Pub Date : 2022-03-16DOI: 10.13052/jmm1550-4646.1844
Q. Minh, P. N. Huu, Takeshi Tsuchiya
Urban traffic estimation is one of the critical tasks for intelligent transportation systems (ITS). To estimate traffic condition, accurately and timely traffic data must be sensed frequently at every location around the city utilizing multimedia data fusion and analytics. This paper proposes a novel approach to urban traffic data collection and analysis leveraging crowd-sourced data from drivers and mobile users. Concretely, we have proposed solutions for mobile crowd-sourced data fusion to which just the right traffic data is collected automatically by GPS modules equipped in mobile devices. In addition, mechanisms for data validation and analytics for traffic estimation have been devised. Consequently, a mobile application is developed and provided to public users so that they can conveniently collect and share traffic data to the system. Besides, users can access traffic information and ITS services such as routing recommendation freely. The proposed system has been deployed for a real-world application in Ho Chi Minh City (HCMC), the largest city in Vietnam. Experimental results from real-field data confirm the feasibility, effectiveness and efficiency of the proposed approaches.
{"title":"Mobile Crowd-sourced Data Fusion and Urban Traffic Estimation","authors":"Q. Minh, P. N. Huu, Takeshi Tsuchiya","doi":"10.13052/jmm1550-4646.1844","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1844","url":null,"abstract":"Urban traffic estimation is one of the critical tasks for intelligent transportation systems (ITS). To estimate traffic condition, accurately and timely traffic data must be sensed frequently at every location around the city utilizing multimedia data fusion and analytics. This paper proposes a novel approach to urban traffic data collection and analysis leveraging crowd-sourced data from drivers and mobile users. Concretely, we have proposed solutions for mobile crowd-sourced data fusion to which just the right traffic data is collected automatically by GPS modules equipped in mobile devices. In addition, mechanisms for data validation and analytics for traffic estimation have been devised. Consequently, a mobile application is developed and provided to public users so that they can conveniently collect and share traffic data to the system. Besides, users can access traffic information and ITS services such as routing recommendation freely. The proposed system has been deployed for a real-world application in Ho Chi Minh City (HCMC), the largest city in Vietnam. Experimental results from real-field data confirm the feasibility, effectiveness and efficiency of the proposed approaches.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121949313","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1849
A. C. Kaladevi, R. Saravanakumar, K. Veena, V. Muthukumaran, N. Thillaiarasu, S. S. Kumar
Speech-based Interaction systems contribute to the growing class of contemporary interactive techniques (Human-Computer Interactive system), which have emerged quickly in the last few years. Versatility, multi-channel synchronization, sensitivity, and timing are all notable characteristics of speech recognition. In addition, several variables influence the precision of voice interaction recognition. However, few researchers have done a significant study on the five eco-condition variables that tend to affect speech recognition rate (SRR): ambient noise, human noise, utterance speed, and frequency. The principal strategic goal of this research is to analyze the influence of the four variables mentioned earlier on SRR, and it includes many stages of experimentation on mixed noise speech data. The sparse representation-based analyzing technique is utilized to analyze the effects. Speech recognition is not noticeably affected by a person’s usual speaking pace. As a result, high-frequency voice signals are more easily recognized (∼∼98.12%) than low-frequency speech signals in noisy environments. By performing the experiments, the test results may help design the distributive controlling and commanding systems.
