Pub Date : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016703
K. Amrutha, Y. Bharath, J. Jayanthi
In Aircraft engines, condition monitoring based strategies are used to lessen upkeep costs, ensure aircraft wellbeing and to reduce the fuel utilization. Currently the performance deterioration of aircraft engines is determined using parameters such as fuel flow, engine fan speed, vibration, oil weight, oil temperature and Exhaust Gas Temperature (EGT) etc. In this paper, a model has been proposed to obtain the performance deterioration of Turboprop engine. In this paper, Multiple Regression Analysis (MRA) with Artificial Neural Network (ANN) and Data clustering with fuzzy logic approach is performed for the prediction of Fuel Flow (FF) parameter and compared for accuracy of their prediction with minimum performance error. Using this model, any performance deterioration that may happen in the aircraft turboprop engine can be effectively recognized and this could also be a marker for the pilots in case of the occurrence of fault in the fuel flow parameter sensor.
{"title":"Aircraft Engine Fuel Flow Parameter Prediction and Health Monitoring System","authors":"K. Amrutha, Y. Bharath, J. Jayanthi","doi":"10.1109/RTEICT46194.2019.9016703","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016703","url":null,"abstract":"In Aircraft engines, condition monitoring based strategies are used to lessen upkeep costs, ensure aircraft wellbeing and to reduce the fuel utilization. Currently the performance deterioration of aircraft engines is determined using parameters such as fuel flow, engine fan speed, vibration, oil weight, oil temperature and Exhaust Gas Temperature (EGT) etc. In this paper, a model has been proposed to obtain the performance deterioration of Turboprop engine. In this paper, Multiple Regression Analysis (MRA) with Artificial Neural Network (ANN) and Data clustering with fuzzy logic approach is performed for the prediction of Fuel Flow (FF) parameter and compared for accuracy of their prediction with minimum performance error. Using this model, any performance deterioration that may happen in the aircraft turboprop engine can be effectively recognized and this could also be a marker for the pilots in case of the occurrence of fault in the fuel flow parameter sensor.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130472045","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016834
V. Manu, A. M. Vijaya Prakash, Mohan U Chandra
Low power and area efficient 16-bit multiplier has been designed and implemented using the Dadda algorithm. Here, the prime building block having low power dissipation and area efficient optimized full adder architecture and Carry Look-Ahead (CLA) adder is designed and implemented. Designing full adder is done by making use of complex cells in the technology node of 65nm to reduce the power dissipation and minimum area using TSMC 65nm library. The proposed multiplier design is optimized, simulated using ISE simulator and synthesized using Cadence Genus EDA tool and results are demonstrated. The power and area of the Dadda multiplier designed using proposed full adder is minimum compared to conventional design. The power and area are improved by an amount of 15.32% and 1.91% respectively, than the conventional-full adder. Dadda Multiplier designed here is used to implement 16-bit ALU the power and area obtained are 20.65% and 1.8% lesser than the existing design.
