Byung Do Lee, Jin-Woong Lee, W. Park, Joonseo Park, Min-Young Cho, S. Singh, M. Pyo, K. Sohn
Herein, data‐driven symmetry identification, property prediction, and low‐dimensional embedding from powder X‐Ray diffraction (XRD) patterns of inorganic crystal structure database (ICSD) and materials project (MP) entries are reported. For this purpose, a fully convolutional neural network (FCN), transformer encoder (T‐encoder), and variational autoencoder (VAE) are used. The results are compared to those obtained from a well‐established crystal graph convolutional neural network (CGCNN). A task‐specified small dataset that focuses on a narrow material system, knowledge (rule)‐based descriptor extraction, and significant data dimension reduction are not the main focus of this study. Conventional powder XRD patterns, which are most widely used in materials research, can be used as a significantly informative material descriptor for deep learning. Both the FCN and T‐encoder outperform the CGCNN for symmetry classification. For property prediction, the performance of the FCN concatenated with multilayer perceptron reaches the performance level of CGCNN. Machine‐learning‐driven material property prediction from the powder XRD pattern deserves appreciation because no such attempts have been made despite common XRD‐driven symmetry (and lattice size) prediction and phase identification. The ICSD and MP data are embedded in the 2D (or 3D) latent space through the VAE, and well‐separated clustering according to the symmetry and property is observed.
{"title":"Powder X‐Ray Diffraction Pattern Is All You Need for Machine‐Learning‐Based Symmetry Identification and Property Prediction","authors":"Byung Do Lee, Jin-Woong Lee, W. Park, Joonseo Park, Min-Young Cho, S. Singh, M. Pyo, K. Sohn","doi":"10.1002/aisy.202200042","DOIUrl":"https://doi.org/10.1002/aisy.202200042","url":null,"abstract":"Herein, data‐driven symmetry identification, property prediction, and low‐dimensional embedding from powder X‐Ray diffraction (XRD) patterns of inorganic crystal structure database (ICSD) and materials project (MP) entries are reported. For this purpose, a fully convolutional neural network (FCN), transformer encoder (T‐encoder), and variational autoencoder (VAE) are used. The results are compared to those obtained from a well‐established crystal graph convolutional neural network (CGCNN). A task‐specified small dataset that focuses on a narrow material system, knowledge (rule)‐based descriptor extraction, and significant data dimension reduction are not the main focus of this study. Conventional powder XRD patterns, which are most widely used in materials research, can be used as a significantly informative material descriptor for deep learning. Both the FCN and T‐encoder outperform the CGCNN for symmetry classification. For property prediction, the performance of the FCN concatenated with multilayer perceptron reaches the performance level of CGCNN. Machine‐learning‐driven material property prediction from the powder XRD pattern deserves appreciation because no such attempts have been made despite common XRD‐driven symmetry (and lattice size) prediction and phase identification. The ICSD and MP data are embedded in the 2D (or 3D) latent space through the VAE, and well‐separated clustering according to the symmetry and property is observed.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88297752","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}
Jinwoo Lee, Yeosang Yoon, H. Park, Joonhwa Choi, Yeong-Tae Jung, Seung Hwan Ko, W. Yeo
Animal locomotion offers valuable references as it is a critical component of survival as animals adapting to a specific environment. Especially, underwater locomotion poses a challenge because water exerts a high antagonistic drag force against the direction of progress. However, marine vertebrates usually use much lower aerobic energy for locomotion than aerial or terrestrial vertebrates due to their unique intermittent gliding locomotion. None of the prior works demonstrate the locomotive strategies of marine vertebrates. Herein, an untethered soft robotic fish capable of reconstructing the marine vertebrates’ effective locomotion and traveling underwater by controlling localized buoyancy with thermoelectric pneumatic actuators is introduced. The actuators enable both heating and cooling to control a localized buoyancy while providing a substantial driving force to the system. Besides mimicking the locomotion, the bidirectional communication system enables the untethered delivery of commands to the underwater subject and real‐time acquisition of the robotic fish's physical information. Underwater imaging validates the fish's practical use as a drone, allowing for inspecting the aquatic environment that is not easily accessible to humans. Future work studies the operation of the robotic fish as a collective swarm to examine a broader range of the underwater area and conduct various strategic missions.