{"title":"Data Analytics on Eco-Conditional Factors Affecting Speech Recognition Rate of Modern Interaction Systems","authors":"A. C. Kaladevi, R. Saravanakumar, K. Veena, V. Muthukumaran, N. Thillaiarasu, S. S. Kumar","doi":"10.13052/jmm1550-4646.1849","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1849","url":null,"abstract":"Speech-based Interaction systems contribute to the growing class of contemporary interactive techniques (Human-Computer Interactive system), which have emerged quickly in the last few years. Versatility, multi-channel synchronization, sensitivity, and timing are all notable characteristics of speech recognition. In addition, several variables influence the precision of voice interaction recognition. However, few researchers have done a significant study on the five eco-condition variables that tend to affect speech recognition rate (SRR): ambient noise, human noise, utterance speed, and frequency. The principal strategic goal of this research is to analyze the influence of the four variables mentioned earlier on SRR, and it includes many stages of experimentation on mixed noise speech data. The sparse representation-based analyzing technique is utilized to analyze the effects. Speech recognition is not noticeably affected by a person’s usual speaking pace. As a result, high-frequency voice signals are more easily recognized (∼∼98.12%) than low-frequency speech signals in noisy environments. By performing the experiments, the test results may help design the distributive controlling and commanding systems.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128512456","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1845
Apisak Ketkhaw, S. Thipchaksurat
One of the serious security problems in wireless local networks (WLAN) is the existence of the rogue access points (RAPs). To prevent our network from the RAP attacks, we need to identify the RAPs by using the RAP detection methods. However, the identification of RAP location is also a challenging task. The objective of this paper is to propose the location prediction scheme for the RAP. We call our proposed scheme as the location prediction of rogue access point (LPRAP). The LPRAP scheme consists of two mechanisms, the RAP detection mechanism and the RAP location prediction mechanism. We apply the concept of the fingerprint in the RAP detection mechanism by considering the SSID, time duration of broadcasting beacon frame and MAC address. We show that this mechanism can detect the number of RAP. For the RAP location prediction mechanism, we utilize the deep neuron network (DNN) to predict the location of RAPs and evaluate its effectiveness. We evaluate the performance of LPRAP by comparing with those of other machine learning methods such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes, and Multi-layer Perceptron (MLP). We also compare with particle swarm optimization algorithm. The results show that LPRAP can accurately predict the location of RAP up to 99.29%.
{"title":"Location Prediction of Rogue Access Point Based on Deep Neural Network Approach","authors":"Apisak Ketkhaw, S. Thipchaksurat","doi":"10.13052/jmm1550-4646.1845","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1845","url":null,"abstract":"One of the serious security problems in wireless local networks (WLAN) is the existence of the rogue access points (RAPs). To prevent our network from the RAP attacks, we need to identify the RAPs by using the RAP detection methods. However, the identification of RAP location is also a challenging task. The objective of this paper is to propose the location prediction scheme for the RAP. We call our proposed scheme as the location prediction of rogue access point (LPRAP). The LPRAP scheme consists of two mechanisms, the RAP detection mechanism and the RAP location prediction mechanism. We apply the concept of the fingerprint in the RAP detection mechanism by considering the SSID, time duration of broadcasting beacon frame and MAC address. We show that this mechanism can detect the number of RAP. For the RAP location prediction mechanism, we utilize the deep neuron network (DNN) to predict the location of RAPs and evaluate its effectiveness. We evaluate the performance of LPRAP by comparing with those of other machine learning methods such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes, and Multi-layer Perceptron (MLP). We also compare with particle swarm optimization algorithm. The results show that LPRAP can accurately predict the location of RAP up to 99.29%.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127247126","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1846
S. Prongnuch, S. Sitjongsataporn
This paper introduces the voice controlled comparator improvement for maneuvering a miniature electric vehicle based on the resource utilization in the system-on-chip (SoC) ecosystem. An intelligent parking assist is to support the driver outside a car while parking in the crowded locations. Voice controlled improvement based on the resource utilization on the SoC ecosystem is modified to command for moving vehicle. The normalized cross correlation (NCC) technique is proposed for voice controlled system with low utilization on the SoC ecosystem. Hardware and software co-design by the Xilinx VIVADO and Vitis software are used to design on an ARM multicore processor and field programmable gate array (FPGA) system inside a ‘Zedboard’ development board. We perform the experiments for Thai command word recognition via Bluetooth using the proposed NCC method to identify the basic command stored on SD card in Zedboard. Empirical results show the voice controlled improvement based on the Pearson’s correlation coefficient (PCC), modified PCC and proposed NCC methods on a Zedboard. The resource utilization on Zedboard are less than as 17.57% in look-up table (LUT), 29.12% in look-up table random access memory (LUTRAM), 6.44% in flip-flop (FF) and 2.38% in input/output (I/O) as compared with a ZYBO system. An average execution time of Zedboard using proposed NCC method is less than PCC and modified PCC as 5.12%, 1%, respectively. Results of proposed NCC of Thai voice command controlled show the validate workability at average percentage accuracy at 90% in the outdoor environments.
