Pub Date : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4966-4978
S. Buakaew, C. Wongtaychatham
This article presents a new design of a quadrature shadow oscillator. The oscillator is realized using one input and two outputs of a second-order filter cell together with external amplifiers in a feedback configuration. The oscillation characteristics are controlled via the external gain without disturbing the internal filter cell, following the concept of the shadow oscillator. The proposed circuit configuration is simple with a small component-count. It consists of, two voltage-different transconductance amplifiers (VDTAs) along with a couple of passive elements. The frequency of oscillation (FO) and the condition of oscillation (CO) are controlled orthogonally via the dc bias current and external gain. Moreover, with the addition of the external gain, the frequency range of oscillation can be further extended. The proposed work is verified by computer simulation with the use of 180 nm complementary metal–oxide–semiconductor (CMOS) model parameters. The simulation gives satisfactory results of two sinusoidal output signals in quadrature with some small total harmonic distortions (THD). In addition, a circuit experiment is performed using the commercial operational transconductance amplifiers LM13700 as the active components. The circuit experiment also demonstrates satisfactory outcome which confirms the validity of the proposed circuit.
{"title":"A miniature tunable quadrature shadow oscillator with orthogonal control","authors":"S. Buakaew, C. Wongtaychatham","doi":"10.11591/ijece.v13i5.pp4966-4978","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4966-4978","url":null,"abstract":"This article presents a new design of a quadrature shadow oscillator. The oscillator is realized using one input and two outputs of a second-order filter cell together with external amplifiers in a feedback configuration. The oscillation characteristics are controlled via the external gain without disturbing the internal filter cell, following the concept of the shadow oscillator. The proposed circuit configuration is simple with a small component-count. It consists of, two voltage-different transconductance amplifiers (VDTAs) along with a couple of passive elements. The frequency of oscillation (FO) and the condition of oscillation (CO) are controlled orthogonally via the dc bias current and external gain. Moreover, with the addition of the external gain, the frequency range of oscillation can be further extended. The proposed work is verified by computer simulation with the use of 180 nm complementary metal–oxide–semiconductor (CMOS) model parameters. The simulation gives satisfactory results of two sinusoidal output signals in quadrature with some small total harmonic distortions (THD). In addition, a circuit experiment is performed using the commercial operational transconductance amplifiers LM13700 as the active components. The circuit experiment also demonstrates satisfactory outcome which confirms the validity of the proposed circuit.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49184780","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5462-5471
Bharathi Ramachandra, Smitha Elsa Peter
The internet of things (IoT) is an emerging and robust technology to interconnect billions of objects or devices via the internet to communicate smartly. The radio frequency identification (RFID) system plays a significant role in IoT systems, providing most features like mutual establishment, key establishment, and data confidentiality. This manuscript designed secure authentication of IoT-based RFID systems using the light-weight PRESENT algorithm on the hardware platform. The PRESENT-256 block cipher is considered in this work, and it supports 64-bit data with a 256-key length. The PRESENT-80/128 cipher is also designed along with PRESENT-256 at electronic codebook (ECB) mode for Secured mutual authentication between RFID tag and reader for IoT applications. The secured authentication is established in two stages: Tag recognition from reader, mutual authentication between tag and reader using PRESENT-80/128/256 cipher modules. The complete secured authentication of IoT-based RFID system simulation results is verified using the chip-scope tool with field-programmable gate array (FPGA) results. The comparative results for PRESENT block cipher with existing PRESENT ciphers and other light-weight algorithms are analyzed with resource improvements. The proposed secured authentication work is compared with similar RFID-mutual authentication (MA) approaches with better chip area and frequency improvements.
