Pub Date : 2024-09-06DOI: 10.1109/TLA.2024.10669245
Mateus Coelho Silva;Alcides Castro e Silva;Marcos T. D. Orlando;Vinicius D. N. Bezzon
The amorphous drug structure represents an important feature to be reached in the pharmaceutical field due to its possibility of increasing drug solubility, considering that at least 40% of commercially available crystalline drugs are poorly soluble in water. However, it is known that the amorphous local structure can vary depending on the amorphization technique used. Therefore, recognizing such variations related to a specific amorphization technique through the pair distribution function (PDF) method, for example, is an important tool for drug characterization concerns. This work presents a method to classify amorphous drugs according to their amorphization techniques and related to the local structure variations using machine learning. We used experimental PDF patterns obtained from low-energy X-rays scattering data to extract information and expanded the data through the Monte Carlo method to create a synthetic dataset. Then, we proposed the evaluation of such a technique using a Deep Neural Network. Based on the results obtained, it is suggested that the proposed technique is suitable for the amorphization technique and local structure recognition task.
考虑到至少 40% 的市售结晶药物在水中的溶解度很低，无定形药物结构是制药领域需要达到的一个重要特征，因为它有可能提高药物的溶解度。然而，众所周知，无定形局部结构会因所用的非晶化技术而变化。因此，通过对分布函数（PDF）方法等识别与特定非晶化技术相关的这种变化，是药物表征方面的一个重要工具。本研究提出了一种根据非晶化技术对非晶药物进行分类的方法，并利用机器学习对与局部结构变化相关的非晶化技术进行分类。我们利用从低能 X 射线散射数据中获得的实验 PDF 模式来提取信息，并通过蒙特卡罗方法对数据进行扩展，从而创建了一个合成数据集。然后，我们提出使用深度神经网络对这种技术进行评估。根据所获得的结果，我们认为所提出的技术适用于非晶化技术和局部结构识别任务。
{"title":"Towards a Machine-Learning-Based Application for Amorphous Drug Recognition","authors":"Mateus Coelho Silva;Alcides Castro e Silva;Marcos T. D. Orlando;Vinicius D. N. Bezzon","doi":"10.1109/TLA.2024.10669245","DOIUrl":"https://doi.org/10.1109/TLA.2024.10669245","url":null,"abstract":"The amorphous drug structure represents an important feature to be reached in the pharmaceutical field due to its possibility of increasing drug solubility, considering that at least 40% of commercially available crystalline drugs are poorly soluble in water. However, it is known that the amorphous local structure can vary depending on the amorphization technique used. Therefore, recognizing such variations related to a specific amorphization technique through the pair distribution function (PDF) method, for example, is an important tool for drug characterization concerns. This work presents a method to classify amorphous drugs according to their amorphization techniques and related to the local structure variations using machine learning. We used experimental PDF patterns obtained from low-energy X-rays scattering data to extract information and expanded the data through the Monte Carlo method to create a synthetic dataset. Then, we proposed the evaluation of such a technique using a Deep Neural Network. Based on the results obtained, it is suggested that the proposed technique is suitable for the amorphization technique and local structure recognition task.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 9","pages":"755-760"},"PeriodicalIF":1.3,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669245","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TLA.2024.10669358
Filipe Ramos;Jose Neto;Fabio Almeida;Silvia Velázquez;Bruno Lima
The National Institute of Metrology, Quality and Technology (Instituto Nacional de Metrologia, Qualidade e Tecnologia - INMETRO) introduces that, starting in 2024, all photovoltaic (PV) inverters sold in the Brazilian market must incorporate an Arc-Fault Circuit Interrupt (AFCI) function into their systems. These inverters are required to comply with the IEC 63027:2023 (Photovoltaic power systems DC arc detection and interruption) standard. Considering this, the Electrical Engineering Laboratory at Mackenzie Presbyterian University (Universidade Presbiteriana Mackenzie UPM) conducted a series of arc-faults tests on three inverters available in the market, following the IEC 63027 standard. Each of the three inverters underwent a total of 32 arcs, considering number of Maximum Power Point Tracking (MPPT) ports, different impedance topologies, arc position in the PV system, and maximum values of voltage and current. The experiments revealed that two of the three inverters are not capable of meeting the international standard for detecting and interrupting series arc-faults, highlighting the need evaluation of PV inverter sold in the Brazilian market. During the analysis, it was noted that for certain parameters proposed by IEC 63027, there is a gap of information regarding evaluation of the data relating to arc self-extinguish or actual AFCI intervention. It is show that this scenario can raise a concern: the possibility exists for an inverter meet the international standard without implementing an effective AFCI technology. The 96 tests conducted were compared in terms of arc detection time and arc energy. The data were analyzed and compared with respect to the phenomena of arc self-extinguishing and the operation of the AFCI. Suggestions for enhancements to the IEC 63027 standard were provided
