The swift advancement of quantum computing devices holds the potential to create robust machines that can tackle an extensive array of issues beyond the scope of conventional computers. Consequently, quantum computing machines create new risks at a velocity and scale never seen before, especially with regard to encryption. Lattice-based cryptography is regarded as post-quantum cryptography’s future and a competitor to a quantum computer attack. Thus, there are several advantages to lattice-based cryptographic protocols, including security, effectiveness, reduced energy usage and speed. In this work, we study the learning with errors (LWE) problem and the cryptosystems that are based on the LWE problem and, in addition, we present a new efficient variant of LWE cryptographic scheme.
{"title":"Learning with Errors: A Lattice-Based Keystone of Post-Quantum Cryptography","authors":"Maria E. Sabani, I. Savvas, Georgia Garani","doi":"10.3390/signals5020012","DOIUrl":"https://doi.org/10.3390/signals5020012","url":null,"abstract":"The swift advancement of quantum computing devices holds the potential to create robust machines that can tackle an extensive array of issues beyond the scope of conventional computers. Consequently, quantum computing machines create new risks at a velocity and scale never seen before, especially with regard to encryption. Lattice-based cryptography is regarded as post-quantum cryptography’s future and a competitor to a quantum computer attack. Thus, there are several advantages to lattice-based cryptographic protocols, including security, effectiveness, reduced energy usage and speed. In this work, we study the learning with errors (LWE) problem and the cryptosystems that are based on the LWE problem and, in addition, we present a new efficient variant of LWE cryptographic scheme.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"36 144","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140708155","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}
Dynamic mode decomposition (DMD) is a powerful tool for separating the background and foreground in videos. This algorithm decomposes a video into dynamic modes, called DMD modes, to facilitate the extraction of the near-zero mode, which represents the stationary background. Simultaneously, it captures the evolving motion in the remaining modes, which correspond to the moving foreground components. However, when applied to noisy video, this separation leads to degradation of the background and foreground components, primarily due to the noise-induced degradation of the DMD mode. This paper introduces a novel noise removal method for the DMD mode in noisy videos. Specifically, we formulate a minimization problem that reduces the noise in the DMD mode and the reconstructed video. The proposed problem is solved using an algorithm based on the plug-and-play alternating direction method of multipliers (PnP-ADMM). We applied the proposed method to several video datasets with different levels of artificially added Gaussian noise in the experiment. Our method consistently yielded superior results in quantitative evaluations using peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared to naive noise removal methods. In addition, qualitative comparisons confirmed that our method can restore higher-quality videos than the naive methods.
{"title":"Optimizing Dynamic Mode Decomposition for Video Denoising via Plug-and-Play Alternating Direction Method of Multipliers","authors":"Hyoga Yamamoto, Shunki Anami, Ryo Matsuoka","doi":"10.3390/signals5020011","DOIUrl":"https://doi.org/10.3390/signals5020011","url":null,"abstract":"Dynamic mode decomposition (DMD) is a powerful tool for separating the background and foreground in videos. This algorithm decomposes a video into dynamic modes, called DMD modes, to facilitate the extraction of the near-zero mode, which represents the stationary background. Simultaneously, it captures the evolving motion in the remaining modes, which correspond to the moving foreground components. However, when applied to noisy video, this separation leads to degradation of the background and foreground components, primarily due to the noise-induced degradation of the DMD mode. This paper introduces a novel noise removal method for the DMD mode in noisy videos. Specifically, we formulate a minimization problem that reduces the noise in the DMD mode and the reconstructed video. The proposed problem is solved using an algorithm based on the plug-and-play alternating direction method of multipliers (PnP-ADMM). We applied the proposed method to several video datasets with different levels of artificially added Gaussian noise in the experiment. Our method consistently yielded superior results in quantitative evaluations using peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared to naive noise removal methods. In addition, qualitative comparisons confirmed that our method can restore higher-quality videos than the naive methods.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"956 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140774659","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}
