Recognition Function Research Articles

Driver Behavior Recognition Based on Neural Networks Theory

The article deals with the problem of driver behavior while driving the vehicle. Driver distraction can lead to serious accidents that threaten human life and public property around the world. Solving the problem of preventing dangerous driving behavior will reduce the risk of getting into an accident in the future. Thus, there is a need for a smart vehicle that will support driver behavior recognition functionality. A possible solution to the problem using an artificial neural network for automatic recognition of driver behavior on a real set of driver behavior data is considered. The high accuracy and efficiency of the developed model recognition is obtained.

An Image Detection–Memory–Recognition Artificial Visual Unit Based on Dual‐Gate Phototransistors

Optoelectronic synapses integrating sensing–memory–processing functions have great advantages in neuromorphic computing for visual information processing and complex learning, recognition, and memory in an energy‐efficient manner. Herein, a light‐induced bidirectional response is demonstrated in the proposed WSe2/MoS2 junction field‐effect transistor (JFET) with an extra Ge back gate. The WSe2/MoS2 JFET exhibits high responsivity and detectivity owing to effective modulation by the top junction and back dielectric gates. The unique bidirectional photoresponse and interfacial state storage properties of the device result in significant synaptic excitatory effects under visible light stimulation and remarkable synaptic inhibitory effects under infrared illumination. Optical storage with visible light and optical erasure with infrared light can be achieved in the device based on its synaptic behavior. The conductance changes under different types of illumination can be used to mimic the weight update in a neural network for image recognition. A high accuracy exceeding 98% was achieved in handwritten digit recognition. This visible and infrared dual‐band phototransistor, which integrates image perception, memory, and recognition functionalities, provides a promising solution for self‐driving, surveillance, computer vision, and biomedical imaging applications.

Human-Machine Interaction via Dual Modes of Voice and Gesture Enabled by Triboelectric Nanogenerator and Machine Learning.

With the development of science and technology, human-machine interaction has brought great benefits to the society. Here, we design a voice and gesture signal translator (VGST), which can translate natural actions into electrical signals and realize efficient communication in human-machine interface. By spraying silk protein on the copper of the device, the VGST can achieve improved output and a wide frequency response of 20-2000 Hz with a high sensitivity of 167 mV/dB, and the resolution of frequency detection can reach 0.1 Hz. By designing its internal structure, its resonant frequency and output voltage can be adjusted. The VGST can be used as a high-fidelity platform to effectively recover recorded music and can also be combined with machine learning algorithms to realize the function of speech recognition with a high accuracy rate of 97%. It also has good antinoise performance to recognize speech correctly even in noisy environments. Meanwhile, in gesture recognition, the triboelectric translator is able to recognize simple hand gestures and to judge the distance between hand and the VGST based on the principle of electrostatic induction. This work demonstrates that triboelectric nanogenerator (TENG) technology can have great application prospects and significant advantages in human-machine interaction and high-fidelity platforms.

Evaluating the usability of a prototype gesture-controlled illuminative textile

In the field of human-computer interaction (HCI), recent years have witnessed an increasing interest in smart textiles with gesture recognition functions. This paper reports usability evaluations of a prototype gesture-controlled illuminative textile developed by the authors. This is an interactive woven POF textile system with computer vision-enabled mid-air gesture recognition. For the usability test, 25 participants (11 males and 14 females) aged between 19 and 56 (M = 30.85, SD = 10.8) were randomly recruited. The study was conducted by the means of the user experience questionnaire (UEQ) and the system usability scale (SUS). Results show that participants responded positively to our gesture-controlled illuminative textile in terms of its attractiveness, perspicuity and stimulation but were less positive about its efficiency. The results will be used to make targeted improvements to the existing product design.

