Pub Date : 2022-12-24DOI: 10.12694/scpe.v23i4.2038
Jahangeer Ali, S. Sofi
The Internet of Things (IoT) is the backbone behind numerous smart and automated applications in the modern era by providing seamless connectivity and information retrieval among the physical and virtual objects. IoT networks are resource constraint platforms hence prone to security and privacy challenges. Blockchain technology comes to the forefront to improvise the security, privacy and less dependency on the third party centralized servers. There exists a rich amount of work with numerous practical applications by fusing IoT and blockchain. In blockchain technology, the consensus mechanisms are considered to be the driving force in its implementation. In this paper, we propose a simplified blockchain based internet of things (BIoT) architecture for resource constrained IoT devices with selective consensus mechanisms based on the scale of IoT networks. We have selectively highlighted some of the important consensus algorithms which are favourable for the IoT networks. We have tailored the blockchain framework in a manner that suits to the resource constrained IoT networks. To evaluate our design, we implemented a prototype leveraging the blockchain and IoT network. The preliminary results suggest that the proposed system incorporating supply chain management of Saffron agri-value chain outperforms the existing systems. Furthermore, we have carried out a detailed case study on the cultivation and marketing strategies for maintaining the originality and transparency starting from farmer-to-consumer as saffron-Agri value chain.
{"title":"Blockchain Enabled Architecture with Selective Consensus Mechanisms for IoT Based Saffron-Agri Value Chain","authors":"Jahangeer Ali, S. Sofi","doi":"10.12694/scpe.v23i4.2038","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2038","url":null,"abstract":"The Internet of Things (IoT) is the backbone behind numerous smart and automated applications in the modern era by providing seamless connectivity and information retrieval among the physical and virtual objects. IoT networks are resource constraint platforms hence prone to security and privacy challenges. Blockchain technology comes to the forefront to improvise the security, privacy and less dependency on the third party centralized servers. There exists a rich amount of work with numerous practical applications by fusing IoT and blockchain. In blockchain technology, the consensus mechanisms are considered to be the driving force in its implementation. In this paper, we propose a simplified blockchain based internet of things (BIoT) architecture for resource constrained IoT devices with selective consensus mechanisms based on the scale of IoT networks. We have selectively highlighted some of the important consensus algorithms which are favourable for the IoT networks. We have tailored the blockchain framework in a manner that suits to the resource constrained IoT networks. To evaluate our design, we implemented a prototype leveraging the blockchain and IoT network. The preliminary results suggest that the proposed system incorporating supply chain management of Saffron agri-value chain outperforms the existing systems. Furthermore, we have carried out a detailed case study on the cultivation and marketing strategies for maintaining the originality and transparency starting from farmer-to-consumer as saffron-Agri value chain. \u0000 ","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80722731","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2040
Z. Tanveer Baig, C. Shastry
Wireless sensor networks (WSN) have been exploited for {countless} application domains, most notably the surveillance of environments and habitats, which has already become a critical mission. As a result, WSNs have been implemented to monitor animal care and track their health status. However, excessive energy utilization and communication traffic on packet transmissions lead to system deterioration, especially whenever perceived information captured in the monitoring area is transferred to the access point over multiple dynamic sinks. Further to manage the energy and data transmission issue, the energy consumption and location aware routing protocol has been architected on the wireless Nano sensor nodes. In this article, a novel hybrid energy and location aware routing protocol to cloud enabled IoT based Wireless Sensor Network towards animal health monitoring and tracking has been proposed. However proposed data routing protocol incorporates the trace file for path selection for data transmission to base station using sink node. Trace file has been obtained on processing the cluster heads established in the network. Therefore, clustering of node in the network has to be achieved using LEACH protocol which enhances the network scalability and network lifetime by clustering the nodes with Metaheuristics constraints like location or node density comparability. The objective of the proposed model is to enhance the network scalability and energy consumption by establishing the multiple node clusters