X-ray photoelectron spectroscopy (XPS) remains a fundamental technique in materials science, offering invaluable insights into the chemical states and electronic structure of a material. However, the interpretation of XPS spectra can be complex, requiring deep expertise and often sophisticated curve-fitting methods. In this study, we present a novel approach to the analysis of XPS data, integrating the utilization of large language models (LLMs), specifically OpenAI’s GPT-3.5/4 Turbo to provide insightful guidance during the data analysis process. Working in the framework of the CIRCE-NAPP beamline at the CELLS ALBA Synchrotron facility where data are obtained using ambient pressure X-ray photoelectron spectroscopy (APXPS), we implement robust curve-fitting techniques on APXPS spectra, highlighting complex cases including overlapping peaks, diverse chemical states, and noise presence. Post curve fitting, we engage the LLM to facilitate the interpretation of the fitted parameters, leaning on its extensive training data to simulate an interaction corresponding to expert consultation. The manuscript presents also a real use case utilizing GPT-4 and Meta’s LLaMA-2 and describes the integration of the functionality into the TANGO control system. Our methodology not only offers a fresh perspective on XPS data analysis, but also introduces a new dimension of artificial intelligence (AI) integration into scientific research. It showcases the power of LLMs in enhancing the interpretative process, particularly in scenarios wherein expert knowledge may not be immediately available. Despite the inherent limitations of LLMs, their potential in the realm of materials science research is promising, opening doors to a future wherein AI assists in the transformation of raw data into meaningful scientific knowledge.
X 射线光电子能谱（XPS）仍然是材料科学中的一项基础技术，能为了解材料的化学状态和电子结构提供宝贵的信息。然而，XPS 光谱的解读可能非常复杂，需要深厚的专业知识和复杂的曲线拟合方法。在本研究中，我们提出了一种分析 XPS 数据的新方法，综合利用大型语言模型 (LLM)，特别是 OpenAI 的 GPT-3.5/4 Turbo，在数据分析过程中提供具有洞察力的指导。在利用环境压力 X 射线光电子能谱（APXPS）获取数据的 CELLS ALBA 同步加速器设施的 CIRCE-NAPP 光束线框架内，我们对 APXPS 光谱实施了强大的曲线拟合技术，突出了包括重叠峰、不同化学状态和噪声存在在内的复杂情况。曲线拟合后，我们利用 LLM 的大量训练数据来模拟与专家咨询相对应的互动，从而促进对拟合参数的解释。手稿还介绍了一个利用 GPT-4 和 Meta 的 LLaMA-2 的实际案例，并描述了将该功能集成到 TANGO 控制系统中的情况。我们的方法不仅为 XPS 数据分析提供了一个全新的视角，还为人工智能（AI）融入科学研究引入了一个新的维度。它展示了 LLM 在增强解释过程中的威力，尤其是在无法立即获得专家知识的情况下。尽管 LLMs 存在固有的局限性，但其在材料科学研究领域的潜力令人期待，为人工智能协助将原始数据转化为有意义的科学知识的未来打开了大门。
{"title":"Large Language Model-Informed X-ray Photoelectron Spectroscopy Data Analysis","authors":"J. de Curtò, I. de Zarzà, Gemma Roig, C. T. Calafate","doi":"10.3390/signals5020010","DOIUrl":"https://doi.org/10.3390/signals5020010","url":null,"abstract":"X-ray photoelectron spectroscopy (XPS) remains a fundamental technique in materials science, offering invaluable insights into the chemical states and electronic structure of a material. However, the interpretation of XPS spectra can be complex, requiring deep expertise and often sophisticated curve-fitting methods. In this study, we present a novel approach to the analysis of XPS data, integrating the utilization of large language models (LLMs), specifically OpenAI’s GPT-3.5/4 Turbo to provide insightful guidance during the data analysis process. Working in the framework of the CIRCE-NAPP beamline at the CELLS ALBA Synchrotron facility where data are obtained using ambient pressure X-ray photoelectron spectroscopy (APXPS), we implement robust curve-fitting techniques on APXPS spectra, highlighting complex cases including overlapping peaks, diverse chemical states, and noise presence. Post curve fitting, we engage the LLM to facilitate the interpretation of the fitted parameters, leaning on its extensive training data to simulate an interaction corresponding to expert consultation. The manuscript presents also a real use case utilizing GPT-4 and Meta’s LLaMA-2 and describes the integration of the functionality into the TANGO control system. Our methodology not only offers a fresh perspective on XPS data analysis, but also introduces a new dimension of artificial intelligence (AI) integration into scientific research. It showcases the power of LLMs in enhancing the interpretative process, particularly in scenarios wherein expert knowledge may not be immediately available. Despite the inherent limitations of LLMs, their potential in the realm of materials science research is promising, opening doors to a future wherein AI assists in the transformation of raw data into meaningful scientific knowledge.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"8 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140374221","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}