{"title":"Compliance Analysis of Series Arc-fault in AFCI- Equipped Inverters in Accordance with IEC 63027","authors":"Filipe Ramos;Jose Neto;Fabio Almeida;Silvia Velázquez;Bruno Lima","doi":"10.1109/TLA.2024.10669358","DOIUrl":"https://doi.org/10.1109/TLA.2024.10669358","url":null,"abstract":"The National Institute of Metrology, Quality and Technology (Instituto Nacional de Metrologia, Qualidade e Tecnologia - INMETRO) introduces that, starting in 2024, all photovoltaic (PV) inverters sold in the Brazilian market must incorporate an Arc-Fault Circuit Interrupt (AFCI) function into their systems. These inverters are required to comply with the IEC 63027:2023 (Photovoltaic power systems DC arc detection and interruption) standard. Considering this, the Electrical Engineering Laboratory at Mackenzie Presbyterian University (Universidade Presbiteriana Mackenzie UPM) conducted a series of arc-faults tests on three inverters available in the market, following the IEC 63027 standard. Each of the three inverters underwent a total of 32 arcs, considering number of Maximum Power Point Tracking (MPPT) ports, different impedance topologies, arc position in the PV system, and maximum values of voltage and current. The experiments revealed that two of the three inverters are not capable of meeting the international standard for detecting and interrupting series arc-faults, highlighting the need evaluation of PV inverter sold in the Brazilian market. During the analysis, it was noted that for certain parameters proposed by IEC 63027, there is a gap of information regarding evaluation of the data relating to arc self-extinguish or actual AFCI intervention. It is show that this scenario can raise a concern: the possibility exists for an inverter meet the international standard without implementing an effective AFCI technology. The 96 tests conducted were compared in terms of arc detection time and arc energy. The data were analyzed and compared with respect to the phenomena of arc self-extinguishing and the operation of the AFCI. Suggestions for enhancements to the IEC 63027 standard were provided","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 9","pages":"761-770"},"PeriodicalIF":1.3,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669358","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TLA.2024.10669250
{"title":"Table of Contents September 2024","authors":"","doi":"10.1109/TLA.2024.10669250","DOIUrl":"https://doi.org/10.1109/TLA.2024.10669250","url":null,"abstract":"","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 9","pages":"713-713"},"PeriodicalIF":1.3,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669250","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TLA.2024.10669248
Daniel Valencia;Elena Muñoz España;Mariela Muñoz Añasco
Vehicle counting systems detect, classify, and count vehicles with sensors or image processing, providing valuable information for road management. Image processing systems provide detailed information on vehicle flow with adequate lighting conditions and a higher computational cost compared to sensor systems. The image processing systems with higher accuracy require higher computational cost. This feature limits the number of application cases in cities with low technology level. This research analyzes urban vehicle counting using an automatic image processing system using YOLOv5 in the vehicle detection-classification stage and the SORT algorithm in the tracking stage. The study used videos recorded from a pedestrian bridge in Popayan, Colombia, for an exploratory study of the influence of preprocessing operations on the performance of a low-tech vehicle counting system. The study performed a comparative statistical analysis to determine the impact of different settings on system performance. An ANOVA analysis evaluates the incidence of frame cut and reshape on YOLO processing. The results indicate that a 30% cut of the image area prior to YOLO processing produces the lowest weighted average error. In addition, the frame reshape only increases the processing time. The study proposes improvements in the performance of an offline automatic vehicle counting system from the video preprocessing stage.