采用Dadda算法设计并实现了低功耗、高效率的16位乘法器。在此,设计并实现了具有低功耗和面积效率的优化全加法器架构和进位预判(CLA)加法器的主要模块。采用台积电65nm库,利用65nm技术节点上的复杂单元进行全加法器设计,以降低功耗和最小面积。对所提出的乘法器设计进行了优化,使用ISE模拟器进行了仿真,并使用Cadence Genus EDA工具进行了合成,并对结果进行了验证。与传统设计相比,采用全加法器设计的倍增器的功率和面积最小。与传统全加法器相比,功率和面积分别提高了15.32%和1.91%。本文设计的dada乘法器用于实现16位ALU,功率和面积比现有设计分别降低20.65%和1.8%。
{"title":"Design and Implementation of Sixteen-bit Low Power and Area Efficient Dadda Multiplier","authors":"V. Manu, A. M. Vijaya Prakash, Mohan U Chandra","doi":"10.1109/RTEICT46194.2019.9016834","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016834","url":null,"abstract":"Low power and area efficient 16-bit multiplier has been designed and implemented using the Dadda algorithm. Here, the prime building block having low power dissipation and area efficient optimized full adder architecture and Carry Look-Ahead (CLA) adder is designed and implemented. Designing full adder is done by making use of complex cells in the technology node of 65nm to reduce the power dissipation and minimum area using TSMC 65nm library. The proposed multiplier design is optimized, simulated using ISE simulator and synthesized using Cadence Genus EDA tool and results are demonstrated. The power and area of the Dadda multiplier designed using proposed full adder is minimum compared to conventional design. The power and area are improved by an amount of 15.32% and 1.91% respectively, than the conventional-full adder. Dadda Multiplier designed here is used to implement 16-bit ALU the power and area obtained are 20.65% and 1.8% lesser than the existing design.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125588595","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016930
Sharada Naik, S. Sondkar
Image processing has wide range of applications in Instrumentation and Measurement, robotics and automation. Random line segment detection and its distance measurement using image processing finds application in land area measurement. The proposed work focuses on random line detection and its distance measurement using image processing techniques. The proposed work has four parts viz; edge detection, line identification, smoothening of the identified line image and distance measurement of the identified lines. The results shows that all random line are identified using image processing techniques and further distance measurement has errors less than 4.5%. The proposed work forms the basis of application like land area measurement using image processing techniques.
{"title":"Random Line Segment Distance Measurement Using Image Processing","authors":"Sharada Naik, S. Sondkar","doi":"10.1109/RTEICT46194.2019.9016930","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016930","url":null,"abstract":"Image processing has wide range of applications in Instrumentation and Measurement, robotics and automation. Random line segment detection and its distance measurement using image processing finds application in land area measurement. The proposed work focuses on random line detection and its distance measurement using image processing techniques. The proposed work has four parts viz; edge detection, line identification, smoothening of the identified line image and distance measurement of the identified lines. The results shows that all random line are identified using image processing techniques and further distance measurement has errors less than 4.5%. The proposed work forms the basis of application like land area measurement using image processing techniques.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126676579","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016959
R. Daryani, Maneesha Gupta
MOS Current Mode Logic (MCML) circuits are the basic elements in the designing of the logic gates and flip flops which are further used in designing of various digital circuits like memory, clock circuits, and registers. On the chips that involve mixed signal circuits, MCML logic circuits are highly preferred. In this paper, MCML circuits with low power consumption have been proposed by modifying the pull down network of the circuit. In the circuits, the Floating Gate Mosfet (FGMOS) and Dynamic Threshold Mosfet (DTMOS) transistors are used in place of the conventional MOS circuits. The FGMOS and DTMOS have modifiable threshold levels. Utilizing this property of the FGMOS and DTMOS, they have been employed in the CML circuits to lower the minimum voltage requirements and also the reduction of power consumption by FGMOS, using 180 nm Complementary Mosfet (CMOS) process parameters. The SPICE simulations are performed and the analysis is done for all the three circuits and the comparisons are drawn. We observe a lower supply voltage requirement in the proposed circuits and the power consumption is decreased by 30% in the FGMOS circuit, making it more suitable for low power circuits.