In gasoline engines, the combustion process involves a flame’s propagation from the spark plug to the cylinder walls, resulting in the localized heating and pressurization of the cylinder content ahead of the flame, which can lead to the autoignition of the gasoline and air. The energy release from the autoignition event causes the engine cylinder to resonate, causing an unpleasant noise and eventual engine damage. This process is termed as knock. Avoiding knock has resulted in limiting the maximum engine pressures, and hence limiting the maximum efficiencies of the engine. Modern engines employ knock sensors to detect resonances, adjusting the spark plug timing to reduce pressures and temperatures, albeit at the expense of engine performance. This paper sets out to review the different signals that can be measured from an engine to detect the start of knock. These signals traditionally consist of the in-cylinder pressure, the vibrations of the engine block, and acoustic noise. This paper reviews each of these techniques, with a focus on recent advances. A number of novel methods are also presented, including identifying perturbations in the engine speed or exhaust temperature; measuring the ion charge across the spark plug leads; and using artificial intelligence to build models based on engine conditions. Each of these approaches is also reviewed and compared to the more traditional approaches. This review finds that in-cylinder pressure measurements remain as the most accurate for detecting knock in modern engines; however, their usage is limited to research settings. Meanwhile, new sensors and processing techniques for vibration measurements will more accurately detect knock in modern vehicles in the short term. Acoustic measurements and other novel approaches are showing promise in the long term.
{"title":"A Review of Recent Advancements in Knock Detection in Spark Ignition Engines","authors":"Vikram Mittal","doi":"10.3390/signals5010009","DOIUrl":"https://doi.org/10.3390/signals5010009","url":null,"abstract":"In gasoline engines, the combustion process involves a flame’s propagation from the spark plug to the cylinder walls, resulting in the localized heating and pressurization of the cylinder content ahead of the flame, which can lead to the autoignition of the gasoline and air. The energy release from the autoignition event causes the engine cylinder to resonate, causing an unpleasant noise and eventual engine damage. This process is termed as knock. Avoiding knock has resulted in limiting the maximum engine pressures, and hence limiting the maximum efficiencies of the engine. Modern engines employ knock sensors to detect resonances, adjusting the spark plug timing to reduce pressures and temperatures, albeit at the expense of engine performance. This paper sets out to review the different signals that can be measured from an engine to detect the start of knock. These signals traditionally consist of the in-cylinder pressure, the vibrations of the engine block, and acoustic noise. This paper reviews each of these techniques, with a focus on recent advances. A number of novel methods are also presented, including identifying perturbations in the engine speed or exhaust temperature; measuring the ion charge across the spark plug leads; and using artificial intelligence to build models based on engine conditions. Each of these approaches is also reviewed and compared to the more traditional approaches. This review finds that in-cylinder pressure measurements remain as the most accurate for detecting knock in modern engines; however, their usage is limited to research settings. Meanwhile, new sensors and processing techniques for vibration measurements will more accurately detect knock in modern vehicles in the short term. Acoustic measurements and other novel approaches are showing promise in the long term.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"108 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140223624","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}