Automated Guided Vehicle (AGV) Driving System Using Vision Sensor and Color Code

Recently, the use of Automated Guided Vehicles (AGVs) at production sites has been increasing due to industrial development, such as the introduction of smart factories. AGVs utilizing the wired induction method, which is cheaper and faster than the wireless induction method, are mainly used at production sites. However, the wired guidance AGV operation system has the disadvantage of being limited to small-batch or collaboration-based production sites, since it is difficult to change the driving route. In this paper, we propose an AGV line-scan algorithm that can perform route recognition, driving commands, and operation through color-code recognition using an Arduino controller and a low-cost vision sensor, instead of the optical sensor conventionally used for these functions. When the proposed algorithm is applied to the AGV car, the CMUcam 5 Pixy2 camera identifies the driving path to follow by tracking a black line using the Otsu method. In addition, it can be confirmed that the driving command is executed using the proposed color code by applying the color recognition function of the CMUcam 5 Pixy2.

A hybrid discriminant fuzzy DNN with enhanced modularity bat algorithm for speech recognition

In recent years, speech processing resides a major application in the domain of signal processing. Due to the audibility loss of some speech signals, people with hearing impairment have difficulty in understanding speech, which reintroduces a crucial role in speech recognition. Automatic Speech Recognition (ASR) development is a major challenge in research in the case of noise, domain, vocabulary size, and language and speaker variability. Speech recognition system design needs careful attention to challenges or issues like performance and database evaluation, feature extraction methods, speech representations and speech classes. In this paper, HDF-DNN model has been proposed with the hybridization of discriminant fuzzy function and deep neural network for speech recognition. Initially, the speech signals are pre-processed to eliminate the unwanted noise and the features are extracted using Mel Frequency Cepstral Coefficient (MFCC). A hybrid Deep Neural Network and Discriminant Fuzzy Logic is used for assisting hearing-impaired listeners with enhanced speech intelligibility. Both DNN and DF have some problems with parameters to address this problem, Enhanced Modularity function-based Bat Algorithm (EMBA) is used as a powerful optimization tool. The experimental results show that the proposed automatic speech recognition-based hybrid deep learning model is effectively-identifies speech recognition more than the MFCC-CNN, CSVM and Deep auto encoder techniques. The proposed method improves the overall accuracy of 8.31%, 9.71% and 10.25% better than, MFCC-CNN, CSVM and Deep auto encoder respectively.

Selective fluorescent probe for sensitive determination of bisphenol A based on molecularly imprinted polymers decorated carbon dots derived from citric acid and ethylenediamine

Bisphenol A (BPA) is an endocrine disrupting chemical and poses a grave threat to the human health. Herein, a fluorescent probe constructed with molecularly imprinted polymers decorated carbon dots (CDs@MIPs) was proposed for determination of BPA with high selectivity. The CDs@MIPs were constructed using BPA, 4-vinylpyridine and ethylene glycol dimethacrylate as template, functional monomer and cross linker, respectively. The obtained fluorescent probe not only owned a highly selective recognition function derived from MIPs but also displayed an excellent sensitivity for sensing BPA stemmed from CDs. The fluorescence intensity of CDs@MIPs was varied before and after the removal of BPA templates. The fluorescent decrease fraction of the fluorescent probe demonstrates a nice linearity in BPA concentration range of 10–2000 nM (r2 = 0.9998) and the detection limit is as low as 1.5 nM. The fluorescent probe was triumphantly utilized to sense the level of BPA in real aqueous and plastic samples with good results. Moreover, the fluorescent probe offered a wonderful means for fast identification and sensitive detection of BPA from environmental aqueous samples.

