Pub Date : 1900-01-01DOI: 10.1109/ISCO.2017.7855955
Thanmayee, H. Prasad
Data sets are growing day by day as they are being captured by information sensing devices such as mobiles, computers, wireless sensor networks, cameras, software logs, weblogs, remote sensing in various fields such as medical, engineering, science and many more. These large data sets are now called Big Data. Working with Big Data is not a common task. As this large data set has information hidden within them, researchers cannot and they have not ignored the large data set. Data mining is an interdisciplinary field in Computer Science which extracts information or the hidden patterns from data. Association rule mining and frequent itemset mining are popular data mining techniques that requires entire data to be in main memory. But large datasets does not fit into main memory. To handle this drawback, Hadoop MapReduce approach is used which has scalability and robustness features to handle large datasets. Apriori, Eclat and FP Growth are well known Frequent Itemset Mining algorithms. These algorithms are revised to work with Big Data using Hadoop MapReduce. But MapReduce framework has problems such as it stores the intermediate data in local disk. So the data needs to be accessed from the local disk which results in high latency problem. To address this issue Spark follows a general execution model that helps in in-memory computing and optimization of arbitrary operator graphs so that querying data becomes much faster when compared to the disk based engines like MapReduce. Thus the paper focuses on enhancing the performance of Frequent Itemset Mining using Apache Spark architecture and study the performance of this Revamped Market Basket Analysis based on FP-Growth by comparing it with Hadoop MapReduce implementation of Frequent Itemset Mining task, BigFIM and also with different datasets.
{"title":"Revamped Market-Basket Analysis using In-Memory Computation framework","authors":"Thanmayee, H. Prasad","doi":"10.1109/ISCO.2017.7855955","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7855955","url":null,"abstract":"Data sets are growing day by day as they are being captured by information sensing devices such as mobiles, computers, wireless sensor networks, cameras, software logs, weblogs, remote sensing in various fields such as medical, engineering, science and many more. These large data sets are now called Big Data. Working with Big Data is not a common task. As this large data set has information hidden within them, researchers cannot and they have not ignored the large data set. Data mining is an interdisciplinary field in Computer Science which extracts information or the hidden patterns from data. Association rule mining and frequent itemset mining are popular data mining techniques that requires entire data to be in main memory. But large datasets does not fit into main memory. To handle this drawback, Hadoop MapReduce approach is used which has scalability and robustness features to handle large datasets. Apriori, Eclat and FP Growth are well known Frequent Itemset Mining algorithms. These algorithms are revised to work with Big Data using Hadoop MapReduce. But MapReduce framework has problems such as it stores the intermediate data in local disk. So the data needs to be accessed from the local disk which results in high latency problem. To address this issue Spark follows a general execution model that helps in in-memory computing and optimization of arbitrary operator graphs so that querying data becomes much faster when compared to the disk based engines like MapReduce. Thus the paper focuses on enhancing the performance of Frequent Itemset Mining using Apache Spark architecture and study the performance of this Revamped Market Basket Analysis based on FP-Growth by comparing it with Hadoop MapReduce implementation of Frequent Itemset Mining task, BigFIM and also with different datasets.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121264378","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7856015
P. Rajesh, K. Umamaheswari
This paper presents the coupling of frequency spectra or degree of association between the EEG and ECG signals at a particular frequency. Coherence is often interpreted as a measure of a functional association and ‘coupling’ between two signals. An electrocardiogram (ECG) is an electrical recording of the heart and is used in the investigation of heart disease. An electrocardiogram (ECG) is a graphic tracing of the electric current generated by the heart muscle during heart beat. It has been used extensively in medicine since it has been proven to be invaluable in various diagnostics applications and clinical applications. An EEG signal reflects the electrical activity of human brain. EEG signals arises from the fact that these waveforms provide the non-invasive diagnostic tool in a wealth of disorders that include epilepsy and comma assessment in intensive e care unit. In this paper, we analyzed the association of heart with brain signals (ECG and EEG) of fundamental animals like Dog and Cow by obtaining magnitude squared coherence and phase coherence parameters at a certain range of frequency. We also analyzed the coherence between heart and brain signals of Healthy subject, Comatic patient and Brain dead person.
