Self-Adaptive Photodynamic-to-Photothermal Switch for Smart Antitumor Photoimmunotherapy

Photodynamic therapy (PDT) and photothermal therapy (PTT) possess different merits in cancer phototherapy, but the tumor microenvironment becomes unfavorable during the phototheranostic progress. Herein, we report a self-adaptive cyanine derivative Cy5-TPA with the PDT-dominated state to PTT-dominated state autoswitch feature for enhanced photoimmunotherapy. The incorporation of rotatable triphenylamine (TPA) moiety renders Cy5-TPA with the temperature or intramolecular-motion regulated photoactivities, which shows preferable reactive oxygen species (ROS) generation at lower temperature while stronger photothermal conversion at higher ones. Such a promising feature permits the in situ switch from PDT-dominated state to PTT-dominated state along with intratumoral temperature increase during laser irradiation, which also works in line with the concurrently reduced intratumoral oxygen level, exhibiting a self-adaptive phototherapeutic behavior to maximize the phototherapeutic antitumor outcome. Most importantly, the self-adaptive PDT-dominated state to PTT-dominated state switch also facilitates the sequential generation and release of damage-associated molecular patterns during immunogenic cell death (ICD). Hence, Cy5-TPA demonstrates excellent photoimmunotherapy performance in ICD induction, dendritic cell maturation, and T cell activation for tumor eradication and metastasis inhibition.

Strain Self-Adaptive Iron Selenides Toward Stable Na+ -Ion Batteries with Impressive Initial Coulombic Efficiency

High tap density electrodes play a vital role in developing rechargeable batteries with high volumetric capacities, however, developing advanced electrodes with satisfied capacity, excellent structural stability, and achieving the resulted batteries with a high initial Coulombic efficiency (ICE) and good rate capability with long lifespan simultaneously, are still an intractable challenge. Herein, an ultrahigh ICE of 94.1% and stable cycling of carbon-free iron selenides anode is enabled with a high tap density of 2.57 g cm-3 up to 4000 cycles at 5 A g-1 through strain-modulating by constructing a homologous heterostructure. Systematical characterization and theoretical calculation show that the self-adaptive homologous heterointerface alleviates the stress of the iron selenide anodes during cycling processes and subsequently improves the stability of the assembled batteries. Additionally, the well-formed homologous heterostructure also contributes to the rapid Na+ diffusion kinetic, increased charge transfer, and good reversibility of the transformation reactions, endowing the appealing rate capability of carbon-free iron selenides. The proposed design strategy provides new insight and inspiration to aid in the ongoing quest for advanced electrode materials with high tap densities and excellent stability.

Self-Adaptive Perception of Object's Deformability with Multiple Deformation Attributes Utilizing Biomimetic Mechanoreceptors

The perception of object's deformability in unstructured interactions relies on both kinesthetic and cutaneous cues to adapt the uncertainties of an object. However, the existing tactile sensors cannot provide adequate cutaneous cues to self-adaptively estimate the material softness, especially in non-standard contact scenarios where the interacting object deviates from the assumption of an elastic half-infinite body. This paper proposes an innovative design of a tactile sensor that integrates the capabilities of two slow-adapting mechanoreceptors within a soft medium, allowing self-decoupled sensing of local pressure and strain at specific locations within the contact interface. By leveraging these localized cutaneous cues, the sensor can accurately and self-adaptively measure the material softness of an object, accommodating variations in thicknesses and applied forces. Furthermore, when combined with a kinesthetic cue from the robot, the sensor can enhance tactile expression by the synergy of two relevant deformation attributes, including material softness and compliance. It is demonstrated that the biomimetic fusion of tactile information can fully comprehend the deformability of an object, hence facilitating robotic decision-making and dexterous manipulation.

Self-Adaptive Liquid Film: Dynamic Realization of Dendrite-Free Zn Deposition Toward Ultralong-Life Aqueous Zn Battery

The poor reversibility and stability of Zn metal anode (ZMA) caused by uncontrolled Zn deposition behaviors and serious side reactions severely impeded the practical application of aqueous Zn metal battery. Herein, a liquid-dynamic and self-adaptive protective layer (LSPL) was constructed on the ZMA surface for inhibiting dendrites and by-products formation. Interestingly, the outer LSPL consists of liquid perfluoropolyether (PFPE), which can dynamically adapt volume change during repeat cycling and inhibit side reactions. Moreover, it can also decrease the de-solvation energy barrier of Zn2+ by strong interaction between C-F bond and foreign Zn2+ , improving Zn2+ transport kinetics. For the LSPL inner region, in-situ formed ZnF2 through the spontaneous chemical reaction between metallic Zn and part PFPE can establish an unimpeded Zn2+ migration pathway for accelerating ion transfer, thereby restricting Zn dendrites formation. Consequently, the LSPL-modified ZMA enables reversible Zn deposition/dissolution up to 2000 h at 1 mA cm-2 and high coulombic efficiency of 99.8% at 4 mA cm-2 . Meanwhile, LSPL@Zn||NH4 V4 O10 full cells deliver an ultralong cycling lifespan of 100 00 cycles with 0.0056% per cycle decay rate at 10 A g-1 . This self-adaptive layer provides a new strategy to improve the interface stability for next-generation aqueous Zn battery.

