Saranya G, Manikandan V, Balaji J, Kandesh M, Karthikeyan A
The power is generated by human motion while walking on the piezoelectric sensor, which is pressed and produces kinetic energy, which is then converted into electrical energy. The generated energy is stored in the battery. The energy in the battery is used to turn on the street lights using the LDR Sensor when the sun’s beam becomes dull, and to pass water to the grass using the motor with the help of the soil moisture Sensor when the soil becomes moisture. And also used for charge the mobile phones using the charging port which is installed in the park and to be used for other purposes in the park. All the data is get tracked and stored in the IOT for continuously monitoring and for future purpose.
{"title":"Footstep Power Generating System","authors":"Saranya G, Manikandan V, Balaji J, Kandesh M, Karthikeyan A","doi":"10.3233/apc210122","DOIUrl":"https://doi.org/10.3233/apc210122","url":null,"abstract":"The power is generated by human motion while walking on the piezoelectric sensor, which is pressed and produces kinetic energy, which is then converted into electrical energy. The generated energy is stored in the battery. The energy in the battery is used to turn on the street lights using the LDR Sensor when the sun’s beam becomes dull, and to pass water to the grass using the motor with the help of the soil moisture Sensor when the soil becomes moisture. And also used for charge the mobile phones using the charging port which is installed in the park and to be used for other purposes in the park. All the data is get tracked and stored in the IOT for continuously monitoring and for future purpose.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124808019","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}
The Internet of Things (IoT) provides an improved flexibility in data collection, network deployment and data transmission to the sink nodes. However, depending on the application, the IoT network tends to consume lot of power from the individual devices. Various conventional solutions are provided to reduce the consumption of energy but most methods focus on increasing the data acquisition speed, data transmission and routing capabilities. However, these methods tend to fall under the trade-off between these three factors. Hence, in order to maintain the trade-off between these constraints, a viable solution is developed in this paper. A deep learning-based routing is built considering the faster acquisition of data, faster data transmission and routing path estimation with increasing path estimation. The paper models a Deep belief Network (DBN) to route the data considering all these constraints. The experimental validation is conducted to check the network lifetime, energy consumption of IoT nodes. The results show that the DBN offers greater source of flexibility with increased data routing capabilities than other methods.
物联网(Internet of Things, IoT)在数据采集、网络部署和数据传输到汇聚节点方面提供了更高的灵活性。然而，根据应用的不同，物联网网络往往会从单个设备中消耗大量电力。为了降低能耗，传统的解决方案多种多样，但大多数方法都侧重于提高数据采集速度、数据传输和路由能力。然而，这些方法往往落在这三个因素之间的权衡之下。因此，为了保持这些约束之间的权衡，本文提出了一个可行的解决方案。考虑到更快的数据采集、更快的数据传输和增加路径估计的路由路径估计，构建了基于深度学习的路由。本文建立了一个深度信念网络(DBN)模型来考虑所有这些约束，实现数据路由。实验验证了物联网节点的网络寿命、能耗。结果表明，DBN提供了比其他方法更大的灵活性，增加了数据路由功能。
{"title":"Network Lifetime Analysis in IOT Environment in Healthcare Sectors Using Deep Learning Routing Approach","authors":"Janaki K","doi":"10.3233/apc210151","DOIUrl":"https://doi.org/10.3233/apc210151","url":null,"abstract":"The Internet of Things (IoT) provides an improved flexibility in data collection, network deployment and data transmission to the sink nodes. However, depending on the application, the IoT network tends to consume lot of power from the individual devices. Various conventional solutions are provided to reduce the consumption of energy but most methods focus on increasing the data acquisition speed, data transmission and routing capabilities. However, these methods tend to fall under the trade-off between these three factors. Hence, in order to maintain the trade-off between these constraints, a viable solution is developed in this paper. A deep learning-based routing is built considering the faster acquisition of data, faster data transmission and routing path estimation with increasing path estimation. The paper models a Deep belief Network (DBN) to route the data considering all these constraints. The experimental validation is conducted to check the network lifetime, energy consumption of IoT nodes. The results show that the DBN offers greater source of flexibility with increased data routing capabilities than other methods.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123673224","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}
Recognizing human action in sports is difficult task as various sequences of activities involved in every scene. Identifying each action individually without overlapping of movements is a tedious process due to continuous change of frames within short duration. So proper tracking of human movements for each action is important. Hence new structure-based human action recognition and tracker technique (HART) is proposed. It uses joint trajectory images and visual feature to design each human action. At first, a structural based method employed to extract human skeleton data points from RGB (Red Green Blue) videos. Next, a Multitude Object Tracker (MOT) is proposed which uses the trajectory of human skeleton joints in an image space for identification of actions. Then, Histogram of Oriented Gradients (HOG) combined with Support Vector Machine (SVM) is applied to extract physical body shape and action information. Finally, the action label and interconnected keypoints in humans is jointly detected as end result. The proposed HART technique effectively performed well with the accuracy of about 82% over the other activity recognition methods.