The ApeTI dataset was built with the aim of retrieving physiological signals such as heart rate, breath rate, and cognitive load from thermal images of great apes. We want to develop computer vision tools that psychologists and animal behavior researchers can use to retrieve physiological signals noninvasively. Our goal is to increase the use of a thermal imaging modality in the community and avoid using more invasive recording methods to answer research questions. The first step to retrieving physiological signals from thermal imaging is their spatial segmentation to then analyze the time series of the regions of interest. For this purpose, we present a thermal imaging dataset based on recordings of chimpanzees with their face and nose annotated using a bounding box and nine landmarks. The face and landmarks’ locations can then be used to extract physiological signals. The dataset was acquired using a thermal camera at the Leipzig Zoo. Juice was provided in the vicinity of the camera to encourage the chimpanzee to approach and have a good view of the face. Several computer vision methods are presented and evaluated on this dataset. We reach mAPs of 0.74 for face detection and 0.98 for landmark estimation using our proposed combination of the Tifa and Tina models inspired by the HRNet models. A proof of concept of the model is presented for physiological signal retrieval but requires further investigation to be evaluated. The dataset and the implementation of the Tina and Tifa models are available to the scientific community for performance comparison or further applications.
建立 ApeTI 数据集的目的是从类人猿的热图像中检索心率、呼吸频率和认知负荷等生理信号。我们希望开发出计算机视觉工具，供心理学家和动物行为研究人员用于非侵入式检索生理信号。我们的目标是增加热成像模式在社区中的使用，避免使用更具侵入性的记录方法来回答研究问题。从热成像中获取生理信号的第一步是对其进行空间分割，然后分析感兴趣区域的时间序列。为此，我们展示了一个基于黑猩猩记录的热成像数据集，该数据集使用边界框和九个地标标注了黑猩猩的脸部和鼻子。脸部和地标的位置可用于提取生理信号。数据集是使用莱比锡动物园的热像仪采集的。在摄像头附近提供了果汁，以鼓励黑猩猩靠近并看清黑猩猩的脸。在此数据集上介绍并评估了几种计算机视觉方法。使用我们受 HRNet 模型启发而提出的 Tifa 和 Tina 模型组合，人脸检测的 mAP 达到 0.74，地标估计的 mAP 达到 0.98。该模型的概念验证已用于生理信号检索，但还需要进一步研究才能进行评估。数据集以及 Tina 和 Tifa 模型的实现可供科学界进行性能比较或进一步应用。
{"title":"ApeTI: A Thermal Image Dataset for Face and Nose Segmentation with Apes","authors":"Pierre-Etienne Martin","doi":"10.3390/signals5010008","DOIUrl":"https://doi.org/10.3390/signals5010008","url":null,"abstract":"The ApeTI dataset was built with the aim of retrieving physiological signals such as heart rate, breath rate, and cognitive load from thermal images of great apes. We want to develop computer vision tools that psychologists and animal behavior researchers can use to retrieve physiological signals noninvasively. Our goal is to increase the use of a thermal imaging modality in the community and avoid using more invasive recording methods to answer research questions. The first step to retrieving physiological signals from thermal imaging is their spatial segmentation to then analyze the time series of the regions of interest. For this purpose, we present a thermal imaging dataset based on recordings of chimpanzees with their face and nose annotated using a bounding box and nine landmarks. The face and landmarks’ locations can then be used to extract physiological signals. The dataset was acquired using a thermal camera at the Leipzig Zoo. Juice was provided in the vicinity of the camera to encourage the chimpanzee to approach and have a good view of the face. Several computer vision methods are presented and evaluated on this dataset. We reach mAPs of 0.74 for face detection and 0.98 for landmark estimation using our proposed combination of the Tifa and Tina models inspired by the HRNet models. A proof of concept of the model is presented for physiological signal retrieval but requires further investigation to be evaluated. The dataset and the implementation of the Tina and Tifa models are available to the scientific community for performance comparison or further applications.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"51 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140238696","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}
Infant electrocardiograms (ECGs) and heart rates (HRs) are very useful biosignals for psychological research and clinical work, but can be hard to analyse properly, particularly longform (≥5 min) recordings taken in naturalistic environments. Infant HRs are typically much faster than adult HRs, and so some of the underlying frequency assumptions made about adult ECGs may not hold for infants. However, the bulk of publicly available ECG approaches focus on adult data. Here, existing open source ECG approaches are tested on infant datasets. The best-performing open source method is then modified to maximise its performance on infant data (e.g., including a 15 Hz high-pass filter, adding local peak correction). The HR signal is then subsequently analysed, developing an approach for cleaning data with separate sets of parameters for the analysis of cleaner and noisier HRs. A Signal Quality Index (SQI) for HR is also developed, providing insights into where a signal is recoverable and where it is not, allowing for more confidence in the analysis performed on naturalistic recordings. The tools developed and reported in this paper provide a base for the future analysis of infant ECGs and related biophysical characteristics. Of particular importance, the proposed solutions outlined here can be efficiently applied to real-world, large datasets.