A Self-Adaptive and Regenerable Hydrogel Interfacial Evaporator with Adjustable Evaporation Area for Solar Water Purification

Solar-driven interfacial evaporation is a potential water purification solution. Here, a novel regenerable hydrogel interfacial evaporator is designed with tunable water production. Such an evaporator is fabricated by readily mixing hydroxypropyl chitosan (HPCS) and dibenzaldehyde-functional poly(ethylene glycol) (DF-PEG) at ambient conditions. Dynamic Schiff base bonds bestow on the HPCS/DF-PEG hydrogel (HDH) evaporator self-adaptivity and pH responsiveness. The as-prepared HDH is enabled to spontaneously change shape to adapt to different molds, endowing the evaporator with adjustable evaporation area. The water production performance of the intelligent evaporator is first evaluated using tunable evaporation index (TEI, the tunable evaporated water mass per hour), which can be altered from 0 kg h-1 to 3.21 kg h-1 under one sun. Besides, the large-scale evaporator can be expediently fabricated by virtue of the self-adaptivity. Benefiting from the pH responsiveness, the HDH evaporator is successfully regenerated with the removal of organic dye by the liquefaction-dialysis-regeneration operations. Meanwhile, the re-created evaporator maintains the self-adaptive characteristic and almost constant water evaporation rate compared to that of the initial evaporator. Therefore, this distinctive concept provides a facile strategy to develop smart and recyclable solar-driven interfacial evaporators for flexible water purification.

Temperature Self-Adaptive and Color-Adjustable Smart Window Based on Templated Cholesteric Liquid Crystals

Cholesteric liquid crystals (CLCs) exhibit selective reflection due to their self-assembled helical superstructures. Reconfigurable templates can achieve integration functions via inducing processes of molecular assemblies. Here we demonstrate temperature self-adaptive and color-adjustable smart windows using CLCs, which are fabricated via the templating method and exhibit simultaneous reflections in the visible and infrared spectra. Reflection bands formed by the refilled CLC materials can be adjusted reversibly both upon thermal and electrical actuation. In CLC with adjustable reflection in the infrared, the central wavelength of the infrared reflection band can be adjusted from 950 nm to 1305 nm via temperature, and from 1150 nm to 950 nm via electric field. A temperature variation of 10.3 °C within 55 s was induced by the single-layer templated CLC cell, and a comfortable temperature range could be effectively maintained by the CLC cell in a varied environment. In CLC with dynamic color in the visible spectrum, color shifts from 530 nm to 650 nm tuned by temperature and from 530 nm to 440 nm adjusted by electric field were obtained. Temperature-responsive reflection in the infrared spectrum contributes to automatic thermal management, and electric-field-induced band shift in the visible spectrum enables active dynamic color adjustment. The presented templated CLC smart windows show considerable potential in energy conservation and biological clock regulation fields.

SaMDE: A Self Adaptive Choice of DNDE and SPIDE Algorithms with MRLDE

Differential evolution (DE) is a proficient optimizer and has been broadly implemented in real life applications of various fields. Several mutation based adaptive approaches have been suggested to improve the algorithm efficiency in recent years. In this paper, a novel self-adaptive method called SaMDE has been designed and implemented on the mutation-based modified DE variants such as modified randomized localization-based DE (MRLDE), donor mutation based DE (DNDE), and sequential parabolic interpolation based DE (SPIDE), which were proposed by the authors in previous research. Using the proposed adaptive technique, an appropriate mutation strategy from DNDE and SPIDE can be selected automatically for the MRLDE algorithm. The experimental results on 50 benchmark problems taken of various test suits and a real-world application of minimization of the potential molecular energy problem validate the superiority of SaMDE over other DE variations.

Self-Adaptive Droplet Bouncing on a Dual Gradient Surface

Rapid detachment of impacting droplets from underlying substrate is highly preferred for mass, momentum, and energy exchange in many practical applications. Driven by this, the past several years have witnessed a surge in engineering macrotexture to reduce solid-liquid contact time. Despite these advances, these strategies in reducing contact time necessitate the elegant control of either the spatial location for droplet contact or the range of impacting velocity. Here, this work circumvents these limitations by designing a dual gradient surface consisting of a vertical spacing gradient made of tapered pillar arrays and a lateral curvature gradient characterized as macroscopic convex. This design enables the impacting droplets to self-adapt to asymmetric or pancake bouncing mode accordingly, which renders significant contact time reduction (up to ≈70%) for a broad range of impacting velocities (≈0.4-1.4 m s-1 ) irrespective of the spatial impacting location. This new design provides a new insight for designing liquid-repellent surfaces, and offers opportunities for applications including dropwise condensation, energy conversion, and anti-icing.

Chiroptical switching in the azobenzene-based self-locked [1]rotaxane by solvent and photoirradiation

Because of its dynamic reversible nature and simple regulation properties, rotaxane systems provided a good route for the construction of responsive supramolecular chiral materials. Here, we covalently encapsulate the photo-responsive guest molecule azobenzene (Azo) in a chiral macrocycle β-cyclodextrin (β-CD) to prepare self-locked chiral [1]rotaxane [Azo-CD]. On this basis, the self-adaptive conformation of [Azo-CD] was manipulated by solvent and photoirradiation; meanwhile, dual orthogonal regulation of the [1]rotaxane chiroptical switching could also be realized.

