More Like this

1. Unsupervised Learning and Adaptive Classification of Neuromorphic Tactile Encoding of Textures

   https://doi.org/10.1109/BIOCAS.2018.8584702  

   Iskarous, Mark M.; Nguyen, Harrison H.; Osborn, Luke E.; Betthauser, Joseph L.; Thakor, Nitish V. (October 2018, Proceedings of IEEE Biomedical Circuits and Systems)

   null (Ed.)

   In this work, we investigated the classification of texture by neuromorphic tactile encoding and an unsupervised learning method. Additionally, we developed an adaptive classification algorithm to detect and characterize the presence of new texture data. The neuromorphic tactile encoding of textures from a multilayer tactile sensor was based on the physical structure and afferent spike signaling of human glabrous skin mechanoreceptors. We explored different neuromorphic spike pattern metrics and dimensionality reduction techniques in order to maximize classification accuracy while improving computational efficiency. Using a dataset composed of 3 textures, we showed that unsupervised learning of the neuromorphic tactile encoding data had high classification accuracy (mean=86.46%, sd=5 .44%). Moreover, the adaptive classification algorithm was successful at determining that there were 3 underlying textures in the training dataset. In this work, tactile information is transformed into neuromorphic spiking activity that can be used as a stimulation pattern to elicit texture sensation for prosthesis users. Furthermore, we provide the basis for identifying new textures adaptively which can be used to actively modify stimulation patterns to improve texture discrimination for the user. 

   more » « less
2. Realism of Tactile Texture Playback: A Combination of Stretch and Vibration

   https://doi.org/10.1109/TOH.2024.3355982  

   Liu, Zhenyu; Kim, Jin-Tae; Rogers, John A; Klatzky, Roberta L; Colgate, J Edward (July 2024, IEEE Transactions on Haptics)

   Not AvailableThis study investigates the effects of two stimulation modalities (stretch and vibration) on natural touch sensation on the volar forearm. The skin-textile interaction was implemented by scanning three natural textures across the left forearm. The resulting in-plane displacements across the skin were recorded by the digital image correlation technique to capture the information imparted by the textures. The texture recordings were used to create three playback modes (stretch, vibration, and both), which were reproduced on the right forearm. Two psychophysical experiments compared the physical texture scans to rendered texture playbacks. The first experiment used a matching task and found that to maximize perceptual realism, i.e., similarity to a physical reference, subjects preferred the rendered texture to have a playback intensity of approximately 1X – 2X higher on DC components (stretch), and 1X – 3.5X higher on AC components (vibration), varying across textures. The second experiment elicited similarity ratings between the texture scans and playbacks and showed that a combination of both stretch and vibration was required to create differentiated texture sensations. However, the intensity amplification and use of both stretch and vibration were still insufficient to create fully realistic texture sensations. We conclude that mechanisms beyond singlesite uniaxial stimuli are needed to reproduce realistic textural sensations. 

   more » « less
3. KnitPicking Textures: Programming and Modifying Complex Knitted Textures for Machine and Hand Knitting

   https://doi.org/10.1145/3332165.3347886  

   Hofmann, Megan; Albaugh, Lea; Sethapakadi, Ticha; Hodgins, Jessica; Hudson, Scott E.; McCann, James; Mankoff, Jennifer (October 2019, Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology)

   Knitting creates complex, soft fabrics with unique texture properties that can be used to create interactive objects.However, little work addresses the challenges of designing and using knitted textures computationally. We present KnitPick: a pipeline for interpreting hand-knitting texture patterns into KnitGraphs which can be output to machine and hand-knitting instructions. Using KnitPick, we contribute a measured and photographed data set of 472 knitted textures. Based on findings from this data set, we contribute two algorithms for manipulating KnitGraphs. KnitCarving shapes a graph while respecting a texture, and KnitPatching combines graphs with disparate textures while maintaining a consistent shape. KnitPick is the first system to bridge the gap between hand- and machine-knitting when creating complex knitted textures. 

   more » « less
4. Robust Contrastive Learning Using Negative Samples with Diminished Semantics

   Songwei Ge, Shlok Mishra (January 2021, Advances in neural information processing systems)

   Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency has been conjectured to induce a lack of robustness to image perturbations or domain shift. In this paper, we show that by generating carefully designed negative samples, contrastive learning can learn more robust representations with less dependence on such features. Contrastive learning utilizes positive pairs which preserve semantic information while perturbing superficial features in the training images. Similarly, we propose to generate negative samples in a reversed way, where only the superfluous instead of the semantic features are preserved. We develop two methods, texture-based and patch-based augmentations, to generate negative samples. These samples achieve better generalization, especially under out-of-domain settings. We also analyze our method and the generated texture-based samples, showing that texture features are indispensable in classifying particular ImageNet classes and especially finer classes. We also show that the model bias between texture and shape features favors them differently under different test settings. 

   more » « less
5. Polycrystalline morphology and anomalous Hall effect in RF-sputtered Co2MnGa films

   https://doi.org/10.1116/6.0004556  

   Wade, Carter E; Phan, Sunny; Coffin, Katherine E; Paynter, Gabe J; Cawein, Ty J; Eyink, Kurt G; Kogan, Andrei; Corbett, Joseph P (July 2025, Journal of Vacuum Science & Technology A)

   The Heusler compound Co2MnGa is a topological semimetal with intriguing electronic and magnetic properties, making it a promising candidate for spintronic applications. This study systematically investigates the effects of substrate temperature and radio frequency (RF) sputtering power on the structure, morphology, and anomalous Hall effect (AHE) in Co2MnGa thin films with the goal to uncover trends in growth–morphology–property relationships. Using x-ray diffraction line analysis, we identify variations in film orientation and crystallinity, revealing the emergence of high-index textures at specific growth conditions. Atomic force microscopy imaging provides insight into grain morphology and size distributions demonstrating a correlation between deposition parameters and film texture. Magnetotransport measurements show a strong dependence of AHE on growth conditions, exhibiting a nonmonotonic relationship with RF power and temperature. Despite significant variations in microstructure, a striking linear relationship between AHE and the zero-field slope of the Hall resistivity is observed, suggesting an underlying universal mechanism. These findings provide a foundation for investigating the complex interplay of Co2MnGa informing us broadly that the AHE is strongly tunable by morphology, while at the same time the critical field remains robust. 

   more » « less