{"title":"Distinct Actions Classification Using Human Action Tracker Technique in Sports Videos","authors":"Kanimozhi S, Anbarasi S, Mythili M","doi":"10.3233/apc210142","DOIUrl":"https://doi.org/10.3233/apc210142","url":null,"abstract":"Recognizing human action in sports is difficult task as various sequences of activities involved in every scene. Identifying each action individually without overlapping of movements is a tedious process due to continuous change of frames within short duration. So proper tracking of human movements for each action is important. Hence new structure-based human action recognition and tracker technique (HART) is proposed. It uses joint trajectory images and visual feature to design each human action. At first, a structural based method employed to extract human skeleton data points from RGB (Red Green Blue) videos. Next, a Multitude Object Tracker (MOT) is proposed which uses the trajectory of human skeleton joints in an image space for identification of actions. Then, Histogram of Oriented Gradients (HOG) combined with Support Vector Machine (SVM) is applied to extract physical body shape and action information. Finally, the action label and interconnected keypoints in humans is jointly detected as end result. The proposed HART technique effectively performed well with the accuracy of about 82% over the other activity recognition methods.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121894118","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}
The contemporary pandemic scenario of COVID-19 has brought to surface the efficacy of old health care wisdom in inhibition and care of diseases where contemporary medicine deceptively wants a real cure. Undeniably, viral diseases for the fascinating vitality of their causal organisms, top this wish list. Ultimately the world seems to be enthusiastic to pay attention about old health care approaches to control viral pandemics if these are found well-intentioned in handling such situations. One such demand is to energetically or intelligently use the therapeutic devices especially the Shirodhara device, at the convenience, anytime, anywhere in a teleconsultation mode. The Shirodhara device design is to be in a manageable form without trailing the legitimacy and principals of Ayurveda. The main elements used in the device comprises of a sensor for perceiving the temperature, a pump for salvaging the medicine, programming device to control the temperature, and regulate the heater and a wavering pipe for free flow of the medicine. The device is premeditated in such a way to evade the faults and snags produced while doing the procedure Shirodhara. Hence, this device is built which is portable, cost effective; it provides a technologically enhanced Shirodhara instrument curtailing the practice of medicine and man power for the procedure.