Water-assisted strong underwater adhesion via interfacial water removal and self-adaptive gelation

In nearly all cases of underwater adhesion, water molecules typically act as a destroyer. Thus, removing interfacial water from the substrate surfaces is essential for forming super-strong underwater adhesion. However, current methods mainly rely on physical means to dislodge interfacial water, such as absorption, hydrophobic repulsion, or extrusion, which are inefficient in removing obstinate hydrated water at contact interface, resulting in poor adhesion. Herein, we present a unique means of reversing the role of water to assist in realizing a self-strengthening liquid underwater adhesive (SLU-adhesive) that can effectively remove water at contact interface. This is achieved through multiscale physical-chemical coupling methods across millimeter to molecular levels and self-adaptive strengthening of the cohesion during underwater operations. As a result, strong adhesion over 1,600 kPa (compared to ~100 to 1,000 kPa in current state of the art) can be achieved on various materials, including inorganic metal and organic plastic materials, without preloading in different environments such as pure water, a wide range of pH solutions (pH = 3 to 11), and seawater. Intriguingly, SLU-adhesive/photothermal nanoparticles (carbon nanotubes) hybrid materials can significantly reduce the time required for complete curing from 24 h to 40 min using near-infrared laser radiation due to unique thermal-response of the chemical reaction rate. The excellent adhesion property and self-adaptive adhesion procedure allow SLU-adhesive materials to demonstrate great potential for broad applications in underwater sand stabilization, underwater repair, and even adhesion failure detection as a self-reporting adhesive. This concept of "water helper" has potential to advance underwater adhesion and manufacturing strategies.

An Adaptive Early Stopping Technique for DenseNet169-Based Knee Osteoarthritis Detection Model

Knee osteoarthritis (OA) detection is an important area of research in health informatics that aims to improve the accuracy of diagnosing this debilitating condition. In this paper, we investigate the ability of DenseNet169, a deep convolutional neural network architecture, for knee osteoarthritis detection using X-ray images. We focus on the use of the DenseNet169 architecture and propose an adaptive early stopping technique that utilizes gradual cross-entropy loss estimation. The proposed approach allows for the efficient selection of the optimal number of training epochs, thus preventing overfitting. To achieve the goal of this study, the adaptive early stopping mechanism that observes the validation accuracy as a threshold was designed. Then, the gradual cross-entropy (GCE) loss estimation technique was developed and integrated to the epoch training mechanism. Both adaptive early stopping and GCE were incorporated into the DenseNet169 for the OA detection model. The performance of the model was measured using several metrics including accuracy, precision, and recall. The obtained results were compared with those obtained from the existing works. The comparison shows that the proposed model outperformed the existing solutions in terms of accuracy, precision, recall, and loss performance, which indicates that the adaptive early stopping coupled with GCE improved the ability of DenseNet169 to accurately detect knee OA.

Artificial Leaky Integrate-and-Fire Sensory Neuron for In-Sensor Computing Neuromorphic Perception at the Edge

Neuromorphic perception and computing show great promise in terms of energy efficiency and data bandwidth compared to von Neumann's computing architecture. In-sensor computing allows perception information processing at the edge, which is highly dependent on the functional fusion of receptors and neurons. Here, a leaky integrate-and-fire (LIF) artificial spiking sensory neuron (ASSN) based on a NbO_x memristor and an a-IGZO thin-film transistor (TFT) is successfully developed. The ASSN is fabricated mainly through simple sputter deposition processes, showing the prospect of high process compatibility and potential for integration fabrication. The device shows excellent spike encoding ability to deliver the neuromorphic information through spike rate and time-to-first spike. Moreover, in the ASSN, the a-IGZO TFT not only provides the fundamental spike signal computing function of the artificial neuron but also has NO₂ gas and ultraviolet (UV) light dual sensitivity to introduce the neuromorphic perception capability. As a result, the ASSN successfully exhibits an inhibitory property under NO₂ stimulation while exhibiting an excitatory state under UV light stimulation. Futhermore, self-adaption and lateral regulation circuits between different ASSNs are proposed at the edge in mimicking biological neurons' rich interconnection and feedback mechanisms. The ASSNs successfully achieve self-regulation after a huge response during a burst stimulus. In addition, the neuron transmits a more obvious output when the target-sensitive events occur through the edge internal regulation. The self-adaption and lateral regulation demonstrated in ASSN move an important step forward to in-sensor computing, which provides the potential for a multiscene perception in complex environments.

