Pattern Recognition Accuracy Research Articles

The role of AI in enhancing hospital operational efficiency and patient care

Artificial intelligence is changing the way hospitals work by being more efficient and patient-centric. This paper explores how AI technologies, such as machine learning and natural language processing, are integrated into healthcare systems to optimize data management, diagnostics, and personalized medicine. Applications driven by AI streamline workflows, facilitate clinical decision-making, and mitigate human error, thereby improving patient outcomes. Some of the key operational efficiencies that can be facilitated by AI include predictive analytics for better resource allocation, automated scheduling to minimize wait times, and supply chain optimization for effective delivery of medical services.The paper describes how the use of AI is instrumental in transforming patient care through a diagnostic precision, personalized medicine and remote monitoring. The use of ML-algorithm powered diagnostic tools increases image and pattern recognition accuracy through early and accurate detection. Personalized medicine is delivered through AI's capability to personalise treatment plans for individualised patient profiles to improve care outcomes. Remote monitoring of the patient can be done at real-time by using complex sensors and telecommunication tools regarding chronic and critical conditions.Despite these gains, integration barriers, concerns about bias and privacy, and the need for extensive education of healthcare professionals remain. In conclusion, the study emphasizes further innovation and interdisciplinary collaboration toward harnessing the full power of AI in healthcare.This paper also outlines future directions, emphasizing AI's capacity to revolutionize healthcare with advancements in analytics, intelligent hospital frameworks, and clinical research. By aligning technical innovation with ethical considerations, AI promises to create a smarter, patient-centric healthcare ecosystem. The findings advocate for strategic adoption of AI technologies to achieve enhanced operational efficiency, cost reduction, and superior patient care.

Ultraweak light-modulated heterostructure with bidirectional photoresponse for static and dynamic image perception

The human visual system’s adaptability to varying brightness levels has inspired the development of optoelectronic neuromorphic devices. However, achieving bidirectional photoresponse, essential for mimicking these functions, often requires high operation voltages or high light intensities. Here, we propose a bidirectional ZnO/CsPbBr3 heterostructure based neuromorphic image sensor array (10 × 10 pixels) capable of ultraweak light stimulation. The device demonstrates positive and negative photoconductivity through the ionization and deionization of oxygen vacancies in the ZnO channel, extendable to other ZnO/perovskites and IGZO/perovskites heterostructures. Operating at a reduced bias voltage of 2.0 V, the array achieves synaptic weight updates under green (525 nm) and UV (365 nm) light with light intensities ranging from as low as 45 nW/cm² to 15.69 mW/cm², mimicking basic synaptic functions and visual adaptation. It performs multiple image pre-processing tasks, including background denoising and encoding spatiotemporal motion, achieving 92% accuracy in pattern recognition and 100% accuracy in motion clustering. This straightforward strategy highlights a potential for intelligent visual systems capable of real-time image processing under low voltage and dark conditions.

A Convolutional Neural Network-Based Method for Distinguishing the Flow Patterns of Gas-Liquid Two-Phase Flow in the Annulus

In order to improve the accuracy and efficiency of flow pattern recognition and to solve the problem of the real-time monitoring of flow patterns, which is difficult to achieve with traditional visual recognition methods, this study introduced a flow pattern recognition method based on a convolutional neural network (CNN), which can recognize the flow pattern under different pressure and flow conditions. Firstly, the complex gas–liquid distribution and its velocity field in the annulus were investigated using a computational fluid dynamics (CFDs) simulation, and the gas–liquid distribution and velocity vectors in the annulus were obtained to clarify the complexity of the flow patterns in the annulus. Subsequently, a sequence model containing three convolutional layers and two fully connected layers was developed, which employed a CNN architecture, and the model was compiled using the Adam optimizer and the sparse classification cross entropy as a loss function. A total of 450 images of different flow patterns were utilized for training, and the trained model recognized slug and annular flows with probabilities of 0.93 and 0.99, respectively, confirming the high accuracy of the model in recognizing annulus flow patterns, and providing an effective method for flow pattern recognition.

Perovskite Thin-Film Transistors for Ultra-Low-Voltage Neuromorphic Visions.

