首页 > 最新文献

2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)最新文献

英文 中文
Design of Improved Content Addressable Memory Using QCA Technology 基于QCA技术的改进型内容可寻址存储器设计
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149853
Sujatha Kotte, Ganapavarapu Kanaka Durga
Data stored at various memory locations of the memory can be accessed by using different searching algorithms. Conventionally, random access memory (RAM) the address-based memory detection method has been used in many computational systems. A new content addressable memory (CAM) cell is proposed in this paper. The proposed memory cell is designed using the QCA technology the three-input majority gate and five-input minority gates are used in the design. QCA designer tool is used for the simulations and its functionality is also verified using this tool. Additionally, performance comparison of proposed CAM cell is performed by considering the parameters like power, area and clock latency. It has been observed that the proposed CAM cell is more robust and less sensitive to temperature variations compare to existing structures.
存储在存储器的不同存储位置的数据可以通过使用不同的搜索算法来访问。传统上,基于地址的随机存取存储器(RAM)检测方法已被应用于许多计算系统中。提出了一种新的内容可寻址存储器(CAM)单元。该存储单元采用QCA技术设计,采用三输入多数门和五输入少数门。QCA设计工具用于仿真,并使用该工具验证了其功能。此外,通过考虑功耗、面积和时钟延迟等参数,对所提出的CAM单元进行了性能比较。已经观察到,与现有结构相比,所提出的CAM细胞更坚固,对温度变化的敏感性更低。
{"title":"Design of Improved Content Addressable Memory Using QCA Technology","authors":"Sujatha Kotte, Ganapavarapu Kanaka Durga","doi":"10.1109/ESDC56251.2023.10149853","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149853","url":null,"abstract":"Data stored at various memory locations of the memory can be accessed by using different searching algorithms. Conventionally, random access memory (RAM) the address-based memory detection method has been used in many computational systems. A new content addressable memory (CAM) cell is proposed in this paper. The proposed memory cell is designed using the QCA technology the three-input majority gate and five-input minority gates are used in the design. QCA designer tool is used for the simulations and its functionality is also verified using this tool. Additionally, performance comparison of proposed CAM cell is performed by considering the parameters like power, area and clock latency. It has been observed that the proposed CAM cell is more robust and less sensitive to temperature variations compare to existing structures.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125525725","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}
引用次数: 0
Design and FPGA Implementation of an Efficient Architecture for Noise Removal in ECG Signals Using Lifting-Based Wavelet Denoising 基于提升小波去噪的心电信号高效去噪架构设计与FPGA实现
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149865
Anusaka Gon, Atin Mukherjee
Noise removal is the most crucial pre-processing step for present-generation biomedical wearable electrocardiogram (ECG) patches and devices to provide efficient detection and monitoring of cardiac arrhythmias. This paper proposes a hardware-efficient and multiplier-less FPGA-based ECG noise removal architecture based on lifting-based wavelet denoising that employs a universal threshold level-dependent function in combination with soft thresholding to produce a noise-free ECG signal. The paper also proposes a modified lifting-based discrete wavelet transform (DWT) algorithm that is multiplier-less and provides a one-step equation for the calculation of the forward output coefficients and the inverse output coefficients. Since a comparator circuit is a very complicated circuitry in VLSI implementation, an optimized median calculation and soft thresholding block with no compare operations for wavelet-based thresholding is proposed. The ECG data is collected from the MIT-BIH arrhythmia database and the ECG noises from the MIT-BIH noise stress database. The proposed denoising technique for the ECG signal is tested on MATLAB which achieves an average improvement in SNR of 7.4 dB and an MSE of 0.0206. The FPGA implementation is performed on the Nexys 4 DDR board, and the proposed wavelet-based denoising architecture results in lower hardware utilization and a relatively high operating frequency of 166 MHz when compared to existing ECG denoising architectures.