with high density cluster head through Metaheuristics Node Clustering optimization techniques. Metaheuristics based node clustering is been obtained using Improved Particle Swarm Optimization. Further it is employed to compute the optimal path for sensed data transmission to base station. Node clustering provides high energy consumption among the sensing nodes and to establish the high energy clusters towards sensed information dissemination to base station on dynamically reforming the nodes clusters with respect to Node density and node location. Simulation analysis of the proposed energy efficient routing protocol provides high performance in energy utilization, packet delivery ratio, packet loss and Average delay compared against the conventional protocols on propagation of the data through sink node to base station
{"title":"Smart Hybridized Routing Protocol for Animal Monitoring and Tracking Applications","authors":"Z. Tanveer Baig, C. Shastry","doi":"10.12694/scpe.v23i4.2040","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2040","url":null,"abstract":"Wireless sensor networks (WSN) have been exploited for {countless} application domains, most notably the surveillance of environments and habitats, which has already become a critical mission. As a result, WSNs have been implemented to monitor animal care and track their health status. However, excessive energy utilization and communication traffic on packet transmissions lead to system deterioration, especially whenever perceived information captured in the monitoring area is transferred to the access point over multiple dynamic sinks. Further to manage the energy and data transmission issue, the energy consumption and location aware routing protocol has been architected on the wireless Nano sensor nodes. In this article, a novel hybrid energy and location aware routing protocol to cloud enabled IoT based Wireless Sensor Network towards animal health monitoring and tracking has been proposed. However proposed data routing protocol incorporates the trace file for path selection for data transmission to base station using sink node. Trace file has been obtained on processing the cluster heads established in the network. Therefore, clustering of node in the network has to be achieved using LEACH protocol which enhances the network scalability and network lifetime by clustering the nodes with Metaheuristics constraints like location or node density comparability. The objective of the proposed model is to enhance the network scalability and energy consumption by establishing the multiple node clusters with high density cluster head through Metaheuristics Node Clustering optimization techniques. Metaheuristics based node clustering is been obtained using Improved Particle Swarm Optimization. Further it is employed to compute the optimal path for sensed data transmission to base station. Node clustering provides high energy consumption among the sensing nodes and to establish the high energy clusters towards sensed information dissemination to base station on dynamically reforming the nodes clusters with respect to Node density and node location. Simulation analysis of the proposed energy efficient routing protocol provides high performance in energy utilization, packet delivery ratio, packet loss and Average delay compared against the conventional protocols on propagation of the data through sink node to base station","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80367910","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2034
M. Marimuthu, J. Akilandeswari, B. Varasree, Gunupudi RAJESH KUMAR, S. Ramasubbareddy
In recent years, many cloud services have become available on the Website}. Discovering suitable cloud services for the end user is incredibly complex and difficult. The cloud brokerage service is an application that aids in providing solutions for this problem. It recommends suitable cloud service providers to the end users depending on their relevant requirements. The Internet provides access to a wide variety of cloud brokers. As a result, choosing a cloud broker or service provider is both time-consuming and tedious. It is now becoming a necessity to choose a proper cloud brokerage service based on trust. Research works found in the literature address some of the issues and provide feasible solutions by proposing frameworks, optimizations and rule based algorithms. However, those works focus solely on delivering a trustworthy service to the end user through application of techniques and algorithms. There is no proper framework model in place to provide suitable and trustworthy recommended services to the users. This article provides a detailed description of the frameworks that are offered by the researchers, including issues and proposes a trustworthy recommendation framework (TRF) to provide trustworthy services to the end user. This article also presents a Trustworthy Recommended Weighted value (TRWv) approach for determining trustworthy services, and it is discovered that the proposed method achieves high accuracy (91.3%) when compared to similar works.