{"title":"Impact of the preprocessing stage on the performance of offline automatic vehicle counting using YOLO","authors":"Daniel Valencia;Elena Muñoz España;Mariela Muñoz Añasco","doi":"10.1109/TLA.2024.10669248","DOIUrl":"https://doi.org/10.1109/TLA.2024.10669248","url":null,"abstract":"Vehicle counting systems detect, classify, and count vehicles with sensors or image processing, providing valuable information for road management. Image processing systems provide detailed information on vehicle flow with adequate lighting conditions and a higher computational cost compared to sensor systems. The image processing systems with higher accuracy require higher computational cost. This feature limits the number of application cases in cities with low technology level. This research analyzes urban vehicle counting using an automatic image processing system using YOLOv5 in the vehicle detection-classification stage and the SORT algorithm in the tracking stage. The study used videos recorded from a pedestrian bridge in Popayan, Colombia, for an exploratory study of the influence of preprocessing operations on the performance of a low-tech vehicle counting system. The study performed a comparative statistical analysis to determine the impact of different settings on system performance. An ANOVA analysis evaluates the incidence of frame cut and reshape on YOLO processing. The results indicate that a 30% cut of the image area prior to YOLO processing produces the lowest weighted average error. In addition, the frame reshape only increases the processing time. The study proposes improvements in the performance of an offline automatic vehicle counting system from the video preprocessing stage.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 9","pages":"723-732"},"PeriodicalIF":1.3,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669248","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TLA.2024.10669244
Jinlong Ma;Tian Qin
Long non-coding RNAs (lncRNAs) represent a fundamental category of epigenetic modulators. Recent research has revealed that lncRNAs play critical roles in gene regulatory mechanisms, substantially influencing the pathogenesis of various human diseases. In this study, a multilayer heterogeneous network was created and we introduced the fast random walk with restart (FRWR) for predicting connections between lncRNAs and diseases. By combining the similarity network of lncRNA, similarity network of disease, and association network of existing lncRNA-disease, a multilayer heterogeneous network was constructed, and the fast random walk with restart method (FRWR) was applied on this network to predict additional potential lncRNA-disease associations. The AUROC value of 0.9034, achieved through leave-one-out cross-validation, underscored the predictive precision of the FRWR technique. Furthermore, a case study of three different diseases provided further validation of the reliability of prediction results. Overall, the multilayer network FRWR method proposed in this work could effectively forecasting the connections between lncRNAs and diseases, offering valuable insights into comprehending the functions of lncRNAs in the context of human health and disease. The source code for the FRWR method can be accessed at: https://github.com/TianTianTian14/FRWR.
