Pub Date : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697684
P. Ghadekar, Shubham Ingole, Dhruv Sonone
Handwritten digit and letter recognition is one of the oldest and a very important topic in the field of pattern recognition. Handwritten digit and letter recognition poses different problem because of different writing styles, similarity in structure and angle of orientation. Therefore it is very important to find effective method for recognition and classification of digit and letter. Handwritten digit and letter recognition has various applications such as number plate recognition, extracting business card information, bank check processing, postal address processing, passport processing, signature processing etc. This paper propose a method of handwritten digit and letter recognition using feature extraction based on hybrid Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT). These extracted features are passed to K-Nearest Neighbour (KNN) and Support Vector Machine (SVM) classifiers for classification. Standard MNIST and EMNIST letter dataset are used for this experiment. Firstly MNIST digit and EMNSIT letter dataset are binarized and later stray pixels are removed. Features are extracted using hybrid Discrete Wavelet Transform and Discrete Cosine Transform. KNN and SVM classifiers are used for classification purpose. The proposed method was able to obtain a highest accuracy of 97.74% for digit and 89.51% for letter using SVM classifier.
{"title":"Handwritten Digit and Letter Recognition Using Hybrid DWT-DCT with KNN and SVM Classifier","authors":"P. Ghadekar, Shubham Ingole, Dhruv Sonone","doi":"10.1109/ICCUBEA.2018.8697684","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697684","url":null,"abstract":"Handwritten digit and letter recognition is one of the oldest and a very important topic in the field of pattern recognition. Handwritten digit and letter recognition poses different problem because of different writing styles, similarity in structure and angle of orientation. Therefore it is very important to find effective method for recognition and classification of digit and letter. Handwritten digit and letter recognition has various applications such as number plate recognition, extracting business card information, bank check processing, postal address processing, passport processing, signature processing etc. This paper propose a method of handwritten digit and letter recognition using feature extraction based on hybrid Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT). These extracted features are passed to K-Nearest Neighbour (KNN) and Support Vector Machine (SVM) classifiers for classification. Standard MNIST and EMNIST letter dataset are used for this experiment. Firstly MNIST digit and EMNSIT letter dataset are binarized and later stray pixels are removed. Features are extracted using hybrid Discrete Wavelet Transform and Discrete Cosine Transform. KNN and SVM classifiers are used for classification purpose. The proposed method was able to obtain a highest accuracy of 97.74% for digit and 89.51% for letter using SVM classifier.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128124574","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697418
G. Gosavi, V. Thakare
An ERP is a bundle of software packages cascaded meshed in integration to replace and expedite the transaction governing systems in an organization, Institute or Industry. The selection of an ERP for an Industry today is an inference of an analog study with no concrete justification to requisites and desperations of the Industry. A lot of parameters like Industry's requirement definition, the Nature, complexity, ease of navigation, financial inputs sought by the ERP, implemetation methodology and pertaining hazards. The software features like aestheticism measure, GUI extent, User friendly nature, obviation of complexity, processing speed, memory utilization, interface designs, reports clarity and extendibility, robustness and security, simplicity and reliability, compactness of code, database paradigms, 00 or RDB philosophies, no db or Cloud frameworks, Web compatibility, integrity and consistency etc. are of vulnerable significance while opting an ERP. The hardware, platform Operating system, the front end used is yet some more deciding constraints. Organizational parameters, assets and inputs, sizes and volumes are some more roles playing add ons. The selection of an ERP is a complex decision and there is no thumb rule for selection of an ERP. Once an ERP is selected, based on the Volume of its implementation and the huge Human and tangible resource set working behind it in Industry, the most concerned but desperately ignored technical Optimization strategy articulation becomes a counting coin factor. The paper aims to provide a thorough comprehensive logic provision encompassed in an Algorithm that will help and assist the intelligent customized selection and post selection Optimization.