{"title":"IoT Based Shirodhara","authors":"Indumathi J, Sendhilkumar A","doi":"10.3233/apc210153","DOIUrl":"https://doi.org/10.3233/apc210153","url":null,"abstract":"The contemporary pandemic scenario of COVID-19 has brought to surface the efficacy of old health care wisdom in inhibition and care of diseases where contemporary medicine deceptively wants a real cure. Undeniably, viral diseases for the fascinating vitality of their causal organisms, top this wish list. Ultimately the world seems to be enthusiastic to pay attention about old health care approaches to control viral pandemics if these are found well-intentioned in handling such situations. One such demand is to energetically or intelligently use the therapeutic devices especially the Shirodhara device, at the convenience, anytime, anywhere in a teleconsultation mode. The Shirodhara device design is to be in a manageable form without trailing the legitimacy and principals of Ayurveda. The main elements used in the device comprises of a sensor for perceiving the temperature, a pump for salvaging the medicine, programming device to control the temperature, and regulate the heater and a wavering pipe for free flow of the medicine. The device is premeditated in such a way to evade the faults and snags produced while doing the procedure Shirodhara. Hence, this device is built which is portable, cost effective; it provides a technologically enhanced Shirodhara instrument curtailing the practice of medicine and man power for the procedure.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128650483","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}
Amature trekkers venturing into the forest often tend to lose their path and find it difficult to return back to their origin or destination. It is important for the rescuers and volunteers to promptly find the trekker in order to increase the probability of survival. Imparting confidence and providing proper guidance to the trekker is also an important part in search and rescue missions. Drones can be used to locate the trekker promptly using RFID technology and global positioning system (GPS) and provide communication systems between the trekker and the rescue team using LoRa.
{"title":"Ensuring the Survivablity of the Trekker Using Drone and RFID Technology","authors":"Rathinapriya V, Rahul D, Rakesh M, Suganthan P","doi":"10.3233/apc210162","DOIUrl":"https://doi.org/10.3233/apc210162","url":null,"abstract":"Amature trekkers venturing into the forest often tend to lose their path and find it difficult to return back to their origin or destination. It is important for the rescuers and volunteers to promptly find the trekker in order to increase the probability of survival. Imparting confidence and providing proper guidance to the trekker is also an important part in search and rescue missions. Drones can be used to locate the trekker promptly using RFID technology and global positioning system (GPS) and provide communication systems between the trekker and the rescue team using LoRa.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"32 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113994073","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}
Android is a widely distributed mobile operating system developed especially for mobile devices with touch screens. It is an open source, Google-distributed Linux-based mobile operating system. Since Android is open source, it enables Android devices to be targeted effectively by malware developers. Third-party markets do not search for malicious applications in their databases, so installing Android Application Packages (APKs) from these uncontrolled market places is often risky. Without user’s notice, these malware infected applications gain access to private user data, send text messages that costs the user, or hide malware apk file inside another application. The total number of new samples of Android malware amounted to 482,579 per month as of March 2020. In this paper deep learning approach that focuses on malware detection in android apps to protect data on user devices. We use different static features that are present in an Android application for the implementation of the proposed system. The system extracts various static features and gives them to the classifier for deep learning and shows the results. This proposed system will assist users in checking applications that are not downloaded from the official market.
{"title":"Deep Learning Based Static Analysis of Malwares in Android Applications","authors":"Nivedha K, Indra Gandhi K, Shibi S, Nithesh V, Ashwin M","doi":"10.3233/apc210133","DOIUrl":"https://doi.org/10.3233/apc210133","url":null,"abstract":"Android is a widely distributed mobile operating system developed especially for mobile devices with touch screens. It is an open source, Google-distributed Linux-based mobile operating system. Since Android is open source, it enables Android devices to be targeted effectively by malware developers. Third-party markets do not search for malicious applications in their databases, so installing Android Application Packages (APKs) from these uncontrolled market places is often risky. Without user’s notice, these malware infected applications gain access to private user data, send text messages that costs the user, or hide malware apk file inside another application. The total number of new samples of Android malware amounted to 482,579 per month as of March 2020. In this paper deep learning approach that focuses on malware detection in android apps to protect data on user devices. We use different static features that are present in an Android application for the implementation of the proposed system. The system extracts various static features and gives them to the classifier for deep learning and shows the results. This proposed system will assist users in checking applications that are not downloaded from the official market.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125629276","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 the medical diagnosis system, detection and labelling of the specific region of interest and classification of diseases in Computer Tomography (CT) images and Magnetic Resonance Imaging (MRI) scans is a challenging task. Another major application is tumor or cancer type of cell detection as well as finding its size and location in the image. This research work focuses on addressing the most challenging research gaps existing in the field of medical diagnosis such as brain tumor identification in medical images, retrieving similar images or region from the database. In these applications, the major task involved in the extraction of sufficient and relevant features, is to identify the region of interest. With the extracted features development of efficient algorithms for the detection of region of interest (ROI) and the learning algorithms also required to classify the new images for the existing features. The highlight of the proposed work is to design an automated detection of the presence of tumor cells in the brain image and classification of normal and abnormal brain images.