Continuous Photothermal and Radiative Cooling Energy Harvesting by VO2 Smart Coatings with Switchable Broadband Infrared Emission

Extensive use of renewable and clean energy is one of the promising ways to solve energy/environmental problems and promote the sustainable development of our society. As inexhaustible energy sources, the photothermal (PT) and radiative cooling (RC) energy from the sun and outer space have recently attracted tremendous interest. However, these two kinds of energy utilization have distinctly opposite spectral properties, especially in the infrared range, making it extremely difficult to integrate these two energy harvesting modes within a fixed device for continuous energy collection. Thus, in the current study, we have proposed a spectrally self-adaptive broadband absorber/emitter (SSBA/E) based on vanadium dioxide (VO₂), a typical phase transition material, to achieve continuous energy harvesting via collecting solar thermal energy in PT mode during the day and obtaining cool energy in wide-band RC mode at night. Experimental results show that owing to the phase transition property of the VO₂ layer, these two energy collection modes can be adaptively switched. Specifically, the VO₂-based device shows a broadband infrared emissivity modulation from 0.21 to 0.75 and low critical temperatures (58.4 and 49.2 °C) during the phase transition, leading to continuous energy harvesting with high efficiency. Due to the broadband infrared emission, the RC maximum power of the SSBA/E device was estimated to be 58 W m^-2. The proposed VO₂ smart coatings are also applicable for many other applications such as thermal management of spacecraft, infrared camouflage, or adaptive optical devices.

Self-Adaptive Antibiofilm Effect and Immune Regulation by Hollow Cu2MoS4 Nanospheres for Treatment of Implant Infections

Implant infections are difficult to cure by traditional antibiotic therapy due to bacterial biofilm-induced antibiotic tolerance and impaired immune responses. To efficiently treat implant infections, therapeutic agents need to kill bacteria and regulate the inflammatory response of immune cells during the biofilm elimination process. Herein, multifunctional smart hollow Cu₂MoS₄ nanospheres (H-CMS NSs) with pH-responsive enzyme-like activities were prepared for self-adaptively eliminating biofilms and regulating the inflammation of macrophages in implant infections. During biofilm infection, the tissue microenvironment around implants is acidic. H-CMS NSs with oxidase (OXD)/peroxidase (POD)-like activities can catalyze reactive oxidative species (ROS) generation for directly killing bacteria and polarizing macrophages to a proinflammatory phenotype. Moreover, the POD-like activity and antibacterial property of H-CMS NSs can be further enhanced under ultrasound (US) irradiation. After the elimination of biofilms, the tissue microenvironment around implants shifts from acidic to neutral. H-CMS NSs show catalase (CAT)-like activity and eliminate excessive ROS, which polarizes macrophages to anti-inflammatory phenotype and promotes healing of infected tissue. This work provides a smart nanozyme with self-adaptive regulation of the antibiofilm activity and immune response by regulating ROS generation/elimination according to the different pathological microenvironments in implant infections during the different therapeutic stages.

MXene-Enabled Self-Adaptive Hydrogel Interface for Active Electroencephalogram Interactions

Human-machine interaction plays a significant role in promoting convenience, production efficiency, and usage experience. Because of the universality and characteristics of electroencephalogram (EEG) signals, active EEG interaction is a promising and cutting-edge method for human-machine interaction. The seamless, skin-compliant, and motion-robust human-machine interface (HMI) for active EEG interaction has been in focus. Herein, we report a self-adaptive HMI (PAAS-MXene hydrogel) that can activate rapid gelation (5 s) using MXene cross-linking and conformably self-adapt to the scalp to help improve signal transduction. In addition to exhibiting satisfactory skin compliance, appropriate adhesion, and good biocompatibility, PAAS-MXene has demonstrated electrical performance reliability, such as low impedance (<50 Ω) at physiologically relevant frequencies, stable polarization potential (the rate of change is less than 6.5 × 10^-4 V/min), negligible ion conductivity, and impedance change after 1000 stretch cycles, thereby realizing acquisition of EEG signals. In addition, a cap-free EEG signal acquisition method based on PAAS-MXene has been proposed. These findings confirm the high-precision detection ability of PAAS-MXene for electrocardiogram signals and EEG signals. Therefore, PAAS-MXene offers an option to actively control intention, motion, and vision through active EEG signals.

Bio-Inspired Self-Adaptive Nanocomposite Array: From Non-antibiotic Antibacterial Actions to Cell Proliferation

Pathogenic bacterial infection and poor native tissue integration are two major issues encountered by biomaterial implants and devices, which are extremely hard to overcome within a single surface, especially for those without involvement of antibiotics. Herein, a self-adaptive surface that can transform from non-antibiotic antibacterial actions to promotion of cell proliferation is developed by in situ assembly of bacteriostatic 3,3'-diaminodipropylamine (DADP)-doped zeolitic imidazolate framework-8 (ZIF-8) on bio-inspired nanopillars. Initially, the nanocomposite surface shows impressive antibacterial effects, even under severe bacterial infection, due to the combination of mechano-bactericidal activity from a nanopillar structure and bacteriostatic activity contributed by pH-responsive release of DADP. After the complete degradation of the ZIF-8 layer, the refurbished nanopillars not only can still physically rupture bacterial membrane but also facilitate mammalian cell proliferation, due to the obvious difference in cell size. More strikingly, the nanocomposite surface totally avoids the usage of antibiotics, eradicating the potential risk of antimicrobial resistance, and the surface exhibited excellent histocompatibility and lower inflammatory response properties as revealed by in vivo tests. This type of self-adaptive surface may provide a promising alternative for addressing the intractable implant-associated requirements, where antibiotic-free antibacterial activity and native tissue integration are both highly needed.