{"title":"Mathematically Modeled Algorithm for Intelligently Customized Optimization of an Erp","authors":"G. Gosavi, V. Thakare","doi":"10.1109/ICCUBEA.2018.8697418","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697418","url":null,"abstract":"An ERP is a bundle of software packages cascaded meshed in integration to replace and expedite the transaction governing systems in an organization, Institute or Industry. The selection of an ERP for an Industry today is an inference of an analog study with no concrete justification to requisites and desperations of the Industry. A lot of parameters like Industry's requirement definition, the Nature, complexity, ease of navigation, financial inputs sought by the ERP, implemetation methodology and pertaining hazards. The software features like aestheticism measure, GUI extent, User friendly nature, obviation of complexity, processing speed, memory utilization, interface designs, reports clarity and extendibility, robustness and security, simplicity and reliability, compactness of code, database paradigms, 00 or RDB philosophies, no db or Cloud frameworks, Web compatibility, integrity and consistency etc. are of vulnerable significance while opting an ERP. The hardware, platform Operating system, the front end used is yet some more deciding constraints. Organizational parameters, assets and inputs, sizes and volumes are some more roles playing add ons. The selection of an ERP is a complex decision and there is no thumb rule for selection of an ERP. Once an ERP is selected, based on the Volume of its implementation and the huge Human and tangible resource set working behind it in Industry, the most concerned but desperately ignored technical Optimization strategy articulation becomes a counting coin factor. The paper aims to provide a thorough comprehensive logic provision encompassed in an Algorithm that will help and assist the intelligent customized selection and post selection Optimization.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133210369","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697512
N. Haswani, P. Deore
Drainage is the system or process by which water, sewage or other liquids are drained from a place and to maintain the proper function of drainage, its condition should be monitored regularly. But manually it is very difficult to monitor all area where a human cannot reach. This influences the blockage of underground pipes and overflows of water cause the health problem. To mitigate all these issues here we are developed and implemented the system using wireless sensor network. It consisting of small devices used to collect data. These sensing devices are called node. The proposed system is low cost, less maintenance, long life and web-based real time system, which update the municipal officer by text message when any manhole crosses the threshold value. This system directly impacts on the health issues of citizens and worker who cleans the underground drainage. It also avoids spreading of infection due to mosquitoes and gives clean and healthy environment as well as controls the diseases such as malaria, dengue, diarrhea, etc. The system reduces the accident caused by an exposed manhole.
{"title":"Web-Based Realtime Underground Drainage or Sewage Monitoring System Using Wireless Sensor Networks","authors":"N. Haswani, P. Deore","doi":"10.1109/ICCUBEA.2018.8697512","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697512","url":null,"abstract":"Drainage is the system or process by which water, sewage or other liquids are drained from a place and to maintain the proper function of drainage, its condition should be monitored regularly. But manually it is very difficult to monitor all area where a human cannot reach. This influences the blockage of underground pipes and overflows of water cause the health problem. To mitigate all these issues here we are developed and implemented the system using wireless sensor network. It consisting of small devices used to collect data. These sensing devices are called node. The proposed system is low cost, less maintenance, long life and web-based real time system, which update the municipal officer by text message when any manhole crosses the threshold value. This system directly impacts on the health issues of citizens and worker who cleans the underground drainage. It also avoids spreading of infection due to mosquitoes and gives clean and healthy environment as well as controls the diseases such as malaria, dengue, diarrhea, etc. The system reduces the accident caused by an exposed manhole.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133973774","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697840
V. Bondre, S. Dorle
In recent development of vehicular adhoc network the consumption of energy by its nodes is major problem now a day. To overcome this problem many algorithms are proposed effectively by different researcher. The two main aspects that can resolve this issue is by having proper routing and network design. Many existing routing protocols are available with vehicular adhoc network, but only few of them can be utilize to resolve with the energy efficient problem. In wireless sensor network when the nodes are deployed they consumed most of the energy continuously to broadcast the message in multi hop connectivity. Generally nodes remain active even when there is no message to forward. This keeps decreasing the energy level of sink node. As a result the performance of the network gets dropped down. In our proposed algorithm, we aim to resolve this by relaying the node energy between active and passive mode. In our methodology sensor nodes gets triggered into active mode after a specific interval of time to exchange its data among them. The simulation results show that our proposed scheme, surpass from the other existing schemes. At the same time, each sensor node will restore its energy at regular interval as well as maintain high reception rate and low delay for multi-hop network.