{"title":"Applications of Object Detection, Brain Tumor Detection and Classification","authors":"Bhagyalakshmi A, Deepa s, Parthiban N","doi":"10.3233/apc210148","DOIUrl":"https://doi.org/10.3233/apc210148","url":null,"abstract":"In the medical diagnosis system, detection and labelling of the specific region of interest and classification of diseases in Computer Tomography (CT) images and Magnetic Resonance Imaging (MRI) scans is a challenging task. Another major application is tumor or cancer type of cell detection as well as finding its size and location in the image. This research work focuses on addressing the most challenging research gaps existing in the field of medical diagnosis such as brain tumor identification in medical images, retrieving similar images or region from the database. In these applications, the major task involved in the extraction of sufficient and relevant features, is to identify the region of interest. With the extracted features development of efficient algorithms for the detection of region of interest (ROI) and the learning algorithms also required to classify the new images for the existing features. The highlight of the proposed work is to design an automated detection of the presence of tumor cells in the brain image and classification of normal and abnormal brain images.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124196393","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}
Jayakumar S, Lokesh Kumar K, Purva Darshini S K, Sanjeev D
In Metropolitan cities, where the amount of automobile continuously expands faster than the obtainable traffic framework to support them, congestion may be a strenuous issue to affect and it becomes much worse in case of car accidents. This problem affects many aspects of contemporary society, health damages, traffic accidents, duration spent, grow in greenhouse emissions and including economic expansion. In this context, current societies can rely on the traffic management system to diminish traffic congestion and its negative chattels. In this project, we propose a traffic management system where the traffic will be monitored with all the automobiles on the road. We will track the number of automobiles entering the signal zone and will predict the traffic is high or low. Hang on the quantity of automobiles in each signal zone, the traffic signals can be automated. So that maximum amount of duration is given to more automobiles whereas the lesser duration for some automobiles. Thus this project aims at reducing the traffic and managing the signals automatically leading to the sensor less traffic management system.
{"title":"Traffic Monitoring System Using IoT and DL","authors":"Jayakumar S, Lokesh Kumar K, Purva Darshini S K, Sanjeev D","doi":"10.3233/apc210141","DOIUrl":"https://doi.org/10.3233/apc210141","url":null,"abstract":"In Metropolitan cities, where the amount of automobile continuously expands faster than the obtainable traffic framework to support them, congestion may be a strenuous issue to affect and it becomes much worse in case of car accidents. This problem affects many aspects of contemporary society, health damages, traffic accidents, duration spent, grow in greenhouse emissions and including economic expansion. In this context, current societies can rely on the traffic management system to diminish traffic congestion and its negative chattels. In this project, we propose a traffic management system where the traffic will be monitored with all the automobiles on the road. We will track the number of automobiles entering the signal zone and will predict the traffic is high or low. Hang on the quantity of automobiles in each signal zone, the traffic signals can be automated. So that maximum amount of duration is given to more automobiles whereas the lesser duration for some automobiles. Thus this project aims at reducing the traffic and managing the signals automatically leading to the sensor less traffic management system.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125449665","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}
Nowaday’s providing the security for image is essential for correspondence. Steganography and cryptography are a technical method for the transfer of information to eliminate burglary and stealing of information. Cryptography steganography hides the occurrence of a mystery message. We need more Secured and confidential images to transfer. Steganography procedure on RGB genuine nature utilizing LSB 3-3-2 technique. On the RED & GREEN line, on the LSB Three-Three-two is a procedure, while on the blue channel, it is just 2 LSB. Messages are not exactly RED and GREEN on BLUE platforms. Double encryption techniques are used, such as Caesar cipher & Vigenere cipher, to preserve the nature of the stegno photos and to increase message safety. Use of steganographic strategies are insufficient to give security to informing it is imperative to join the strategy of cryptography. A combination of Caesar Encryption and Vigenere applies to message until they are inserted in LSB Three-Three-Two methods to provide extra protection. At this point we are providing the Caesar code and Vigenere image estimating to enhance security. The target of this is to upgrade the secrecy & security of the image steganography. It will be more efficient because using the two fold layer of security.