{"title":"Voice Controlled Comparator Improvement Based on Resource Utilization in SoC Ecosystem for Parking Assist System","authors":"S. Prongnuch, S. Sitjongsataporn","doi":"10.13052/jmm1550-4646.1846","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1846","url":null,"abstract":"This paper introduces the voice controlled comparator improvement for maneuvering a miniature electric vehicle based on the resource utilization in the system-on-chip (SoC) ecosystem. An intelligent parking assist is to support the driver outside a car while parking in the crowded locations. Voice controlled improvement based on the resource utilization on the SoC ecosystem is modified to command for moving vehicle. The normalized cross correlation (NCC) technique is proposed for voice controlled system with low utilization on the SoC ecosystem. Hardware and software co-design by the Xilinx VIVADO and Vitis software are used to design on an ARM multicore processor and field programmable gate array (FPGA) system inside a ‘Zedboard’ development board. We perform the experiments for Thai command word recognition via Bluetooth using the proposed NCC method to identify the basic command stored on SD card in Zedboard. Empirical results show the voice controlled improvement based on the Pearson’s correlation coefficient (PCC), modified PCC and proposed NCC methods on a Zedboard. The resource utilization on Zedboard are less than as 17.57% in look-up table (LUT), 29.12% in look-up table random access memory (LUTRAM), 6.44% in flip-flop (FF) and 2.38% in input/output (I/O) as compared with a ZYBO system. An average execution time of Zedboard using proposed NCC method is less than PCC and modified PCC as 5.12%, 1%, respectively. Results of proposed NCC of Thai voice command controlled show the validate workability at average percentage accuracy at 90% in the outdoor environments.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115170483","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1843
S.K. Bethi, Nageswara Rao Moparthi
Wireless Sensor Network (WSN) is highly used in many applications for monitoring purposes. Many researchers were carried out in energy efficiency and security to improve network performance. In this research, the Adaptive Secure Energy Efficiency Routing Protocol (ASEERP) is proposed to improve security and reduce the energy consumption of the WSN. Gaussian distribution is used in this model to improve the synchronization of the model for the routing. Initialization of the node is carried out based on the residual energy of the node and neighbor node of WSN. The model routing phase transmits the data based on direct transmission and relay transmission based on path availability and distance. The direct transmission is carried out in a possible scenario to save energy in the neighbor nodes. The co-operation phase in the model helps to select the best relay based on the residual energy if the transmission is carried out based on the relay node. The source information and relay information are combined to analyze the neighbourhood information to adaptively select the optimal path in the model. The incoming packets and outgoing packets of the sensor nodes are measured to detect the attack and attack indicator estimation is used to detect the malicious node to deny access to it. The proposed ASEERP model has an energy consumption of 57 J, the existing LEACH-C model has 80 J and the SMEER model has 72 J for 600 ms time.
{"title":"Adaptive Secure Energy Efficiency Routing Protocol for Wireless Sensor Network","authors":"S.K. Bethi, Nageswara Rao Moparthi","doi":"10.13052/jmm1550-4646.1843","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1843","url":null,"abstract":"Wireless Sensor Network (WSN) is highly used in many applications for monitoring purposes. Many researchers were carried out in energy efficiency and security to improve network performance. In this research, the Adaptive Secure Energy Efficiency Routing Protocol (ASEERP) is proposed to improve security and reduce the energy consumption of the WSN. Gaussian distribution is used in this model to improve the synchronization of the model for the routing. Initialization of the node is carried out based on the residual energy of the node and neighbor node of WSN. The model routing phase transmits the data based on direct transmission and relay transmission based on path availability and distance. The direct transmission is carried out in a possible scenario to save energy in the neighbor nodes. The co-operation phase in the model helps to select the best relay based on the residual energy if the transmission is carried out based on the relay node. The source information and relay information are combined to analyze the neighbourhood information to adaptively select the optimal path in the model. The incoming packets and outgoing packets of the sensor nodes are measured to detect the attack and attack indicator estimation is used to detect the malicious node to deny access to it. The proposed ASEERP model has an energy consumption of 57 J, the existing LEACH-C model has 80 J and the SMEER model has 72 J for 600 ms time.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131178419","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1842
Q. Minh, Vysotskii GIa, Sang Nguyen Tan, P. N. Huu, Takeshi Tsuchiya
Intelligent hydroponic farming that leverages IoT advantages is a pattern of modern farming technology as it not only increases crop productions but also reduces negative impacts from traditional methods. This paper proposed a fog computing enabled hydroponic farming framework that devises low-cost data collection and novel data analysis mechanisms to deliver intelligent farming systems. In this framework, the data from multiple IoT sensors at the garden are collected, filtered and analyzed by artificial neural network (ANN) models deployed at the fog landscapes, while the ANN models are trained in the cloud with a large amount of historical farming data. This approach allows the intelligent models being updated, reducing the communication cost and response time, while utilizing computing resources available on the network edge. The evaluation results on the developed prototype depict the effectiveness and the performance of the proposed approach revealing that it is feasible and ready to be applied in real-world applications.
