Simple Recognition Research Articles

Biomimetic Cell Membrane Layers for the Detection of Insulin and Glucagon.

The growing need for reliable and rapid insulin testing to enhance glycemic management has spurred intensive exploration of new insulin-binding bioreceptors and innovative biosensing platforms for detecting this hormone, along with glucagon, in biological samples. Here, by leveraging the native protein receptors on the HepG2 cell membrane, we construct a simple and chemical-free biomimetic molecular recognition layer for the detection of insulin and glucagon. Unlike traditional affinity sensors, which require lengthy surface modifications on the electrochemical transducers and use of two different capture antibodies to recognize each analyte, this new biomimetic sensing strategy employs a simple drop-casting of a natural cell membrane recognition layer onto the electrochemical transducer. This approach allows for the concurrent capture and detection of both insulin and glucagon. We investigate the presence of insulin and glucagon receptors on the HepG2 cell membrane and demonstrate its multiplexing bioelectronic sensing capabilities through the binding of the captured insulin and glucagon to enzyme-tagged signaling antibodies. This new molecular recognition layer offers highly sensitive simultaneous detection of insulin and glucagon under decentralized conditions, holding considerable promise for the management of diabetes and the development of diverse biomimetic diagnostic platforms.

Evaluation of the electrochemical response of aromatic peptides for biodetection of dopamine

Biologically inspired aromatic peptide-based materials are gaining increasing interest as novel charge transport materials for bioelectronics due to their remarkable electrical response and inherent biocompatibility. In this work, the electrochemical response of ten aromatic amino acids and eleven aromatic peptides has been evaluated to assess the potential of incorporating peptides into electrochemical sensors not as biorecognition elements but as biocompatible electronic materials. While the electrochemical response of amino acids is null in all cases, the hexapeptide of phenylalanine (Phe) capped with eight polyethylene glycol units at the N-terminus and, especially, the cyclic dipeptide formed by two dehydro-phenylalanine residues (cyclo(ΔPhe2)), which organize in fibrillary self-assembled structures of nano- and submicrometric size, respectively, are the most electroactive peptides. Electrodes to electrochemically detect the oxidation of dopamine have been prepared using a plasma-activated polyethylene terephthalate glycol substrate covered with a poly(3,4-ethylenedioxythiophene) layer and a peptide coating deposited at the surface. The highest analytical sensitivity and the lowest limits of detection and quantifications have been obtained for the electrode coated with cyclo(ΔPhe2), which shows much better results than that without peptide. These results, on the one hand, confirm the significant role of electron transport through π-stacking interactions in the electrochemical response of peptides and, on the other hand, demonstrate that peptides can be directly used as electronic materials rather than as simple recognition elements in electrochemical biosensors.

Plant Leaf Disease Detection Using Xception Model

The traditional farming practices have been causing significant financial losses to farmers due to various reasons. However, the implementation of a modern, smart agricultural system utilizing machine learning techniques appears promising in safeguarding farmers and traders against these risks. This advanced system facilitates farmers in identifying common diseases through simple image recognition, employing a variety of image processing methods. Notably, the Convolutional Neural Network (CNN) algorithm stands out as an effective choice among these methods. Interestingly, among the available models, there has been limited utilization of the Xception model, and no comprehensive comparative study involving this model with different classifiers was found. To address this gap, a study was undertaken in two distinct approaches. Firstly, the Xception model demonstrated remarkable accuracy in detecting plant diseases, achieving an impressive 98.3 percent accuracy rate. In comparison, other classifiers such as logistic regression and three additional methods attained accuracy rates of 93 percent and 92 percent, respectively. Secondly, a comparative analysis was conducted on the top 12 papers out of a selection of 45 papers, each employing different methods. The Xception method once again proved to be effective in this context. Through these tests and review studies, the Xception method emerged as a reliable and superior choice. It is expected that this research will provide valuable insights for researchers and stakeholders, potentially guiding the development of new research initiatives in this field.