{"title":"A Complete Pipeline for Heart Rate Extraction from Infant ECGs","authors":"Harry T. Mason, A. P. Martinez-Cedillo, Q. Vuong, Maria Carmen Garcia-de-Soria, Stephen Smith, Elena Geangu, Marina I. Knight","doi":"10.3390/signals5010007","DOIUrl":"https://doi.org/10.3390/signals5010007","url":null,"abstract":"Infant electrocardiograms (ECGs) and heart rates (HRs) are very useful biosignals for psychological research and clinical work, but can be hard to analyse properly, particularly longform (≥5 min) recordings taken in naturalistic environments. Infant HRs are typically much faster than adult HRs, and so some of the underlying frequency assumptions made about adult ECGs may not hold for infants. However, the bulk of publicly available ECG approaches focus on adult data. Here, existing open source ECG approaches are tested on infant datasets. The best-performing open source method is then modified to maximise its performance on infant data (e.g., including a 15 Hz high-pass filter, adding local peak correction). The HR signal is then subsequently analysed, developing an approach for cleaning data with separate sets of parameters for the analysis of cleaner and noisier HRs. A Signal Quality Index (SQI) for HR is also developed, providing insights into where a signal is recoverable and where it is not, allowing for more confidence in the analysis performed on naturalistic recordings. The tools developed and reported in this paper provide a base for the future analysis of infant ECGs and related biophysical characteristics. Of particular importance, the proposed solutions outlined here can be efficiently applied to real-world, large datasets.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"1976 7‐8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140246819","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}
Predicting rock bursts is essential for maintaining worker safety and the long-term growth of subsurface infrastructure. The purpose of this study is to investigate the precursor reactions and processes of rock instability. To determine the degree of rock damage, the research examines the time-varying acoustic emission (AE) features that occur when rocks are compressed uniaxially and introduces AE parameters such as the b-value, γ-value, and βt-value. The findings suggest that the evolution of rock damage during loading is adequately reflected by the b-value, γ-value, and βt-value. The relationships between b-value, γ-value, and βt-value are studied, as well as the possibility of using these three metrics as early-warning systems for rock failure.