{"title":"Coherence analysis between heart and brain of healthy and unhealthy subjects","authors":"P. Rajesh, K. Umamaheswari","doi":"10.1109/ISCO.2017.7856015","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7856015","url":null,"abstract":"This paper presents the coupling of frequency spectra or degree of association between the EEG and ECG signals at a particular frequency. Coherence is often interpreted as a measure of a functional association and ‘coupling’ between two signals. An electrocardiogram (ECG) is an electrical recording of the heart and is used in the investigation of heart disease. An electrocardiogram (ECG) is a graphic tracing of the electric current generated by the heart muscle during heart beat. It has been used extensively in medicine since it has been proven to be invaluable in various diagnostics applications and clinical applications. An EEG signal reflects the electrical activity of human brain. EEG signals arises from the fact that these waveforms provide the non-invasive diagnostic tool in a wealth of disorders that include epilepsy and comma assessment in intensive e care unit. In this paper, we analyzed the association of heart with brain signals (ECG and EEG) of fundamental animals like Dog and Cow by obtaining magnitude squared coherence and phase coherence parameters at a certain range of frequency. We also analyzed the coherence between heart and brain signals of Healthy subject, Comatic patient and Brain dead person.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128204906","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7856002
Vaishali Patil, Ramesh Vasappanavara, T. Ghorpade
Information network derived from various domains are studied recently. Searching for Similarity is a major task into such types Information Network. Lot of research on computing similar objects is done in Homogeneous Information Network. But real world scenario can be described easily by Heterogeneous Information Network (HIN) which consists of different types of entities and relationship among them. Due to multiple type of entities and links between them in HIN, it is necessary to find the similarities between the nodes of HIN. In Homogeneous Information Network, there is only single type of node and links in between them. There are many existing methods by which similarity among the nodes of Homogeneous Information Network can be calculated. But those methods cannot be applied for the HIN because semantic meaning behind each path cannot be considered. If we want to apply techniques of Homogeneous Information Network on HIN then we need to project HIN into Homogeneous Information Network which causes loss of Information. So there is a need to apply different techniques or similarity measures on HIN to calculate the similarities between nodes in HIN. There are many similarity measures implemented by researchers for HIN. Similarity search basically concentrates on discovering the most similarity objects for a given query entity. In a comparative analysis section, we have discussed some of the measures used for similarity.
{"title":"Comparative analysis of similarity measures in Heterogeneous Information Network","authors":"Vaishali Patil, Ramesh Vasappanavara, T. Ghorpade","doi":"10.1109/ISCO.2017.7856002","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7856002","url":null,"abstract":"Information network derived from various domains are studied recently. Searching for Similarity is a major task into such types Information Network. Lot of research on computing similar objects is done in Homogeneous Information Network. But real world scenario can be described easily by Heterogeneous Information Network (HIN) which consists of different types of entities and relationship among them. Due to multiple type of entities and links between them in HIN, it is necessary to find the similarities between the nodes of HIN. In Homogeneous Information Network, there is only single type of node and links in between them. There are many existing methods by which similarity among the nodes of Homogeneous Information Network can be calculated. But those methods cannot be applied for the HIN because semantic meaning behind each path cannot be considered. If we want to apply techniques of Homogeneous Information Network on HIN then we need to project HIN into Homogeneous Information Network which causes loss of Information. So there is a need to apply different techniques or similarity measures on HIN to calculate the similarities between nodes in HIN. There are many similarity measures implemented by researchers for HIN. Similarity search basically concentrates on discovering the most similarity objects for a given query entity. In a comparative analysis section, we have discussed some of the measures used for similarity.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130100290","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7855998
Jivesh Verma, P. Dey, A. Prajapati, T. Das
Back Surface Field layer is very much important for both single and multi-junction solar cells for controlling the recombination rate. In this work multi BSF layers are used at both top and bottom cells to get higher external quantum efficiency from the cell. The work is done taking double junction InGaP/GaAs Solar cell and the optimization of the BSF layers is done using the computational numerical modeling with Silvaco ATLAS simulation technique. The structure, photo-generation rate, thickness of BSF layers is discussed in this paper. For this optimized cell structure, the maximum available short circuit current density is 17.35 mA/cm2 and is obtained at an open circuit voltage of 2.69 V which leads to a higher conversion efficiency.