{"title":"Disease-IncRNA associations prediction based on fast random walk with restart in heterogeneous networks","authors":"Jinlong Ma;Tian Qin","doi":"10.1109/TLA.2024.10669244","DOIUrl":"https://doi.org/10.1109/TLA.2024.10669244","url":null,"abstract":"Long non-coding RNAs (lncRNAs) represent a fundamental category of epigenetic modulators. Recent research has revealed that lncRNAs play critical roles in gene regulatory mechanisms, substantially influencing the pathogenesis of various human diseases. In this study, a multilayer heterogeneous network was created and we introduced the fast random walk with restart (FRWR) for predicting connections between lncRNAs and diseases. By combining the similarity network of lncRNA, similarity network of disease, and association network of existing lncRNA-disease, a multilayer heterogeneous network was constructed, and the fast random walk with restart method (FRWR) was applied on this network to predict additional potential lncRNA-disease associations. The AUROC value of 0.9034, achieved through leave-one-out cross-validation, underscored the predictive precision of the FRWR technique. Furthermore, a case study of three different diseases provided further validation of the reliability of prediction results. Overall, the multilayer network FRWR method proposed in this work could effectively forecasting the connections between lncRNAs and diseases, offering valuable insights into comprehending the functions of lncRNAs in the context of human health and disease. The source code for the FRWR method can be accessed at: https://github.com/TianTianTian14/FRWR.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 9","pages":"739-745"},"PeriodicalIF":1.3,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669244","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TLA.2024.10620392
Yago Ávila Moré;Basil Mohammed Al-Hadithi;Victor Cadix Martín
Modelling pedestrians and groups of people is a highly multidisciplinary technique, given the significant interest it attracts from various branches of science and engineering. This results in many different methodologies that may arise from diverse objectives. The model developed in this work is an agent-based model, in which pedestrian behaviour is defined by a set of forces. Each force models an aspect of pedestrian gait, with the objective of creating a virtual environment to train and test control systems for collaborative robots or autonomous vehicles. To meet the modelling requirements, the system employs various algorithms, such as "flocking", which simulates the coordination and formation of groups, "pathfinding", which enables agents to discover optimal routes within a given space, and algorithms specialized in avoiding walls and dynamic obstacles. These components collaborate to accurately depict how crowds move and react in different environments and situations. Thanks to the modularity of this approach, which facilitates the adjustment and expansion of the components, the developed system can be integrated into various applications, such as simulating non-playable characters (NPCs) in video games or modelling the evacuation of a building.
{"title":"Modelling pedestrian behaviour using swarm techniques","authors":"Yago Ávila Moré;Basil Mohammed Al-Hadithi;Victor Cadix Martín","doi":"10.1109/TLA.2024.10620392","DOIUrl":"10.1109/TLA.2024.10620392","url":null,"abstract":"Modelling pedestrians and groups of people is a highly multidisciplinary technique, given the significant interest it attracts from various branches of science and engineering. This results in many different methodologies that may arise from diverse objectives. The model developed in this work is an agent-based model, in which pedestrian behaviour is defined by a set of forces. Each force models an aspect of pedestrian gait, with the objective of creating a virtual environment to train and test control systems for collaborative robots or autonomous vehicles. To meet the modelling requirements, the system employs various algorithms, such as \"flocking\", which simulates the coordination and formation of groups, \"pathfinding\", which enables agents to discover optimal routes within a given space, and algorithms specialized in avoiding walls and dynamic obstacles. These components collaborate to accurately depict how crowds move and react in different environments and situations. Thanks to the modularity of this approach, which facilitates the adjustment and expansion of the components, the developed system can be integrated into various applications, such as simulating non-playable characters (NPCs) in video games or modelling the evacuation of a building.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 8","pages":"670-677"},"PeriodicalIF":1.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620392","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TLA.2024.10620391
Fernando Jorge Monteiro Dias;Paulo Eduardo Darski Rocha;Luiz Artur Pecorelli Peres;Sergio Escalante
This work investigates the performance of residential microgeneration photovoltaic PV systems connected to the electrical grid. It considers the overall available energy for powering households and charging electric vehicles (EVs). The conducted assessments elucidate the developed methodology and criteria for sizing PV panels, utilizing calculations derived from PV-SOL software. Analysis of atmospheric emissions indicates a reduction in greenhouse gases, notably fossil carbon dioxide (CO2). These assessments have been compared to internal combustion vehicle (ICV) calculations, expressed in the annual equivalent number of trees required to neutralize emissions. Results from Rio de Janeiro, with ample annual sunlight availability, show a positive energy supply balance for such installations. Combining PV power with EV charging is promising, assuming an average daily journey of 84 km and nighttime charging occurring approximately 4 hours after peak hours.