噪声去除是当前生物医学可穿戴心电图贴片和设备最关键的预处理步骤,以提供有效的心律失常检测和监测。本文提出了一种基于提升小波去噪的基于fpga的心电降噪架构,该架构采用通用阈值水平相关函数与软阈值相结合来产生无噪声的心电信号。本文还提出了一种改进的基于提升的离散小波变换(DWT)算法,该算法是无乘子的,并提供了计算正向输出系数和逆向输出系数的一步式。由于比较器电路在VLSI实现中是一个非常复杂的电路,提出了一种优化的中值计算和不需要比较操作的软阈值块用于基于小波的阈值分割。心电数据采集自MIT-BIH心律失常数据库,心电噪声采集自MIT-BIH噪声应激数据库。在MATLAB上对所提出的心电信号去噪技术进行了测试,平均信噪比提高了7.4 dB, MSE提高了0.0206。FPGA在Nexys 4 DDR板上实现,与现有的心电去噪架构相比,所提出的基于小波的去噪架构具有较低的硬件利用率和相对较高的166 MHz工作频率。
{"title":"Design and FPGA Implementation of an Efficient Architecture for Noise Removal in ECG Signals Using Lifting-Based Wavelet Denoising","authors":"Anusaka Gon, Atin Mukherjee","doi":"10.1109/ESDC56251.2023.10149865","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149865","url":null,"abstract":"Noise removal is the most crucial pre-processing step for present-generation biomedical wearable electrocardiogram (ECG) patches and devices to provide efficient detection and monitoring of cardiac arrhythmias. This paper proposes a hardware-efficient and multiplier-less FPGA-based ECG noise removal architecture based on lifting-based wavelet denoising that employs a universal threshold level-dependent function in combination with soft thresholding to produce a noise-free ECG signal. The paper also proposes a modified lifting-based discrete wavelet transform (DWT) algorithm that is multiplier-less and provides a one-step equation for the calculation of the forward output coefficients and the inverse output coefficients. Since a comparator circuit is a very complicated circuitry in VLSI implementation, an optimized median calculation and soft thresholding block with no compare operations for wavelet-based thresholding is proposed. The ECG data is collected from the MIT-BIH arrhythmia database and the ECG noises from the MIT-BIH noise stress database. The proposed denoising technique for the ECG signal is tested on MATLAB which achieves an average improvement in SNR of 7.4 dB and an MSE of 0.0206. The FPGA implementation is performed on the Nexys 4 DDR board, and the proposed wavelet-based denoising architecture results in lower hardware utilization and a relatively high operating frequency of 166 MHz when compared to existing ECG denoising architectures.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126623216","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}
引用次数: 0
Substrate Noise Evaluation and Reduction of N-MOSFET Using Optimized Silicone-On-Insulator based on Seagull optimization algorithm 基于海鸥优化算法的N-MOSFET衬底噪声评价与降低
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149882
Sanjay Sharma, R. P. Yadav, V. Janyani
Silicone-on-Insulator (SOI) chips contains numerous single-transistor islands that are dielectrically isolated on the silicon substrate. Leakage currents, radiation-induced photocurrents, latch-up effects and other parasitic effects caused by the huge substrate are initially protected from the thin active silicon layer by the vertical isolation. Correspondingly, the SOI eliminates the need for intricate trench or well creation techniques providing inter device separation. VLSI chips are more compact that results extreme simplification and circuit design. Although the SOI-MOSFET is developed to overcome these restrictions, additional problems are also generated such as kink effect in the I-V characteristics. To address the kink effect issue, the ideally selective buried oxide (SELBOX) MOSFET is developed. In this model, the fully depleted SOI-MOSFET is designed based on the n-MOSFET silicone substrate with optimally selected Buried Oxide (BOX) layer using the seagull optimization algorithm based on the capacitance of the material for reducing the substrate leakage current. Then, the gate oxide insulator, the bi-layer high k-dielectric materials such as Al203 and Si3N4 are used. For evaluating the designed model, the noise is manually injected into the MOSFET based on the noise models in TCAD. The drain current characteristic and transfer characteristics of the SOI-MOSFET are experimentally analysed. In this analysis, the noise affected MOSFET produces drain current of 1.4μA for 3v (Vds) and the noise reduced SOI-MOSFET produces 1.78μA for 3v (Vds). Thus, the designed fully depleted SOI-MOSFET model performs better by reducing the substrate noise.
