error and integral of absolute controller output for path following. Based on the results obtained, it was concluded that TLBO offers superior results.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"12 1","pages":"99-104"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85958401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/CONFLUENCE.2017.7943226
Blessy Chacko, S. Agrwal, S. Gupta, Harendra Chahar, Saurabh R. Srivastava, N. Srivastav
Image fusion is the process for combining the characteristics of two or more images into an image file to generate more information into an image. Research Issues of Image fusion is enhancement of visual quality of fused image by reducing the noise. Wavelet transformation based Image fusion techniques provide better robustness for statistical attacks in comparison to Discrete Cosine Transform domain and Spatial Domain-based Image fusion. The combined technique of discrete cosine harmonic wavelet transform (DCHWT) provides advantages of DWT and DCT both techniques but the DWT have the disadvantage of fraction loss in embedding which increases mean square error and results decreasing PSNR. Robustness of fusion technique is proportional to PSNR. The Proposed algorithm presents Hybrid Integer wavelet transform and 4×4 block discrete cosine transform based image fusion technique to obtain image quality and higher informatics compared to DWT-DCT and DCHWT based fusion technique. The proposed combined 4×4 block IWT-DCT based image fusion technique reduces the MSE compared to existing DWT-DCT and DCHWT based image fusion.
{"title":"Performance of image fusion technique using 4×4 block wavelet cosine transformation","authors":"Blessy Chacko, S. Agrwal, S. Gupta, Harendra Chahar, Saurabh R. Srivastava, N. Srivastav","doi":"10.1109/CONFLUENCE.2017.7943226","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943226","url":null,"abstract":"Image fusion is the process for combining the characteristics of two or more images into an image file to generate more information into an image. Research Issues of Image fusion is enhancement of visual quality of fused image by reducing the noise. Wavelet transformation based Image fusion techniques provide better robustness for statistical attacks in comparison to Discrete Cosine Transform domain and Spatial Domain-based Image fusion. The combined technique of discrete cosine harmonic wavelet transform (DCHWT) provides advantages of DWT and DCT both techniques but the DWT have the disadvantage of fraction loss in embedding which increases mean square error and results decreasing PSNR. Robustness of fusion technique is proportional to PSNR. The Proposed algorithm presents Hybrid Integer wavelet transform and 4×4 block discrete cosine transform based image fusion technique to obtain image quality and higher informatics compared to DWT-DCT and DCHWT based fusion technique. The proposed combined 4×4 block IWT-DCT based image fusion technique reduces the MSE compared to existing DWT-DCT and DCHWT based image fusion.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"15 1","pages":"618-622"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77049470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/CONFLUENCE.2017.7943242
Chetan Juneja, R. S. Rai, H. Kothari
Pervasive and networked use of digital technologies has disrupted business strategies, industry structure and emergence of newer organizational forms with firms increasingly competing as software based ecosystems increasingly driven by convergence, changing materiality relationship between form and function of products and inter firm relationships. Decomposition of digital ecosystems into core and complementary module can potentially enable combinatorial innovation and asymmetric business models of platform providers and complementors. The layered modular architecture of digital artifacts, modularity and generativity of the ecosystem architecture help the evolutionary changes to the ecosystem through voluntaristic innovation by heterogeneous contributors which is a critical driver of ecosystem success. In this study using multi-theoretic lens of resource based view, platform architecture, strategic logic of opportunity and strategy as practice we develop a nomological network to explore the impact of platform architecture on complementor firm performance and posit a mediating role of firm's dynamic capabilities enabling competitive action.