{"title":"A New Technique of Designing Low Power, Low Voltage MOS CML Circuits by using Modifications in the PDN","authors":"R. Daryani, Maneesha Gupta","doi":"10.1109/RTEICT46194.2019.9016959","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016959","url":null,"abstract":"MOS Current Mode Logic (MCML) circuits are the basic elements in the designing of the logic gates and flip flops which are further used in designing of various digital circuits like memory, clock circuits, and registers. On the chips that involve mixed signal circuits, MCML logic circuits are highly preferred. In this paper, MCML circuits with low power consumption have been proposed by modifying the pull down network of the circuit. In the circuits, the Floating Gate Mosfet (FGMOS) and Dynamic Threshold Mosfet (DTMOS) transistors are used in place of the conventional MOS circuits. The FGMOS and DTMOS have modifiable threshold levels. Utilizing this property of the FGMOS and DTMOS, they have been employed in the CML circuits to lower the minimum voltage requirements and also the reduction of power consumption by FGMOS, using 180 nm Complementary Mosfet (CMOS) process parameters. The SPICE simulations are performed and the analysis is done for all the three circuits and the comparisons are drawn. We observe a lower supply voltage requirement in the proposed circuits and the power consumption is decreased by 30% in the FGMOS circuit, making it more suitable for low power circuits.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126366715","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016958
J. J. Jijesh, Shivashankar, H. Pooja, Shwetha Nagesh, T. Gagandeep, Immanuel S Shimron
The development of robotics technology has taken over manual work, robotics cleaners have taken major attention in robotics research due to their effectiveness of assisting human in cleaning process. The robot technology and many of the related robot appliances are being used smarter and more automated. Here represents the technology that proposed the working of robot for cleaning. Vacuum cleaner is integrated with rocker bogie model. Rocker Bogie is six wheeled model that helps to move in uneven surface. The robot basically works in both automatic and manual mode as per the need. Microcontroller places a major role in the development of the entire system with hardware and soft ware involved in it. The major functionality of the robot is to perform the picking and storing operation. It is programmed to accept inputs to sense obstacles around it and control the robot to avoid any collision. The objects are detected by the system and with the help of vacuum the cleaning is carried out. In the automatic mode robot control all the operations itself and change the lane in case of hurdle detection and moves back. In the manual mode, the keypad is used to perform the expected task and to operate the robot. The RF module has been used to transmit and receive the information between remote and robot. The whole circuitry is connected with solar powered battery. This in turn benefits the society to keep the environment clean and eradicate the diseases.
{"title":"Swachh Robo Ones Cleanliness Identity","authors":"J. J. Jijesh, Shivashankar, H. Pooja, Shwetha Nagesh, T. Gagandeep, Immanuel S Shimron","doi":"10.1109/RTEICT46194.2019.9016958","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016958","url":null,"abstract":"The development of robotics technology has taken over manual work, robotics cleaners have taken major attention in robotics research due to their effectiveness of assisting human in cleaning process. The robot technology and many of the related robot appliances are being used smarter and more automated. Here represents the technology that proposed the working of robot for cleaning. Vacuum cleaner is integrated with rocker bogie model. Rocker Bogie is six wheeled model that helps to move in uneven surface. The robot basically works in both automatic and manual mode as per the need. Microcontroller places a major role in the development of the entire system with hardware and soft ware involved in it. The major functionality of the robot is to perform the picking and storing operation. It is programmed to accept inputs to sense obstacles around it and control the robot to avoid any collision. The objects are detected by the system and with the help of vacuum the cleaning is carried out. In the automatic mode robot control all the operations itself and change the lane in case of hurdle detection and moves back. In the manual mode, the keypad is used to perform the expected task and to operate the robot. The RF module has been used to transmit and receive the information between remote and robot. The whole circuitry is connected with solar powered battery. This in turn benefits the society to keep the environment clean and eradicate the diseases.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122188569","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016863
Satyasrikanth Palle, H. Vibha, B. M. Sriraksha, A. Yeshashwini
This paper presents Smart Movable Road Divider for controlling the traffic congestion in metropolitan cities and to provide a free path for the ambulance. The work presented in this paper focuses on reducing the latency in traffic and free path for ambulance. The existing Road Dividers consists of equal number of lanes. Usually, in morning and evening peak hours the opposite side of the Road Divider is generally underutilized. To overcome this, Smart Movable Road Divider is implemented where the divider is moved based on the density of the traffic using IR Sensors. If the density of the traffic is high on one side, the divider is moved to the other side. Then the density of traffic is stored in cloud which is possible through IoT. A free path for Ambulance is provided using RF Module by controlling the traffic signal. A Prototype is developed and tested for the Congestion control which also works on safety measures by intimating the drivers about the movement of the Divider.