Development of a molecularly imprinted electrochemiluminescence sensor based on bifunctional bilayer structured ZIF-8-based magnetic particles for dopamine sensing

A bilayer-structured ZIF-8 composite with dual functions of sensing and recognition was synthesized, with ZIF-8 serving as an electrochemiluminescence (ECL) probe carrier and molecularly imprinted membrane to construct a molecularly imprinted electrochemiluminescence sensor. The inner layer was a ZIF-8 layer loaded with a luminescent probe, which was obtained by the reaction of zinc ions with 2-methylimidazole on the magnetic [email protected]2O4 surface in the presence of Ru(bpy)32+, the composite magnetic particle is marked as ZIF(Ru)/[email protected]2O4. The outer layer was a layer with recognition function using ZIF-8 as an imprinted membrane, which was obtained by a layer-by-layer self-assembly method on the surface of ZIF(Ru)/[email protected]2O4 with dopamine (DA) as a template molecule, which was marked as ZIF(MIP)/ZIF(Ru)/[email protected]2O4. After eluting the template molecules, the composite particle was immobilized on the surface of a magnetically controlled glassy carbon electrode (MGCE) to obtain a molecular imprinting (MIP) modified electrode. When dopamine molecules were re-adsorbed by the MIP, a charge/energy transfer between dopamine and Ru(bpy)32+ occurred. It subsequently led to the quenching of electrochemiluminescence, which was used as the basis for the detection of dopamine by a molecularly imprinted electrochemiluminescence sensor. When the dopamine concentration was in the range of 1.0 × 10−14 ∼ 5.0 × 10−10 mol/L, the ECL intensity change of the sensor and the dopamine concentration had a good linear relationship, and the detection limit was 4.8 × 10−15 mol/L. The molecularly imprinted electrochemiluminescence sensor was successfully applied to the detection of dopamine in human serum samples.

Incorporating Driving Style Recognition Into MPC for Energy Management of Plug-In Hybrid Electric Buses

Vehicle fuel economy is greatly influenced by the driver’s driving style. To achieve remarkable promotion in the fuel economy, a novel predictive energy management strategy (EMS) with strong adaptability to driving styles is presented for plug-in hybrid electric buses (PHEBs) in this article. First, a combined unsupervised and supervised algorithm for the driving style identification is devised based on instant driving conditions. In the algorithm, a multidimensional Gaussian distribution (MGD)-based analysis on factors influencing driver’s driving style provides valuable inputs for local mean <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> nearest neighbor (LMKNN) algorithm, and outstanding regression ability of the LMKNN returns exact recognition result and then incorporating the driving style recognition function into the model predictive control (MPC) to formulate a driver-oriented predictive EMS, where estimate distribution and particle swarm optimization (ED-PSO) algorithm is introduced to obtain optimal control sequence over a receding horizon. Finally, simulation validations in the MATLAB/Simulink environment show that the total cost of the proposed strategy is decreased by 12.53% compared to the charge-depleting and charge-sustaining (CD-CS) method, without sacrificing the real-time applicability.

Solid‐phase microextraction and cuticular hydrocarbon differences related to reproductive activity in juniper bark borer Semanotus bifasciatus Motschulsky

AbstractCuticular hydrocarbons of Cerambycidae species can function as signals for sex recognition. Little is known about the copulatory signals of the juniper bark borer Semanotus bifasciatus, a major economic threat to Platycladus orientalis Franco in China. Here, we investigated the cuticular hydrocarbons of both sexes of S. bifasciatus to determine the chemically mediated mating signals using the solid‐phase microextraction (SPME) technique with carbowax/divinylbenzene fibers (CAR/DVB) and then analyzed by coupled gas chromatography‐mass spectrometry (GC‐MS). A series of aliphatic saturated straight‐chain n‐alkanes (n‐C23 to n‐C28), internally branched monomethylalkanes at carbons 3, 11, or 13, and dimethylalkanes were identified, which showed no qualitative differences in either sex and were similar in the samples with SPME fiber extraction and those with hexane extraction. The bioassay showed that 11‐methylpentacosane (11‐MeC25), 11‐methylhexacosane (11‐MeC26), and 11‐methylheptacosane (11‐MeC27) have sex‐specific recognition functions that triggered more mating attempts at a female‐specific ratio of 100:4:60 than at a male‐specific ratio of 100:85:50. In addition, the female‐specific ratio of 11‐methylalkanes can elicit about 70% of male mating attempts within about 60 s, whereas live females elicit about 98% of male mating attempts within 25 s. The discrepancy in the initiation of mating attempts by synthetic mixtures and live females suggests that the methyl isomers 3‐MeC25, 3‐MeC27, and/or 11,15‐diMeC27 may also be involved in the mating behavior of S. bifasciatus. These results suggest that 11‐MeC25, 11‐MeC26, and 11‐MeC27 constitute the contact sex pheromone of S. bifasciatus, with the presence or absence of 11‐MeC26 in particular playing an important role in mate recognition by males.

