Solar energy is naturally available from sun, and it can be extracted by using a photovoltaic (PV) cell. However, solar energy extraction entirely depends on the climatic conditions and angle of rays falling on PV cells. Hence, maximum powerpoint tracking (MPPT) is considered in most areas under variable climatic conditions, which acts as a controller unit for PV cells. MPPT can enhance the efficiency of PV cells. However, designing an MPPT model is challenging as different uncertainties in the climatic condition may lead to more fluctuations in voltage and current in PV cells. Under the shaded condition, the PV cell may have other MPPT points that lead to the PV cell’s low efficiency in analyzing maximum power. Hence, this paper introduces a cost-effective and optimized system for the PV model that can find optimal power and improve PV cells’ efficiency. The proposed system achieves better computational performance with ~35% and ~42% than existing MPPT techniques. The improved particle swarm optimization (PSO) is smoother due to the enhanced form of MPP tracking. Hence, improved PSO takes 0.038 sec while the existing PSO technique takes 0.045 sec to obtain the MPP tracking.
{"title":"A cost-effective and optimized maximum powerpoint tracking system for the photovoltaic model","authors":"Yoganandini Arehalli Puttalingaiah, Anitha Gowda Shesadri","doi":"10.11591/ijece.v13i5.pp4942-4949","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4942-4949","url":null,"abstract":"Solar energy is naturally available from sun, and it can be extracted by using a photovoltaic (PV) cell. However, solar energy extraction entirely depends on the climatic conditions and angle of rays falling on PV cells. Hence, maximum powerpoint tracking (MPPT) is considered in most areas under variable climatic conditions, which acts as a controller unit for PV cells. MPPT can enhance the efficiency of PV cells. However, designing an MPPT model is challenging as different uncertainties in the climatic condition may lead to more fluctuations in voltage and current in PV cells. Under the shaded condition, the PV cell may have other MPPT points that lead to the PV cell’s low efficiency in analyzing maximum power. Hence, this paper introduces a cost-effective and optimized system for the PV model that can find optimal power and improve PV cells’ efficiency. The proposed system achieves better computational performance with ~35% and ~42% than existing MPPT techniques. The improved particle swarm optimization (PSO) is smoother due to the enhanced form of MPP tracking. Hence, improved PSO takes 0.038 sec while the existing PSO technique takes 0.045 sec to obtain the MPP tracking.","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":"47285009","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.pp5222-5231
Jacob Abraham, K. Suriyan, Beulah Jackson, Mahendran Natarajan, Thanga Mariappan Lakshmanaperumal
Antenna design has significantly advanced as a result of the widespread need for wireless communications and data substitution through wireless devices. The research article's goal is to provide a conceptual framework, difficulties, and opportunities for a source as well as a general overview of the antenna used in wireless communications applications. In this proposed research, we will go over a variety of topics related to mobile communication and fifth generation (5G) technologies, including its pros and benefits. A thorough comparison between the expected properties of the antennas and each generation, from 1st generation (1G) to 5G, is also included. This article also provides an overview of the investigated 5G technologies and various antenna designs.
{"title":"Performance analysis of smart optimization antenna for wireless networks","authors":"Jacob Abraham, K. Suriyan, Beulah Jackson, Mahendran Natarajan, Thanga Mariappan Lakshmanaperumal","doi":"10.11591/ijece.v13i5.pp5222-5231","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5222-5231","url":null,"abstract":"Antenna design has significantly advanced as a result of the widespread need for wireless communications and data substitution through wireless devices. The research article's goal is to provide a conceptual framework, difficulties, and opportunities for a source as well as a general overview of the antenna used in wireless communications applications. In this proposed research, we will go over a variety of topics related to mobile communication and fifth generation (5G) technologies, including its pros and benefits. A thorough comparison between the expected properties of the antennas and each generation, from 1st generation (1G) to 5G, is also included. This article also provides an overview of the investigated 5G technologies and various antenna designs.","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":"49029086","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.pp5232-5242
A. Mohammed, H. Mostafa, A. A. Ammar
In recent years, the wireless spectrum has become increasingly scarce as demand for wireless services has grown, requiring imaginative approaches to increase capacity within a limited spectral resource. This article proposes a new method that combines modified symbol time compression with orthogonal frequency division multiplexing (MSTC-OFDM), to enhance capacity for the narrow-band internet of things (NB-IoT) system. The suggested method, MSTC-OFDM, is based on the modified symbol time compression (MSTC) technique. The MSTC is a compressed waveform technique that increases capacity by compressing the occupied symbol time without losing bit error rate (BER) performance or data throughput. A comparative analysis is provided between the traditional orthogonal frequency division multiplexing (OFDM) system and the MSTC-OFDM method. The simulation results show that the MSTC-OFDM scheme drastically decreases the symbol time (ST) by 75% compared to a standard OFDM system. As a result, the MSTC-OFDM system offers four times the bit rate of a typical OFDM system using the same bandwidth and modulation but with a little increase in complexity. Moreover, compared to an OFDM system with 16 quadrature amplitude modulation (16QAM-OFDM), the MSTC-OFDM system reduces the signal-to-noise ratio (SNR) by 3.9 dB to transmit the same amount of data.