{"title":"Multi BSF layer InGaP/GaAs high efficiency solar cell","authors":"Jivesh Verma, P. Dey, A. Prajapati, T. Das","doi":"10.1109/ISCO.2017.7855998","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7855998","url":null,"abstract":"Back Surface Field layer is very much important for both single and multi-junction solar cells for controlling the recombination rate. In this work multi BSF layers are used at both top and bottom cells to get higher external quantum efficiency from the cell. The work is done taking double junction InGaP/GaAs Solar cell and the optimization of the BSF layers is done using the computational numerical modeling with Silvaco ATLAS simulation technique. The structure, photo-generation rate, thickness of BSF layers is discussed in this paper. For this optimized cell structure, the maximum available short circuit current density is 17.35 mA/cm2 and is obtained at an open circuit voltage of 2.69 V which leads to a higher conversion efficiency.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128811544","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7856033
Bharathkumar V., Irshad Sm, G. S., R. Geethamani
The objective of this paper is to design and implement the low cost digital meter using PIC microcontroller, which could be used for monitoring the temperature and humidity of our environment. In this paper, it is focused mainly for our homes. The temperature is measured using LM35 temperature sensor and the humidity is measured using DHT11 humidity sensor. The measured parameters are displayed through LCD screens, normally like a digital meter. Apart from acting as a meter, it performs the function of automated control system which controls the motor driver connected to the fan, based on the temperature sensed using the microcontroller. When the fire catches the home and the sensor values exceeds the limit, an alert SMS will be sent to the person living in the home through the SIM900 GSM module. Also, an SMS carrying the home address will be sent to the fire department which alerts the fire fighters to urge to the location so that they can protect the home from fire. This paper also proposes the idea of automatic humidity controller using dehumidifier controlled by the microcontroller through the relay module. Thus, the proposed microcontroller based automated digital meter model has been discussed in the paper.
{"title":"Microcontroller based digital meter with alert system using GSM","authors":"Bharathkumar V., Irshad Sm, G. S., R. Geethamani","doi":"10.1109/ISCO.2017.7856033","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7856033","url":null,"abstract":"The objective of this paper is to design and implement the low cost digital meter using PIC microcontroller, which could be used for monitoring the temperature and humidity of our environment. In this paper, it is focused mainly for our homes. The temperature is measured using LM35 temperature sensor and the humidity is measured using DHT11 humidity sensor. The measured parameters are displayed through LCD screens, normally like a digital meter. Apart from acting as a meter, it performs the function of automated control system which controls the motor driver connected to the fan, based on the temperature sensed using the microcontroller. When the fire catches the home and the sensor values exceeds the limit, an alert SMS will be sent to the person living in the home through the SIM900 GSM module. Also, an SMS carrying the home address will be sent to the fire department which alerts the fire fighters to urge to the location so that they can protect the home from fire. This paper also proposes the idea of automatic humidity controller using dehumidifier controlled by the microcontroller through the relay module. Thus, the proposed microcontroller based automated digital meter model has been discussed in the paper.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128823809","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7855999
K. Ramkumar, P. Newton
Scheduling process is a tedious task in heterogeneous networks because of the large number of users and the reduced radio resource facilities. Scheduling is nothing but granting certain number of sources to the users in a frequency and timing fashion. Resources define the symbols and subcarriers for transmitting the bits in scheduling. There are many ways to assign these things to the subscribers. Interference is one of the biggest issues in downlink scheduling algorithms. Due to high demands of the user requirement and speed, the network fails to validate their interference ranges and finally it assigns the resources wrongly. This cause the Non-Interference users get more number of blocks when comparing with the Interference users. This paper proposes a new technique to overcome the above issue and assign the resources starting from the users who are in non-interference range to interference range users. The outcome of the proposed work properly assigns the resources and increases the system throughput of the standard subscribers and also mitigates the wrong resource block assignment of the interference users.