Realization of Self-Adaptive Higher Teaching Management Based Upon Expression and Speech Multimodal Emotion Recognition

In the process of communication between people, everyone will have emotions, and different emotions will have different effects on communication. With the help of external performance information accompanied by emotional expression, such as emotional speech signals or facial expressions, people can easily communicate with each other and understand each other. Emotion recognition is an important network of affective computers and research centers for signal processing, pattern detection, artificial intelligence, and human-computer interaction. Emotions convey important information in human communication and communication. Since the end of the last century, people have started the research on emotion recognition, especially how to correctly judge the emotion type has invested a lot of time and energy. In this paper, multi-modal emotion recognition is introduced to recognize facial expressions and speech, and conduct research on adaptive higher education management. Language and expression are the most direct ways for people to express their emotions. After obtaining the framework of the dual-modal emotion recognition system, the BOW model is used to identify the characteristic movement of local areas or key points. The recognition rates of emotion recognition for 1,000 audios of anger, disgust, fear, happiness, sadness and surprise are: 97.3, 83.75, 64.87, 89.87, 84.12, and 86.68%, respectively.

Adaptive Thin Film Temperature Sensor for Bearing's Rolling Elements Temperature Measurement

With the continuous improvement of train speeds, it is necessary to find the possible problems of bearings in time, otherwise they will cause serious consequences. Aiming at the characteristics of rapid temperature change of bearings, a thin film thermocouple temperature sensor was developed to measure the real-time temperature of the bearing’s rolling elements during train operation. Using dc pulse magnetron sputtering technology, Al₂O₃ film, NiCr film, NiSi film, and SiO₂ film were successively deposited on an aluminum alloy substrate. We studied their microstructure, static characteristics, dynamic characteristics, and repeatability. Finally, we installed an adaptive film temperature sensor on the bearing testing machine to measure the temperature of the rolling elements. The results show that the developed temperature sensor has good linearity in the range of 30~180 ℃. The Seebeck coefficient is 40.69 μV/℃, the nonlinear fitting error is less than 0.29%, the maximum repeatability error is less than 4.55%, and the dynamic response time is 1.42 μs. The temperature of the measured rolling elements is 6~10 ℃ higher than that of the outer ring, which can reflect the actual temperature of the bearing operation.

Self-Adaptive Single-Atom Catalyst Boosting Selective Ferroptosis in Tumor Cells

Ferroptosis, resulting from the catastrophic accumulation of lipid reactive oxygen species (ROS) and the inactivation of glutathione (GSH)-dependent peroxidase 4 (GPX4), has emerged as a form of regulated cell death for cancer therapy. Despite progress made with current ferroptosis inducers, efficient systems to trigger ferroptosis remain challenging, owing largely to their low activity, uncontrollable behavior, and even nonselective interactions. Here, we report a self-adaptive ferroptosis platform by engineering a DNA modulator onto the surface of single-atom nanozymes (SAzymes). The modulator could not only specifically intensify the ROS-generating activity but also endow the SAzymes with on-demand GSH-consuming ability in tumor cells, accelerating selective and safe ferroptosis. The self-adaptive antitumor response has been demonstrated in colon cancer and breast cancer, promoting the development of selective cancer therapy.

Self-Adaptive Particle Swarm Optimization-Based Echo State Network for Time Series Prediction

Echo state networks (ESNs), belonging to the family of recurrent neural networks (RNNs), are suitable for addressing complex nonlinear tasks due to their rich dynamic characteristics and easy implementation. The reservoir of the ESN is composed of a large number of sparsely connected neurons with randomly generated weight matrices. How to set the structural parameters of the ESN becomes a difficult problem in practical applications. Traditionally, the design of the parameters of the ESN structure is performed manually. The manual adjustment of the ESN parameters is not convenient since it is an extremely challenging and time-consuming task. This paper proposes an ensemble of five particle swarm optimization (PSO) strategies to design the structure of ESN and then reduce the manual intervention in the design process. An adaptive selection mechanism is used for each particle in the evolution to select a strategy from the strategy candidate pool for evolution. In addition, leaky integration neurons are used as reservoir internal neurons, which are added within the adaptive mechanism for optimization. The root mean squared error (RMSE) is adopted as the evaluation criterion. The experimental results on Mackey-Glass time series benchmark dataset show that the proposed method outperforms other traditional evolutionary methods. Furthermore, experimental results on electrocardiogram dataset show that the proposed method on the ensemble of PSO displays an excellent performance on real-world problems.

Scale-adaptive deep network for deformable image registration

PURPOSE

Multiresolution hierarchical strategy is typically used in conventional optimization-based image registration to capture varying magnitudes of deformations while avoiding undesirable local minima. A rough concept of the scale is captured in deep networks by the reception field of kernels, and it has been realized to be both desirable and challenging to capture convolutions of different scales simultaneously in registration networks. In this study, we propose a registration network that is conscious of and self-adaptive to deformation of various scales to improve registration performance.