{"title":"Secured authentication of radio-frequency identification system using PRESENT block cipher","authors":"Bharathi Ramachandra, Smitha Elsa Peter","doi":"10.11591/ijece.v13i5.pp5462-5471","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5462-5471","url":null,"abstract":"The internet of things (IoT) is an emerging and robust technology to interconnect billions of objects or devices via the internet to communicate smartly. The radio frequency identification (RFID) system plays a significant role in IoT systems, providing most features like mutual establishment, key establishment, and data confidentiality. This manuscript designed secure authentication of IoT-based RFID systems using the light-weight PRESENT algorithm on the hardware platform. The PRESENT-256 block cipher is considered in this work, and it supports 64-bit data with a 256-key length. The PRESENT-80/128 cipher is also designed along with PRESENT-256 at electronic codebook (ECB) mode for Secured mutual authentication between RFID tag and reader for IoT applications. The secured authentication is established in two stages: Tag recognition from reader, mutual authentication between tag and reader using PRESENT-80/128/256 cipher modules. The complete secured authentication of IoT-based RFID system simulation results is verified using the chip-scope tool with field-programmable gate array (FPGA) results. The comparative results for PRESENT block cipher with existing PRESENT ciphers and other light-weight algorithms are analyzed with resource improvements. The proposed secured authentication work is compared with similar RFID-mutual authentication (MA) approaches with better chip area and frequency improvements.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43365832","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4987-4995
Sujatha Kotte, Ganapavarapu Kanaka Durga
The high-performance digital circuits can be constructed at high operating frequency, reduced power dissipation, portability, and large density. Using conventional complementary-metal-oxide-semiconductor (CMOS) design process, it is quite difficult to achieve ultra-high-speed circuits due to scaling problems. Recently quantum dot cellular automata (QCA) are prosed to develop logic circuits at atomic level. In this paper, we analyzed the performance of QCA circuits under different temperature effects and observed that polarization of the cells is highly sensitive to temperature. In case of the 3-input majority gate the cell polarization drops to 50% with an increase in the temperature of 18 K and for 5 input majority gate the cell polarization drops more quickly than the 3-input majority. Further, the performance of majority gates also compared in terms of area and power dissipation. It has been noticed that the proposed logic gates can also be used for developing simple and complex and memory circuits.
{"title":"A thermally aware performance analysis of quantum cellular automata logic gates","authors":"Sujatha Kotte, Ganapavarapu Kanaka Durga","doi":"10.11591/ijece.v13i5.pp4987-4995","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4987-4995","url":null,"abstract":"The high-performance digital circuits can be constructed at high operating frequency, reduced power dissipation, portability, and large density. Using conventional complementary-metal-oxide-semiconductor (CMOS) design process, it is quite difficult to achieve ultra-high-speed circuits due to scaling problems. Recently quantum dot cellular automata (QCA) are prosed to develop logic circuits at atomic level. In this paper, we analyzed the performance of QCA circuits under different temperature effects and observed that polarization of the cells is highly sensitive to temperature. In case of the 3-input majority gate the cell polarization drops to 50% with an increase in the temperature of 18 K and for 5 input majority gate the cell polarization drops more quickly than the 3-input majority. Further, the performance of majority gates also compared in terms of area and power dissipation. It has been noticed that the proposed logic gates can also be used for developing simple and complex and memory circuits.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41475013","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5550-5559
Venkata Nagaraju Thatha, S. Donepudi, M. Safali, S. P. Praveen, Nguyen Trong Tung, Nguyen Ha Huy Cuong
Cloud computing has emerged as the actual trend in business information technology service models, since it provides processing that is both cost-effective and scalable. Enterprise networks are adopting software-defined networking (SDN) for network management flexibility and lower operating costs. Information technology (IT) services for enterprises tend to use both technologies. Yet, the effects of cloud computing and software defined networking on business network security are unclear. This study addresses this crucial issue. In a business network that uses both technologies, we start by looking at security, namely distributed denial-of-service (DDoS) attack defensive methods. SDN technology may help organizations protect against DDoS assaults provided the defensive architecture is structured appropriately. To mitigate DDoS attacks, we offer a highly configurable network monitoring and flexible control framework. We present a dataset shift-resistant graphic model-based attack detection system for the new architecture. The simulation findings demonstrate that our architecture can efficiently meet the security concerns of the new network paradigm and that our attack detection system can report numerous threats using real-world network data.