硅绝缘体(SOI)芯片包含许多在硅衬底上介质隔离的单晶体管岛。由巨大衬底引起的泄漏电流、辐射诱导光电流、锁存效应和其他寄生效应最初通过垂直隔离保护薄有源硅层。相应地,SOI消除了复杂的沟槽或造井技术的需要,提供了设备间的分离。VLSI芯片更紧凑,从而极大地简化了电路设计。尽管SOI-MOSFET是为了克服这些限制而开发的,但也产生了额外的问题,例如I-V特性中的扭结效应。为了解决扭结效应问题,开发了理想的选择性埋藏氧化物(SELBOX) MOSFET。在该模型中,基于n-MOSFET硅基板设计了全耗尽SOI-MOSFET,并采用基于材料电容的海鸥优化算法优化选择了埋藏氧化物(BOX)层,以减小衬底泄漏电流。然后,采用栅极氧化物绝缘子、双层高k介电材料Al203和Si3N4。为了评估设计的模型,基于TCAD中的噪声模型,人工将噪声注入到MOSFET中。实验分析了SOI-MOSFET的漏极电流特性和转移特性。在本分析中,噪声影响的MOSFET在3v (Vds)时产生1.4μA的漏极电流,而噪声降低的SOI-MOSFET在3v (Vds)时产生1.78μA的漏极电流。因此,设计的完全耗尽SOI-MOSFET模型通过降低衬底噪声而具有更好的性能。
{"title":"Substrate Noise Evaluation and Reduction of N-MOSFET Using Optimized Silicone-On-Insulator based on Seagull optimization algorithm","authors":"Sanjay Sharma, R. P. Yadav, V. Janyani","doi":"10.1109/ESDC56251.2023.10149882","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149882","url":null,"abstract":"Silicone-on-Insulator (SOI) chips contains numerous single-transistor islands that are dielectrically isolated on the silicon substrate. Leakage currents, radiation-induced photocurrents, latch-up effects and other parasitic effects caused by the huge substrate are initially protected from the thin active silicon layer by the vertical isolation. Correspondingly, the SOI eliminates the need for intricate trench or well creation techniques providing inter device separation. VLSI chips are more compact that results extreme simplification and circuit design. Although the SOI-MOSFET is developed to overcome these restrictions, additional problems are also generated such as kink effect in the I-V characteristics. To address the kink effect issue, the ideally selective buried oxide (SELBOX) MOSFET is developed. In this model, the fully depleted SOI-MOSFET is designed based on the n-MOSFET silicone substrate with optimally selected Buried Oxide (BOX) layer using the seagull optimization algorithm based on the capacitance of the material for reducing the substrate leakage current. Then, the gate oxide insulator, the bi-layer high k-dielectric materials such as Al203 and Si3N4 are used. For evaluating the designed model, the noise is manually injected into the MOSFET based on the noise models in TCAD. The drain current characteristic and transfer characteristics of the SOI-MOSFET are experimentally analysed. In this analysis, the noise affected MOSFET produces drain current of 1.4μA for 3v (Vds) and the noise reduced SOI-MOSFET produces 1.78μA for 3v (Vds). Thus, the designed fully depleted SOI-MOSFET model performs better by reducing the substrate noise.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116395437","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}
引用次数: 0
Detection of Multi-varieties of On-tree Mangoes using MangoYOLO5 利用MangoYOLO5检测多品种树上芒果
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149849
Hari Chandana Pichhika, P. Subudhi
Automated harvesting and detection of fruits are crucial for agronomic applications like estimation and mapping of yield. Earlier, fruit detection methods were mostly dependent on hand-crafted features and were prone to changes in the actual orchard environment. However, recently deep learning-based methods especially one-stage object detection techniques like YOLO has achieved a higher detection accuracy to detect different fruits including mango in on-tree orchard images. In our previous work, we proposed a lightweight YOLOv5 model named "MangoYOLO5" for the detection of mangoes, and we have achieved an accuracy of 94.4% on one variety. Now, we have created a dataset of seven varieties of on-tree mangoes, with four varieties being publicly available, and the other three varieties from a local mango orchard using a UAV. We have tried detecting these seven varieties using the MangoYOLO5 model and achieved an average accuracy of 92%. It shows that the mango detection performance is 3.4% better than the YOLOv5s, taking into several characteristics like occlusion, distance, and lighting conditions. Additionally, compared to the original YOLOv5s, the achieved lighter model requires 55.55% less training time, which can significantly affect on real-time implementations.