{"title":"Energy Efficient Routing in Vehicular Adhoc Network for Emergency Services","authors":"V. Bondre, S. Dorle","doi":"10.1109/ICCUBEA.2018.8697840","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697840","url":null,"abstract":"In recent development of vehicular adhoc network the consumption of energy by its nodes is major problem now a day. To overcome this problem many algorithms are proposed effectively by different researcher. The two main aspects that can resolve this issue is by having proper routing and network design. Many existing routing protocols are available with vehicular adhoc network, but only few of them can be utilize to resolve with the energy efficient problem. In wireless sensor network when the nodes are deployed they consumed most of the energy continuously to broadcast the message in multi hop connectivity. Generally nodes remain active even when there is no message to forward. This keeps decreasing the energy level of sink node. As a result the performance of the network gets dropped down. In our proposed algorithm, we aim to resolve this by relaying the node energy between active and passive mode. In our methodology sensor nodes gets triggered into active mode after a specific interval of time to exchange its data among them. The simulation results show that our proposed scheme, surpass from the other existing schemes. At the same time, each sensor node will restore its energy at regular interval as well as maintain high reception rate and low delay for multi-hop network.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134224978","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697683
Avani M. Sakhapara, D. Pawade, Saumil Dedhia, Twinkle Bhanushali, V. Doshi
In this digital era, capturing photos using smartphone camera is very handy. Especially when we are hanging out with friends or family or attending a wedding and so on, we end up taking many group photos. But when browsing through these group photos, most of the times, a person is interested in only those photos in which he himself is present. So, currently we manually browse through such group photos in the phone gallery and then identify the pictures in which the specific person is present. For group photos, this procedure needs to be repeated for every person in the group. In this paper, we have designed and implemented an Android platform based photo grouping application named “EuphoriaGrouping” (EUG) using Neural Networks. EUG application automates the process of detecting faces and identifying persons from a group photo. It maintains a catalogue of group photos for every person present in the group photo. For person identification, two different convolutional neural network models, viz, Custom Built and OpenFace CNN are used. Implementation and performance comparison of these models is presented.
{"title":"Machine Learning Based Approach for Person Identification in Group Photos","authors":"Avani M. Sakhapara, D. Pawade, Saumil Dedhia, Twinkle Bhanushali, V. Doshi","doi":"10.1109/ICCUBEA.2018.8697683","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697683","url":null,"abstract":"In this digital era, capturing photos using smartphone camera is very handy. Especially when we are hanging out with friends or family or attending a wedding and so on, we end up taking many group photos. But when browsing through these group photos, most of the times, a person is interested in only those photos in which he himself is present. So, currently we manually browse through such group photos in the phone gallery and then identify the pictures in which the specific person is present. For group photos, this procedure needs to be repeated for every person in the group. In this paper, we have designed and implemented an Android platform based photo grouping application named “EuphoriaGrouping” (EUG) using Neural Networks. EUG application automates the process of detecting faces and identifying persons from a group photo. It maintains a catalogue of group photos for every person present in the group photo. For person identification, two different convolutional neural network models, viz, Custom Built and OpenFace CNN are used. Implementation and performance comparison of these models is presented.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"287 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123100247","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697852
Nikhil V. Soniminde, Sudeen D. Thenade
In this modern digital era, the Content Based Video Retrieval (CBVR) utilizes the video contents for representation, indexing and retrieval applications. The paper attempts Content Based Video Retrieval with TSnBTC (Thepade's Sorted n-ary Block Truncation Coding) color feature extraction technique and windowing of RGB planes into number of different partitions, such as windowing in $1times 1,2times 2,3times 3,4times 4$ and then TSnBTC is applied on these partitions. This Paper analyses the effect of 11 different similarity measures on accuracy of video retrieval. The similarity measures used are distances like Euclidean, Chebychev, City Block Metric, Hamming, Mean Squared Error, Soergel, Sorensen, Canberra, Kulczynsk, Cosine and Jaccard across 3 families such as LP Minkowski family, L1 family and Inner Product family in which Sorensen distance gives higher accuracy immediately next higher accuracy is given by City Block Metric distance. The process of feature vector extraction by using 20th frequency frame of videos. The test bed of 500 videos of different 10 categories of video sets is used for experimental appraise of proposed TSnBTC based video retrieval method. Each testbed category consist of 50 videos. The average video retrieval accuracy is computed for each of the partitioning variations of proposed technique. Through experimentation it has been found that TSPBTC (Pentanary), TSSBTC (Septanary), TSOBTC (Octanary) gives better video retrieval accuracy as compared to TSTBTC (Ternary) and TSQBTC (Quarternary) and partitioning (global windowing) improves the accuracy of content based video retrieval.