{"title":"Security and risk analysis in the cloud with software defined networking architecture","authors":"Venkata Nagaraju Thatha, S. Donepudi, M. Safali, S. P. Praveen, Nguyen Trong Tung, Nguyen Ha Huy Cuong","doi":"10.11591/ijece.v13i5.pp5550-5559","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5550-5559","url":null,"abstract":"Cloud computing has emerged as the actual trend in business information technology service models, since it provides processing that is both cost-effective and scalable. Enterprise networks are adopting software-defined networking (SDN) for network management flexibility and lower operating costs. Information technology (IT) services for enterprises tend to use both technologies. Yet, the effects of cloud computing and software defined networking on business network security are unclear. This study addresses this crucial issue. In a business network that uses both technologies, we start by looking at security, namely distributed denial-of-service (DDoS) attack defensive methods. SDN technology may help organizations protect against DDoS assaults provided the defensive architecture is structured appropriately. To mitigate DDoS attacks, we offer a highly configurable network monitoring and flexible control framework. We present a dataset shift-resistant graphic model-based attack detection system for the new architecture. The simulation findings demonstrate that our architecture can efficiently meet the security concerns of the new network paradigm and that our attack detection system can report numerous threats using real-world network data.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42735309","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5569-5575
G. Abdikerimova, M. Yessenova, A.Ye. Yerzhanova, Zhanat Manbetova, G. Murzabekova, D. Kaibassova, Roza Bekbayeva, Madina Aldashova
Currently, artificial neural networks are experiencing a rebirth, which is primarily due to the increase in the computing power of modern computers and the emergence of very large training data sets available in global networks. The article considers Laws texture masks as weights for a machine-learning algorithm for clustering aerospace images. The use of Laws texture masks in machine learning can help in the analysis of the textural characteristics of objects in the image, which are further identified as pockets of weeds. When solving problems in applied areas, in particular in the field of agriculture, there are often problems associated with small sample sizes of images obtained from aerospace and unmanned aerial vehicles and insufficient quality of the source material for training. This determines the relevance of research and development of new methods and algorithms for classifying crop damage. The purpose of the work is to use the method of texture masks of Laws in machine learning for automated processing of high-resolution images in the case of small samples using the example of problems of segmentation and classification of the nature of damage to crops.
{"title":"Applying textural Law’s masks to images using machine learning","authors":"G. Abdikerimova, M. Yessenova, A.Ye. Yerzhanova, Zhanat Manbetova, G. Murzabekova, D. Kaibassova, Roza Bekbayeva, Madina Aldashova","doi":"10.11591/ijece.v13i5.pp5569-5575","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5569-5575","url":null,"abstract":"Currently, artificial neural networks are experiencing a rebirth, which is primarily due to the increase in the computing power of modern computers and the emergence of very large training data sets available in global networks. The article considers Laws texture masks as weights for a machine-learning algorithm for clustering aerospace images. The use of Laws texture masks in machine learning can help in the analysis of the textural characteristics of objects in the image, which are further identified as pockets of weeds. When solving problems in applied areas, in particular in the field of agriculture, there are often problems associated with small sample sizes of images obtained from aerospace and unmanned aerial vehicles and insufficient quality of the source material for training. This determines the relevance of research and development of new methods and algorithms for classifying crop damage. The purpose of the work is to use the method of texture masks of Laws in machine learning for automated processing of high-resolution images in the case of small samples using the example of problems of segmentation and classification of the nature of damage to crops.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48012010","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5843-5852
Nur Hasanah Ali, A. Abdullah, N. Saad, A. Muda
Treatment of stroke patients can be effectively carried out with the help of collateral circulation performance. Collateral circulation scoring as it is now used is dependent on visual inspection, which can lead to an inter- and intra-rater discrepancy. In this study, a collateral circulation classification using the ResNet50 was analyzed by using cone beam computed tomography (CBCT) images for the ischemic stroke patient. The remarkable performance of deep learning classification helps neuroradiologists with fast image classification. A pre-trained deep network ResNet50 was applied to extract robust features and learn the structure of CBCT images in their convolutional layers. Next, the classification layer of the ResNet50 was performed into binary classification as “good” and “poor” classes. The images were divided by 80:20 for training and testing. The empirical results support the claim that the application of ResNet50 offers consistent accuracy, sensitivity, and specificity values. The performance value of the classification accuracy was 76.79%. The deep learning approach was employed to unveil how biological image analysis could generate incredibly dependable and repeatable outcomes. The experiments performed on CBCT images evidenced that the proposed ResNet50 using convolutional neural network (CNN) architecture is indeed effective in classifying collateral circulation.