{"title":"Interference aware downlink scheduling algorithm in Mobile networks","authors":"K. Ramkumar, P. Newton","doi":"10.1109/ISCO.2017.7855999","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7855999","url":null,"abstract":"Scheduling process is a tedious task in heterogeneous networks because of the large number of users and the reduced radio resource facilities. Scheduling is nothing but granting certain number of sources to the users in a frequency and timing fashion. Resources define the symbols and subcarriers for transmitting the bits in scheduling. There are many ways to assign these things to the subscribers. Interference is one of the biggest issues in downlink scheduling algorithms. Due to high demands of the user requirement and speed, the network fails to validate their interference ranges and finally it assigns the resources wrongly. This cause the Non-Interference users get more number of blocks when comparing with the Interference users. This paper proposes a new technique to overcome the above issue and assign the resources starting from the users who are in non-interference range to interference range users. The outcome of the proposed work properly assigns the resources and increases the system throughput of the standard subscribers and also mitigates the wrong resource block assignment of the interference users.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125066699","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7856027
Dhanashri H. Gawali, V. Wadhai
Mobile healthcare systems have great potential for continuous monitoring. These devices are often battery operated. Thus energy management in these wearable, wireless devices is a big challenge for longer durations. In this paper a systematic review of various techniques suggested in literature for energy efficiency and management in such wireless devices is presented. Various research efforts made to optimize the power of wearable, wireless devices at system level, algorithm level and circuit level have been presented. It is followed by energy harvesting technology and wireless power transfer technology useful for energy management in wearable devices.
{"title":"Recent trends in energy management of wireless wearable bio sensor design","authors":"Dhanashri H. Gawali, V. Wadhai","doi":"10.1109/ISCO.2017.7856027","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7856027","url":null,"abstract":"Mobile healthcare systems have great potential for continuous monitoring. These devices are often battery operated. Thus energy management in these wearable, wireless devices is a big challenge for longer durations. In this paper a systematic review of various techniques suggested in literature for energy efficiency and management in such wireless devices is presented. Various research efforts made to optimize the power of wearable, wireless devices at system level, algorithm level and circuit level have been presented. It is followed by energy harvesting technology and wireless power transfer technology useful for energy management in wearable devices.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132376076","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7856020
Saurabh Barthwal, Piyush Menghani
Today's traffic system is struggling for emergency vehicles like Ambulance, ICU on wheel, fire brigade's van etc. Presently we have “Move over Law” [1] which is also known as “Right Lane Life Lane”. This system works only for continuous flow of traffic but fails when any life savior vehicle stuck in a long traffic queue due to traffic light. This paper proposes new approach on managing all emergency vehicles of a city The basic idea behind this system is to keep the traffic flow continuous at every traffic light for life saving vehicle by using machine to machine (M2M) communication with aggregation and processing of vehicle and traffic light data to ensure continuous flow of traffic.
今天的交通系统正为救护车、监护病房、消防队的货车等紧急车辆而挣扎。目前我们有“Move over Law”[1]，也被称为“Right Lane Life Lane”。该系统只适用于持续的交通流量，但当任何救命车因交通灯而被困在长长的交通队列中时，该系统就会失效。本文提出了一种管理城市所有应急车辆的新方法，其基本思想是通过机器对机器(M2M)通信，通过对车辆和交通灯数据的聚合和处理，使每个交通灯处的交通流量保持连续，以保证交通的连续性。
{"title":"An advance system for emergency vehicles: Based on M2M communication","authors":"Saurabh Barthwal, Piyush Menghani","doi":"10.1109/ISCO.2017.7856020","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7856020","url":null,"abstract":"Today's traffic system is struggling for emergency vehicles like Ambulance, ICU on wheel, fire brigade's van etc. Presently we have “Move over Law” [1] which is also known as “Right Lane Life Lane”. This system works only for continuous flow of traffic but fails when any life savior vehicle stuck in a long traffic queue due to traffic light. This paper proposes new approach on managing all emergency vehicles of a city The basic idea behind this system is to keep the traffic flow continuous at every traffic light for life saving vehicle by using machine to machine (M2M) communication with aggregation and processing of vehicle and traffic light data to ensure continuous flow of traffic.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114182600","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7855981
B. Murugan, V. Balusamy, R. Padmanaban
MONEL has very good corrosion resistance and is used for cladding marine components. However, to avoid hot cracking, nickel is first overlayed on the substrate before MONEL is overlayed. Friction surfacing (FS) is a new solid state technique that could be used to do the same cladding process without any nickel overlay. In this study, MONEL K500 was deposited on AISI 1012 substrate using FS. Three parameters namely the spindle speed, axial load and the horizontal feed rate were varied at five levels and FS trials were conducted. Thickness of the coatings was measured for all the surfacing trials. Response surface methodology is utilized to develop a mathematical model for the thickness of the surfaced layer in terms of the three chosen parameters. The significance of the spindle speed, axial load and the horizontal feed rate in producing coatings with good bond integrity is investigated.