{"title":"An effective technique for increasing capacity and improving bandwidth in 5G narrow-band internet of things","authors":"A. Mohammed, H. Mostafa, A. A. Ammar","doi":"10.11591/ijece.v13i5.pp5232-5242","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5232-5242","url":null,"abstract":"In recent years, the wireless spectrum has become increasingly scarce as demand for wireless services has grown, requiring imaginative approaches to increase capacity within a limited spectral resource. This article proposes a new method that combines modified symbol time compression with orthogonal frequency division multiplexing (MSTC-OFDM), to enhance capacity for the narrow-band internet of things (NB-IoT) system. The suggested method, MSTC-OFDM, is based on the modified symbol time compression (MSTC) technique. The MSTC is a compressed waveform technique that increases capacity by compressing the occupied symbol time without losing bit error rate (BER) performance or data throughput. A comparative analysis is provided between the traditional orthogonal frequency division multiplexing (OFDM) system and the MSTC-OFDM method. The simulation results show that the MSTC-OFDM scheme drastically decreases the symbol time (ST) by 75% compared to a standard OFDM system. As a result, the MSTC-OFDM system offers four times the bit rate of a typical OFDM system using the same bandwidth and modulation but with a little increase in complexity. Moreover, compared to an OFDM system with 16 quadrature amplitude modulation (16QAM-OFDM), the MSTC-OFDM system reduces the signal-to-noise ratio (SNR) by 3.9 dB to transmit the same amount of 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":"49191145","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.pp5824-5832
Cynthia Sherin, Kayalvizhi Jayavel
Vehicle re-identification identifies target vehicles using images obtained by numerous non-overlapping real-time surveillance cameras. The effectiveness of re-identification is further challenging because of illumination changes, pose differences of captured images, and resolution. Fine-grained appearance changes in vehicles are recognized in addition to the coarse-grained characteristics like color of the vehicle along with model, and other custom features like logo stickers, annual service signs, and hangings to overcome these challenges. To prove the efficiency of our proposed bipartite attention framework, a novel dataset called Attributes27 which has 27 labelled attributes for each class are created. Our framework contains three major sections: The first section where the overall and semantic characteristics of every individual vehicle image are extracted by a double branch convolutional neural network (CNN) layer. Secondly, to identify the region of interests (ROIs) each branch has a self-attention block linked to it. Lastly to extract the regional features from the obtained ROIs, a partition-alignment block is deployed. The results of our proposed system’s evaluation on the Attributes27 and VeRi-776 datasets has highlighted significant regional attributes of each vehicle and improved the accuracy. Attributes27 and VeRi-776 datasets exhibits 98.5% and 84.3% accuracy respectively which are comparatively higher than the existing methods with 78.6% accuracy.