Bimetallic MOF synergy molecularly imprinted ratiometric electrochemical sensor based on MXene decorated with polythionine for ultra-sensitive sensing of catechol

Dual-signal ratiometric molecularly imprinted polymer (MIP) electrochemical sensors with bimetallic active sites and high-efficiency catalytic activity were fabricated for the sensing of catechol (CC) with high selectivity and sensitivity. The amino-functionalization bimetallic organic framework materials (Fe@Ti-MOF-NH2), coupled with two-dimensional layered titanium carbide (MXene) co-modified glassy carbon electrode provides an expanded surface while amplifying the output signal through the electropolymerization immobilization of polythionine (pTHi) and MIP. The oxidation of CC and pTHi were presented as the response signal and the internal reference signal. The oxidation peak current at +0.42 V rose with increased concentration of CC, while the peak currents of pTHi at −0.20 V remained constant. Compared to the common single-signal sensing system, this one (MIP/pTHi/MXene/Fe@Ti-MOF-NH2/GCE), a novel ratiometric MIP electrochemical sensor exhibited two segments wide dynamic range of 1.0–300 μM (R2 = 0.9924) and 300–4000 μM (R2 = 0.9912), as well as an ultralow detection limit of 0.54 μM (S/N = 3). Due to the specific recognition function of MIPs and the advantages of built-in correction of pTHi, the prepared surface imprinting sensor presented an excellent performance in selectivity and reproducibility. Besides, this sensor possessed superior anti-interference ability with ions and biomolecules, excellent reproducibility, repeatability, and acceptable stability. Furthermore, the proposed sensing system exhibits high specific recognition in the determination of environmental matrices and biological fluids in real samples with satisfactory results. Therefore, this signal-enhanced ratiometric MIP electrochemical sensing strategy can accurately and selectively analyze and detect other substances.

A novel Aptamer-induced CHA amplification strategy for ultrasensitive detection of Staphylococcus aureus and NIR-triggered photothermal bactericidal Activity based on aptamer-modified magnetic Fe3O4@AuNRs

The development of multifunctional biosensors integrating recognition and therapeutic functions is critical for ensuring food safety and preventing foodborne diseases. Herein, an integrated design strategy was demonstrated to establish an innovative Fe3O4 @AuNRs-aptasensor for efficient detecting Staphylococcus aureus (S. aureus), which could enrich and photothermally eliminate bacteria under the radiation of near-infrared light irradiation (NIR). The detection assay relies on the binding of aptamer to Fe3O4 @AuNRs (Fe3O4 @ AuNRs-aptasensor) to induce the release of c-aptamer (c-Apt) in the presence of S. aureus, thereby triggering catalytic hairpin assembly (CHA) reaction and restoring the fluorescence of the reporter. The developed biosensor achieved direct, ultrasensitive, and specificity detection of S. aureus with a linear response ranging from 102 to 106 CFU/mL and a detection limit of 101 CFU/mL under optimal conditions. Furthermore, the aptasensor can be applied for the detection of S. aureus in milk with recoveries of 90.3–95.6% at the concentration between 1.0 × 102 and 1.0 × 104 CFU/mL. Additionally, Fe3O4 @AuNRs-aptasensor shows high photothermal sterilization performance under NIR irradiation. The study emphasizes the combination of high sensitivity base on molecular detection and photothermal antibacterial activity of novel nanomaterials activated by NIR light to design multifunctional probe, which show great potential for application in food analysis and early foodborne disease diagnosis.