{"title":"Process parameter effects in the friction surfacing of MONEL over mild steel","authors":"B. Murugan, V. Balusamy, R. Padmanaban","doi":"10.1109/ISCO.2017.7855981","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7855981","url":null,"abstract":"MONEL has very good corrosion resistance and is used for cladding marine components. However, to avoid hot cracking, nickel is first overlayed on the substrate before MONEL is overlayed. Friction surfacing (FS) is a new solid state technique that could be used to do the same cladding process without any nickel overlay. In this study, MONEL K500 was deposited on AISI 1012 substrate using FS. Three parameters namely the spindle speed, axial load and the horizontal feed rate were varied at five levels and FS trials were conducted. Thickness of the coatings was measured for all the surfacing trials. Response surface methodology is utilized to develop a mathematical model for the thickness of the surfaced layer in terms of the three chosen parameters. The significance of the spindle speed, axial load and the horizontal feed rate in producing coatings with good bond integrity is investigated.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114555468","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 : 1900-01-01DOI: 10.1109/ISCO.2017.7855958
Gauri Deshpande, Santosh V. Chapaneri, Deepak Jayaswal
Saliency is the quality by which any object or a pixel in an image stands out relative to its neighbours. Detecting such regions from an image is a crucial problem of research, since it has wide applications in advertising, automatic image compression, image thumbnailing, etc. In this paper, a salient region detection approach is proposed by using machine learning. In order to train the saliency model, low level features such as color channels and their probabilities, also probabilities using 3D color histograms, subband features along with statistical priors such as frequency prior, color prior, chance of happening (CoH) and center bias prior (CBP) are used. The proposed model is compared with existing state of art algorithms. Human eye fixation points are used to compare the models by estimating area under ROC curves. Other parameters such as precision, recall, F-measure are also used for comparison. This comparison shows that the proposed saliency model gives better performance than the existing salient region detection approaches.
{"title":"Learning visual saliency with statistical priors","authors":"Gauri Deshpande, Santosh V. Chapaneri, Deepak Jayaswal","doi":"10.1109/ISCO.2017.7855958","DOIUrl":"https://doi.org/10.1109/ISCO.2017.7855958","url":null,"abstract":"Saliency is the quality by which any object or a pixel in an image stands out relative to its neighbours. Detecting such regions from an image is a crucial problem of research, since it has wide applications in advertising, automatic image compression, image thumbnailing, etc. In this paper, a salient region detection approach is proposed by using machine learning. In order to train the saliency model, low level features such as color channels and their probabilities, also probabilities using 3D color histograms, subband features along with statistical priors such as frequency prior, color prior, chance of happening (CoH) and center bias prior (CBP) are used. The proposed model is compared with existing state of art algorithms. Human eye fixation points are used to compare the models by estimating area under ROC curves. Other parameters such as precision, recall, F-measure are also used for comparison. This comparison shows that the proposed saliency model gives better performance than the existing salient region detection approaches.","PeriodicalId":321113,"journal":{"name":"2017 11th International Conference on Intelligent Systems and Control (ISCO)","volume":"15 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117226440","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：