{"title":"Energetic and Environmental Benefits of Residential Solar Microgeneration Added to Electric Vehicle Recharging in the City of Rio de Janeiro","authors":"Fernando Jorge Monteiro Dias;Paulo Eduardo Darski Rocha;Luiz Artur Pecorelli Peres;Sergio Escalante","doi":"10.1109/TLA.2024.10620391","DOIUrl":"10.1109/TLA.2024.10620391","url":null,"abstract":"This work investigates the performance of residential microgeneration photovoltaic PV systems connected to the electrical grid. It considers the overall available energy for powering households and charging electric vehicles (EVs). The conducted assessments elucidate the developed methodology and criteria for sizing PV panels, utilizing calculations derived from PV-SOL software. Analysis of atmospheric emissions indicates a reduction in greenhouse gases, notably fossil carbon dioxide (CO2). These assessments have been compared to internal combustion vehicle (ICV) calculations, expressed in the annual equivalent number of trees required to neutralize emissions. Results from Rio de Janeiro, with ample annual sunlight availability, show a positive energy supply balance for such installations. Combining PV power with EV charging is promising, assuming an average daily journey of 84 km and nighttime charging occurring approximately 4 hours after peak hours.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 8","pages":"686-694"},"PeriodicalIF":1.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620391","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TLA.2024.10620386
Joao Vítor Arantes Cabral;Alberto José Álvares;Guilherme Caribé de Carvalho
Recent developments in the field of Additive Manufacturing have been improving the capabilities of the technique not only to be able to build complex geometry parts layer by layer with different materials, but also including the so-called Industry 4.0 technologies, namely Internet of Things (IoT), big data (BD) and Digital Twins (DT). The combination of these technologies with Additive Manufacturing allows online process monitoring and simulation, along with the cloud storage of the process and geometry data collected during the material deposition. The analysis of such data allows online and post-deposition identification of eventual process instabilities that can lead to quality problems. Considering the above-mentioned concepts, this work presents a DT architecture based on the ISO 23247-Digital Twin Framework for Manufacturing standard. In this sense, an approach of a Digital Twin framework for metal additive manufacturing process in a robotic cell composed of a robotic arm, positioning table and welding machine is presented and validated, focusing on the collection and cloud storage of both geometrical and process data along with near real-time process simulation.
{"title":"Digital Twin Implementation for an Additive Manufacturing Robotic Cell based on the ISO 23247 Standard","authors":"Joao Vítor Arantes Cabral;Alberto José Álvares;Guilherme Caribé de Carvalho","doi":"10.1109/TLA.2024.10620386","DOIUrl":"10.1109/TLA.2024.10620386","url":null,"abstract":"Recent developments in the field of Additive Manufacturing have been improving the capabilities of the technique not only to be able to build complex geometry parts layer by layer with different materials, but also including the so-called Industry 4.0 technologies, namely Internet of Things (IoT), big data (BD) and Digital Twins (DT). The combination of these technologies with Additive Manufacturing allows online process monitoring and simulation, along with the cloud storage of the process and geometry data collected during the material deposition. The analysis of such data allows online and post-deposition identification of eventual process instabilities that can lead to quality problems. Considering the above-mentioned concepts, this work presents a DT architecture based on the ISO 23247-Digital Twin Framework for Manufacturing standard. In this sense, an approach of a Digital Twin framework for metal additive manufacturing process in a robotic cell composed of a robotic arm, positioning table and welding machine is presented and validated, focusing on the collection and cloud storage of both geometrical and process data along with near real-time process simulation.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 8","pages":"651-658"},"PeriodicalIF":1.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620386","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TLA.2024.10620388
Xiaolong Jiang;Jiabao Fan;Jie Zhang;Ziyong Lin;Mingyong Li
Cross-modal hash retrieval has been widely applied due to its efficiency and low storage overhead. In the domain of supervised cross-modal hash retrieval, existing methods exhibit limitations in refining data features, leading to insufficiently detailed semantic information extraction and inaccurate reflection of data similarity. The challenge lies in utilizing multi-level deep semantic features of the data to generate more refined hash representations, thereby reducing the semantic gap and heterogeneity caused by different modalities. To address this challenging problem, we propose a multilevel deep semantic feature asymmetric network structure (MDSAN). Firstly, this architecture explores the multilevel deep features of the data, generating more accurate hash representations under richer supervised information guidance. Secondly, we investigate the preservation of asymmetric similarity within and between different modalities, allowing for a more comprehensive utilization of the multilevel deep features to bridge the gap among diverse modal data. Our network architecture effectively enhances model accuracy and robustness. Extensive experiments on three datasets validate the significant improvement advantages of the MDSAN model structure compared to current methods.