{"title":"Implementation of Smart Movable Road Divider and Ambulance Clearance using IoT","authors":"Satyasrikanth Palle, H. Vibha, B. M. Sriraksha, A. Yeshashwini","doi":"10.1109/RTEICT46194.2019.9016863","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016863","url":null,"abstract":"This paper presents Smart Movable Road Divider for controlling the traffic congestion in metropolitan cities and to provide a free path for the ambulance. The work presented in this paper focuses on reducing the latency in traffic and free path for ambulance. The existing Road Dividers consists of equal number of lanes. Usually, in morning and evening peak hours the opposite side of the Road Divider is generally underutilized. To overcome this, Smart Movable Road Divider is implemented where the divider is moved based on the density of the traffic using IR Sensors. If the density of the traffic is high on one side, the divider is moved to the other side. Then the density of traffic is stored in cloud which is possible through IoT. A free path for Ambulance is provided using RF Module by controlling the traffic signal. A Prototype is developed and tested for the Congestion control which also works on safety measures by intimating the drivers about the movement of the Divider.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"24 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114130159","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016912
S. S. Kumar, D. Hemanth, S. Dwneeth, K. Dilip, A. Divyatej
Present life style of the people makes them to get things done in easier and smart way. People tend more towards the comfortable and luxurious life style. As the result, they are more comfortable of purchasing goods online rather than personally visiting and buying goods. This increases the marketing of online goods purchased. The client puts in a request of required product in any electronic-retailer (e-retailer) site. On the confirmation of the request is affirmed the e-retailer will send the product detail and shipping data of the package to the client, the client thus can check this details, and the client will probably securely get his bundle regardless of whether he is present anyplace on the planet. Smart Freight Box (SFB) is designed using IoT interface, which is to be fit in house window which is accessible for client as well as customer. The Box is designed with two doors each present on opposite side which is accessible using IoT platform, to provide security for the product till collected by the right person. Camera is installed inside the SFB to provide safety measures for being cheated in certain conditions. The main focus here is to place the product in the box, to be collected by the right person without any damage, or being stolen.
{"title":"Automated Package Delivery Accepting System - Smart Freight Box","authors":"S. S. Kumar, D. Hemanth, S. Dwneeth, K. Dilip, A. Divyatej","doi":"10.1109/RTEICT46194.2019.9016912","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016912","url":null,"abstract":"Present life style of the people makes them to get things done in easier and smart way. People tend more towards the comfortable and luxurious life style. As the result, they are more comfortable of purchasing goods online rather than personally visiting and buying goods. This increases the marketing of online goods purchased. The client puts in a request of required product in any electronic-retailer (e-retailer) site. On the confirmation of the request is affirmed the e-retailer will send the product detail and shipping data of the package to the client, the client thus can check this details, and the client will probably securely get his bundle regardless of whether he is present anyplace on the planet. Smart Freight Box (SFB) is designed using IoT interface, which is to be fit in house window which is accessible for client as well as customer. The Box is designed with two doors each present on opposite side which is accessible using IoT platform, to provide security for the product till collected by the right person. Camera is installed inside the SFB to provide safety measures for being cheated in certain conditions. The main focus here is to place the product in the box, to be collected by the right person without any damage, or being stolen.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"241 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116155724","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016698
R. Nishitha, S. Naik, V. Raksha, U. Kulsum
In all over the world India is the second largest populated country. People here like to shop their daily needs in malls because of the quality of service they provide to the consumers. The main problem that we face here is having to wait for long queues even to bill one or two products or at times there might be problems with several other billing counters which would temporarily be out of service and all must go through the billing process only at one remaining counter. In this paper, we will discuss about the solution for various problems arising in the malls such as time consuming while billing, miscounting, thefts and other such discrepancy. We are implementing an automatic billing system which helps us to solve all the problems as mentioned above with the help of RFID scanners and detector for scanning of products and prevention in theft and IoT for data management purpose. It not only makes the billing system easier, it also helps us to transmit billing information to customer's mobile and automatic detection of amount from their interlinked bank account.