An empirical study on analysis window functions for text-independent speaker recognition

An empirical study on analysis window functions for text-independent speaker recognition

Integrative transcriptomic profiling reveals the key pathways in the regulation mechanism of fish intestine-spleen immunity during the bacterial challenges

In teleost, the immune roles of the gut-associated lymphoid tissue (GALT) have been well recognized. The antibacterial functions of the spleen have been also documented in various fish species. However, the mechanism of fish intestine-spleen immunity during bacterial infection still remains largely unknown. In this study, an integrative analysis was conducted in the black rockfish intestine and spleen after Aeromonas salmonicida and Edwardsiella tarda infection on the transcriptomic level. The immune gene libraries were constructed in the intestine and spleen. A total of 211 and 253 differentially expressed genes were observed in the immune gene library of spleen and intestine, respectively. One more category of immune genes was found in the intestine (9 categories) than in the spleen (8 categories). Potential evidence of the cooperation in the intestine-spleen axis was obtained based on the functional annotation and enrichment analyses of joint immune genes between intestine and spleen. In addition, bioinformatic and ceRNA analyses for transcriptomic data were performed. Finally, two key immune genes (CO3 and MRC1) and their related non-coding RNAs were observed in the functions of bacterial recognition and binding. According to the pathway “intestinal immune network for IgA production” predicted in the splenic transcriptome by functional enrichment, a novel regulatory pathway of the immunity of the intestine-spleen axis was hypothesized in black rockfish during bacterial infection. Moreover, the regulatory relationships between the immune transcripts in this pathway were verified preliminarily by RT-qPCR. Dual-luciferase reporter assays were performed to determine the regulations between the ceRNAs of MRC1/miR-23b-5p/LNC_00057980 and CO3/miR-214/LNC_00096415 axis. Overall, our findings demonstrate the key pathways of MRC1/miR-23b-5p/LNC_00057980 and CO3/miR-214/LNC_00096415 in the regulation mechanism of intestine-spleen axis during two different Gram-negative bacteria infection in black rockfish.

Radiotherapy/Chemotherapy-Immunotherapy for Cancer Management: From Mechanisms to Clinical Implications.

Cancer immunotherapy has drawn much attention because it can restart the recognition and killing function of the immune system to normalize the antitumor immune response. However, the role of radiotherapy and chemotherapy in cancer treatment cannot be ignored. Due to cancer heterogeneity, combined therapy has become a new trend, and its efficacy has been confirmed in many studies. This review discussed the clinical implications and the underlying mechanisms of cancer immunotherapy in combination with radiotherapy or chemotherapy, offering an outline for clinicians as well as inspiration for future research.

Function of the Speech Recognition of the Smartphone to Automatically Operate a Portable Sample Pretreatment Microfluidic System.

We proposed a portable sample pretreatment microsystem, which can be automatically operated through speech recognition in a smartphone app. The proposed sample pretreatment microsystem consists of a microfluidic chip, an air router, pressure and vacuum lines with air pump motors, six 3-way solenoid valves, and a microcontroller with a Bluetooth module. The command of a human voice conducted the whole process of DNA extraction from pathogenic bacterial samples. Thus, manual interference during the DNA extraction is eliminated, preventing any potential infection from human touch. The palm-sized sample pretreatment microsystem can be run by a portable battery or a conventional smartphone charger. Genomic DNA ofSalmonella typhimuriumwas purified on a chip in less than 1 min with an extraction efficiency of 70 ± 5%.

Elucidating the origins of acyltransferase selectivity in primary and secondary metabolism.