{"title":"Fog Computing Enabled Hydroponic Farming Systems","authors":"Q. Minh, Vysotskii GIa, Sang Nguyen Tan, P. N. Huu, Takeshi Tsuchiya","doi":"10.13052/jmm1550-4646.1842","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1842","url":null,"abstract":"Intelligent hydroponic farming that leverages IoT advantages is a pattern of modern farming technology as it not only increases crop productions but also reduces negative impacts from traditional methods. This paper proposed a fog computing enabled hydroponic farming framework that devises low-cost data collection and novel data analysis mechanisms to deliver intelligent farming systems. In this framework, the data from multiple IoT sensors at the garden are collected, filtered and analyzed by artificial neural network (ANN) models deployed at the fog landscapes, while the ANN models are trained in the cloud with a large amount of historical farming data. This approach allows the intelligent models being updated, reducing the communication cost and response time, while utilizing computing resources available on the network edge. The evaluation results on the developed prototype depict the effectiveness and the performance of the proposed approach revealing that it is feasible and ready to be applied in real-world applications.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129121134","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1847
P. Kanakaraja, Sarat K. Kotamraju, K. Kavya
In this work, a study of location systems in indoor environments is carried out, starting with the measurement techniques used, the different types of methodologies that can be applied to obtain the position of a device, and the technologies most used to solve these kinds of problems. Lately, it has been an expansion in utilizing location-based services, which builds the investigation of this framework. Also, while the outdoor location is substantially more progressed, the indoor location is continually under audit and, by its inclination, requires a lot tighter precision. The indoor environment can lead the communication from global navigation system and GPS system. The ultrawide band and WLAN techniques are many communication protocols those applications need proper techniques to guide indoor environment. The main objective of this article is based on making a review of the state of the art of location systems in indoor environments, analysing the strengths and weaknesses of existing systems and analysing the possibility of proposing, from a theoretical point of view, the use of information fusion techniques to improve existing systems. Specifically, the possibility of using a system architecture in which several technologies are merged to achieve a more precise result will be analysed. To compare various existing Indoor Navigational methods advantages, disadvantages, and applications. All proposed Indoor Methods based on the requirement the user utilizes required localization techniques. This article mainly focuses on sensor fusion techniques. Moreover, this research introduces an architecture with different layers based on sensor fusion techniques to smooth indoor navigations. The novel methodology providing efficient outcomes like sensitivity 98.34%, accuracy 97.89%, Recall 96.78% and F measure 96.73%.