{"title":"IoT Based Automatic Billing System Using Barcode Scanner by Android Device and Monitoring Unregistered Barcode by RFID","authors":"R. Nishitha, S. Naik, V. Raksha, U. Kulsum","doi":"10.1109/RTEICT46194.2019.9016698","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016698","url":null,"abstract":"In all over the world India is the second largest populated country. People here like to shop their daily needs in malls because of the quality of service they provide to the consumers. The main problem that we face here is having to wait for long queues even to bill one or two products or at times there might be problems with several other billing counters which would temporarily be out of service and all must go through the billing process only at one remaining counter. In this paper, we will discuss about the solution for various problems arising in the malls such as time consuming while billing, miscounting, thefts and other such discrepancy. We are implementing an automatic billing system which helps us to solve all the problems as mentioned above with the help of RFID scanners and detector for scanning of products and prevention in theft and IoT for data management purpose. It not only makes the billing system easier, it also helps us to transmit billing information to customer's mobile and automatic detection of amount from their interlinked bank account.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"3 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113955139","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 : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016871
R. Vaishnavi
This paper primarily focuses on the study and implementation of two target detection algorithms and also on the formulation of a tracking model to track the detected targets. These detection algorithms- one under the category of Detect before track (DBT) approach and other being Track before detect (TBD) are implemented for point target detection in Infrared Search and Track (IRST) systems for airborne targets. Performance of these algorithms is tested on real Infrared image sequences by plotting receiver operating characteristics (ROC) curves under different scenarios. Results are compared by discussing advantages and shortcomings of both approaches in terms of computational complexity and target detection capability. To track the detected targets with linear trajectories, a tracking algorithm based on Kalman filtering is used. This model is applied for targets under different scenarios and simulation results are presented in this paper.
{"title":"Implementation of algorithms for Point target detection and tracking in Infrared image sequences","authors":"R. Vaishnavi","doi":"10.1109/RTEICT46194.2019.9016871","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016871","url":null,"abstract":"This paper primarily focuses on the study and implementation of two target detection algorithms and also on the formulation of a tracking model to track the detected targets. These detection algorithms- one under the category of Detect before track (DBT) approach and other being Track before detect (TBD) are implemented for point target detection in Infrared Search and Track (IRST) systems for airborne targets. Performance of these algorithms is tested on real Infrared image sequences by plotting receiver operating characteristics (ROC) curves under different scenarios. Results are compared by discussing advantages and shortcomings of both approaches in terms of computational complexity and target detection capability. To track the detected targets with linear trajectories, a tracking algorithm based on Kalman filtering is used. This model is applied for targets under different scenarios and simulation results are presented in this paper.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"286 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131903353","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}
In women, the 2nd most common cancer is breast cancer annually about 16 lakh women are identified. Detection and treatment in the early stage improve survival rates. Dataset of Wisconsin Breast cancer will provide the features of the digitized image. In this paper, a model is developed and different optimization algorithms were implemented to access the correctness of classifying data with respect to accuracy which is feasible for computer-aided diagnosis. Machine learning can assist and alert expert radiologist more effectively than current screening techniques. In this paper RMS propagation (Root Mean Square Propagation) and SGD (stochastic gradient descent) optimization algorithms were implemented on a deep neural network with sigmoid neurons and accuracy is compared.
{"title":"Implementation of optimization algorithms on Wisconsin Breast cancer dataset using deep neural network","authors":"Nagadevi Darapureddy, Nagaprakash Karatapu, Tirumala Krishna Battula","doi":"10.1109/RTEICT46194.2019.9016822","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016822","url":null,"abstract":"In women, the 2nd most common cancer is breast cancer annually about 16 lakh women are identified. Detection and treatment in the early stage improve survival rates. Dataset of Wisconsin Breast cancer will provide the features of the digitized image. In this paper, a model is developed and different optimization algorithms were implemented to access the correctness of classifying data with respect to accuracy which is feasible for computer-aided diagnosis. Machine learning can assist and alert expert radiologist more effectively than current screening techniques. In this paper RMS propagation (Root Mean Square Propagation) and SGD (stochastic gradient descent) optimization algorithms were implemented on a deep neural network with sigmoid neurons and accuracy is compared.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134471072","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}