水果的自动收获和检测对于估计和绘制产量图等农艺应用至关重要。在此之前,水果检测方法大多依赖于手工制作的特征,并且容易在实际果园环境中发生变化。然而,近年来基于深度学习的方法,特别是像YOLO这样的单阶段目标检测技术,在检测果树图像中包括芒果在内的不同水果方面取得了更高的检测精度。在我们之前的工作中,我们提出了一个轻量级的YOLOv5模型,命名为“MangoYOLO5”,用于芒果的检测,我们在一个品种上达到了94.4%的准确率。现在,我们已经创建了一个7种芒果的数据集,其中4个品种是公开的,另外3个品种来自当地的一个芒果果园,使用无人机。我们尝试使用MangoYOLO5模型对这7个品种进行检测,平均准确率达到92%。研究表明,考虑到遮挡、距离和光照条件等几个特征,芒果的检测性能比YOLOv5s提高了3.4%。此外,与最初的yolov5相比,获得的更轻的模型所需的训练时间减少了55.55%,这可以显著影响实时实现。
{"title":"Detection of Multi-varieties of On-tree Mangoes using MangoYOLO5","authors":"Hari Chandana Pichhika, P. Subudhi","doi":"10.1109/ESDC56251.2023.10149849","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149849","url":null,"abstract":"Automated harvesting and detection of fruits are crucial for agronomic applications like estimation and mapping of yield. Earlier, fruit detection methods were mostly dependent on hand-crafted features and were prone to changes in the actual orchard environment. However, recently deep learning-based methods especially one-stage object detection techniques like YOLO has achieved a higher detection accuracy to detect different fruits including mango in on-tree orchard images. In our previous work, we proposed a lightweight YOLOv5 model named \"MangoYOLO5\" for the detection of mangoes, and we have achieved an accuracy of 94.4% on one variety. Now, we have created a dataset of seven varieties of on-tree mangoes, with four varieties being publicly available, and the other three varieties from a local mango orchard using a UAV. We have tried detecting these seven varieties using the MangoYOLO5 model and achieved an average accuracy of 92%. It shows that the mango detection performance is 3.4% better than the YOLOv5s, taking into several characteristics like occlusion, distance, and lighting conditions. Additionally, compared to the original YOLOv5s, the achieved lighter model requires 55.55% less training time, which can significantly affect on real-time implementations.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123910599","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}
引用次数: 0
Ground Robots for Disaster Response: A Review 地面机器人灾害响应:综述
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149862
R. Mathew, Pratik Jagtap, Kingshuk Mitra
Because of human activity, the number of disasters in the world is rising daily. and other environmental factors. A total of 327 disaster events were recorded in 2016 out of these 136 were man-made and 191 were natural disasters, the former accounted for $8 billion in losses and the latter$46 billion. As of July 2020, the number of natural disasters has gone up to 207 and 118 man-made disasters. These numbers are proof that there is a need to find better ways to combat disaster incidents, the limitations to the extent of rescue tasks that can be performed by humans calls for the use of robotic technologies in this field. While several robots such as The BigDog, Thermite 3.0 and Parosha Cheetah GOSAFER are being used presently, there is still some uncertainty about completely relying on them. Furthermore, the paper talks about issues faced while using these robots and how advancements in newer robots such as the Centauro Robot, RoboSimian, Octopus Robot and ATLAS Robot have helped overcome these problems, making use of robots and robotic technologies more effective and efficient and in turn integrating robots with disaster response tasks even better. Based on the mechanism and methods used for their functioning and operation, the mentioned robots have been discussed.