Employing Deep Neural Networks and High‐Throughput Computing for the Recognition and Prediction of Vein‐Like Structures

In this investigation, convolutional neural networks (CNNs) are leveraged to engineer a simple segmentation and recognition algorithm specialized for the delineation of complex, network‐like morphologies—often termed “vein‐like structures (VLSs)”—in scanning electron microscopy (SEM) imagery. These intricate formations frequently appear during the nitriding treatment of medium‐ to high‐carbon alloy steels. To navigate the multifaceted characteristics of such architectures, CNN‐based methodologies are synergized with high‐throughput thermodynamic computations via Thermo‐Calc. This integration aims to quantify both the theoretical upper bounds and the actual values of the VLSs. By establishing deep neural network models for both theoretical upper bounds and actual measurements, the gap between thermodynamics and thermokinetics in the nitriding process is bridged. Applying this amalgamated predictive schema to 8Cr4Mo4V steel, a groundbreaking departure from conventional paradigms that exclusively depend on thermodynamic calculation‐based diffusion models is effectuated. The emergent model yields transformative implications for the metallurgical sector, paving the way for the refinement of future nitriding algorithms and enhancements in nitriding methodologies.

Proposal and detailed theoretical analysis on a photonic neural network with optically pumped Spin-VCSEL spiking neurons

A dual-layer photonic spiking neural network (PSNN) was constructed, where multiple optically pumped spin vertical-cavity surface-emitting lasers (Spin-VCSELs) were proposed as spiking neurons. Based on a detailed theoretical analysis of leaky integrate-and-fire (LIF) and refractory period characteristics of Spin-VCSEL neurons, the training and testing performance for the studied PSNN was evaluated using two standard pattern classification tasks (Iris dataset, simple digit recognition). The results showed that, by selecting appropriate parameters such as frequency detuning and number of pre-synaptic neurons, etc., higher training/testing accuracies beyond 90% can be obtained. When compared with traditional electrically pumped VCSEL, a threshold reduction of up to 50% can be achieved under nanosecond scale spin relaxation time and circular polarization optical pumping, the feasibility of realizing high accuracy (88%) pattern classification near the reduced threshold was also verified. Therefore, optically pumped Spin-VCSEL neurons can become a valuable new choice for high-performance PSNN with reduced power consumption.

Ultrasensitive strategy for OTA analysis by both recognition-activated multiple isothermal cyclic strand displacement amplification and DNAzyme-mediated cyclic signal reporting mechanism

We propose a recognition-driven ultrasensitive fluorescence sensing strategy for accurate analysis of ochratoxin A (OTA) by taking Mg2+-dependent DNAzyme based catalysis as the final signal output module. Recognition of target OTA destroys the simple double-strand recognition structure and contributes to the liberation of primer probe, which can trigger and activate the primer-mediated multiple isothermal cyclic strand displacement amplification (M-CSDA) process. The designed dual templates (T-P, T-A) can contribute to the generation of enormous nicked products (DNAzyme and primer), which will take effect in the triggering of M-CSDA. Meanwhile, one of the nicked products (DNAzyme) will also take part in the cyclically cleavage of designed hairpin probes (HP) with the presence of the cofactor Mg2+, inducing the recovery of fluorescent signal of quenched hairpin probes. Only the trace amount of target OTA could generate drastic fluorescent signal and ultrasensitive detection of OTA could be well achieved. Under optimized conditions, the detection limit of this method for OTA is 0.59 fg/mL. The characteristics of this method including the simplicity in dual signal amplification design, isothermal operation process and easy fluorescence measurement model exhibit the superior sensitivity and specificity for OTA detection. And this strategy can be further expanded for the design of ultrasensitive aptamer-sensing methods for series analytes.