{"title":"Bioinspired Soft Robotic Fish for Wireless Underwater Control of Gliding Locomotion","authors":"Jinwoo Lee, Yeosang Yoon, H. Park, Joonhwa Choi, Yeong-Tae Jung, Seung Hwan Ko, W. Yeo","doi":"10.1002/aisy.202100271","DOIUrl":"https://doi.org/10.1002/aisy.202100271","url":null,"abstract":"Animal locomotion offers valuable references as it is a critical component of survival as animals adapting to a specific environment. Especially, underwater locomotion poses a challenge because water exerts a high antagonistic drag force against the direction of progress. However, marine vertebrates usually use much lower aerobic energy for locomotion than aerial or terrestrial vertebrates due to their unique intermittent gliding locomotion. None of the prior works demonstrate the locomotive strategies of marine vertebrates. Herein, an untethered soft robotic fish capable of reconstructing the marine vertebrates’ effective locomotion and traveling underwater by controlling localized buoyancy with thermoelectric pneumatic actuators is introduced. The actuators enable both heating and cooling to control a localized buoyancy while providing a substantial driving force to the system. Besides mimicking the locomotion, the bidirectional communication system enables the untethered delivery of commands to the underwater subject and real‐time acquisition of the robotic fish's physical information. Underwater imaging validates the fish's practical use as a drone, allowing for inspecting the aquatic environment that is not easily accessible to humans. Future work studies the operation of the robotic fish as a collective swarm to examine a broader range of the underwater area and conduct various strategic missions.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77979308","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}
Modular soft robots have strong adaptability and versatility in various application contexts. However, the introduction of connection mechanisms will always either reduce the structural compliance or need extra actuation appendages, resulting in the complexity of the structure and system of the robot. To address these issues, herein, a compliant and passive connection strategy is demonstrated, which is accomplished utilizing the reclosable fasteners (RFs), and other varieties including hook‐and‐loop fasteners, as the connection mechanisms to the soft modules for the rapid assembly of various soft machines. The module is a pneumatic soft actuator with both ends designed with a multifaceted structure to attach the RFs in different orientations, resulting in various assembling patterns, including linear connection, orthogonal connection, and oblique connection. Moreover, an alignment mechanism is also designed to improve the alignment precision between two assembled modules. The versatility of the RF enables soft modules capable of assembling not only between identical modules but also with diverse additional accessories for various application scenarios. Different functional assemblies are demonstrated including soft grippers, soft walking robots, and shape‐morphing electrical devices. This approach to the connection mechanisms provides routes to new modular soft robots and devices.
{"title":"Modular Assembly of Soft Machines via Multidirectional Reclosable Fasteners","authors":"Huiyan Yang, Shiyan Jin, Wei Dawid Wang","doi":"10.1002/aisy.202200048","DOIUrl":"https://doi.org/10.1002/aisy.202200048","url":null,"abstract":"Modular soft robots have strong adaptability and versatility in various application contexts. However, the introduction of connection mechanisms will always either reduce the structural compliance or need extra actuation appendages, resulting in the complexity of the structure and system of the robot. To address these issues, herein, a compliant and passive connection strategy is demonstrated, which is accomplished utilizing the reclosable fasteners (RFs), and other varieties including hook‐and‐loop fasteners, as the connection mechanisms to the soft modules for the rapid assembly of various soft machines. The module is a pneumatic soft actuator with both ends designed with a multifaceted structure to attach the RFs in different orientations, resulting in various assembling patterns, including linear connection, orthogonal connection, and oblique connection. Moreover, an alignment mechanism is also designed to improve the alignment precision between two assembled modules. The versatility of the RF enables soft modules capable of assembling not only between identical modules but also with diverse additional accessories for various application scenarios. Different functional assemblies are demonstrated including soft grippers, soft walking robots, and shape‐morphing electrical devices. This approach to the connection mechanisms provides routes to new modular soft robots and devices.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"68 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88523356","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}
Davide Zappetti, Yi Sun, Matthieu Gevers, S. Mintchev, D. Floreano
Collision resilience is an important feature of robots deployed in unstructured and partially unpredictable environments. Herein, a novel dual stiffness (DS) tensegrity platform to integrate collision resilience into a robot body is proposed. The proposed DS tensegrity platform is rigid during normal robot operation, but softens upon collision to withstand the impact. The DS behavior is achieved by means of a novel DS strut that is rigid, but can buckle without breaking under high loads, thus preventing damage to the robot. Compression tests and finite element method simulations show that both the DS struts and DS tensegrities undergo substantial stiffness change with maximum load‐bearing ratios up to 10.5 and 5.74, respectively, before and after buckling. These DS tensegrity structures are integrated into two types of robots, a drone and a rover, that are shown to withstand falls from 2 and 5 m, respectively. The mechanical tunability of the proposed DS tensegrity system makes it suitable for impact attenuation in a wide range of situations and robot types.