{"title":"Global Windowing Based Thepade's Sorted N-Ary Block Truncation Coding (TSnBTC) for Content Based Video Retrieval with Various Similarity Measures","authors":"Nikhil V. Soniminde, Sudeen D. Thenade","doi":"10.1109/ICCUBEA.2018.8697852","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697852","url":null,"abstract":"In this modern digital era, the Content Based Video Retrieval (CBVR) utilizes the video contents for representation, indexing and retrieval applications. The paper attempts Content Based Video Retrieval with TSnBTC (Thepade's Sorted n-ary Block Truncation Coding) color feature extraction technique and windowing of RGB planes into number of different partitions, such as windowing in $1times 1,2times 2,3times 3,4times 4$ and then TSnBTC is applied on these partitions. This Paper analyses the effect of 11 different similarity measures on accuracy of video retrieval. The similarity measures used are distances like Euclidean, Chebychev, City Block Metric, Hamming, Mean Squared Error, Soergel, Sorensen, Canberra, Kulczynsk, Cosine and Jaccard across 3 families such as LP Minkowski family, L1 family and Inner Product family in which Sorensen distance gives higher accuracy immediately next higher accuracy is given by City Block Metric distance. The process of feature vector extraction by using 20th frequency frame of videos. The test bed of 500 videos of different 10 categories of video sets is used for experimental appraise of proposed TSnBTC based video retrieval method. Each testbed category consist of 50 videos. The average video retrieval accuracy is computed for each of the partitioning variations of proposed technique. Through experimentation it has been found that TSPBTC (Pentanary), TSSBTC (Septanary), TSOBTC (Octanary) gives better video retrieval accuracy as compared to TSTBTC (Ternary) and TSQBTC (Quarternary) and partitioning (global windowing) improves the accuracy of content based video retrieval.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124572504","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697662
C. Aparna, Jyothisha J Nairt
In social network analysis and graph theory, influence node is a measure that used to quantify the importance of a node in that network. Community is a collection of node. Influencing community indicate the community which have higher impact in the network. The influence of a community is categorized into two, inner influence and outer influence. The existing techniques largely ignore the outer influence of communities. Outer influence of a community is the capability to spread internal opinion, knowledge to external users of the community in social network. So we propose a method to find the influence of a community by using overlapping nature of a network.
{"title":"Influencing Community Detection Using Overlapping Communities","authors":"C. Aparna, Jyothisha J Nairt","doi":"10.1109/ICCUBEA.2018.8697662","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697662","url":null,"abstract":"In social network analysis and graph theory, influence node is a measure that used to quantify the importance of a node in that network. Community is a collection of node. Influencing community indicate the community which have higher impact in the network. The influence of a community is categorized into two, inner influence and outer influence. The existing techniques largely ignore the outer influence of communities. Outer influence of a community is the capability to spread internal opinion, knowledge to external users of the community in social network. So we propose a method to find the influence of a community by using overlapping nature of a network.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132261385","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697601
Sumedh Kadam, Aayush Gala, Pritesh Gehlot, Aditya Kurup, K. Ghag
Spam messages are widely used nowadays to promote the business. In order to tackle this issue, spam filtering algorithms are used to detect and remove spams. Naive Bayes is popularly used in spam filtering. But the major drawback of this algorithm is that it assumes independence between every pair of features. As a result, features occurring in the same context are not given weightage during classification. An innovative classification method based on Multinomial Naive Bayes and Word Embedding is proposed. First posterior probabilities are calculated using Multinomial Naive Bayes. If the absolute difference of the ham and spam posterior probabilities is less than a certain threshold, word embedding is used to find out the closeness of the features in vector space. Results show that Multinomial Naive Bayes combined with Word Embedding gives better accuracy than Multinomial Naive Bayes alone.