预测岩爆对于维护工人安全和地下基础设施的长期发展至关重要。本研究的目的是调查岩石失稳的前兆反应和过程。为了确定岩石的破坏程度，研究人员检查了岩石受到单轴压缩时发生的时变声发射（AE）特征，并引入了 b 值、γ 值和βt 值等 AE 参数。研究结果表明，b 值、γ 值和βt 值能够充分反映加载过程中岩石损伤的演变。研究了 b 值、γ 值和βt 值之间的关系，以及使用这三个指标作为岩石破坏预警系统的可能性。
{"title":"Study of Time–Frequency Domain of Acoustic Emission Precursors in Rock Failure during Uniaxial Compression","authors":"Gang Jing, Pedro Marin Montanari, Giuseppe Lacidogna","doi":"10.3390/signals5010006","DOIUrl":"https://doi.org/10.3390/signals5010006","url":null,"abstract":"Predicting rock bursts is essential for maintaining worker safety and the long-term growth of subsurface infrastructure. The purpose of this study is to investigate the precursor reactions and processes of rock instability. To determine the degree of rock damage, the research examines the time-varying acoustic emission (AE) features that occur when rocks are compressed uniaxially and introduces AE parameters such as the b-value, γ-value, and βt-value. The findings suggest that the evolution of rock damage during loading is adequately reflected by the b-value, γ-value, and βt-value. The relationships between b-value, γ-value, and βt-value are studied, as well as the possibility of using these three metrics as early-warning systems for rock failure.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"15 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140411864","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}
Pick-and-place operations are an integral part of robotic automation and smart manufacturing. By utilizing deep learning techniques on resource-constraint embedded devices, the pick-and-place operations can be made more accurate, efficient, and sustainable, compared to the high-powered computer solution. In this study, we propose a new technique for object detection on an embedded system using SSD Mobilenet V2 FPN Lite with the optimisation of the hyperparameter and image enhancement. By increasing the Red Green Blue (RGB) saturation level of the images, we gain a 7% increase in mean Average Precision (mAP) when compared to the control group and a 20% increase in mAP when compared to the COCO 2017 validation dataset. Using a Learning Rate of 0.08 with an Edge Tensor Processing Unit (TPU), we obtain high real-time detection scores of 97%. The high detection scores are important to the control algorithm, which uses the bounding box to send a signal to the collaborative robot for pick-and-place operation.
{"title":"Object Detection with Hyperparameter and Image Enhancement Optimisation for a Smart and Lean Pick-and-Place Solution","authors":"Elven Kee, Jun Jie Chong, Zi Jie Choong, Michael Lau","doi":"10.3390/signals5010005","DOIUrl":"https://doi.org/10.3390/signals5010005","url":null,"abstract":"Pick-and-place operations are an integral part of robotic automation and smart manufacturing. By utilizing deep learning techniques on resource-constraint embedded devices, the pick-and-place operations can be made more accurate, efficient, and sustainable, compared to the high-powered computer solution. In this study, we propose a new technique for object detection on an embedded system using SSD Mobilenet V2 FPN Lite with the optimisation of the hyperparameter and image enhancement. By increasing the Red Green Blue (RGB) saturation level of the images, we gain a 7% increase in mean Average Precision (mAP) when compared to the control group and a 20% increase in mAP when compared to the COCO 2017 validation dataset. Using a Learning Rate of 0.08 with an Edge Tensor Processing Unit (TPU), we obtain high real-time detection scores of 97%. The high detection scores are important to the control algorithm, which uses the bounding box to send a signal to the collaborative robot for pick-and-place operation.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"33 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140430889","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}
We consider the challenge of detecting and clustering point and collective anomalies in streaming data that exhibit significant nonlinearities and seasonal structures. The challenge is motivated by detecting problems in a communications network, where we can measure the throughput of nodes, and wish to rapidly detect anomalous traffic behaviour. Our approach is to train a neural network-based nonlinear autoregressive exogenous model on initial training data, then to use the sequential collective and point anomaly framework to identify anomalies in the residuals generated by comparing one-step-ahead predictions of the fitted model with the observations, and finally, we cluster the detected anomalies with fuzzy c-means clustering using empirical cumulative distribution functions. The autoregressive model is sufficiently general and robust such that it provides the nearly (locally) stationary residuals required by the anomaly detection procedure. The combined methods are successfully implemented to create an adaptive, robust, computational framework that can be used to cluster point and collective anomalies in streaming data. We validate the method on both data from the core of the UK’s national communications network and the multivariate Skoltech anomaly benchmark and find that the proposed method succeeds in dealing with different forms of anomalies within the nonlinear signals and outperforms conventional methods for anomaly detection and clustering.