{"title":"Dual Stiffness Tensegrity Platform for Resilient Robotics","authors":"Davide Zappetti, Yi Sun, Matthieu Gevers, S. Mintchev, D. Floreano","doi":"10.1002/aisy.202200025","DOIUrl":"https://doi.org/10.1002/aisy.202200025","url":null,"abstract":"Collision resilience is an important feature of robots deployed in unstructured and partially unpredictable environments. Herein, a novel dual stiffness (DS) tensegrity platform to integrate collision resilience into a robot body is proposed. The proposed DS tensegrity platform is rigid during normal robot operation, but softens upon collision to withstand the impact. The DS behavior is achieved by means of a novel DS strut that is rigid, but can buckle without breaking under high loads, thus preventing damage to the robot. Compression tests and finite element method simulations show that both the DS struts and DS tensegrities undergo substantial stiffness change with maximum load‐bearing ratios up to 10.5 and 5.74, respectively, before and after buckling. These DS tensegrity structures are integrated into two types of robots, a drone and a rover, that are shown to withstand falls from 2 and 5 m, respectively. The mechanical tunability of the proposed DS tensegrity system makes it suitable for impact attenuation in a wide range of situations and robot types.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86938441","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}
Cong Fang, Huayao Li, Long Li, Hu-Yin Su, Jiang Tang, Xiang Bai, Huan Liu
An electronic nose (e‐nose) mimics the mammalian olfactory system in identifying odors and expands human olfaction boundaries by tracing toxins and explosives. However, existing feature‐based odor recognition algorithms rely on domain‐specific expertise, which may limit the performance due to information loss during the feature extraction process. Inspired by human olfaction, a smart electronic nose enabled by an all‐feature olfactory algorithm (AFOA) is proposed, whereby all features in a gas sensing cycle of semiconductor gas sensors, including the response, equilibrium, and recovery processes are utilized. Specifically, our method combines 1D convolutional and recurrent neural networks with channel and temporal attention modules to fully utilize complementary global and dynamic information. It is further demonstrated that a novel data augmentation method can transform the raw data into a suitable representation for feature extraction. Results show that the e‐nose simply comprising of six semiconductor gas sensors achieves superior performances to state‐of‐the‐art methods on the Chinese liquor data. Ablation studies reveal the contribution of each sensor in odor recognition. Therefore, a deep‐learning‐enabled codesign of sensor arrays and recognition algorithms can reduce the heavy demand for a huge amount of highly specialized gas sensors and provide interpretable insights into odor recognition dynamics in an iterative way.
{"title":"Smart Electronic Nose Enabled by an All‐Feature Olfactory Algorithm","authors":"Cong Fang, Huayao Li, Long Li, Hu-Yin Su, Jiang Tang, Xiang Bai, Huan Liu","doi":"10.1002/aisy.202200074","DOIUrl":"https://doi.org/10.1002/aisy.202200074","url":null,"abstract":"An electronic nose (e‐nose) mimics the mammalian olfactory system in identifying odors and expands human olfaction boundaries by tracing toxins and explosives. However, existing feature‐based odor recognition algorithms rely on domain‐specific expertise, which may limit the performance due to information loss during the feature extraction process. Inspired by human olfaction, a smart electronic nose enabled by an all‐feature olfactory algorithm (AFOA) is proposed, whereby all features in a gas sensing cycle of semiconductor gas sensors, including the response, equilibrium, and recovery processes are utilized. Specifically, our method combines 1D convolutional and recurrent neural networks with channel and temporal attention modules to fully utilize complementary global and dynamic information. It is further demonstrated that a novel data augmentation method can transform the raw data into a suitable representation for feature extraction. Results show that the e‐nose simply comprising of six semiconductor gas sensors achieves superior performances to state‐of‐the‐art methods on the Chinese liquor data. Ablation studies reveal the contribution of each sensor in odor recognition. Therefore, a deep‐learning‐enabled codesign of sensor arrays and recognition algorithms can reduce the heavy demand for a huge amount of highly specialized gas sensors and provide interpretable insights into odor recognition dynamics in an iterative way.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80125502","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}
Xinqiang Pan, Jiejun Wang, Zhen Deng, Y. Shuai, W. Luo, Qin Xie, Yao Xiao, Song Tang, Shuwen Jiang, Chuangui Wu, Feng Zhu, Jianwei Zhang, W. Zhang
Sensory adaptation plays a critical role in humans interacting with the environment. Inspired by humans, realization of sensory adaptation on robots can make them adapt to the environment gradually. The gradual change of sensitivity that depends on recent experience of external stimuli is the most important process for the adaptation. To realize sensory adaptation, such change of sensitivity needs to be realized. It is proposed to fabricate the memristor based on single‐crystalline LiNbO3 thin film. The resistance of the memristor can be changed monotonically and gradually with the increase in the number of voltage pulses, which can be ascribed to the property of single‐crystalline thin films. Based on the characteristic, it is proposed to use the memristor as artificial synapse of the proposed bioinspired system, using conductance of the memristor to denote susceptibility value to realize the gradual change of sensitivity by recent external stimuli. A novel general excitation method of signals from multimodal sensors on memristor is proposed and utilized in the signal‐coupling module of the system, which makes the system realize sensory adaptation for different stimuli accepted by multimodal sensors. Using artificial sensory memory systems, sensory adaptation on robot is realized for the first time herein.
