Nanoparticle Classification Using Frequency Domain Analysis on Resource-Limited Platforms

Yayla, Mikail; Toma, Anas; Chen, Kuan-Hsun; Lenssen, Jan Eric; Shpacovitch, Victoria; Hergenröder, Roland; Weichert, Frank; Chen, Jian-Jia

doi:10.3390/s19194138

Cited by 9 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This setup provides indirect imaging for the downstream detection of nano-sized objects. Further explanations of the technical aspects and application scenarios, such as detecting viruses, can be found in the literature [53][54][55][56]. While a high degree of reliability is essential for detecting nanoparticles, recording with the PAMONO sensor is prone to disturbances originating from its high sensitivity to changes in the nanometer scale, temperature dependence, sensitivity to external impacts, and contaminations of the analyzed samples [74].…”

Section: Pamono Sensor Image Streamsmentioning

confidence: 99%

“…As an example of a sensor affected by different disturbances, Section 3 describes the Plasmon-Assisted Microscopy of Nano-Objects (PAMONO) sensor, which has been the subject of several research questions [53][54][55][56] and served as a starting point for the research presented in this paper. It is affected by disturbances during image acquisition, resulting in varying artifact characteristics, for which some are shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

2021

Self Cite

View full text Add to dashboard Cite

Deep learning methods have become increasingly popular for optical sensor image analysis. They are adaptable to specific tasks and simultaneously demonstrate a high degree of generalization capability. However, applying deep neural networks to problems with low availability of labeled training data can lead to a model being incapable of generalizing to possible scenarios that may occur in test data, especially with the occurrence of dominant imaging artifacts. We propose a data-centric augmentation approach based on generative adversarial networks that overlays the existing labeled data with synthetic artifacts that are generated from data not present in the training set. This augmentation leads to a more robust generalization capability in semantic segmentation. Our method does not need any additional labeling and does not lead to additional memory or time consumption during inference. Further, we find it to be more effective than comparable approaches that are based on procedurally generated disturbances and the direct use of real disturbances. Building upon the improved segmentation results, we observe that our approach leads to improvements of 22% in the F1-score for an evaluated detection problem, which promises significant robustness towards future disturbances. In the context of sensor-based data analysis, the compensation of image artifacts is a challenge. When the structures of interest are not clearly visible in an image, algorithms that can cope with artifacts are crucial for obtaining the desired information. Thereby, the high variation of artifacts, the combination of different types of artifacts, and their similarity to signals of interest are specific issues that have to be considered in the analysis. Despite the high generalization capability of deep learning-based approaches, their recent success was driven by the availability of large amounts of labeled data. Therefore, the provision of comprehensive labeled image data with different characteristics of image artifacts is of importance. At the same time, applying deep neural networks to problems with low availability of labeled data remains a challenge. This work presents a data-centric augmentation approach based on generative adversarial networks that augments the existing labeled data with synthetic artifacts generated from data not present in the training set. In our experiments, this augmentation leads to a more robust generalization in segmentation. Our method does not need additional labeling and does not lead to additional memory or time consumption during inference. Further, we find it to be more effective than comparable augmentations based on procedurally generated artifacts and the direct use of real artifacts. Building upon the improved segmentation results, we observe that our approach leads to improvements of 22% in the F1-score for an evaluated detection problem. Having achieved these results with an example sensor, we expect increased robustness against artifacts in future applications.

show abstract

Section: Pamono Sensor Image Streamsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The work [6] can be considered as a continuation of the previous work published in Sensors [7] and describing the employment of SPR-based sensor for sizing and quantification of individual biological nano-particles (virus-like particles, viruses or extracellular vesicles). The previous work [7] introduced the Plasmon Assisted Microscopy of Nano-sized Objects (PAMONO) sensor as a biosensor for quantification and sizing of single microvesicles and virus-like particles (VLPs).…”

Section: Summary Of the Special Issuementioning

confidence: 99%

“…PAMONO sensor utilizes Kretschmann's scheme of plasmon excitation for label-free and specific detection of biological nano-particles. However, if previously in [7] the detection and sizing of nano-particles was performed using Convolutional Neural Networks (CNNs), in the work presented in this special issue [6] frequency domain analysis approach was used for the characterization of nano-paricles. The employment of frequency domain analysis is less computation intensive in comparison with application of CNNs for nano-particle characterization.…”

Section: Summary Of the Special Issuementioning

confidence: 99%

Surface Plasmon Resonance (SPR)-Based Biosensors as Instruments with High Versatility and Sensitivity

Shpacovitch

Hergenröder

2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…For unstructured data such as text or images, Deep Learning is currently among the state of the art, whereas for structured data, decision-tree ensembles such as Gradient Boosting or Random Forest seem to work best 3 . Hence it is no surprise that for real-time applications, tree ensembles have become important to augment our society in many ields, e.g., classiication of celestial objects in astrophysics [11], pedestrian detection [32], 3D face analysis [17], noise signal analysis [37], nano-partical analysis [26,40], etc.…”

Section: Introductionmentioning

confidence: 99%

Efficient Realization of Decision Trees for Real-Time Inference

Chen

Hakert

et al. 2022

ACM Trans. Embed. Comput. Syst.

Self Cite

View full text Add to dashboard Cite

For timing-sensitive edge applications, the demand for efficient lightweight machine learning solutions has increased recently. Tree ensembles are among the state-of-the-art in many machine learning applications. While single decision trees are comparably small, an ensemble of trees can have a significant memory footprint leading to cache locality issues, which are crucial to performance in terms of execution time. In this work, we analyze memory-locality issues of the two most common realizations of decision trees, i.e. native and if-else trees. We highlight, that both realizations demand a more careful memory layout to improve caching behavior and maximize performance. We adopt a probabilistic model of decision tree inference to find the best memory layout for each tree at the application layer. Further, we present an efficient heuristic to take architecture-dependent information into account thereby optimizing the given ensemble for a target computer architecture. Our code-generation framework, which is freely available on an open-source repository, produces optimized code sessions while preserving the structure and accuracy of the trees. With several real-world data sets, we evaluate the elapsed time of various tree realizations on server hardware as well as embedded systems for Intel and ARM processors. Our optimized memory layout achieves a reduction in execution time up to 75 % execution for server-class systems, and up to 70 % for embedded systems, respectively.

show abstract

Nanoparticle Classification Using Frequency Domain Analysis on Resource-Limited Platforms

Cited by 9 publications

References 13 publications

A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

Surface Plasmon Resonance (SPR)-Based Biosensors as Instruments with High Versatility and Sensitivity

Efficient Realization of Decision Trees for Real-Time Inference

Contact Info

Product

Resources

About