{"title":"Cloud Broker Recommendation Framework to Provide Trustworthy Cloud Services to the End User","authors":"M. Marimuthu, J. Akilandeswari, B. Varasree, Gunupudi RAJESH KUMAR, S. Ramasubbareddy","doi":"10.12694/scpe.v23i4.2034","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2034","url":null,"abstract":"In recent years, many cloud services have become available on the Website}. Discovering suitable cloud services for the end user is incredibly complex and difficult. The cloud brokerage service is an application that aids in providing solutions for this problem. It recommends suitable cloud service providers to the end users depending on their relevant requirements. The Internet provides access to a wide variety of cloud brokers. As a result, choosing a cloud broker or service provider is both time-consuming and tedious. It is now becoming a necessity to choose a proper cloud brokerage service based on trust. Research works found in the literature address some of the issues and provide feasible solutions by proposing frameworks, optimizations and rule based algorithms. However, those works focus solely on delivering a trustworthy service to the end user through application of techniques and algorithms. There is no proper framework model in place to provide suitable and trustworthy recommended services to the users. This article provides a detailed description of the frameworks that are offered by the researchers, including issues and proposes a trustworthy recommendation framework (TRF) to provide trustworthy services to the end user. This article also presents a Trustworthy Recommended Weighted value (TRWv) approach for determining trustworthy services, and it is discovered that the proposed method achieves high accuracy (91.3%) when compared to similar works.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75243956","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2029
P. Hemalatha, G. Shankar, D. M. Deepak Raj
There are numerous image classification strategies are developed in deep learning. However, due to the complexity of images, conventional image classification strategies have been incapable to meet real application needs. As the amount of pixel information rises, the classification becomes more difficult. However, CNN is widely used method for object identification in picture due to its simple and accurate, but still, it remains hazy which strategies are most supportive for analysing and distinguishing the objects in pictures. In this paper we introduced a CNN network and clustering-based technique called IBCNN to perform classification based on patch extraction. The proposed method can accomplish their goals in the following four different ways: a) Automatic Kernel selection; b) resilient patch size selection; c) CNN layer; and d) pooling layer modification. In addition, it also modifies the pooling layer with average value and calculate the pixel size. The proposed method was applied on ten different image datasets. Finally, the proposed model is compared to three benchmarking models: such as WCNN, MLP, and ELM-CNN to estimate its performance. The obtained results shows that the proposed method gives competitive results compared to the other models.
{"title":"A New Improved Binary Convolutional Model for Classification of Images","authors":"P. Hemalatha, G. Shankar, D. M. Deepak Raj","doi":"10.12694/scpe.v23i4.2029","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2029","url":null,"abstract":"There are numerous image classification strategies are developed in deep learning. However, due to the complexity of images, conventional image classification strategies have been incapable to meet real application needs. As the amount of pixel information rises, the classification becomes more difficult. However, CNN is widely used method for object identification in picture due to its simple and accurate, but still, it remains hazy which strategies are most supportive for analysing and distinguishing the objects in pictures. In this paper we introduced a CNN network and clustering-based technique called IBCNN to perform classification based on patch extraction. The proposed method can accomplish their goals in the following four different ways: a) Automatic Kernel selection; b) resilient patch size selection; c) CNN layer; and d) pooling layer modification. In addition, it also modifies the pooling layer with average value and calculate the pixel size. The proposed method was applied on ten different image datasets. Finally, the proposed model is compared to three benchmarking models: such as WCNN, MLP, and ELM-CNN to estimate its performance. The obtained results shows that the proposed method gives competitive results compared to the other models.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90442583","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2037
Soundararajan Anuradha, P. Kanmani
Cloud Computing (CC) environment is developing as a recently discovered caliber for computing applications over the network. Fault tolerance is one of the foremost issues in CC environment. Since the negligence in resource have a profound effect on job execution, throughput, response time and performance of the entire network. In this work, in order to address the issue, Quadruple Osmotic Hybrid Classification and Whale Optimization (QOHC-WO) is introduced to fault-tolerance under the requirement of different user request tasks. Initially, Quadruple Fault Tolerance Level is applied to allocate the fault tolerance level. Followed by, Hybrid Vector Classifier is used to categorize the user request tasks (task) and cloud server nodes (node). Then, the Osmotic function is employed for performing the migration among virtual machines with lesser response time. This helps to solve the maximum level of fault issue. Finally, Improved Whale Optimization Algorithm is applied to find the optimal allocation of tasks with the corresponding node. In addition, the Bandit function and Whale optimization are used to address the trade-off between exploitation and exploration. Experimental setup of the proposed QOHC-WO method and existing methods are carried out with different factors such as task response time, the number of VM migrations, and percentage of fault detected rate with respect to a number of tasks. The analyzed results validate that the proposed QOHC-WO method achieves a higher fault detection rate with minimum response time as well as task migration than the state-of-the-art methods.