{"title":"Fusion of Information in Indoor Localization Techniques","authors":"P. Kanakaraja, Sarat K. Kotamraju, K. Kavya","doi":"10.13052/jmm1550-4646.1847","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1847","url":null,"abstract":"In this work, a study of location systems in indoor environments is carried out, starting with the measurement techniques used, the different types of methodologies that can be applied to obtain the position of a device, and the technologies most used to solve these kinds of problems. Lately, it has been an expansion in utilizing location-based services, which builds the investigation of this framework. Also, while the outdoor location is substantially more progressed, the indoor location is continually under audit and, by its inclination, requires a lot tighter precision. The indoor environment can lead the communication from global navigation system and GPS system. The ultrawide band and WLAN techniques are many communication protocols those applications need proper techniques to guide indoor environment. The main objective of this article is based on making a review of the state of the art of location systems in indoor environments, analysing the strengths and weaknesses of existing systems and analysing the possibility of proposing, from a theoretical point of view, the use of information fusion techniques to improve existing systems. Specifically, the possibility of using a system architecture in which several technologies are merged to achieve a more precise result will be analysed. To compare various existing Indoor Navigational methods advantages, disadvantages, and applications. All proposed Indoor Methods based on the requirement the user utilizes required localization techniques. This article mainly focuses on sensor fusion techniques. Moreover, this research introduces an architecture with different layers based on sensor fusion techniques to smooth indoor navigations. The novel methodology providing efficient outcomes like sensitivity 98.34%, accuracy 97.89%, Recall 96.78% and F measure 96.73%.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115228730","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 : 2022-03-16DOI: 10.13052/jmm1550-4646.1848
D. Rao, K. Ramesh, V. S. Ghali, M. Rao
The purpose of this research has been used to detect osteoporosis disease for Knee radiography. It can improve diagnostic performance over using the scan thermal image mode alone. During 2016 and 2021, researchers gathered CT, MRI, CTA, ultra sound images from individuals who had both skeletal bone density assessment and knee radiology at a local medical clinic for subjective labelling. But following models are most complicate to detect diagnosis of osteoporosis. Therefore, five level convolutional neural networks (CNN) models were used to diagnose osteoporosis from knee radiography. They also looked at ensemble models that included clinical variables in each U-Net. Every net was given an efficiency, accuracy, recall, sensitivity, negative predictive value (npv), F1 measure, and area under curve (AUC) rating. Exclusively knee rays were used to test the U-Net model, but GoogleNet, S-transform, ResNet and FCNN had the lowest accuracy, precision, and specificity. Whenever patient’s data were added, Efficient U-Net had the highest accuracy 99.23%, recall 98.76%, npv 0.93%, F1 score 99.23%, and AUC 99.72% scores among five level prediction methods. The U-Net models correctly identified osteoporosis from Knee radiography, and their performance had improved even more when clinical variables from health records were complex. This u-net based osteoporosis diagnosis is most helpful for future generation for better pre-detections.
{"title":"The Osteoporosis Disease Diagnosis and Classification Using U-net Deep Learning Process","authors":"D. Rao, K. Ramesh, V. S. Ghali, M. Rao","doi":"10.13052/jmm1550-4646.1848","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1848","url":null,"abstract":"The purpose of this research has been used to detect osteoporosis disease for Knee radiography. It can improve diagnostic performance over using the scan thermal image mode alone. During 2016 and 2021, researchers gathered CT, MRI, CTA, ultra sound images from individuals who had both skeletal bone density assessment and knee radiology at a local medical clinic for subjective labelling. But following models are most complicate to detect diagnosis of osteoporosis. Therefore, five level convolutional neural networks (CNN) models were used to diagnose osteoporosis from knee radiography. They also looked at ensemble models that included clinical variables in each U-Net. Every net was given an efficiency, accuracy, recall, sensitivity, negative predictive value (npv), F1 measure, and area under curve (AUC) rating. Exclusively knee rays were used to test the U-Net model, but GoogleNet, S-transform, ResNet and FCNN had the lowest accuracy, precision, and specificity. Whenever patient’s data were added, Efficient U-Net had the highest accuracy 99.23%, recall 98.76%, npv 0.93%, F1 score 99.23%, and AUC 99.72% scores among five level prediction methods. The U-Net models correctly identified osteoporosis from Knee radiography, and their performance had improved even more when clinical variables from health records were complex. This u-net based osteoporosis diagnosis is most helpful for future generation for better pre-detections.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132800963","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 : 2022-02-04DOI: 10.13052/jmm1550-4646.18316
R. Banchuin, R. Chaisricharoen
In this research, the time domain analysis of the fractional order biquadratic system with nonzero input and nonzero damping ratio has been performed. Unlike the previous works, the analysis has been generically done with dimensional consistency awareness without referring to any specific physical system where nonzero input and nonzero damping ratio have been allowed. The fractional differential equation of the system has been derived and analytically solved. The physical measurability of the dimensions of the fractional derivative terms which have been defined in Caputo sense, and response with significantly different dynamic from its dimensional consistency ignored counterpart have been obtained due to our dimensional consistency awareness. The resulting solution is applicable to the fractional biquadratic systems of any kind with any physical nature. Based on such solution and numerical simulations, the influence of the fractional order parameter to all major time domain parameters have been studied in detailed. The obtain results provide insight to the fractional order biquadratic system with dimensional consistency awareness in a generic point of view.