METHODS

Dilated inception modules (DIMs) are proposed to incorporate receptive fields of different sizes in a computationally efficient way. Scale adaptive modules (SAMs) are proposed to guide and adjust shallow features using convolutional kernels with spatially adaptive dilation rate learned from deep features. DIMs and SAMs are integrated into a registration network which takes a U-net structure. The network is trained in an unsupervised setting and completes registration with a single evaluation run.

RESULTS

Experiment with two-dimensional (2D) cardiac MRIs showed that the adaptive dilation rate in SAM corresponded well to the deformation scale. Evaluated with left ventricle segmentation, our method achieved a Dice coefficient of (0.93 ± 0.02), significantly better than SimpleElastix and networks without DIM or SAM. The average surface distance was less than 2 mm, comparable to SimpleElastix without statistical significance. Experiment with synthetic data demonstrated the effectiveness of DIMs and SAMs, which led to a significant reduction in target registration error (TRE) based on dense deformation field. The three-dimensional (3D) version of the network achieved a 2.52 mm mean TRE on anatomical landmarks in DIR-Lab thoracic 4DCTs, lower than SimpleElastix and networks without DIM or SAM with statistical significance. The average registration times were 0.002 s for 2D images with size 256 × 256 and 0.42 s for 3D images with size 256 × 256 × 96.

CONCLUSIONS

The introduction and integration of DIMs and SAMs addressed the heterogeneous scale problem in an efficient and self-adaptive way. The proposed method provides an alternative to the inefficient multiresolution registration setups.

A Self-Aware and Scalable Solution for Efficient Mobile-Cloud Hybrid Robotics

Backed by the virtually unbounded resources of the cloud, battery-powered mobile robotics can also benefit from cloud computing, meeting the demands of even the most computationally and resource-intensive tasks. However, many existing mobile-cloud hybrid (MCH) robotic tasks are inefficient in terms of optimizing trade-offs between simultaneously conflicting objectives, such as minimizing both battery power consumption and network usage. To tackle this problem we propose a novel approach that can be used not only to instrument an MCH robotic task but also to search for its efficient configurations representing compromise solution between the objectives. We introduce a general-purpose MCH framework to measure, at runtime, how well the tasks meet these two objectives. The framework employs these efficient configurations to make decisions at runtime, which are based on: (1) changing of the environment (i.e., WiFi signal level variation), and (2) itself in a changing environment (i.e., actual observed packet loss in the network). Also, we introduce a novel search-based multi-objective optimization (MOO) algorithm, which works in two steps to search for efficient configurations of MCH applications. Analysis of our results shows that: (i) using self-adaptive and self-aware decisions, an MCH foraging task performed by a battery-powered robot can achieve better optimization in a changing environment than using static offloading or running the task only on the robot. However, a self-adaptive decision would fall behind when the change in the environment happens within the system. In such a case, a self-aware system can perform well, in terms of minimizing the two objectives. (ii) The Two-Step algorithm can search for better quality configurations for MCH robotic tasks of having a size from small to medium scale, in terms of the total number of their offloadable modules.

Easy Way to Achieve Self-Adaptive Cooling of Passive Radiative Materials

Passive radiative cooling includes using the atmospheric window to emit heat energy to the cold outer space and hence reduce the temperature of objects on Earth. In most cases, radiative cooling is required in summer and suppressed in winter for thermal comfort. Recent radiative cooling materials cannot self-adjust cooling capacity according to season and environment, thus limiting their applications. In this study, we have designed a temperature-controlled phase change structure (TCPCS). The TCPCS benefits radiative coolers to adjust their cooling ability according to the ambient temperature. In the outdoor test, the TCPCS can help the cooler to turn off at low temperatures and turn on at high temperatures automatically; the coolers with and without TCPCS have maximal temperature differences of 9.7 and 19.6 °C, respectively, in a whole day. Furthermore, we have further improved and designed a V-shaped TCPCS that can simultaneously achieve the dual functions of cooling in summer and heating in winter. The TCPCS assembled here is a simple, feasible, and scalable structure for self-adaptive cooling.

A Self-adaptive and Self-Sufficient Energy Harvesting System

Self-adaptive vibration energy harvesters convert the kinetic energy from vibration sources into electrical energy and continuously adapt their resonance frequency to the vibration frequency. Only when the two frequencies match can the system harvest energy efficiently. The harvesting of vibration sources with a time-variant frequency therefore requires self-adaptive vibration harvesting systems without human intervention. This work presents a self-adaptive energy harvesting system that works completely self-sufficiently. Using magnetic forces, the axial load on a bending beam is changed and thus the resonance frequency is set. The system achieves a relative tuning range of 23% at a center frequency of 36.4 Hz. Within this range, the resonance frequency of the harvester can be set continuously and precisely. With a novel optimized method for frequency measurement and with customized electronics, the system only needs 22 µW to monitor the external vibration frequency and is therefore also suitable for environments with low vibration amplitudes. The system was verified on a vibrational test bench and can easily be tailored to a specific vibration source.