{"title":"Brain cone beam computed tomography image analysis using ResNet50 for collateral circulation classification","authors":"Nur Hasanah Ali, A. Abdullah, N. Saad, A. Muda","doi":"10.11591/ijece.v13i5.pp5843-5852","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5843-5852","url":null,"abstract":"Treatment of stroke patients can be effectively carried out with the help of collateral circulation performance. Collateral circulation scoring as it is now used is dependent on visual inspection, which can lead to an inter- and intra-rater discrepancy. In this study, a collateral circulation classification using the ResNet50 was analyzed by using cone beam computed tomography (CBCT) images for the ischemic stroke patient. The remarkable performance of deep learning classification helps neuroradiologists with fast image classification. A pre-trained deep network ResNet50 was applied to extract robust features and learn the structure of CBCT images in their convolutional layers. Next, the classification layer of the ResNet50 was performed into binary classification as “good” and “poor” classes. The images were divided by 80:20 for training and testing. The empirical results support the claim that the application of ResNet50 offers consistent accuracy, sensitivity, and specificity values. The performance value of the classification accuracy was 76.79%. The deep learning approach was employed to unveil how biological image analysis could generate incredibly dependable and repeatable outcomes. The experiments performed on CBCT images evidenced that the proposed ResNet50 using convolutional neural network (CNN) architecture is indeed effective in classifying collateral circulation.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42458538","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5874-5884
N. Kamaruddin, Mohd Hafiz Mohd Nasir, A. Wahab, Frederick C. Harris Jr.
Dysphoria is a trigger point for maladjusted individuals who cannot cope with disappointments and crushed expectations, resulting in negative emotions if it is not detected early. Individuals who suffer from dysphoria tend to deny their mental state. They try to hide, suppress, or ignore the symptoms, making one feel worse, unwanted, and unloved. Psychologists and psychiatrists identify dysphoria using standardized instruments like questionnaires and interviews. These methods can boast a high success rate. However, the limited number of trained psychologists and psychiatrists and the small number of health institutions focused on mental health limit access to early detection. In addition, the negative connotation and taboo about dysphoria discourage the public from openly seeking help. An alternative approach to collecting ‘pure’ data is proposed in this paper. The brain signals are captured using the electroencephalogram as the input to the machine learning approach to detect negative emotions. It was observed from the experimental results that participants who scored severe dysphoria recorded ‘fear’ emotion even before stimuli were presented during the eyes-close phase. This finding is crucial to further understanding the effect of dysphoria and can be used to study the correlation between dysphoria and negative emotions.