Turbofan engine health status prediction with neural network pattern recognition and automated feature engineering

PurposeThis study aims to present the concept of aircraft turbofan engine health status prediction with artificial neural network (ANN) pattern recognition but augmented with automated features engineering (AFE).Design/methodology/approachThe main concept of engine health status prediction was based on three case studies and a validation process. The first two were performed on the engine health status parameters, namely, performance margin and specific fuel consumption margin. The third one was generated and created for the engine performance and safety data, specifically created for the final test. The final validation of the neural network pattern recognition was the validation of the proposed neural network architecture in comparison to the machine learning classification algorithms. All studies were conducted for ANN, which was a two-layer feedforward network architecture with pattern recognition. All case studies and tests were performed for both simple pattern recognition network and network augmented with automated feature engineering (AFE).FindingsThe greatest achievement of this elaboration is the presentation of how on the basis of the real-life engine operational data, the entire process of engine status prediction might be conducted with the application of the neural network pattern recognition process augmented with AFE.Practical implicationsThis research could be implemented into the engine maintenance strategy and planning. Engine health status prediction based on ANN augmented with AFE is an extremely strong tool in aircraft accident and incident prevention.Originality/valueAlthough turbofan engine health status prediction with ANN is not a novel approach, what is absolutely worth emphasizing is the fact that contrary to other publications this research was based on genuine, real engine performance operational data as well as AFE methodology, which makes the entire research very reliable. This is also the reason the prediction results reflect the effect of the real engine wear and deterioration process.

Hand Trajectory Recognition by Radar with a Finite-State Machine and a Bi-LSTM

Gesture plays an important role in human–machine interaction. However, the insufficient accuracy and high complexity of gesture recognition have blocked its widespread application. A gesture recognition method that combines state machine and bidirectional long short-term memory (Bi-LSTM) fusion neural network is proposed to improve the accuracy and efficiency. Firstly, gestures with large movements are categorized into simple trajectory gestures and complex trajectory gestures in advance. Afterwards, different recognition methods are applied for the two categories of gestures, and the final result of gesture recognition is obtained by combining the outputs of the two methods. The specific method used is a state machine that recognizes six simple trajectory gestures and a bidirectional LSTM fusion neural network that recognizes four complex trajectory gestures. Finally, the experimental results show that the proposed simple trajectory gesture recognition method has an average accuracy of 99.58%, and the bidirectional LSTM fusion neural network has an average accuracy of 99.47%, which can efficiently and accurately recognize 10 gestures with large movements. In addition, by collecting more gesture data from untrained participants, it was verified that the proposed neural network has good generalization performance and can adapt to the various operating habits of different users.

Variation in encoding context benefits item recognition.

The current study assesses whether varying the encoding context of a repeated event is a potential strategy to improve recognition memory across retrieval contexts. Context variability, also known as encoding variability, has historically been investigated primarily using recall and cued recall tasks, with the consensus being that encoding variability is not necessarily beneficial for episodic retrieval. However, recent studies (see text) suggest that test type may determine the strategy's effectiveness. Aligned with these recent findings, we found consistent benefits to simple item recognition when a word was studied in more variable contexts compared to less variable contexts across four experiments. This main effect of context variability occurred when crossed with a manipulation of repetition spacing and when crossed with a manipulation of encoding-retrieval context match. Variation in encoding contexts beyond the future retrieval context led to better item recognition than repeated study exposures within the future retrieval context. We argue that the current study and other recent findings indicate a need to re-evaluate the historical consensus on encoding variability as a beneficial strategy for learning.

Pyrene‐based ratiometric fluorescent chemosensor for sensitive detection of hypochlorite in a perfect aqueous solution