{"title":"A Dimensional Consistency Aware Time Domain Analysis of the Generic Fractional Order Biquadratic System","authors":"R. Banchuin, R. Chaisricharoen","doi":"10.13052/jmm1550-4646.18316","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.18316","url":null,"abstract":"In this research, the time domain analysis of the fractional order biquadratic system with nonzero input and nonzero damping ratio has been performed. Unlike the previous works, the analysis has been generically done with dimensional consistency awareness without referring to any specific physical system where nonzero input and nonzero damping ratio have been allowed. The fractional differential equation of the system has been derived and analytically solved. The physical measurability of the dimensions of the fractional derivative terms which have been defined in Caputo sense, and response with significantly different dynamic from its dimensional consistency ignored counterpart have been obtained due to our dimensional consistency awareness. The resulting solution is applicable to the fractional biquadratic systems of any kind with any physical nature. Based on such solution and numerical simulations, the influence of the fractional order parameter to all major time domain parameters have been studied in detailed. The obtain results provide insight to the fractional order biquadratic system with dimensional consistency awareness in a generic point of view.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126337174","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 : 2022-02-04DOI: 10.13052/jmm1550-4646.18314
S. Babu, Maravarman Manoharan, R. Pitchai
Deep learning has recently grown a lot of interest as a way to create a fast, efficient, and reliable image identification and categorization system. India, being one of the world’s most important rice producers and consumers, relies heavily on rice to propel its economy and provide its food needs. In the crop protective device, early and precise diagnosis of plant diseases is critical. Traditionally, identification was done either through visual inspection or laboratory testing. It is critical to identify any disease early and perform the necessary treatment to the damaged plants in order to guarantee the rice plants’ healthy and proper growth. Because disease detection by hand takes a long time and requires a lot of effort, having an automated system is unavoidable. A rice plant disease identification method depends on deep learning methodologies are presented in this research. Leaf smut, bacterial leaf blight, sheat blight, and brown spot diseases are four of the most frequent rice plant diseases identified in this study. The rice plant disease is identified and recognized using deep learning algorithms. This method of early detection of rice diseases could be utilized as a preventative tool as well as an early detection. The proposed approach provides enhanced accuracy of 99.45% and it is compared with the existing state-of-the-art approaches.
{"title":"Detection of Rice Plant Disease Using Deep Learning Techniques","authors":"S. Babu, Maravarman Manoharan, R. Pitchai","doi":"10.13052/jmm1550-4646.18314","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.18314","url":null,"abstract":"Deep learning has recently grown a lot of interest as a way to create a fast, efficient, and reliable image identification and categorization system. India, being one of the world’s most important rice producers and consumers, relies heavily on rice to propel its economy and provide its food needs. In the crop protective device, early and precise diagnosis of plant diseases is critical. Traditionally, identification was done either through visual inspection or laboratory testing. It is critical to identify any disease early and perform the necessary treatment to the damaged plants in order to guarantee the rice plants’ healthy and proper growth. Because disease detection by hand takes a long time and requires a lot of effort, having an automated system is unavoidable. A rice plant disease identification method depends on deep learning methodologies are presented in this research. Leaf smut, bacterial leaf blight, sheat blight, and brown spot diseases are four of the most frequent rice plant diseases identified in this study. The rice plant disease is identified and recognized using deep learning algorithms. This method of early detection of rice diseases could be utilized as a preventative tool as well as an early detection. The proposed approach provides enhanced accuracy of 99.45% and it is compared with the existing state-of-the-art approaches.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133883569","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：