{"title":"Logic of digital competition: A framework for impact of digital architecture on firm performance in software based ecosystems","authors":"Chetan Juneja, R. S. Rai, H. Kothari","doi":"10.1109/CONFLUENCE.2017.7943242","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943242","url":null,"abstract":"Pervasive and networked use of digital technologies has disrupted business strategies, industry structure and emergence of newer organizational forms with firms increasingly competing as software based ecosystems increasingly driven by convergence, changing materiality relationship between form and function of products and inter firm relationships. Decomposition of digital ecosystems into core and complementary module can potentially enable combinatorial innovation and asymmetric business models of platform providers and complementors. The layered modular architecture of digital artifacts, modularity and generativity of the ecosystem architecture help the evolutionary changes to the ecosystem through voluntaristic innovation by heterogeneous contributors which is a critical driver of ecosystem success. In this study using multi-theoretic lens of resource based view, platform architecture, strategic logic of opportunity and strategy as practice we develop a nomological network to explore the impact of platform architecture on complementor firm performance and posit a mediating role of firm's dynamic capabilities enabling competitive action.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"17 1","pages":"702-707"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83002355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/CONFLUENCE.2017.7943123
Devika Chhachhiya, Amita Sharma, Manish Gupta
Designing an optimal Neural Network architecture plays an important role in the performance of a neural network model. In the past few years, various bio-inspired optimization techniques have been applied to find the optimal architecture of a neural network model. In this paper Particle Swarm Optimization (PSO) technique has been applied with back propagation algorithm to find an optimal architecture for feed forward Neural Network. To optimize the architecture of neural network model Parameters considered are hidden neurons, learning rate and activation function. Fitness function applied for the selection of the optimal combination of the parameters is root mean square error (RMSE). Due to privatization of education number of private institutes and universities are increasing rapidly every year. This increase has resulted in huge number of data (NAAC reports) regarding the assessment and accreditation of higher education institutions. Dataset of 380 educational institutes has been collected from the official site of National Assessment and Accreditation Council (NAAC). Hybrid of PSO with back propagation has been applied on this dataset. Results obtained from both of the algorithms are compared on the basis of the fitness function and accuracy obtained.
{"title":"Designing optimal architecture of neural network with particle swarm optimization techniques specifically for educational dataset","authors":"Devika Chhachhiya, Amita Sharma, Manish Gupta","doi":"10.1109/CONFLUENCE.2017.7943123","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943123","url":null,"abstract":"Designing an optimal Neural Network architecture plays an important role in the performance of a neural network model. In the past few years, various bio-inspired optimization techniques have been applied to find the optimal architecture of a neural network model. In this paper Particle Swarm Optimization (PSO) technique has been applied with back propagation algorithm to find an optimal architecture for feed forward Neural Network. To optimize the architecture of neural network model Parameters considered are hidden neurons, learning rate and activation function. Fitness function applied for the selection of the optimal combination of the parameters is root mean square error (RMSE). Due to privatization of education number of private institutes and universities are increasing rapidly every year. This increase has resulted in huge number of data (NAAC reports) regarding the assessment and accreditation of higher education institutions. Dataset of 380 educational institutes has been collected from the official site of National Assessment and Accreditation Council (NAAC). Hybrid of PSO with back propagation has been applied on this dataset. Results obtained from both of the algorithms are compared on the basis of the fitness function and accuracy obtained.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"76 1","pages":"52-57"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86457212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/CONFLUENCE.2017.7943114
Neetu Faujdar, Shipra Saraswat
The bucket sort is a non-comparison sorting algorithm in which elements are scattered over the buckets. We have concluded, based on state-of-art that most of the researchers have been using the insertion sort within buckets. The other sorting technique is also used in many papers over the buckets. From the state-of-art of bucket sort, we have analyzed that insertion sort is preferable in case of low volume of data to be sorted. In this work, authors have used the merge, count and insertion sort separately over the buckets and the results are compared with each other. The sorting benchmark has been used to test the algorithms. For testing the algorithms, sorting benchmark has been used. We have defined the threshold (τ) defined the threshold for saving the time and space of the algorithms. Results indicate that, count sort comes out to be more efficient within the buckets for every type of dataset.
{"title":"The detailed experimental analysis of bucket sort","authors":"Neetu Faujdar, Shipra Saraswat","doi":"10.1109/CONFLUENCE.2017.7943114","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2017.7943114","url":null,"abstract":"The bucket sort is a non-comparison sorting algorithm in which elements are scattered over the buckets. We have concluded, based on state-of-art that most of the researchers have been using the insertion sort within buckets. The other sorting technique is also used in many papers over the buckets. From the state-of-art of bucket sort, we have analyzed that insertion sort is preferable in case of low volume of data to be sorted. In this work, authors have used the merge, count and insertion sort separately over the buckets and the results are compared with each other. The sorting benchmark has been used to test the algorithms. For testing the algorithms, sorting benchmark has been used. We have defined the threshold (τ) defined the threshold for saving the time and space of the algorithms. Results indicate that, count sort comes out to be more efficient within the buckets for every type of dataset.","PeriodicalId":6651,"journal":{"name":"2017 7th International Conference on Cloud Computing, Data Science & Engineering - Confluence","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86243211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：