AbstractWe synthesized a pyrene‐based sensitive fluorescent chemosensor, TPA‐Cl ((E)‐N,N,N‐trimethyl‐2‐oxo‐2‐(2‐(pyren‐1‐ylmethylene)hydrazinyl)ethan‐1‐aminium chloride), to detect hypochlorite in a perfect aqueous solution. TPA‐Cl showed high selectivity for hypochlorite through fluorescence color change from sky blue to blue. The detection limit for hypochlorite was calculated as 0.27 μM, which is a quite low value. Moreover, the presence of other anions or ROS hardly hindered the sensing of hypochlorite by TPA‐Cl. Furthermore, TPA‐Cl could be applied successfully as a test kit for the simple recognition of hypochlorite. Surprisingly, TPA‐Cl is the first pyrene‐based fluorescent chemosensor that can detect ClO− by using the TPA‐Cl‐coated test kit. Moreover, TPA‐Cl could achieve the quantification of ClO− in various environmental water samples. The hydrolytic cleavage and oxidation mechanism of TPA‐Cl by hypochlorite was elucidated through UV–vis and fluorescent spectroscopy, 1H NMR titration, ESI‐MS analysis and DFT calculation.

Activity recognition based on spatio-temporal features with transfer learning

<span lang="EN-US">Human action recognition (HAR) has gathered significant attention recently due to its high demand in various application domains. We explore different CNN architectures for extracting Spatio-Temporal features. In addition to spatial correlation in 2D images, video actions also own the temporal domain attributes. Many research attempts addressed simple activity recognition, but complex activity recognition is still challenging. In the proposed work, the concept of transfer learning consists of two pre-trained networks, ResNet50 and VGG16, which are used to extract Spatiotemporal features and are later fused using the averaging method. Pre-processed frames are considered for the pre-trained network, the pre-processing consists of frame extraction, resizing, and contrast enhancement. The fused features are trained using a multiclass non-linear SVM classifier that achieved an accuracy of 89.71% on the UCF-101 database.</span>

Object Detection for the Visually Impaired

This paper presents the design and development of a mobile application, built using Flutter, that leverages object detection to enhance the lives of visually impaired individuals. The application addresses a crucial challenge faced by this community – the lack of real-time information about their surroundings. We propose a solution that utilizes pre-trained machine learning models, potentially through TensorFlow Lite for on-device processing, to identify objects within the user's field of view captured by the smartphone camera. The application goes beyond simple object recognition. Detected objects are translated into natural language descriptions through text-to-speech functionality, providing crucial auditory cues about the environment. This real-time information stream empowers users to navigate their surroundings with greater confidence and independence. Accessibility is a core principle of this project. The user interface will be designed with compatibility for screen readers, ensuring seamless interaction for users who rely on assistive technologies. Haptic feedback mechanisms will be incorporated to provide non-visual cues and enhance the user experience. The ultimate goal of this project is to create a user-friendly and informative application that empowers visually impaired people to gain greater independence in their daily lives. The application has the potential to improve spatial awareness, foster a sense of security, and promote overall inclusion within society

Morphologic Features of Invasion in Lung Adenocarcinoma: Diagnostic Pitfalls.

Reproducibility of pulmonary invasive adenocarcinoma diagnosis is poor when applying the World Health Organization (WHO) classification. In this article, we aimed first to explain by 3-dimensional morphology why simple pattern recognition induces pitfalls for the assessment of invasion as applied in the current WHO classification of pulmonary adenocarcinomas. The underlying iatrogenic-induced morphologic alterations in collapsed adenocarcinoma in situ overlap with criteria for invasive adenocarcinoma. Pitfalls in seemingly acinar and papillary carcinoma are addressed with additional cytokeratin 7 and elastin stains. In addition, we provide more stringent criteria for a better reproducible and likely generalizable classification.

Graphs obtained by disjoint unions and joins of cliques and stable sets

We consider the set of graphs that can be constructed from a one-vertex graph by repeatedly adding a clique or a stable set linked to all or none of the vertices added in previous steps. This class of graphs contains various well-studied graph families such as threshold, domishold, co-domishold and complete multipartite graphs, as well as graphs with linear clique-width at most 2. We show that it can be characterized by three forbidden induced subgraphs as well as by properties involving maximal stable sets and minimal dominating sets. We also give a simple recognition algorithm and formulas for the computation of the stability and domination numbers of these graphs.

Sandwich-like voltametric immunosensing of interleukin-8 based on β-cyclodextrin/carbon nanotubes and methylthionine chloride@UIO-66 framework.