由于人类活动,世界上的灾害数量每天都在增加。以及其他环境因素。2016年共发生327起灾害事件,其中136起人为灾害,191起自然灾害,人为灾害造成的损失为80亿美元,自然灾害造成的损失为460亿美元。截至2020年7月,自然灾害增加到207起,人为灾害增加到118起。这些数字证明,有必要找到更好的方法来应对灾害事件,人类可以执行的救援任务的范围有限,这要求在这一领域使用机器人技术。虽然目前有几个机器人,如The BigDog, Thermite 3.0和parasha Cheetah GOSAFER正在使用,但完全依赖它们仍然存在一些不确定性。此外,本文还讨论了使用这些机器人时面临的问题,以及诸如半人马座机器人、RoboSimian、章鱼机器人和ATLAS机器人等新机器人的进步如何帮助克服这些问题,使机器人和机器人技术的使用更加有效和高效,从而更好地将机器人与灾难响应任务相结合。基于其功能和操作的机制和方法,讨论了上述机器人。
{"title":"Ground Robots for Disaster Response: A Review","authors":"R. Mathew, Pratik Jagtap, Kingshuk Mitra","doi":"10.1109/ESDC56251.2023.10149862","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149862","url":null,"abstract":"Because of human activity, the number of disasters in the world is rising daily. and other environmental factors. A total of 327 disaster events were recorded in 2016 out of these 136 were man-made and 191 were natural disasters, the former accounted for $8 billion in losses and the latter$46 billion. As of July 2020, the number of natural disasters has gone up to 207 and 118 man-made disasters. These numbers are proof that there is a need to find better ways to combat disaster incidents, the limitations to the extent of rescue tasks that can be performed by humans calls for the use of robotic technologies in this field. While several robots such as The BigDog, Thermite 3.0 and Parosha Cheetah GOSAFER are being used presently, there is still some uncertainty about completely relying on them. Furthermore, the paper talks about issues faced while using these robots and how advancements in newer robots such as the Centauro Robot, RoboSimian, Octopus Robot and ATLAS Robot have helped overcome these problems, making use of robots and robotic technologies more effective and efficient and in turn integrating robots with disaster response tasks even better. Based on the mechanism and methods used for their functioning and operation, the mentioned robots have been discussed.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124863558","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}
引用次数: 0
Underwater Object Detection Using Synthetic Data 基于合成数据的水下目标检测
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149870
Nitish Reddy Nandyala, Rakesh Kumar Sanodiya
The ability to detect life in challenging underwater environments holds the potential to preserve many aquatic species and coral reefs. Recent object detection research has witnessed a remarkable upsurge in natural images but not in Underwater, due to the imbalanced lighting, inadequate contrast, frequent occlusions, and the mimicry displayed by aquatic life forms. The assessment of object recognition models utilized in various contexts has augmented the need for annotated datasets. Due to the labor-intensive nature of generating these datasets, we have opted to undertake training using synthetic images as an alternative. In this study, we train the cutting-edge YOLO object detection system on a synthetic underwater dataset, with the aim of achieving category-agnostic object detection and then evaluated through practical assessments conducted on real underwater images. In addition, we provide benchmarking results for different YOLO versions in this work, assessing their performance on both real-world and synthetic datasets. Our investigation reveal that YOLOv5 shines in its ability to perform on synthetic data, whereas the latest YOLOv8, excels in real data domains, outpacing other two models tested. These findings have far reaching implications for the design and development of object detection in underwater environments.
在具有挑战性的水下环境中探测生命的能力有可能保护许多水生物种和珊瑚礁。近年来,由于光线不平衡、对比度不足、频繁遮挡以及水生生物形式的模仿,自然图像的目标检测研究出现了显著的增长,但水下图像的目标检测研究却没有取得显著进展。在各种环境中使用的对象识别模型的评估增加了对注释数据集的需求。由于生成这些数据集的劳动密集型性质,我们选择使用合成图像作为替代方法进行训练。在本研究中,我们在一个合成的水下数据集上训练前沿的YOLO目标检测系统,目的是实现与类别无关的目标检测,然后通过对真实水下图像进行实际评估来进行评估。此外,我们在这项工作中提供了不同YOLO版本的基准测试结果,评估了它们在真实世界和合成数据集上的性能。我们的调查显示,YOLOv5在处理合成数据方面表现出色,而最新的YOLOv8在实际数据领域表现出色,超过了测试的其他两种模型。这些发现对水下环境中目标探测的设计和发展具有深远的意义。
{"title":"Underwater Object Detection Using Synthetic Data","authors":"Nitish Reddy Nandyala, Rakesh Kumar Sanodiya","doi":"10.1109/ESDC56251.2023.10149870","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149870","url":null,"abstract":"The ability to detect life in challenging underwater environments holds the potential to preserve many aquatic species and coral reefs. Recent object detection research has witnessed a remarkable upsurge in natural images but not in Underwater, due to the imbalanced lighting, inadequate contrast, frequent occlusions, and the mimicry displayed by aquatic life forms. The assessment of object recognition models utilized in various contexts has augmented the need for annotated datasets. Due to the labor-intensive nature of generating these datasets, we have opted to undertake training using synthetic images as an alternative. In this study, we train the cutting-edge YOLO object detection system on a synthetic underwater dataset, with the aim of achieving category-agnostic object detection and then evaluated through practical assessments conducted on real underwater images. In addition, we provide benchmarking results for different YOLO versions in this work, assessing their performance on both real-world and synthetic datasets. Our investigation reveal that YOLOv5 shines in its ability to perform on synthetic data, whereas the latest YOLOv8, excels in real data domains, outpacing other two models tested. These findings have far reaching implications for the design and development of object detection in underwater environments.