{"title":"Word Embedding Based Multinomial Naive Bayes Algorithm for Spam Filtering","authors":"Sumedh Kadam, Aayush Gala, Pritesh Gehlot, Aditya Kurup, K. Ghag","doi":"10.1109/ICCUBEA.2018.8697601","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697601","url":null,"abstract":"Spam messages are widely used nowadays to promote the business. In order to tackle this issue, spam filtering algorithms are used to detect and remove spams. Naive Bayes is popularly used in spam filtering. But the major drawback of this algorithm is that it assumes independence between every pair of features. As a result, features occurring in the same context are not given weightage during classification. An innovative classification method based on Multinomial Naive Bayes and Word Embedding is proposed. First posterior probabilities are calculated using Multinomial Naive Bayes. If the absolute difference of the ham and spam posterior probabilities is less than a certain threshold, word embedding is used to find out the closeness of the features in vector space. Results show that Multinomial Naive Bayes combined with Word Embedding gives better accuracy than Multinomial Naive Bayes alone.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134125582","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697566
Sheetal Jain, Soumya Shrivastava, Zia Saquib, Seema Shah, A. Rodrigues
Control system is the core of the water distribution system (WDS). WDS system has information in the form of data feeds. By analyzing these data feeds, we can provide enough information about the leakage area in the system to take control manually over the system. In this paper, leakage areas are isolated using various Machine Learning (ML) techniques. EPANET (Environmental Protection Agency Networks) is used to model the hydraulic behavior of WDS. In WDS, leakage scenarios are created through EPANET by varying the input parameters (such as roughness, tank level, base demand). This data is then analyzed using different supervised machine learning techniques to determine the high-pressure links to identify the critical areas. We also compare the accuracy of different supervised machine learning algorithm which involves the importance of feature engineering term used in Machine learning.
{"title":"Identification of High Pressure Critical Links in Water Distribution Systems","authors":"Sheetal Jain, Soumya Shrivastava, Zia Saquib, Seema Shah, A. Rodrigues","doi":"10.1109/ICCUBEA.2018.8697566","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697566","url":null,"abstract":"Control system is the core of the water distribution system (WDS). WDS system has information in the form of data feeds. By analyzing these data feeds, we can provide enough information about the leakage area in the system to take control manually over the system. In this paper, leakage areas are isolated using various Machine Learning (ML) techniques. EPANET (Environmental Protection Agency Networks) is used to model the hydraulic behavior of WDS. In WDS, leakage scenarios are created through EPANET by varying the input parameters (such as roughness, tank level, base demand). This data is then analyzed using different supervised machine learning techniques to determine the high-pressure links to identify the critical areas. We also compare the accuracy of different supervised machine learning algorithm which involves the importance of feature engineering term used in Machine learning.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133774730","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697627
Rahul Patil, P. Bais, K. Baviskar, Snehal Shevate, M. Kalyani
With the increase in number of vehicles being used over the globe, we hereby look into some of the problems being faced by the drivers today. The problems that are in the lime light in this paper include Fuel quantity measurement, fuel theft detection, driver drowsiness, air pressure sensing in vehicle tyres etc. The Fuel quantity measurement and air pressure measurement is done using HCSR04 ultrasonic sensors. Output from both the sensors is sent to Raspberry pi and is further stored into firebase. Further android application retrieves data from firebase, displays the output on screen and generates the alert message in case of undesired events for eg: low fuel quantity, low air pressure in tyres. Drowsiness is detected using Heartbeat rate sensor which senses the heartbeat rate of the driver and sends the output to Arduino. Further through bluetooth technology, the data is shared with Android application and driver is notified incase of a positive drowsiness detection.
{"title":"An Android Application for Driver Assistance and Event Alert System Using Ultrasonic Sensor and Heart Rate Sensor","authors":"Rahul Patil, P. Bais, K. Baviskar, Snehal Shevate, M. Kalyani","doi":"10.1109/ICCUBEA.2018.8697627","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697627","url":null,"abstract":"With the increase in number of vehicles being used over the globe, we hereby look into some of the problems being faced by the drivers today. The problems that are in the lime light in this paper include Fuel quantity measurement, fuel theft detection, driver drowsiness, air pressure sensing in vehicle tyres etc. The Fuel quantity measurement and air pressure measurement is done using HCSR04 ultrasonic sensors. Output from both the sensors is sent to Raspberry pi and is further stored into firebase. Further android application retrieves data from firebase, displays the output on screen and generates the alert message in case of undesired events for eg: low fuel quantity, low air pressure in tyres. Drowsiness is detected using Heartbeat rate sensor which senses the heartbeat rate of the driver and sends the output to Arduino. Further through bluetooth technology, the data is shared with Android application and driver is notified incase of a positive drowsiness detection.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133776823","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：