{"title":"Regional feature learning using attribute structural analysis in bipartite attention framework for vehicle re-identification","authors":"Cynthia Sherin, Kayalvizhi Jayavel","doi":"10.11591/ijece.v13i5.pp5824-5832","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5824-5832","url":null,"abstract":"Vehicle re-identification identifies target vehicles using images obtained by numerous non-overlapping real-time surveillance cameras. The effectiveness of re-identification is further challenging because of illumination changes, pose differences of captured images, and resolution. Fine-grained appearance changes in vehicles are recognized in addition to the coarse-grained characteristics like color of the vehicle along with model, and other custom features like logo stickers, annual service signs, and hangings to overcome these challenges. To prove the efficiency of our proposed bipartite attention framework, a novel dataset called Attributes27 which has 27 labelled attributes for each class are created. Our framework contains three major sections: The first section where the overall and semantic characteristics of every individual vehicle image are extracted by a double branch convolutional neural network (CNN) layer. Secondly, to identify the region of interests (ROIs) each branch has a self-attention block linked to it. Lastly to extract the regional features from the obtained ROIs, a partition-alignment block is deployed. The results of our proposed system’s evaluation on the Attributes27 and VeRi-776 datasets has highlighted significant regional attributes of each vehicle and improved the accuracy. Attributes27 and VeRi-776 datasets exhibits 98.5% and 84.3% accuracy respectively which are comparatively higher than the existing methods with 78.6% accuracy.","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":"44011080","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.pp5126-5134
P. Topannavar, D. M. Yadav
Alzheimer’s disease (AD) is an irremediable neurodegenerative illness developed by the fast deterioration of brain cells. AD is mostly common in elder people and it extremely disturbs the physical and mental health of patients, therefore early detection is essential to prevent AD development. However, the precise detection of AD and mild cognitive impairment (MCI) is difficult during classification. In this paper, the Residual network i.e., ResNet-18 is used for extracting the features, and the proposed improved marine predators algorithm (IMPA) is developed for choosing the optimum features to perform an effective classification of AD. The multi-verse optimizer (MVO) used in the IMPA helps to balance exploration and exploitation, which leads to the selection of optimal relevant features. Further, the classification of AD is accomplished using the multiclass support vector machine (MSVM). Open access series of imaging studies-1 (OASIS-1) and Alzheimer disease neuroimaging initiative (ADNI) datasets are used to evaluate the IMPA-MSVM method. The performance of the IMPA-MSVM method is analyzed using accuracy, sensitivity, specificity, positive predictive value (PPV) and matthews correlation coefficient (MCC). The existing methods such as the deep learning-based segmenting method using SegNet (DLSS), mish activation function (MAF) with spatial transformer network (STN) and BrainNet2D are used to evaluate the IMPA-MSVM method. The accuracy of IMPA-MSVM for the ADNI dataset is 98.43% which is more when compared to the DLSS and MAF-STN.
{"title":"An effective feature selection using improved marine predators algorithm for Alzheimer’s disease classification","authors":"P. Topannavar, D. M. Yadav","doi":"10.11591/ijece.v13i5.pp5126-5134","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5126-5134","url":null,"abstract":"Alzheimer’s disease (AD) is an irremediable neurodegenerative illness developed by the fast deterioration of brain cells. AD is mostly common in elder people and it extremely disturbs the physical and mental health of patients, therefore early detection is essential to prevent AD development. However, the precise detection of AD and mild cognitive impairment (MCI) is difficult during classification. In this paper, the Residual network i.e., ResNet-18 is used for extracting the features, and the proposed improved marine predators algorithm (IMPA) is developed for choosing the optimum features to perform an effective classification of AD. The multi-verse optimizer (MVO) used in the IMPA helps to balance exploration and exploitation, which leads to the selection of optimal relevant features. Further, the classification of AD is accomplished using the multiclass support vector machine (MSVM). Open access series of imaging studies-1 (OASIS-1) and Alzheimer disease neuroimaging initiative (ADNI) datasets are used to evaluate the IMPA-MSVM method. The performance of the IMPA-MSVM method is analyzed using accuracy, sensitivity, specificity, positive predictive value (PPV) and matthews correlation coefficient (MCC). The existing methods such as the deep learning-based segmenting method using SegNet (DLSS), mish activation function (MAF) with spatial transformer network (STN) and BrainNet2D are used to evaluate the IMPA-MSVM method. The accuracy of IMPA-MSVM for the ADNI dataset is 98.43% which is more when compared to the DLSS and MAF-STN.","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":"43693961","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.pp5764-5769
Tamilarasi Suresh, Tsehay Admassu Assegie, S. Ganesan, R. Tulasi, Radha Mothukuri, Ayodeji Olalekan Salau
This study investigates the Shapley additive explanation (SHAP) of the extreme boosting (XGBoost) model for breast cancer diagnosis. The study employed Wisconsin’s breast cancer dataset, characterized by 30 features extracted from an image of a breast cell. SHAP module generated different explainer values representing the impact of a breast cancer feature on breast cancer diagnosis. The experiment computed SHAP values of 569 samples of the breast cancer dataset. The SHAP explanation indicates perimeter and concave points have the highest impact on breast cancer diagnosis. SHAP explains the XGB model diagnosis outcome showing the features affecting the XGBoost model. The developed XGB model achieves an accuracy of 98.42%.