{"title":"Multilevel Deep Semantic Feature Asymmetric Network for Cross-Modal Hashing Retrieval","authors":"Xiaolong Jiang;Jiabao Fan;Jie Zhang;Ziyong Lin;Mingyong Li","doi":"10.1109/TLA.2024.10620388","DOIUrl":"10.1109/TLA.2024.10620388","url":null,"abstract":"Cross-modal hash retrieval has been widely applied due to its efficiency and low storage overhead. In the domain of supervised cross-modal hash retrieval, existing methods exhibit limitations in refining data features, leading to insufficiently detailed semantic information extraction and inaccurate reflection of data similarity. The challenge lies in utilizing multi-level deep semantic features of the data to generate more refined hash representations, thereby reducing the semantic gap and heterogeneity caused by different modalities. To address this challenging problem, we propose a multilevel deep semantic feature asymmetric network structure (MDSAN). Firstly, this architecture explores the multilevel deep features of the data, generating more accurate hash representations under richer supervised information guidance. Secondly, we investigate the preservation of asymmetric similarity within and between different modalities, allowing for a more comprehensive utilization of the multilevel deep features to bridge the gap among diverse modal data. Our network architecture effectively enhances model accuracy and robustness. Extensive experiments on three datasets validate the significant improvement advantages of the MDSAN model structure compared to current methods.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 8","pages":"621-631"},"PeriodicalIF":1.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620388","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TLA.2024.10620389
Gabriel Andrade Queiroz;Ederson Rosa da Silva
5G mobile communication systems have increasing demands related to Quality of Service (QoS) parameters integrated with high user densification in heterogeneous network scenarios. In this sense, 5G networks are expected to handle a wide range of applications and services. Therefore, scheduling algorithms that can benefit users of real-time (RT) and non-real-time (NRT) applications are studied. System-level simulations are carried out to analyze the performance of a new proposed Channel and Quality of Service Aware scheduler (CQAS) and compare it to Round Robin (RR), Best Channel Quality Indicator (CQI), and QoS Aware Scheduler (QAS) in a heterogeneous network with multiple traffic models while varying the number of users to stress test the network. The results show that CQAS has significant gains in overall throughput and latency while performing well in the reliability and fairness index.
{"title":"A new Channel and QoS Aware Scheduler algorithm for real time and non real time traffic in 5G heterogeneous networks","authors":"Gabriel Andrade Queiroz;Ederson Rosa da Silva","doi":"10.1109/TLA.2024.10620389","DOIUrl":"10.1109/TLA.2024.10620389","url":null,"abstract":"5G mobile communication systems have increasing demands related to Quality of Service (QoS) parameters integrated with high user densification in heterogeneous network scenarios. In this sense, 5G networks are expected to handle a wide range of applications and services. Therefore, scheduling algorithms that can benefit users of real-time (RT) and non-real-time (NRT) applications are studied. System-level simulations are carried out to analyze the performance of a new proposed Channel and Quality of Service Aware scheduler (CQAS) and compare it to Round Robin (RR), Best Channel Quality Indicator (CQI), and QoS Aware Scheduler (QAS) in a heterogeneous network with multiple traffic models while varying the number of users to stress test the network. The results show that CQAS has significant gains in overall throughput and latency while performing well in the reliability and fairness index.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 8","pages":"659-669"},"PeriodicalIF":1.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：