The level of interleukin-8 (IL-8) in the body is an effective factor for the early diagnosis of acute tubular necrosis and oral tumor. In this work, a novel sandwich-like voltametric immunosensor (SVS) of IL-8 was constructed by preparing β-cyclodextrin/carbon nanotube (CD/CNT) to immobilize primary antibody (PAb) of IL-8 and UIO-66-NH2 MOFs structure to immobilize second antibody (SAb) and methylene blue (Mb) probe. In this designed SVS, the prepared CD/CNT nanohybrid with large surface area and conductivity can immobilize PAb via simple host-guest recognition, and UIO-66-NH2 provided an ideal platform to accommodate SAb and a large number of Mb molecules as signal-amplifier. In the existence of target IL-8, the current peak of Mb from the SVS assay increases with the increasement of IL-8 level. Through optimizing and adjusting various factors, a wide linearity (0.001-2.5ngmL-1) and low analytical limit (0.2pgmL-1) of IL-8 were realized, so it's expected the developed SVS strategy has significant applications for the detection of IL-8.

Design of Network-on-Chip-Based Restricted Coulomb Energy Neural Network Accelerator on FPGA Device.

Sensor applications in internet of things (IoT) systems, coupled with artificial intelligence (AI) technology, are becoming an increasingly significant part of modern life. For low-latency AI computation in IoT systems, there is a growing preference for edge-based computing over cloud-based alternatives. The restricted coulomb energy neural network (RCE-NN) is a machine learning algorithm well-suited for implementation on edge devices due to its simple learning and recognition scheme. In addition, because the RCE-NN generates neurons as needed, it is easy to adjust the network structure and learn additional data. Therefore, the RCE-NN can provide edge-based real-time processing for various sensor applications. However, previous RCE-NN accelerators have limited scalability when the number of neurons increases. In this paper, we propose a network-on-chip (NoC)-based RCE-NN accelerator and present the results of implementation on a field-programmable gate array (FPGA). NoC is an effective solution for managing massive interconnections. The proposed RCE-NN accelerator utilizes a hierarchical-star (H-star) topology, which efficiently handles a large number of neurons, along with routers specifically designed for the RCE-NN. These approaches result in only a slight decrease in the maximum operating frequency as the number of neurons increases. Consequently, the maximum operating frequency of the proposed RCE-NN accelerator with 512 neurons increased by 126.1% compared to a previous RCE-NN accelerator. This enhancement was verified with two datasets for gas and sign language recognition, achieving accelerations of up to 54.8% in learning time and up to 45.7% in recognition time. The NoC scheme of the proposed RCE-NN accelerator is an appropriate solution to ensure the scalability of the neural network while providing high-performance on-chip learning and recognition.

Multiparty conversation via multirobot system: incorporation of nonverbal user responses for continued conversation

Recent years have seen the advent of conversational humanoid robots. Implementing multiple robots is a promising approach for continuing human–robot conversations when a robot encounters speech-recognition errors. This strategy is effective for the user's verbal responses; however, people generally use nonverbal responses, such as nods or smiles, to respond to the interlocutor. In this study, we proposed a conversational strategy for twin robots in which the second robot recognized a human's nonverbal responses and interrupted the conversation by mentioning these responses. Moreover, we developed an interrogative dialogue system using simple nonverbal recognition modules. To verify the effectiveness of this conversational strategy, a subject-based experiment was conducted in which humans conversed with the two robots, and their impressions were evaluated through a questionnaire. We compared the outcomes under two conditions: whether the second robot's interruption was inserted or otherwise. Our results indicate that language-only ineffectiveness in responding to ambiguous responses regarding satisfaction and comprehension was mitigated. Thus, such a dialogue system is advantageous because it can facilitate robust conversation without relying solely on speech recognition.