{"title":"Explainable extreme boosting model for breast cancer diagnosis","authors":"Tamilarasi Suresh, Tsehay Admassu Assegie, S. Ganesan, R. Tulasi, Radha Mothukuri, Ayodeji Olalekan Salau","doi":"10.11591/ijece.v13i5.pp5764-5769","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5764-5769","url":null,"abstract":"This study investigates the Shapley additive explanation (SHAP) of the extreme boosting (XGBoost) model for breast cancer diagnosis. The study employed Wisconsin’s breast cancer dataset, characterized by 30 features extracted from an image of a breast cell. SHAP module generated different explainer values representing the impact of a breast cancer feature on breast cancer diagnosis. The experiment computed SHAP values of 569 samples of the breast cancer dataset. The SHAP explanation indicates perimeter and concave points have the highest impact on breast cancer diagnosis. SHAP explains the XGB model diagnosis outcome showing the features affecting the XGBoost model. The developed XGB model achieves an accuracy of 98.42%.","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":"41383108","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.pp5491-5500
Nur Nafi’iyah, C. Fatichah, D. Herumurti, E. Astuti, R. Putra, E. Prakasa, Yosi Kristian
Under extreme conditions postmortem, dental radiography examinations can play an essential role in individual identification. In forensic odontology, individual identification traditionally compares antemortem dental records radiographs with those obtained on postmortem examination. As such, these traditional methods are vulnerable to oversights or mistakes in the individual identification of unidentified bodies. Digital technology can develop forensic odontology well. An automatic individual identification system is needed to support the forensic odontology process more easily and quickly because there are still opportunities to be created. We aimed to review the complete range of recent developments in identifying individuals from panoramic radiographs. We study methods in gender identification, age estimation, radiographic segmentation, performance analysis, and promising future directions.
{"title":"System of gender identification and age estimation from radiography: a review","authors":"Nur Nafi’iyah, C. Fatichah, D. Herumurti, E. Astuti, R. Putra, E. Prakasa, Yosi Kristian","doi":"10.11591/ijece.v13i5.pp5491-5500","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5491-5500","url":null,"abstract":"Under extreme conditions postmortem, dental radiography examinations can play an essential role in individual identification. In forensic odontology, individual identification traditionally compares antemortem dental records radiographs with those obtained on postmortem examination. As such, these traditional methods are vulnerable to oversights or mistakes in the individual identification of unidentified bodies. Digital technology can develop forensic odontology well. An automatic individual identification system is needed to support the forensic odontology process more easily and quickly because there are still opportunities to be created. We aimed to review the complete range of recent developments in identifying individuals from panoramic radiographs. We study methods in gender identification, age estimation, radiographic segmentation, performance analysis, and promising future directions.","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":"43560474","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.pp5674-5680
Trong Hieu Luu, Phan Nguyen Ky Phuc, T. Lam, Zhi-qiu Yu, Van Tinh Lam
Solar panel quality inspection is a time consuming and costly task. This study tries to develop as reliable method for evaluating the panels quality by using ensemble technique based on three machine learning models namely logistic regression, support vector machine and artificial neural network. The data in this study came from infrared camera which were captured in dark room. The panels are supplied with direct current (DC) power while the infrared camera is located perpendicular with panel surface. Dataset is divided into four classes where each class represent for a level of damage percentage. The approach is suitable for systems which has limited resources as well as number of training images which is very popular in reality. Result shows that the proposed method performs with the accuracy is higher than 90%.