{"title":"Early detection of dysphoria using electroencephalogram affective modelling","authors":"N. Kamaruddin, Mohd Hafiz Mohd Nasir, A. Wahab, Frederick C. Harris Jr.","doi":"10.11591/ijece.v13i5.pp5874-5884","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5874-5884","url":null,"abstract":"Dysphoria is a trigger point for maladjusted individuals who cannot cope with disappointments and crushed expectations, resulting in negative emotions if it is not detected early. Individuals who suffer from dysphoria tend to deny their mental state. They try to hide, suppress, or ignore the symptoms, making one feel worse, unwanted, and unloved. Psychologists and psychiatrists identify dysphoria using standardized instruments like questionnaires and interviews. These methods can boast a high success rate. However, the limited number of trained psychologists and psychiatrists and the small number of health institutions focused on mental health limit access to early detection. In addition, the negative connotation and taboo about dysphoria discourage the public from openly seeking help. An alternative approach to collecting ‘pure’ data is proposed in this paper. The brain signals are captured using the electroencephalogram as the input to the machine learning approach to detect negative emotions. It was observed from the experimental results that participants who scored severe dysphoria recorded ‘fear’ emotion even before stimuli were presented during the eyes-close phase. This finding is crucial to further understanding the effect of dysphoria and can be used to study the correlation between dysphoria and negative emotions.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43640564","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5707-5716
Fredy H. Martínez, Holman Montiel, Luis Wanumen
Social behaviors in animals such as bees, ants, and birds have shown high levels of intelligence from a multi-agent system perspective. They present viable solutions to real-world problems, particularly in navigating constrained environments with simple robotic platforms. Among these behaviors is swarm flocking, which has been extensively studied for this purpose. Flocking algorithms have been developed from basic behavioral rules, which often require parameter tuning for specific applications. However, the lack of a general formulation for tuning has made these strategies difficult to implement in various real conditions, and even to replicate laboratory behaviors. In this paper, we propose a flocking scheme for small autonomous robots that can self-learn in dynamic environments, derived from a deep reinforcement learning process. Our approach achieves flocking independently of population size and environmental characteristics, with minimal external intervention. Our multi-agent system model considers each agent’s action as a linear function dynamically adjusting the motion according to interactions with other agents and the environment. Our strategy is an important contribution toward real-world flocking implementation. We demonstrate that our approach allows for autonomous flocking in the system without requiring specific parameter tuning, making it ideal for applications where there is a need for simple robotic platforms to navigate in dynamic environments.
{"title":"A deep reinforcement learning strategy for autonomous robot flocking","authors":"Fredy H. Martínez, Holman Montiel, Luis Wanumen","doi":"10.11591/ijece.v13i5.pp5707-5716","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5707-5716","url":null,"abstract":"Social behaviors in animals such as bees, ants, and birds have shown high levels of intelligence from a multi-agent system perspective. They present viable solutions to real-world problems, particularly in navigating constrained environments with simple robotic platforms. Among these behaviors is swarm flocking, which has been extensively studied for this purpose. Flocking algorithms have been developed from basic behavioral rules, which often require parameter tuning for specific applications. However, the lack of a general formulation for tuning has made these strategies difficult to implement in various real conditions, and even to replicate laboratory behaviors. In this paper, we propose a flocking scheme for small autonomous robots that can self-learn in dynamic environments, derived from a deep reinforcement learning process. Our approach achieves flocking independently of population size and environmental characteristics, with minimal external intervention. Our multi-agent system model considers each agent’s action as a linear function dynamically adjusting the motion according to interactions with other agents and the environment. Our strategy is an important contribution toward real-world flocking implementation. We demonstrate that our approach allows for autonomous flocking in the system without requiring specific parameter tuning, making it ideal for applications where there is a need for simple robotic platforms to navigate in dynamic environments.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44765051","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5747-5754
Mohamed Bal-Ghaoui, My Hachem El Yousfi Alaoui, A. Jilbab, Abdennacer Bourouhou
Breast ultrasound images are highly valuable for the early detection of breast cancer. However, the drawback of these images is low-quality resolution and the presence of speckle noise, which affects their interpretability and makes them radiologists’ expertise-dependent. As medical images, breast ultrasound datasets are scarce and imbalanced, and annotating them is tedious and time-consuming. Transfer learning, as a deep learning technique, can be used to overcome the dataset deficiency in available images. This paper presents the implementation of transfer learning U-Net backbones for the automatic segmentation of breast ultrasound lesions and implements a threshold selection mechanism to deliver optimal generalized segmentation results of breast tumors. The work uses the public breast ultrasound images (BUSI) dataset and implements ten state-of-theart candidate models as U-Net backbones. We have trained these models with a five-fold cross-validation technique on 630 images with benign and malignant cases. Five out of ten models showed good results, and the best U-Net backbone was found to be DenseNet121. It achieved an average Dice coefficient of 0.7370 and a sensitivity of 0.7255. The model’s robustness was also evaluated against normal cases, and the model accurately detected 72 out of 113 images, which is higher than the four best models.