{"title":"A Memristor‐Based Bioinspired Multimodal Sensory Memory System for Sensory Adaptation of Robots","authors":"Xinqiang Pan, Jiejun Wang, Zhen Deng, Y. Shuai, W. Luo, Qin Xie, Yao Xiao, Song Tang, Shuwen Jiang, Chuangui Wu, Feng Zhu, Jianwei Zhang, W. Zhang","doi":"10.1002/aisy.202200031","DOIUrl":"https://doi.org/10.1002/aisy.202200031","url":null,"abstract":"Sensory adaptation plays a critical role in humans interacting with the environment. Inspired by humans, realization of sensory adaptation on robots can make them adapt to the environment gradually. The gradual change of sensitivity that depends on recent experience of external stimuli is the most important process for the adaptation. To realize sensory adaptation, such change of sensitivity needs to be realized. It is proposed to fabricate the memristor based on single‐crystalline LiNbO3 thin film. The resistance of the memristor can be changed monotonically and gradually with the increase in the number of voltage pulses, which can be ascribed to the property of single‐crystalline thin films. Based on the characteristic, it is proposed to use the memristor as artificial synapse of the proposed bioinspired system, using conductance of the memristor to denote susceptibility value to realize the gradual change of sensitivity by recent external stimuli. A novel general excitation method of signals from multimodal sensors on memristor is proposed and utilized in the signal‐coupling module of the system, which makes the system realize sensory adaptation for different stimuli accepted by multimodal sensors. Using artificial sensory memory systems, sensory adaptation on robot is realized for the first time herein.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"76 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86673593","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}
Magnetic micro/nanorobots (MagRobots) with unparalleled advantages, including remote mobility, high reconfigurability and programmability, lack of fuel requirement, and versatility, can be manipulated under a magnetic field, which has attracted considerable research attention in the biomedicine. Magnetic materials, as the key components of MagRobots, generate reactive oxygen species (ROS) in vivo to induce tissue/organ damage through Fenton/Fenton‐like reactions, which may hinder the clinical application of MagRobots. Here, the biologically active Prussian blue is generated on the surfaces of MagRobots via an in situ reaction to obtain magnetically actuated ROS‐scavenging nano‐robots (ROSrobots). The generated Prussian blue blocks ROS production and endows the MagRobots with additional functionalities, markedly expanding their potential medical applications. Under the action of a magnetic field, the reconfigurable ROSrobots realize multimode transformation, locomotion, and manipulation in complex environments. Importantly, a simple control method is proposed to achieve movement in 3D geometries to allow the completion of tasks in a complex environment. Furthermore, the osteoarthritis (OA) rat model was employed for proof of concept. Notably, under the guidance of ultrasound imaging, ROSrobots can be accurately injected into the articular cavity to actively target the treatment of OA. This research may further promote the clinical application of MagRobots.