Two validation studies of a performance validity test for autistic adults

In two studies we examined the potential of a simple emotion recognition task, the Morel Emotional Numbing Test (MENT), as a performance validity test (PVT) for autism-related cognitive difficulties in adulthood. The aim of a PVT is to indicate non-credible performance, which can aid the interpretation of psychological assessments. There are currently no validated PVTs for autism-related difficulties in adulthood. In Study 1, non-autistic university students (aged 18–46 years) were instructed to simulate that they were autistic during a psychological assessment (simulation condition; n = 26). These students made more errors on the MENT than those instructed to do their best (control condition; n = 26). In Study 2, we tested how well autistic adults performed on the MENT. We found that clinically diagnosed autistic adults and non-autistic adults (both n = 25; 27–57 years; IQ > 80) performed equally well on the MENT. Moreover, autistic adults made significantly fewer errors than the instructed simulators in Study 1. The MENT reached a specificity of ≥98% (identifying 100% of non-simulators as non-simulator in Study 1 and 98% in Study 2) and a sensitivity of 96% (identifying 96% of simulators as simulator). Together these findings provide the first empirical evidence for the validity of the MENT as a potential PVT for autism-related cognitive difficulties.

Simple recognition of hand gestures using single-channel EMG signals.

Electromyography (EMG) signals are used for many different purposes, such as recording and measuring the electrical activity generated by varying the body's skeletal muscles. Biosignals are different types of biomedical signals, like EMG signals, which can be used for the neural linkage with computers and are obtained from a particular part of the body such as tissue, muscle, organ, or cell system like the nervous system. Surface electromyography (SEMG) is a non-invasive method that can be used as an effective system for controlling upper arm prostheses. This study focused on classifying the five types of distinct finger movements investigated in four unique channels.We have used a classification technique, the k-nearest neighbors (KNN), to categorize the collected samples. Two time-domain features, (a) maximum (Max) and (b) minimum (Min), were used with one of these three features separately: mean absolute value (MAV), root mean square (RMS), and simple square integral (SSI) to classify gestures. We chose classification accuracy as a criterion for evaluating the effectiveness of every classification. We figured out that the first grouping, that is, (MAV, Max, Min), was the best choice for classification. The accuracy percentage in the four channels for the first group was 91.0%, 89.9%, 89.8%, and 96.0%, respectively.

Molecularly imprinted 2D photonic crystal hydrogel sensor for sodium dichloroisocyanurate.

Sodium dichloroisocyanurate (SDIC) is an efficient, safe and convenient halogen disinfectant that is widely used for hospital, tableware and swimming pool disinfection. In order to ensure its effective use and safety, especially in clinical settings, effective identification methods are necessary. The effective chlorine content is one of the quality standards for chlorine-containing disinfectants, but its complex experimental operation as well as poor specificity and portability limit its application. In contrast, testing based on molecularly imprinted photonic crystal sensors provides excellent performance. Therefore, it is of great significance to establish a new and simple SDIC recognition method. We prepared a novel molecularly imprinted two-dimensional (2D) photonic crystal hydrogel (MIPH) for sensitive and label-free recognition of SDIC. The response performance of the resultant MIPH sensor was determined by monitoring particle spacing changes in the polystyrene (PS) 2D photonic crystals embedded in the hydrogel. Particle spacing changes were recorded by measuring changes in the diameter of the Debye diffraction ring of the MIPH sensor. As the concentration of SDIC in solution increased from 1 × 10-2 to 1.0 mmol L-1, the diameter of the Debye diffraction ring increased by 6 mm, and the corresponding photonic crystal particle spacing decreased by 56 nm. The particle spacing changes in the MIPH sensor showed a linear relationship with the SDIC concentration in the range of 1 × 10-2-1.0 mmol L-1, and the limit of detection (S/N = 3) was found to be 3 × 10-3 mmol L-1. The constructed hydrogel sensor was successfully used to detect SDIC in sodium dichloroisocyanurate disinfectant powder, demonstrating recoveries of 96-100% and RSD of 7.2-7.6%. Our molecularly imprinted SDIC photonic crystal hydrogel provides a universal strategy for designing sensors for other clinical disinfectants.