The Self-Adaptive Fuel Supply Mechanism in Micro DMFC Based on the Microvalve

To achieve a self-adaptive fuel supply mechanism for the micro direct methanol fuel cell (μDMFC), we designed and developed a thermal control microvalve channel structure, where we considered the relationship between the temperature characteristics, viscosity, and velocity of the methanol solution. Both the single channel model and three-dimensional cell model for the microvalve were established using the COMSOL Multiphysics program. The results demonstrated that in the microvalve channel, the viscosity of the solution decreased, and the flow rate at the microvalve outlet increased with the increasing temperature. Meanwhile, the geometry structure of the microvalve single channel was optimized, so that the effect of the control speed of the microvalve under temperature changes became more prominent. In the full-cell model analysis, a low-velocity methanol solution at the low current density can significantly inhibit methanol crossover. At the high current densities, an increase in the methanol solution flow rate was beneficial to an increase in the cell reaction output. The μDMFC was fabricated and the experiment was conducted, where the results showed that the power density of the self-adaptive cell reached a maximum value of 16.56 mW/cm² in 2 M methanol solution, which was up to 7% better than conventional cell performance. The proposed microvalve structure can effectively improve the output power of the μDMFC during the whole reaction process, and it may improve the stability of the cell operation.

Extended Codebook with Multispectral Sequences for Background Subtraction

The Codebook model is one of the popular real-time models for background subtraction. In this paper, we first extend it from traditional Red-Green-Blue (RGB) color model to multispectral sequences. A self-adaptive mechanism is then designed based on the statistical information extracted from the data themselves, with which the performance has been improved, in addition to saving time and effort to search for the appropriate parameters. Furthermore, the Spectral Information Divergence is introduced to evaluate the spectral distance between the current and reference vectors, together with the Brightness and Spectral Distortion. Experiments on five multispectral sequences with different challenges have shown that the multispectral self-adaptive Codebook model is more capable of detecting moving objects than the corresponding RGB sequences. The proposed research framework opens a door for future works for applying multispectral sequences in moving object detection.

A Theory for Energy-Optimized Operation of Self-Adaptive Vibration Energy Harvesting Systems with Passive Frequency Adjustment

Self-adaptive vibration energy harvesting systems vary their resonance frequency automatically to better exploit changing environmental conditions. The energy required for the adjustment is taken from the energy storage of the harvester module. The energy gained by an adjustment step has to exceed the energy expended on it to justify the adjustment. A smart self-adaptive system takes this into account and operates in a manner that maximizes the energy output. This paper presents a theory for the optimal operation of a vibration energy harvester with a passive resonance-frequency adjustment mechanism (one that only requires energy for the adjustment steps proper, but not during the hold phases between the steps). Several vibration scenarios are considered to derive a general guideline. It is shown that there exist conditions under which a narrowing of the adjustment bandwidth improves the system characteristics. The theory is applied to a self-adaptive energy harvesting system based on electromagnetic transduction with narrowband resonators. It is demonstrated that the novel optimum mode of operation increases the energy output by a factor of 3.6.

Highly Stretchable Superhydrophobic Composite Coating Based on Self-Adaptive Deformation of Hierarchical Structures

With the rapid development of stretchable electronics, functional textiles, and flexible sensors, water-proof protection materials are required to be built on various highly flexible substrates. However, maintaining the antiwetting of superhydrophobic surface under stretching is still a big challenge since the hierarchical structures at hybridized micro-nanoscales are easily damaged following large deformation of the substrates. This study reports a highly stretchable and mechanically stable superhydrophobic surface prepared by a facile spray coating of carbon black/polybutadiene elastomeric composite on a rubber substrate followed by thermal curing. The resulting composite coating can maintain its superhydrophobic property (water contact angle ≈170° and sliding angle <4°) at an extremely large stretching strain of up to 1000% and can withstand 1000 stretching-releasing cycles without losing its superhydrophobic property. Furthermore, the experimental observation and modeling analysis reveal that the stable superhydrophobic properties of the composite coating are attributed to the unique self-adaptive deformation ability of 3D hierarchical roughness of the composite coating, which delays the Cassie-Wenzel transition of surface wetting. In addition, it is first observed that the damaged coating can automatically recover its superhydrophobicity via a simple stretching treatment without incorporating additional hydrophobic materials.

A Self-Adaptive Model-Based Wi-Fi Indoor Localization Method

This paper presents a novel method for indoor localization, developed with the main aim of making it useful for real-world deployments. Many indoor localization methods exist, yet they have several disadvantages in real-world deployments—some are static, which is not suitable for long-term usage; some require costly human recalibration procedures; and others require special hardware such as Wi-Fi anchors and transponders. Our method is self-calibrating and self-adaptive thus maintenance free and based on Wi-Fi only. We have employed two well-known propagation models—free space path loss and ITU models—which we have extended with additional parameters for better propagation simulation. Our self-calibrating procedure utilizes one propagation model to infer parameters of the space and the other to simulate the propagation of the signal without requiring any additional hardware beside Wi-Fi access points, which is suitable for real-world usage. Our method is also one of the few model-based Wi-Fi only self-adaptive approaches that do not require the mobile terminal to be in the access-point mode. The only input requirements of the method are Wi-Fi access point positions, and positions and properties of the walls. Our method has been evaluated in single- and multi-room environments, with measured mean error of 2–3 and 3–4 m, respectively, which is similar to existing methods. The evaluation has proven that usable localization accuracy can be achieved in real-world environments solely by the proposed Wi-Fi method that relies on simple hardware and software requirements.