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127927047","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}
引用次数: 0
Investigation of RF-based networking for underwater wireless sensor networks using dynamic cluster head selection strategy 基于动态簇头选择策略的水下无线传感器网络射频组网研究
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149879
Pavan Ganesh Pss, Nujeti Lavanya
Communication between two underwater wireless nodes or two underwater vehicles is possible with RF communication, provided the aspects of low transmission distance and high attenuation are taken care of in the communication system design. Notably, a cluster-based communication architecture is better suited than direct communication architecture when an RF signal is considered. This paper presents a cluster-based two-hop communication mechanism between two underwater nodes or two underwater vehicles. Particularly, a novel dynamic cluster head selection mechanism based on the unused energy and distance from cluster head to buoy has been proposed. This mechanism ensures uniform power consumption among all the underwater nodes or vehicles in a cluster. Moreover, it eliminates the necessity for a dedicated cluster head. The network performance using the proposed model has been analyzed in terms of the total network’s life and the time after which a node dies first in the network. The results have been compared with the existing communication mechanisms like communication via a fixed cluster head and direct communication.
在通信系统设计中考虑到低传输距离和高衰减的情况下,两个水下无线节点或两个水下航行器之间可以通过射频通信进行通信。值得注意的是,当考虑射频信号时,基于集群的通信体系结构比直接通信体系结构更适合。提出了一种基于集群的水下节点或水下航行器间的两跳通信机制。特别提出了一种基于未使用能量和簇头到浮标距离的簇头动态选择机制。这种机制确保了集群中所有水下节点或车辆的功耗均匀。此外,它消除了专用集群头的必要性。使用该模型对网络性能进行了分析,分析了网络的总寿命和网络中节点首先死亡的时间。结果与现有的通信机制如通过固定簇头通信和直接通信进行了比较。
{"title":"Investigation of RF-based networking for underwater wireless sensor networks using dynamic cluster head selection strategy","authors":"Pavan Ganesh Pss, Nujeti Lavanya","doi":"10.1109/ESDC56251.2023.10149879","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149879","url":null,"abstract":"Communication between two underwater wireless nodes or two underwater vehicles is possible with RF communication, provided the aspects of low transmission distance and high attenuation are taken care of in the communication system design. Notably, a cluster-based communication architecture is better suited than direct communication architecture when an RF signal is considered. This paper presents a cluster-based two-hop communication mechanism between two underwater nodes or two underwater vehicles. Particularly, a novel dynamic cluster head selection mechanism based on the unused energy and distance from cluster head to buoy has been proposed. This mechanism ensures uniform power consumption among all the underwater nodes or vehicles in a cluster. Moreover, it eliminates the necessity for a dedicated cluster head. The network performance using the proposed model has been analyzed in terms of the total network’s life and the time after which a node dies first in the network. The results have been compared with the existing communication mechanisms like communication via a fixed cluster head and direct communication.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"400 5-6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114016266","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}
引用次数: 0
A novel Optimization technique in 5G based IoVs using hybrid Fuzzy Weight-NSGA Scheme 基于混合模糊权重- nsga方案的5G车联网优化新技术
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149880
Satyabrata Sahoo, S. Sahoo, R. C. Barik, M. R. Kabat
With the advancement of 5G based Internet-of-Vehicles (IoVs) networks, to inculcate the current demand in resource sharing among connected devices require Quality of Services (QoS) in data traffics, link capacity and coverage. In this paper we address the multi-objective resource optimization problem in Software-Defined-Network of 5G enabled IoV. A novel technique is proposed as hybrid Fuzzy Weight-NSGA to incorporate optimization of three diversified cost objective functions as connections and the end-to-end delays. The empirical simulation proposed FW-NSGA outperforms with respect to optimization of connections among existing literatures.