{"title":"Ensembling techniques in solar panel quality classification","authors":"Trong Hieu Luu, Phan Nguyen Ky Phuc, T. Lam, Zhi-qiu Yu, Van Tinh Lam","doi":"10.11591/ijece.v13i5.pp5674-5680","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5674-5680","url":null,"abstract":"Solar panel quality inspection is a time consuming and costly task. This study tries to develop as reliable method for evaluating the panels quality by using ensemble technique based on three machine learning models namely logistic regression, support vector machine and artificial neural network. The data in this study came from infrared camera which were captured in dark room. The panels are supplied with direct current (DC) power while the infrared camera is located perpendicular with panel surface. Dataset is divided into four classes where each class represent for a level of damage percentage. The approach is suitable for systems which has limited resources as well as number of training images which is very popular in reality. Result shows that the proposed method performs with the accuracy is higher than 90%.","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":"45837340","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.pp5833-5842
Bao T. Nguyen, S. T. Nguyen, Anh H. Vo
Image captioning aims to automatically generate one or more description sentences for a given input image. Most of the existing captioning methods use encoder-decoder model which mainly focus on recognizing and capturing the relationship between objects appearing in the input image. However, when generating captions for fashion images, it is important to not only describe the items and their relationships, but also mention attribute features of clothes (shape, texture, style, fabric, and more). In this study, one novel model is proposed for fashion image captioning task which can capture not only the items and their relationship, but also their attribute features. Two different attention mechanisms (spatial-attention and channel-wise attention) is incorporated to the traditional encoder-decoder model, which dynamically interprets the caption sentence in multi-layer feature map in addition to the depth dimension of the feature map. We evaluate our proposed architecture on Fashion-Gen using three different metrics (CIDEr, ROUGE-L, and BLEU-1), and achieve the scores of 89.7, 50.6 and 45.6, respectively. Based on experiments, our proposed method shows significant performance improvement for the task of fashion-image captioning, and outperforms other state-of-the-art image captioning methods.
{"title":"Channel and spatial attention mechanism for fashion image captioning","authors":"Bao T. Nguyen, S. T. Nguyen, Anh H. Vo","doi":"10.11591/ijece.v13i5.pp5833-5842","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5833-5842","url":null,"abstract":"Image captioning aims to automatically generate one or more description sentences for a given input image. Most of the existing captioning methods use encoder-decoder model which mainly focus on recognizing and capturing the relationship between objects appearing in the input image. However, when generating captions for fashion images, it is important to not only describe the items and their relationships, but also mention attribute features of clothes (shape, texture, style, fabric, and more). In this study, one novel model is proposed for fashion image captioning task which can capture not only the items and their relationship, but also their attribute features. Two different attention mechanisms (spatial-attention and channel-wise attention) is incorporated to the traditional encoder-decoder model, which dynamically interprets the caption sentence in multi-layer feature map in addition to the depth dimension of the feature map. We evaluate our proposed architecture on Fashion-Gen using three different metrics (CIDEr, ROUGE-L, and BLEU-1), and achieve the scores of 89.7, 50.6 and 45.6, respectively. Based on experiments, our proposed method shows significant performance improvement for the task of fashion-image captioning, and outperforms other state-of-the-art image captioning methods.","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":"46325567","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.pp5454-5461
Sepideh Sheikhi Nejad, Ahmad Khademzadeh, A. Rahmani, A. Broumandnia
In recent years, the number of end users connected to the internet of things (IoT) has increased, and we have witnessed the emergence of the cloud computing paradigm. These users utilize network resources to meet their quality of service (QoS) requirements, but traditional networks are not configured to backing maximum of scalability, real-time data transfer, and dynamism, resulting in numerous challenges. This research presents a new platform of IoT architecture that adds the benefits of two new technologies: software-defined networking and fog paradigm. Software-defined networking (SDN) refers to a centralized control layer of the network that enables sophisticated methods for traffic control and resource allocation. So, fog paradigm allows for data to be analyzed and managed at the edge of the network, making it suitable for tasks that require low and predictable delay. Thus, this research provides an in-depth view of the platform organize and performance of its base ingredients, as well as the potential uses of the suggested platform in various applications.
{"title":"Software defined fog platform","authors":"Sepideh Sheikhi Nejad, Ahmad Khademzadeh, A. Rahmani, A. Broumandnia","doi":"10.11591/ijece.v13i5.pp5454-5461","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5454-5461","url":null,"abstract":"In recent years, the number of end users connected to the internet of things (IoT) has increased, and we have witnessed the emergence of the cloud computing paradigm. These users utilize network resources to meet their quality of service (QoS) requirements, but traditional networks are not configured to backing maximum of scalability, real-time data transfer, and dynamism, resulting in numerous challenges. This research presents a new platform of IoT architecture that adds the benefits of two new technologies: software-defined networking and fog paradigm. Software-defined networking (SDN) refers to a centralized control layer of the network that enables sophisticated methods for traffic control and resource allocation. So, fog paradigm allows for data to be analyzed and managed at the edge of the network, making it suitable for tasks that require low and predictable delay. Thus, this research provides an in-depth view of the platform organize and performance of its base ingredients, as well as the potential uses of the suggested platform in various applications.","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":"46386766","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：