{"title":"Fault Tolerant Load Balancing with Quadruple Osmotic Hybrid Classifier and Whale Optimization for Cloud Computing","authors":"Soundararajan Anuradha, P. Kanmani","doi":"10.12694/scpe.v23i4.2037","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2037","url":null,"abstract":"Cloud Computing (CC) environment is developing as a recently discovered caliber for computing applications over the network. Fault tolerance is one of the foremost issues in CC environment. Since the negligence in resource have a profound effect on job execution, throughput, response time and performance of the entire network. In this work, in order to address the issue, Quadruple Osmotic Hybrid Classification and Whale Optimization (QOHC-WO) is introduced to fault-tolerance under the requirement of different user request tasks. Initially, Quadruple Fault Tolerance Level is applied to allocate the fault tolerance level. Followed by, Hybrid Vector Classifier is used to categorize the user request tasks (task) and cloud server nodes (node). Then, the Osmotic function is employed for performing the migration among virtual machines with lesser response time. This helps to solve the maximum level of fault issue. Finally, Improved Whale Optimization Algorithm is applied to find the optimal allocation of tasks with the corresponding node. In addition, the Bandit function and Whale optimization are used to address the trade-off between exploitation and exploration. Experimental setup of the proposed QOHC-WO method and existing methods are carried out with different factors such as task response time, the number of VM migrations, and percentage of fault detected rate with respect to a number of tasks. The analyzed results validate that the proposed QOHC-WO method achieves a higher fault detection rate with minimum response time as well as task migration than the state-of-the-art methods.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86219513","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2046
D. David, P. Anitha, K. Ramalakshmi, M. Selvarathi, T. J. Jebaseeli, P. Suresh, P. Dhivya
Uncertainty is stated as the indication of the quality of the calibration certificate. When uncertainties occurred in a stubbed ground plane, it affects the performance of every source. Hence, a thorough analysis of uncertainties on a monopole antenna is required. The proposed research work is to focus on designing a planar monopole antenna to improve the bandwidth with minimal changes on the ground plane mainly for medical applications and to reduce the uncertainty. The narrowband antenna on the ground plane is redesigned to boost up the gain and broadens the monopole antenna’s bandwidth impedance. Then the ground plane is integrated with the rectangular plate. As a result the bandwidth is 42.5 GHz ahead.
{"title":"Design an Uncertain Model for the Stubbed Ground Plane by Increasing the Bandwidth of the Monopole Antenna","authors":"D. David, P. Anitha, K. Ramalakshmi, M. Selvarathi, T. J. Jebaseeli, P. Suresh, P. Dhivya","doi":"10.12694/scpe.v23i4.2046","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2046","url":null,"abstract":"Uncertainty is stated as the indication of the quality of the calibration certificate. When uncertainties occurred in a stubbed ground plane, it affects the performance of every source. Hence, a thorough analysis of uncertainties on a monopole antenna is required. The proposed research work is to focus on designing a planar monopole antenna to improve the bandwidth with minimal changes on the ground plane mainly for medical applications and to reduce the uncertainty. The narrowband antenna on the ground plane is redesigned to boost up the gain and broadens the monopole antenna’s bandwidth impedance. Then the ground plane is integrated with the rectangular plate. As a result the bandwidth is 42.5 GHz ahead.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86830428","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2026
N. Swaroop Kumar, K. Ramesh, A. Maheswary, R. Revathi
Since its introduction, the Global Positioning System (GPS) is finding many countless, useful, and emergency applications, focused mainly on track. As the technology is advancing day by day and the best feature of GPS, which does not, relies on mobile signal to work, making it a feasible feature to incorporate into other devices as functionalities. By adopting GPS to a system, accurate mapping and geographical labeling can be obtained. GPS works better with the coordination of nodes and requires centralized monitoring and a reporting system. As it is a known fact that a demerit follows merit anywhere else, In GPS also, the major attention is required to make the nodes to success in mapping the intermediate space between agent node used for reporting and the remaining nodes of a cluster, where satellite and node coordination can be possible integer ambiguity technique. Many researchers have proposed solutions to the aforementioned problem; unfortunately still today the proposed methods are weaker in achieving lesser time delay of Total Electron Content (TEC). The proposed Centric Self-Learning Interconnected Nodes Reading (CSINR) technique is novel in terms addressing the intermediate nodes failing to label the inter-connected object spaces between reporting agents and nodes using integer ambiguity technique for node co-ordination and using a dedicated GPS prediction-based clock system, which predicts precise and accurate mapping between interconnected nodes. Based on the information shared between among the network managers a separate pseudo-connected network will be formed and further this network will be considered an interconnected nodes network. From the information calculated from temporal factors and clock offset the separate pseudo network is extracted by using the proposed CSINR technique. Add-on self-improvement is introduced to the proposed method by a self--learning feature to an individual join extract the principal rate of partisan neighbouring join to sustain accuracy in order consistent basis. An evaluation ratio of 97.43%, sensitivity of node occurrence is resulted as 92.78% and accuracy of 97.43% and 97.12% is achieved among a cluster of 32and 64 nodes respectively.