随着基于5G的车联网(iot)网络的发展,要满足当前连接设备之间资源共享的需求,需要在数据流量、链路容量和覆盖范围方面提供服务质量(QoS)。本文研究了基于5G的车联网软件定义网络中的多目标资源优化问题。提出了一种混合模糊权重-非遗传算法,将三个不同的代价目标函数作为连接和端到端延迟进行优化。经验模拟提出的FW-NSGA在现有文献之间的连接优化方面表现优异。
{"title":"A novel Optimization technique in 5G based IoVs using hybrid Fuzzy Weight-NSGA Scheme","authors":"Satyabrata Sahoo, S. Sahoo, R. C. Barik, M. R. Kabat","doi":"10.1109/ESDC56251.2023.10149880","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149880","url":null,"abstract":"With the advancement of 5G based Internet-of-Vehicles (IoVs) networks, to inculcate the current demand in resource sharing among connected devices require Quality of Services (QoS) in data traffics, link capacity and coverage. In this paper we address the multi-objective resource optimization problem in Software-Defined-Network of 5G enabled IoV. A novel technique is proposed as hybrid Fuzzy Weight-NSGA to incorporate optimization of three diversified cost objective functions as connections and the end-to-end delays. The empirical simulation proposed FW-NSGA outperforms with respect to optimization of connections among existing literatures.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127195926","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}
引用次数: 0
High Resolution DOA Estimation of Narrowband Signal for MUSIC, MVDR and Beamscan Algorithm 基于MUSIC、MVDR和波束扫描算法的窄带信号高分辨率DOA估计
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149863
Meenal Job, Ram Suchit Yadav
This paper presents the in-depth understanding for the direction of arrival (DOA) estimate technique. Here, we have considered three DOA algorithm, i.e., Beamscan, Minimum Variance Distortionless Response (MVDR), Multiple Signal Classification (MUSIC), which are used to estimate broadside angle with Uniform Linear Array (ULA) (10 isotropic antennas) and azimuth and elevation angles with Uniform Rectangular Array (URA) (16x16). Simulation is carried out by considering narrowband signal impinge on the array. Operating frequency of the system is 300MHz. DOA is estimated from the peaks of output signal. For different arriving signal, Beamscan technique forms a conventional beam and scan it over direction of interest to get the spatial spectrum. When signals come from directions that are closer than the beamwidth, then beam scanning is unable to resolve the signals. MVDR beam is examine over the specified region. It has smaller band-widths so has higher resolution. MVDR correctly estimates the DOAs of the signal. It is sensitive to position error so under such situation MUSIC provides accurate DOA estimation and better spatial resolution. Study is carried out in 2-D for the estimation of azimuth and elevation angle of URA. It uses the same algorithm as in 1-D. Simulation is carried out in Matrix laboratory (MATLAB) R2020 Version.
本文对到达方向(DOA)估计技术进行了深入的了解。在这里,我们考虑了三种DOA算法,即波束扫描,最小方差无失真响应(MVDR),多信号分类(MUSIC),它们用于估计均匀线性阵列(ULA)(10个各向同性天线)的宽侧角和均匀矩形阵列(URA) (16 × 16)的方位角和仰角。考虑了窄带信号对阵列的冲击,进行了仿真。系统工作频率为300MHz。从输出信号的峰值估计DOA。对于不同的到达信号,波束扫描技术形成一个常规波束,在目标方向上进行扫描,得到空间频谱。当信号来自比波束宽度更近的方向时,波束扫描无法解析信号。在指定区域上检查MVDR波束。它具有更小的带宽,因此具有更高的分辨率。MVDR可以正确估计信号的doa。在这种情况下,MUSIC对位置误差很敏感,可以提供准确的DOA估计和更好的空间分辨率。在二维空间中进行了URA方位角和仰角估计的研究。它使用与一维相同的算法。仿真在Matrix laboratory (MATLAB) R2020 Version中进行。
{"title":"High Resolution DOA Estimation of Narrowband Signal for MUSIC, MVDR and Beamscan Algorithm","authors":"Meenal Job, Ram Suchit Yadav","doi":"10.1109/ESDC56251.2023.10149863","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149863","url":null,"abstract":"This paper presents the in-depth understanding for the direction of arrival (DOA) estimate technique. Here, we have considered three DOA algorithm, i.e., Beamscan, Minimum Variance Distortionless Response (MVDR), Multiple Signal Classification (MUSIC), which are used to estimate broadside angle with Uniform Linear Array (ULA) (10 isotropic antennas) and azimuth and elevation angles with Uniform Rectangular Array (URA) (16x16). Simulation is carried out by considering narrowband signal impinge on the array. Operating frequency of the system is 300MHz. DOA is estimated from the peaks of output signal. For different arriving signal, Beamscan technique forms a conventional beam and scan it over direction of interest to get the spatial spectrum. When signals come from directions that are closer than the beamwidth, then beam scanning is unable to resolve the signals. MVDR beam is examine over the specified region. It has smaller band-widths so has higher resolution. MVDR correctly estimates the DOAs of the signal. It is sensitive to position error so under such situation MUSIC provides accurate DOA estimation and better spatial resolution. Study is carried out in 2-D for the estimation of azimuth and elevation angle of URA. It uses the same algorithm as in 1-D. Simulation is carried out in Matrix laboratory (MATLAB) R2020 Version.