{"title":"Online Detection and Fuzzy Clustering of Anomalies in Non-Stationary Time Series","authors":"Changjiang He, David S. Leslie, James A. Grant","doi":"10.3390/signals5010003","DOIUrl":"https://doi.org/10.3390/signals5010003","url":null,"abstract":"We consider the challenge of detecting and clustering point and collective anomalies in streaming data that exhibit significant nonlinearities and seasonal structures. The challenge is motivated by detecting problems in a communications network, where we can measure the throughput of nodes, and wish to rapidly detect anomalous traffic behaviour. Our approach is to train a neural network-based nonlinear autoregressive exogenous model on initial training data, then to use the sequential collective and point anomaly framework to identify anomalies in the residuals generated by comparing one-step-ahead predictions of the fitted model with the observations, and finally, we cluster the detected anomalies with fuzzy c-means clustering using empirical cumulative distribution functions. The autoregressive model is sufficiently general and robust such that it provides the nearly (locally) stationary residuals required by the anomaly detection procedure. The combined methods are successfully implemented to create an adaptive, robust, computational framework that can be used to cluster point and collective anomalies in streaming data. We validate the method on both data from the core of the UK’s national communications network and the multivariate Skoltech anomaly benchmark and find that the proposed method succeeds in dealing with different forms of anomalies within the nonlinear signals and outperforms conventional methods for anomaly detection and clustering.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"10 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139600045","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}
Brain responses to discrete stimuli are modulated when multiple stimuli are presented in sequence. These alterations are especially pronounced when the time course of an evoked response overlaps with responses to subsequent stimuli, such as in a rapid serial visual presentation (RSVP) paradigm used to control a brain–computer interface (BCI). The present study explored whether the measurement or classification of select brain responses during RSVP would improve through application of an established technique for dealing with overlapping stimulus presentations, known as irregular or “jittered” stimulus onset interval (SOI). EEG data were collected from 24 healthy adult participants across multiple rounds of RSVP calibration and copy phrase tasks with varying degrees of SOI jitter. Analyses measured three separate brain signals sensitive to attention: N200, P300, and occipitoparietal alpha attenuation. Presentation jitter visibly reduced intrusion of the SSVEP, but in general, it did not positively or negatively affect attention effects, classification, or system performance. Though it remains unclear whether stimulus overlap is detrimental to BCI performance overall, the present study demonstrates that single-trial classification approaches may be resilient to rhythmic intrusions like SSVEP that appear in the averaged EEG.
{"title":"The Effect of Jittered Stimulus Onset Interval on Electrophysiological Markers of Attention in a Brain–Computer Interface Rapid Serial Visual Presentation Paradigm","authors":"Daniel Klee, Tab Memmott, Barry Oken","doi":"10.3390/signals5010002","DOIUrl":"https://doi.org/10.3390/signals5010002","url":null,"abstract":"Brain responses to discrete stimuli are modulated when multiple stimuli are presented in sequence. These alterations are especially pronounced when the time course of an evoked response overlaps with responses to subsequent stimuli, such as in a rapid serial visual presentation (RSVP) paradigm used to control a brain–computer interface (BCI). The present study explored whether the measurement or classification of select brain responses during RSVP would improve through application of an established technique for dealing with overlapping stimulus presentations, known as irregular or “jittered” stimulus onset interval (SOI). EEG data were collected from 24 healthy adult participants across multiple rounds of RSVP calibration and copy phrase tasks with varying degrees of SOI jitter. Analyses measured three separate brain signals sensitive to attention: N200, P300, and occipitoparietal alpha attenuation. Presentation jitter visibly reduced intrusion of the SSVEP, but in general, it did not positively or negatively affect attention effects, classification, or system performance. Though it remains unclear whether stimulus overlap is detrimental to BCI performance overall, the present study demonstrates that single-trial classification approaches may be resilient to rhythmic intrusions like SSVEP that appear in the averaged EEG.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"23 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139443711","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：