{"title":"Magnetically Actuated Reactive Oxygen Species Scavenging Nano‐Robots for Targeted Treatment","authors":"Yongzheng Zhao, Hao Xiong, Yanhong Li, Wei Gao, Chen Hua, Jianrong Wu, C. Fan, Xiaojun Cai, Yuanyi Zheng","doi":"10.1002/aisy.202200061","DOIUrl":"https://doi.org/10.1002/aisy.202200061","url":null,"abstract":"Magnetic micro/nanorobots (MagRobots) with unparalleled advantages, including remote mobility, high reconfigurability and programmability, lack of fuel requirement, and versatility, can be manipulated under a magnetic field, which has attracted considerable research attention in the biomedicine. Magnetic materials, as the key components of MagRobots, generate reactive oxygen species (ROS) in vivo to induce tissue/organ damage through Fenton/Fenton‐like reactions, which may hinder the clinical application of MagRobots. Here, the biologically active Prussian blue is generated on the surfaces of MagRobots via an in situ reaction to obtain magnetically actuated ROS‐scavenging nano‐robots (ROSrobots). The generated Prussian blue blocks ROS production and endows the MagRobots with additional functionalities, markedly expanding their potential medical applications. Under the action of a magnetic field, the reconfigurable ROSrobots realize multimode transformation, locomotion, and manipulation in complex environments. Importantly, a simple control method is proposed to achieve movement in 3D geometries to allow the completion of tasks in a complex environment. Furthermore, the osteoarthritis (OA) rat model was employed for proof of concept. Notably, under the guidance of ultrasound imaging, ROSrobots can be accurately injected into the articular cavity to actively target the treatment of OA. This research may further promote the clinical application of MagRobots.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84932986","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}
Suman Timilsina, Hoonjae Shin, K. Sohn, Ji Sik Kim
Increasing ubiquitous collaborative intelligence between humans and machines requires human–machine communication (HMC) that is more human and less machine‐like to accomplish given tasks. Although speech signals are considered the best modes of communication in HMC, background noise often interferes with these signals. Therefore, research focused on integrating lip‐reading technology into HMC has gained significant attention. However, lip‐reading functions effectively only in well‐lit environments. In contrast, HMC may occur daily in dark environments owing to potential energy shortages, increased exploration in darkness, nighttime emergencies, etc. Herein, a possible method for HMC in the dark mode is presented, which is realized based on deep learning motion patterns of persistent luminescence (PL) of the skin surrounding the lips. An ultrasoft PL–polymer composite patch is used to record the motion pattern of the skin during speech in the dark. It is found that visual geometric group network (VGGNET‐5) and residual neural network (ResNet‐34) could predict spoken words in darkness with test accuracies of 98.5% and 98.75%, respectively. Furthermore, these models could effectively distinguish similar‐sounding words such as “around” and “ground.” Dark‐mode communication can allow a wide range of people, including disabled people with limited dexterity and voice tremors, to communicate with artificial intelligence machines.
{"title":"Dark‐Mode Human–Machine Communication Realized by Persistent Luminescence and Deep Learning","authors":"Suman Timilsina, Hoonjae Shin, K. Sohn, Ji Sik Kim","doi":"10.1002/aisy.202200036","DOIUrl":"https://doi.org/10.1002/aisy.202200036","url":null,"abstract":"Increasing ubiquitous collaborative intelligence between humans and machines requires human–machine communication (HMC) that is more human and less machine‐like to accomplish given tasks. Although speech signals are considered the best modes of communication in HMC, background noise often interferes with these signals. Therefore, research focused on integrating lip‐reading technology into HMC has gained significant attention. However, lip‐reading functions effectively only in well‐lit environments. In contrast, HMC may occur daily in dark environments owing to potential energy shortages, increased exploration in darkness, nighttime emergencies, etc. Herein, a possible method for HMC in the dark mode is presented, which is realized based on deep learning motion patterns of persistent luminescence (PL) of the skin surrounding the lips. An ultrasoft PL–polymer composite patch is used to record the motion pattern of the skin during speech in the dark. It is found that visual geometric group network (VGGNET‐5) and residual neural network (ResNet‐34) could predict spoken words in darkness with test accuracies of 98.5% and 98.75%, respectively. Furthermore, these models could effectively distinguish similar‐sounding words such as “around” and “ground.” Dark‐mode communication can allow a wide range of people, including disabled people with limited dexterity and voice tremors, to communicate with artificial intelligence machines.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"207 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75541190","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 traditional von Neumann architecture separates memory from the central processing unit (CPU), resulting in aggravated data transfer bottlenecks between the CPU and memory during a data volume surge. Emerging technologies, such as in‐memory computing (IMC), provide a new way to overcome the limitations due to the separation of memory and computation. However, existing IMC efforts are generally limited to a single (gate‐control or drain‐control) mode of operation to achieve functionality. Herein, a 2D ferroelectric channel device that enables the feasibility of multioperation modes is proposed. In addition, rich functionalities, such as logic, nonvolatile memory, and neuromimetic plasticity modulation, by switching the operating modes are realized. A device that facilitates multimodal operations and a promising technical solution for further development of burgeoning computing architecture is provided.