A self-adaptive and nonmechanical motion autofocusing system for optical microscopes

For the design of a passive autofocusing (AF) system for optical microscopes, many time-consuming and tedious experiments have been performed to determine and design a better focus criterion function, owing to the sample-dependence of this function. To accelerate the development of the AF systems in optical microscopes and to increase AF speed as well as maintain the AF accuracy, this study proposes a self-adaptive and nonmechanical motion AF system. The presented AF system does not require the selection and design of a focus criterion function when it is developed. Instead, the system can automatically determine a better focus criterion function for an observed sample by analyzing the texture features of the sample and subsequently perform an AF procedure to bring the sample into focus in the objective of an optical microscope. In addition, to increase the AF speed, the Z axis scanning of the mechanical motion of the sample or the objective is replaced by focusing scanning performed by a liquid lens, which is driven by an electrical current and does not involve mechanical motion. Experiments show that the reproducibility of the results obtained with the proposed self-adaptive and nonmechanical motion AF system is better than that provided by that of traditional AF systems, and that the AF speed is 10 times faster than that of traditional AF systems. Also, the self-adaptive function increased the speed of AF process by an average of 10.5% than Laplacian and Tenegrad functions.

Solid-Liquid Self-Adaptive Polymeric Composite

A solid-liquid self-adaptive composite (SAC) is synthesized using a simple mixing-evaporation protocol, with poly(dimethylsiloxane) (PDMS) and poly(vinylidene fluoride) (PVDF) as active constituents. SAC exists as a porous solid containing a near equivalent distribution of the solid (PVDF)-liquid (PDMS) phases, with the liquid encapsulated and stabilized within a continuous solid network percolating throughout the structure. The pores, liquid, and solid phases form a complex hierarchical structure, which offers both mechanical robustness and a significant structural adaptability under external forces. SAC exhibits attractive self-healing properties during tension, and demonstrates reversible self-stiffening properties under compression with a maximum of 7-fold increase seen in the storage modulus. In a comparison to existing self-healing and self-stiffening materials, SAC offers distinct advantages in the ease of fabrication, high achievable storage modulus, and reversibility. Such materials could provide a new class of adaptive materials system with multifunctionality, tunability, and scale-up potentials.

A novel approach for arrhythmia diagnosis: Self-adaptive and distribution-free mode

Arrhythmia diagnosis is very significant to ensure human health. In this paper, a new model is developed for arrhythmia diagnosis. A salient feature of the algorithm is a synergistic combination of statistical and fuzzy set-based techniques. It is distribution-free and is realized in an unsupervised mode. Arrhythmia diagnosis is viewed as a certain statistical hypothesis testing. 'Abnormal' is typically a much complex concept, so it can be described with the technology of fuzzy sets which bring a facet of robustness to the overall scheme and play an important role in the successive step of hypothesis testing. Intensive fuzzification is engaged in parameters determination which is self-adaptive and no parameter needs to be specified by the user. The algorithm is validated with a number of experiments, which prove its effectiveness for arrhythmia diagnosis.

Self-Adaptive Strategy Based on Fuzzy Control Systems for Improving Performance in Wireless Sensors Networks

The solutions to cope with new challenges that societies have to face nowadays involve providing smarter daily systems. To achieve this, technology has to evolve and leverage physical systems automatic interactions, with less human intervention. Technological paradigms like Internet of Things (IoT) and Cyber-Physical Systems (CPS) are providing reference models, architectures, approaches and tools that are to support cross-domain solutions. Thus, CPS based solutions will be applied in different application domains like e-Health, Smart Grid, Smart Transportation and so on, to assure the expected response from a complex system that relies on the smooth interaction and cooperation of diverse networked physical systems. The Wireless Sensors Networks (WSN) are a well-known wireless technology that are part of large CPS. The WSN aims at monitoring a physical system, object, (e.g., the environmental condition of a cargo container), and relaying data to the targeted processing element. The WSN communication reliability, as well as a restrained energy consumption, are expected features in a WSN. This paper shows the results obtained in a real WSN deployment, based on SunSPOT nodes, which carries out a fuzzy based control strategy to improve energy consumption while keeping communication reliability and computational resources usage among boundaries.

A Self-Adaptive Behavior-Aware Recruitment Scheme for Participatory Sensing

Participatory sensing services utilizing the abundant social participants with sensor-enabled handheld smart device resources are gaining high interest nowadays. One of the challenges faced is the recruitment of participants by fully utilizing their daily activity behavior with self-adaptiveness toward the realistic application scenarios. In the paper, we propose a self-adaptive behavior-aware recruitment scheme for participatory sensing. People are assumed to join the sensing tasks along with their daily activity without pre-defined ground truth or any instructions. The scheme is proposed to model the tempo-spatial behavior and data quality rating to select participants for participatory sensing campaign. Based on this, the recruitment is formulated as a linear programming problem by considering tempo-spatial coverage, data quality, and budget. The scheme enables one to check and adjust the recruitment strategy adaptively according to application scenarios. The evaluations show that our scheme provides efficient sensing performance as stability, low-cost, tempo-spatial correlation and self-adaptiveness.