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128224975","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}
引用次数: 0
Scalp EEG-based Classification of Disorder of Consciousness States using Machine Learning Techniques 基于头皮脑电图的意识状态障碍的机器学习分类
Pub Date : 2023-05-04 DOI: 10.1109/ESDC56251.2023.10149867
Sreelakshmi Raveendran, Santhos A. Kumar, Raghavendra Kenchiah, Farsana M K, Ravindranath Choudary, S. Bansal, B. S, A. G. Ramakrishnan, S. R, Kala S
Disorders of consciousness (DOC) described by impaired wakefulness and awareness, can be categorized into Coma, Unresponsive Wakefulness Syndrome (UWS), and Minimally Conscious State (MCS). Resting-state EEG-based differentiation of these classes acts as a helping hand or even more to the conventional behavioral assessment methods in the diagnosis and prognosis of DOC patients. In this paper, multi-class classification of DOC patients using different machine learning models was performed and the results were analyzed using features like sample entropy, permutation entropy, and absolute and relative power extracted from resting state EEG data. The one-way ANOVA method determined the discriminative ability of the features with a post hoc Least Significant Difference (LSD) test. All four features showed significant differences (p < 0.05) in delta, alpha, and beta bands between the groups. The feature significance was also measured across the different brain regions as well. The classification results showed that the Random Forest classifier best classified the group with an accuracy of 78% and a precision of 88%.
意识障碍(DOC)由觉醒和意识受损所描述,可分为昏迷、无反应觉醒综合征(UWS)和最低意识状态(MCS)。基于静息状态脑电图的这些分类对DOC患者的诊断和预后的常规行为评估方法起到了帮助甚至更多的作用。本文采用不同的机器学习模型对DOC患者进行多类分类,并利用静息状态脑电图数据提取的样本熵、排列熵、绝对功率和相对功率等特征对分类结果进行分析。单因素方差分析方法通过事后最小显著性差异(LSD)检验确定特征的判别能力。各组间δ、α、β波段均有显著性差异(p < 0.05)。在不同的大脑区域也测量了特征的重要性。分类结果表明,Random Forest分类器对该组的分类准确率为78%,精密度为88%。
{"title":"Scalp EEG-based Classification of Disorder of Consciousness States using Machine Learning Techniques","authors":"Sreelakshmi Raveendran, Santhos A. Kumar, Raghavendra Kenchiah, Farsana M K, Ravindranath Choudary, S. Bansal, B. S, A. G. Ramakrishnan, S. R, Kala S","doi":"10.1109/ESDC56251.2023.10149867","DOIUrl":"https://doi.org/10.1109/ESDC56251.2023.10149867","url":null,"abstract":"Disorders of consciousness (DOC) described by impaired wakefulness and awareness, can be categorized into Coma, Unresponsive Wakefulness Syndrome (UWS), and Minimally Conscious State (MCS). Resting-state EEG-based differentiation of these classes acts as a helping hand or even more to the conventional behavioral assessment methods in the diagnosis and prognosis of DOC patients. In this paper, multi-class classification of DOC patients using different machine learning models was performed and the results were analyzed using features like sample entropy, permutation entropy, and absolute and relative power extracted from resting state EEG data. The one-way ANOVA method determined the discriminative ability of the features with a post hoc Least Significant Difference (LSD) test. All four features showed significant differences (p < 0.05) in delta, alpha, and beta bands between the groups. The feature significance was also measured across the different brain regions as well. The classification results showed that the Random Forest classifier best classified the group with an accuracy of 78% and a precision of 88%.","PeriodicalId":354855,"journal":{"name":"2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114161501","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}
引用次数: 0
期刊
2023 11th International Symposium on Electronic Systems Devices and Computing (ESDC)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1