{"title":"Multioperation Mode Ferroelectric Channel Devices for Memory and Computation","authors":"Yibo Sun, Shuiyuan Wang, Xiaozhang Chen, Zhenhan Zhang, Peng Zhou","doi":"10.1002/aisy.202100198","DOIUrl":"https://doi.org/10.1002/aisy.202100198","url":null,"abstract":"The traditional von Neumann architecture separates memory from the central processing unit (CPU), resulting in aggravated data transfer bottlenecks between the CPU and memory during a data volume surge. Emerging technologies, such as in‐memory computing (IMC), provide a new way to overcome the limitations due to the separation of memory and computation. However, existing IMC efforts are generally limited to a single (gate‐control or drain‐control) mode of operation to achieve functionality. Herein, a 2D ferroelectric channel device that enables the feasibility of multioperation modes is proposed. In addition, rich functionalities, such as logic, nonvolatile memory, and neuromimetic plasticity modulation, by switching the operating modes are realized. A device that facilitates multimodal operations and a promising technical solution for further development of burgeoning computing architecture is provided.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"215 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74075977","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}
Juan Chen, Andrew Scott Johnson, Jada Weber, Oluwafemi Isaac Akomolafe, Jinghua Jiang, C. Peng
Programmable soft materials have shown applications in artificial muscles, soft robotics, flexible electronics, and biomedicines due to their adaptive structural transformations. As an ordered soft material, directional shape changes of liquid crystal elastomer (LCE) can be easily achieved via external stimuli thanks to its anisotropic elasticity. However, harnessing the interplay between molecular ordering, geometry, and shape morphing in this anisotropic material to create programmable and complex shape changes remains a challenge. Here, by integrating the concepts of kirigami or Chinese paper cutting “JianZhi” in the light‐actuated LCE encoded with controlled molecular orientations, various complex 3D shape morphing behaviors are demonstrated. Versatile combinations of fundamental shape changes such as bending, folding, twisting, and rolling are enabled by fine‐tuning the molecular orientations and geometries in the monolithic LCE kirigami. Furthermore, various functions such as fluttering of the Chinese crane bird “QianZhiHe,” arbitrary directional locomotion in the annulus and linear locomotion in the complex Chinese character are also realized. These complex, fast‐response, untethered, remote, reversible, and programmable shape morphologies actuated in a monolith of LCE kirigami will open opportunities in soft robotics and smart materials.
{"title":"Programmable Light‐Driven Liquid Crystal Elastomer Kirigami with Controlled Molecular Orientations","authors":"Juan Chen, Andrew Scott Johnson, Jada Weber, Oluwafemi Isaac Akomolafe, Jinghua Jiang, C. Peng","doi":"10.1002/aisy.202100233","DOIUrl":"https://doi.org/10.1002/aisy.202100233","url":null,"abstract":"Programmable soft materials have shown applications in artificial muscles, soft robotics, flexible electronics, and biomedicines due to their adaptive structural transformations. As an ordered soft material, directional shape changes of liquid crystal elastomer (LCE) can be easily achieved via external stimuli thanks to its anisotropic elasticity. However, harnessing the interplay between molecular ordering, geometry, and shape morphing in this anisotropic material to create programmable and complex shape changes remains a challenge. Here, by integrating the concepts of kirigami or Chinese paper cutting “JianZhi” in the light‐actuated LCE encoded with controlled molecular orientations, various complex 3D shape morphing behaviors are demonstrated. Versatile combinations of fundamental shape changes such as bending, folding, twisting, and rolling are enabled by fine‐tuning the molecular orientations and geometries in the monolithic LCE kirigami. Furthermore, various functions such as fluttering of the Chinese crane bird “QianZhiHe,” arbitrary directional locomotion in the annulus and linear locomotion in the complex Chinese character are also realized. These complex, fast‐response, untethered, remote, reversible, and programmable shape morphologies actuated in a monolith of LCE kirigami will open opportunities in soft robotics and smart materials.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83887698","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：