Carrier-protein-S-acyltransferases (ATs) are enzymes that load acyl groups onto carrier proteins (CP). These catalysts can exist as components of larger megasynth(et)ases that act in-cis (i.e., intramolecularly) or as so-called trans-ATs that act “in-trans”, forming intermolecular complexes with a corresponding CP or CP domain. A growing number of crystal structures of trans-ATs, including have been resolved in recent years. In many cases, these structures feature a CP covalently tethered to its cognate AT, revealing the specific protein-protein interactions and conformational reorganization that mediate CP-AT binding and catalysis. To complement insights offered by these experimental structures, we have employed long-timescale molecular dynamics simulations to provide a dynamical understanding of biomolecular recognition and acyltransferase function. These simulations reveal key differences that may explain the distinct specificities of trans-AT that operate in primary and secondary metabolism, while also demonstrating that certain internal rigid body motions of the AT that modulate active site access are common among all trans-ATs examined herein.

Structural investigation of the small heat shock protein HSPB1 in the presence of a phase-separated client.

Many of the proteins found in pathological protein fibrils and aggregates also exhibit tendencies for liquid-liquid phase separation (LLPS) both in vitro and in cells. The transition between the LLPS state and the aggregate state can be modulated by protein chaperones that can block the liquid-to-solid transition and help maintain the LLPS state. Previously, we have characterized the structural features exhibited by FUS LC, a protein that has been demonstrated to undergo LLPS and form fibrils, as it transitions from the LLPS state to the fibril state. Here, we build on this work and examine the α-crystallin chaperone HSPB1 as it interacts with FUS LC in the LLPS state, and compare the structural features of HSPB1 without a client protein to its structural features in the presence of a phase-separated client protein. The heterogeneous nature of the chaperone and client system and the wide range of dynamics adopted by the component proteins present unique challenges for structural interrogation. We therefore integrate solid-state magic angle spinning NMR spectroscopy, coarse-grained molecular dynamics simulations, and cryo-EM to build a model for the dynamics adopted by HSPB1 as it interacts with client proteins, with a specific focus on the role of the N-terminal domain of HSPB1 in client recognition and chaperone function.

An Accurate, Rapid and Cost-Effective Method for T-nos Detection Based on CRISPR/Cas12a.

CRISPR/Cas12a technology is used for nucleic acid detection due to its specific recognition function and non-specific single-stranded DNA cleavage activity. Here, we developed a fluorescence visualisation detection method based on PCR and CRISPR/Cas12a approaches. The method was used to detect the nopaline synthase terminator (T-nos) of genetically modified (GM) crops, circumventing the need for expensive instruments and technicians. For enhanced sensitivity and stability of PCR-CRISPR/Cas12a detection, we separately optimised the reaction systems for PCR amplification and CRISPR/Cas12a detection. Eleven samples of soybean samples were assessed to determine the applicability of the PCR-CRISPR/Cas12a method. The method could specifically detect target gene levels as low as 60 copies in the reaction within 50 min. In addition, accurate detection of all 11 samples confirmed the applicability. The method is not limited by large-scale instruments, making it suitable for mass detection of transgenic components in plants in the field. In conclusion, we developed a new, accurate, rapid, and cost-effective method for GM detection.

A large-scale brain network of species-specific dynamic human body perception.

This ultrahigh field 7T fMRI study addressed the question of whether there exists a core network of brain areas at the service of different aspects of body perception. Participants viewed naturalistic videos of monkey and human faces, bodies, and objects along with mosaic-scrambled videos for control of low-level features. Independent component analysis (ICA) based network analysis was conducted to find body and species modulations at both the voxel and the network levels. Among the body areas, the highest species selectivity was found in the middle frontal gyrus and amygdala. Two large-scale networks were highly selective to bodies, dominated by the lateral occipital cortex and right superior temporal sulcus (STS) respectively. The right STS network showed high species selectivity, and its significant human body-induced node connectivity was focused around the extrastriate body area (EBA), STS, temporoparietal junction (TPJ), premotor cortex, and inferior frontal gyrus (IFG). The human body-specific network discovered here may serve as a brain-wide internal model of the human body serving as an entry point for a variety of processes relying on body descriptions as part of their more specific categorization, action, or expression recognition functions.