{"title":"U-Net transfer learning backbones for lesions segmentation in breast ultrasound images","authors":"Mohamed Bal-Ghaoui, My Hachem El Yousfi Alaoui, A. Jilbab, Abdennacer Bourouhou","doi":"10.11591/ijece.v13i5.pp5747-5754","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5747-5754","url":null,"abstract":"Breast ultrasound images are highly valuable for the early detection of breast cancer. However, the drawback of these images is low-quality resolution and the presence of speckle noise, which affects their interpretability and makes them radiologists’ expertise-dependent. As medical images, breast ultrasound datasets are scarce and imbalanced, and annotating them is tedious and time-consuming. Transfer learning, as a deep learning technique, can be used to overcome the dataset deficiency in available images. This paper presents the implementation of transfer learning U-Net backbones for the automatic segmentation of breast ultrasound lesions and implements a threshold selection mechanism to deliver optimal generalized segmentation results of breast tumors. The work uses the public breast ultrasound images (BUSI) dataset and implements ten state-of-theart candidate models as U-Net backbones. We have trained these models with a five-fold cross-validation technique on 630 images with benign and malignant cases. Five out of ten models showed good results, and the best U-Net backbone was found to be DenseNet121. It achieved an average Dice coefficient of 0.7370 and a sensitivity of 0.7255. The model’s robustness was also evaluated against normal cases, and the model accurately detected 72 out of 113 images, which is higher than the four best models.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46089661","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5853-5864
S. Madhusudhanan, S. Jaganathan, Dattuluri Venkatavara Prasad
In real-world scenarios, a system's continual updating of learning knowledge becomes more critical as the data grows faster, producing vast volumes of data. Moreover, the learning process becomes complex when the data features become varied due to the addition or deletion of classes. In such cases, the generated model should learn effectively. Incremental learning refers to the learning of data which constantly arrives over time. This learning requires continuous model adaptation but with limited memory resources without sacrificing model accuracy. In this paper, we proposed a straightforward knowledge transfer algorithm (convolutional auto-encoded extreme learning machine (CAE-ELM)) implemented through the incremental learning methodology for the task of supervised classification using an extreme learning machine (ELM). Incremental learning is achieved by creating an individual train model for each set of homogeneous data and incorporating the knowledge transfer among the models without sacrificing accuracy with minimal memory resources. In CAE-ELM, convolutional neural network (CNN) extracts the features, stacked autoencoder (SAE) reduces the size, and ELM learns and classifies the images. Our proposed algorithm is implemented and experimented on various standard datasets: MNIST, ORL, JAFFE, FERET and Caltech. The results show a positive sign of the correctness of the proposed algorithm.
{"title":"Convolutional auto-encoded extreme learning machine for incremental learning of heterogeneous images","authors":"S. Madhusudhanan, S. Jaganathan, Dattuluri Venkatavara Prasad","doi":"10.11591/ijece.v13i5.pp5853-5864","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5853-5864","url":null,"abstract":"In real-world scenarios, a system's continual updating of learning knowledge becomes more critical as the data grows faster, producing vast volumes of data. Moreover, the learning process becomes complex when the data features become varied due to the addition or deletion of classes. In such cases, the generated model should learn effectively. Incremental learning refers to the learning of data which constantly arrives over time. This learning requires continuous model adaptation but with limited memory resources without sacrificing model accuracy. In this paper, we proposed a straightforward knowledge transfer algorithm (convolutional auto-encoded extreme learning machine (CAE-ELM)) implemented through the incremental learning methodology for the task of supervised classification using an extreme learning machine (ELM). Incremental learning is achieved by creating an individual train model for each set of homogeneous data and incorporating the knowledge transfer among the models without sacrificing accuracy with minimal memory resources. In CAE-ELM, convolutional neural network (CNN) extracts the features, stacked autoencoder (SAE) reduces the size, and ELM learns and classifies the images. Our proposed algorithm is implemented and experimented on various standard datasets: MNIST, ORL, JAFFE, FERET and Caltech. The results show a positive sign of the correctness of the proposed algorithm.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":"101 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65382831","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：