{"title":"A Novel Dual Encryption Algorithm to Enhance the Security in Image Transmission Using LSB 3-2-2 Technique","authors":"Anitha R, Ashok kumar P M, Ravi Kumar T","doi":"10.3233/apc210147","DOIUrl":"https://doi.org/10.3233/apc210147","url":null,"abstract":"Nowaday’s providing the security for image is essential for correspondence. Steganography and cryptography are a technical method for the transfer of information to eliminate burglary and stealing of information. Cryptography steganography hides the occurrence of a mystery message. We need more Secured and confidential images to transfer. Steganography procedure on RGB genuine nature utilizing LSB 3-3-2 technique. On the RED & GREEN line, on the LSB Three-Three-two is a procedure, while on the blue channel, it is just 2 LSB. Messages are not exactly RED and GREEN on BLUE platforms. Double encryption techniques are used, such as Caesar cipher & Vigenere cipher, to preserve the nature of the stegno photos and to increase message safety. Use of steganographic strategies are insufficient to give security to informing it is imperative to join the strategy of cryptography. A combination of Caesar Encryption and Vigenere applies to message until they are inserted in LSB Three-Three-Two methods to provide extra protection. At this point we are providing the Caesar code and Vigenere image estimating to enhance security. The target of this is to upgrade the secrecy & security of the image steganography. It will be more efficient because using the two fold layer of security.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126081575","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}
Biometric recognition is one of the effective authentication techniques which is utilized in various applications for making the individual identification process. During the verification and authentication process different biometric features such as signature, ear, iris, face, palm, finger knuckle details are used to perform this process. Due to the easy acceptance of the palm surface, fine textures and stable features characteristics are helps to choose the finger knuckle feature for biometric process in this work. First the finger biometric features are collected from PolyU finger knuckle database. After that, the noise present in the images are eliminated using weighted median filter and the knuckle region is located with the help of the variational approach. After that key point descriptors are extracted using sparse autoencoder approach. Finally, the specific features are trained using compositional networks and features matching is performed by Chebyshev distance. The matching process authenticate the user whether they are authorized person or not. At last efficiency of the system is evaluated using MATLAB based experimental results such as false acceptance rate, equal error rate and false rejection rate.
{"title":"Automatic Biometric System for Finger Knuckle Using Sparse Encoder Approaches","authors":"Suganthi Devi S","doi":"10.3233/apc210155","DOIUrl":"https://doi.org/10.3233/apc210155","url":null,"abstract":"Biometric recognition is one of the effective authentication techniques which is utilized in various applications for making the individual identification process. During the verification and authentication process different biometric features such as signature, ear, iris, face, palm, finger knuckle details are used to perform this process. Due to the easy acceptance of the palm surface, fine textures and stable features characteristics are helps to choose the finger knuckle feature for biometric process in this work. First the finger biometric features are collected from PolyU finger knuckle database. After that, the noise present in the images are eliminated using weighted median filter and the knuckle region is located with the help of the variational approach. After that key point descriptors are extracted using sparse autoencoder approach. Finally, the specific features are trained using compositional networks and features matching is performed by Chebyshev distance. The matching process authenticate the user whether they are authorized person or not. At last efficiency of the system is evaluated using MATLAB based experimental results such as false acceptance rate, equal error rate and false rejection rate.","PeriodicalId":413281,"journal":{"name":"Advances in Parallel Computing Technologies and Applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114250216","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：