{"title":"A Novel CSINR Technique for Accurate and Precise GPS Communication by Geographical Centric Self-learning Nodes","authors":"N. Swaroop Kumar, K. Ramesh, A. Maheswary, R. Revathi","doi":"10.12694/scpe.v23i4.2026","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2026","url":null,"abstract":"Since its introduction, the Global Positioning System (GPS) is finding many countless, useful, and emergency applications, focused mainly on track. As the technology is advancing day by day and the best feature of GPS, which does not, relies on mobile signal to work, making it a feasible feature to incorporate into other devices as functionalities. By adopting GPS to a system, accurate mapping and geographical labeling can be obtained. GPS works better with the coordination of nodes and requires centralized monitoring and a reporting system. As it is a known fact that a demerit follows merit anywhere else, In GPS also, the major attention is required to make the nodes to success in mapping the intermediate space between agent node used for reporting and the remaining nodes of a cluster, where satellite and node coordination can be possible integer ambiguity technique. Many researchers have proposed solutions to the aforementioned problem; unfortunately still today the proposed methods are weaker in achieving lesser time delay of Total Electron Content (TEC). The proposed Centric Self-Learning Interconnected Nodes Reading (CSINR) technique is novel in terms addressing the intermediate nodes failing to label the inter-connected object spaces between reporting agents and nodes using integer ambiguity technique for node co-ordination and using a dedicated GPS prediction-based clock system, which predicts precise and accurate mapping between interconnected nodes. Based on the information shared between among the network managers a separate pseudo-connected network will be formed and further this network will be considered an interconnected nodes network. From the information calculated from temporal factors and clock offset the separate pseudo network is extracted by using the proposed CSINR technique. Add-on self-improvement is introduced to the proposed method by a self--learning feature to an individual join extract the principal rate of partisan neighbouring join to sustain accuracy in order consistent basis. An evaluation ratio of 97.43%, sensitivity of node occurrence is resulted as 92.78% and accuracy of 97.43% and 97.12% is achieved among a cluster of 32and 64 nodes respectively.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77620163","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2030
SRINIVAS KOLLI, A. V. Praveen Krishna, M. Sreedevi
Artificial intelligence has been provided powerful research attributes like data mining and clustering for reducing bigdata functioning. Clustering in multi-labeled categorical analysis gives huge amount of relevant data that explains evaluation and portrayal of qualities as trending notion. A wide range of scenarios, data from many dimensions may be used to provide efficient clustering results. Multi-view clustering techniques had been outdated, however they all provide less accurate results when a single clustering of input data is applied. Numerous data groups are conceivable due to diversity of multi-dimensional data, each with its own unique set of viewpoints. When dealing multi-view labelled data, obtaining quantifiable and realistic cluster results may be challenge. This study provides unique strategy termed OCMHAMCV (Orthogonal Constrained Meta Heuristic Adaptive Multi-View Cluster). In beginning, OMF approach used to cluster similar labelled sample data into prototypes of dimensional clusters of low-dimensional data. Utilize adaptive heuristics integrate complementary data several dimensions complexity of computational analysis data representation data in appropriate orthonormality constrained viewpoint. Studies on massive data sets reveal that proposed method outperforms more traditional multi-view clustering techniques scalability and efficiency. The performance measures like accuracy 98.32%, sensitivity 93.42%, F1-score 98.53% and index score 96.02% has been attained, which was good improvement. Therefore it is proved that proposed methodology suitable for document summarization application for future scientific analysis.
{"title":"A Meta Heuristic Multi-View Data Analysis over Unconditional Labeled Material: An Intelligence OCMHAMCV","authors":"SRINIVAS KOLLI, A. V. Praveen Krishna, M. Sreedevi","doi":"10.12694/scpe.v23i4.2030","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2030","url":null,"abstract":"Artificial intelligence has been provided powerful research attributes like data mining and clustering for reducing bigdata functioning. Clustering in multi-labeled categorical analysis gives huge amount of relevant data that explains evaluation and portrayal of qualities as trending notion. A wide range of scenarios, data from many dimensions may be used to provide efficient clustering results. Multi-view clustering techniques had been outdated, however they all provide less accurate results when a single clustering of input data is applied. Numerous data groups are conceivable due to diversity of multi-dimensional data, each with its own unique set of viewpoints. When dealing multi-view labelled data, obtaining quantifiable and realistic cluster results may be challenge. This study provides unique strategy termed OCMHAMCV (Orthogonal Constrained Meta Heuristic Adaptive Multi-View Cluster). In beginning, OMF approach used to cluster similar labelled sample data into prototypes of dimensional clusters of low-dimensional data. Utilize adaptive heuristics integrate complementary data several dimensions complexity of computational analysis data representation data in appropriate orthonormality constrained viewpoint. Studies on massive data sets reveal that proposed method outperforms more traditional multi-view clustering techniques scalability and efficiency. The performance measures like accuracy 98.32%, sensitivity 93.42%, F1-score 98.53% and index score 96.02% has been attained, which was good improvement. Therefore it is proved that proposed methodology suitable for document summarization application for future scientific analysis.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78201974","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2047
I. Hamidu, B. Afotey, Zakaria AYATUL-LAHI
The objective of the study is to develop low-cost IoT based sensor to monitor real-time greenhouse gases (GHG) emissions data from selected industry locations (city blocks) in a top-down approach. Three (3) industry locations were selected within the Suame Industrial complex (the largest single cluster of artisanal engineering and light manufacturing in Sub Saharan Africa and even Africa) which has no reported GHG emissions data. A GHG monitor was developed using Atmega328 microcontroller and a sim800I GSM module was used to collect a 24-hour real-time minute-by-minute emissions data from the selected industry locations. A MQ-4 (methane/natural gas sensor), MQ-135 (Nitrous Oxide sensors) and DHT22 (temperature and humidity sensor) were used in the GHG monitor design. The GHG of concern were carbon dioxide, methane and nitrous oxide. A total of 3627 emissions data were collected and analyzed from the three (3) industry locations. Location 3 had the highest average carbon dioxide emissions of 508.11 ppm, followed by location 2 with 477.31 ppm with the least emissions in location 1 with 472.51 ppm which are above the global carbon dioxide average of 414.7 ppm. The average methane emission was highest in location 1 with 0.1599 ppm (1599 ppb), followed by location 3 with 0.1366 ppm (1366 ppb) with the least average methane emission of 0.1358 ppm (1358 ppb) in location 2 which are slightly below the global methane average of 1895.7 ppb. The MQ-135 nitrous oxide sensor reported zero emissions data throughout the deployment at the various industry locations which indicated the nitrous oxides emission in the selected sample site is negligible or below the detectable range of the sensor.
{"title":"Design and Development of a Low-cost Sensor IoT Computing Device for Greenhouse Gas Momitor from Selected Industry Locations","authors":"I. Hamidu, B. Afotey, Zakaria AYATUL-LAHI","doi":"10.12694/scpe.v23i4.2047","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2047","url":null,"abstract":"The objective of the study is to develop low-cost IoT based sensor to monitor real-time greenhouse gases (GHG) emissions data from selected industry locations (city blocks) in a top-down approach. Three (3) industry locations were selected within the Suame Industrial complex (the largest single cluster of artisanal engineering and light manufacturing in Sub Saharan Africa and even Africa) which has no reported GHG emissions data. A GHG monitor was developed using Atmega328 microcontroller and a sim800I GSM module was used to collect a 24-hour real-time minute-by-minute emissions data from the selected industry locations. A MQ-4 (methane/natural gas sensor), MQ-135 (Nitrous Oxide sensors) and DHT22 (temperature and humidity sensor) were used in the GHG monitor design. The GHG of concern were carbon dioxide, methane and nitrous oxide. A total of 3627 emissions data were collected and analyzed from the three (3) industry locations. Location 3 had the highest average carbon dioxide emissions of 508.11 ppm, followed by location 2 with 477.31 ppm with the least emissions in location 1 with 472.51 ppm which are above the global carbon dioxide average of 414.7 ppm. The average methane emission was highest in location 1 with 0.1599 ppm (1599 ppb), followed by location 3 with 0.1366 ppm (1366 ppb) with the least average methane emission of 0.1358 ppm (1358 ppb) in location 2 which are slightly below the global methane average of 1895.7 ppb. The MQ-135 nitrous oxide sensor reported zero emissions data throughout the deployment at the various industry locations which indicated the nitrous oxides emission in the selected sample site is negligible or below the detectable range of the sensor.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89312999","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 : 2022-12-23DOI: 10.12694/scpe.v23i4.2048
K. Venkatesh, S. Pasupathy, S. Raja
Acute Myeloid Leukemia (AML) is a form of the condition that is fatal and has a high mortality rate. It is characterised by abnormal cells growing rapidly inside the human body. The conventional method for detecting AML seems to be examining the blood sample manually under a microscope, which is a manual and cumbersome task that also requires well-trained medical expertise for efficient identification. On the other hand, considering medical diagnosis, the capacity to classify medical images faster and accurate is essential. The classification of medical images my currently be accomplished using a range of methodologies including Machine Learning (ML), Deep Learning (DL) and Transfer Learning (RL). While these approaches are effective for large datasets, they can take a while and~not ideal for small datasets. In recent years, advances in Deep Convolutional Neural Networks (DCNN) have made it possible and produce more accurate and promising outcome while processing a~medical image. However, the paradigm that DCNN~use for training includes a large number of annotations in order to prevent overfitting and produce promising results. Obtaining large-scale semantic annotations in clinical operations might be problematic in some cases, particularly biological expertise knowledge is needed. It is also regular occurrence in scenarios where only a small number of annotated classes are accessible in some circumstances. At this context, in order overcome the drawback of traditional approach a framework has been developed which comprises of Enhanced Few-Shot Learning Technique integrated Base Classifier (Feature Encoder)-EFLTBC. The proposed model has built using base classifier and meta-learning block, and it optimized the better results. To diagnose AML, the doctor must count the number of white blood cells and red blood cells and see if there are any abnormal health conditions in that using a microscope. However, obtaining an accurate result takes time and effort. To address these issues, the proposed Novel AML detection model employing is used in this study. Base classifier utilizing ResNet-18 pretrained model and meta learning block has computed using the average feature of every samples. Also, the dataset that we used consisting of three classes includes Normal monocytes, Abnormal monocytes, Lymphocyte and Experimental results outperform various existing deep learning technique with the accuracy of 97%, recall of 96.55% F1-Score of 96.65% and precision of 96.60.
{"title":"Acute Myeloid Leukemia Multi-classification using Enhanced Few-shot Learning Technique","authors":"K. Venkatesh, S. Pasupathy, S. Raja","doi":"10.12694/scpe.v23i4.2048","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2048","url":null,"abstract":"Acute Myeloid Leukemia (AML) is a form of the condition that is fatal and has a high mortality rate. It is characterised by abnormal cells growing rapidly inside the human body. The conventional method for detecting AML seems to be examining the blood sample manually under a microscope, which is a manual and cumbersome task that also requires well-trained medical expertise for efficient identification. On the other hand, considering medical diagnosis, the capacity to classify medical images faster and accurate is essential. The classification of medical images my currently be accomplished using a range of methodologies including Machine Learning (ML), Deep Learning (DL) and Transfer Learning (RL). While these approaches are effective for large datasets, they can take a while and~not ideal for small datasets. In recent years, advances in Deep Convolutional Neural Networks (DCNN) have made it possible and produce more accurate and promising outcome while processing a~medical image. However, the paradigm that DCNN~use for training includes a large number of annotations in order to prevent overfitting and produce promising results. Obtaining large-scale semantic annotations in clinical operations might be problematic in some cases, particularly biological expertise knowledge is needed. It is also regular occurrence in scenarios where only a small number of annotated classes are accessible in some circumstances. At this context, in order overcome the drawback of traditional approach a framework has been developed which comprises of Enhanced Few-Shot Learning Technique integrated Base Classifier (Feature Encoder)-EFLTBC. The proposed model has built using base classifier and meta-learning block, and it optimized the better results. To diagnose AML, the doctor must count the number of white blood cells and red blood cells and see if there are any abnormal health conditions in that using a microscope. However, obtaining an accurate result takes time and effort. To address these issues, the proposed Novel AML detection model employing is used in this study. Base classifier utilizing ResNet-18 pretrained model and meta learning block has computed using the average feature of every samples. Also, the dataset that we used consisting of three classes includes Normal monocytes, Abnormal monocytes, Lymphocyte and Experimental results outperform various existing deep learning technique with the accuracy of 97%, recall of 96.55% F1-Score of 96.65% and precision of 96.60.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84905007","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：