Perovskite thin-film transistors (TFTs) simultaneously possessing exceptional carrier transport capabilities, nonvolatile memory effects, and photosensitivity have recently attracted attention in fields of both complementary circuits and neuromorphic computing. Despite continuous performance improvements through additive and composition engineering of the channel materials, the equally crucial dielectric/channel interfaces of perovskite TFTs have remained underexplored. Here, it is demonstrated that engineering the dielectric/channel interface in 2D tin perovskite TFTs not only enhances the performance and operational stability for their utilization in complementary circuits but also enables efficient synaptic behaviors (optical information sensing and storage) under an extremely low operating voltage of -1mV at the same time. The interface-engineered TFT arrays operating at -1mV are then demonstrated as the preprocessing hardware for neuromorphic visions with pattern recognition accuracy of 92.2% and long-term memory capability. Such a low operating voltage provides operational feasibility to the design of large-scale-integrated and wearable/implantable neuromorphic hardware.

Nitrogen-doped carbon quantum dot-decorated In2O3 synaptic transistors for neuromorphic computing

Nitrogen-doped carbon quantum dots (N-CQDs) are promising materials for electronic devices due to their variable bandgap and structural stability. Here, we integrate N-CQDs into In2O3 synaptic transistors with electrolyte gating, resulting in a hybrid structure. The surface functional groups and defects of N-CQDs empower the charge trapping mechanism, permitting controlled conduction and charge regulation, which are crucial for emulating linear and symmetric artificial synaptic devices. Devices incorporating N-CQDs demonstrate enhanced stability and memory characteristics, low energy consumption, consistent retention, and a significant hysteresis window across multiple voltage cycles. Finally, the study emulates biological synapses and cognitive functions, achieving an energy consumption of 10 fJ per synaptic event and a pattern recognition accuracy of 91.2% on the MNIST dataset in hardware neural networks. This work demonstrates the potential of well-manipulating charge trapping in N-CQDs to develop high-performance, nonvolatile synaptic devices.

Partial Discharge Data Augmentation and Pattern Recognition Method Based on DAE-GAN

Accurate identification of partial discharge (PD) and its types is essential for assessing the operating conditions of electrical equipment. To enhance PD pattern recognition under imbalanced and limited sample conditions, a method based on a Deep Autoencoder-embedded Generative Adversarial Network (DAE-GAN) is proposed. First, the Deep Autoencoder (DAE) is embedded within the Generative Adversarial Network (GAN) to improve the realism of generated samples. Then, complementary PD data samples are introduced during GAN training to address the issue of limited sample size. Lastly, the model’s discriminator is fine-tuned with augmented and balanced training data to enable PD pattern recognition. The DAE-GAN method is used to augment data and recognize patterns in experimental PD signals. The results demonstrate that, under imbalanced and small sample conditions, DAE-GAN generates more authentic PD samples with improved probability distribution fitting compared to other algorithms, leading to varying levels of enhancement in pattern recognition accuracy.

Analog‐Digital Hybridity of Resistive Switching in Ion‐Irradiated BiFeO3 Memristor for Synergistic Neuromorphic Functionality and Artificial Learning

AbstractMemristors‐based neuromorphic devices represent emerging computing architectures to perform complex tasks by outpacing the traditional Von‐Neumann architectures in terms of speed, and energy efficiency. In this work, the resistive switching (RS) behavior of sol‐gel grown and ion‐irradiated BFO films is investigated under electrical stimulus. The Ag/BFO/FTO memristors emulate a combination of digital and analog RS behavior within a single device. The possible mechanism of analog digital hybridity is addressed by considering the formation of the conducting filament by oxygen vacancies, Ag+ ions and Schottky barrier height modulation. The ion‐irradiated BFO samples are analyzed using the Raman, XRD, and XPS studies. To uphold bioinspired synaptic actions, crucial synaptic functionalities like pair‐pulse facilitation and long‐term potentiation/depression are effectively achieved. More intricate synaptic behaviors are also demonstrated such as spike‐time‐dependent plasticity and Pavlovian classical conditioning, which represent the prominent attributes of both learning and forgetting behavior. Additionally, high pattern recognition accuracy (96.1%) is achieved in an artificial neural network simulation by using the synaptic weights of the memristors. This synergistic effect of digital and analog RS in ion‐irradiated BFO can be beneficial for the emulation of complex learning behavior as well as its incorporation into low‐power neuromorphic computing.

A robust myoelectric pattern recognition framework based on individual motor unit activities against electrode array shifts

Background and objectiveElectrode shift is always one of the critical factors to compromise the performance of myoelectric pattern recognition (MPR) based on surface electromyogram (SEMG). However, current studies focused on the global features of SEMG signals to mitigate this issue but it is just an oversimplified description of the human movements without incorporating microscopic neural drive information. The objective of this work is to develop a novel method for calibrating the electrode array shifts toward achieving robust MPR, leveraging individual motor unit (MU) activities obtained through advanced SEMG decomposition. MethodsAll of the MUs from decomposition of SEMG data recorded at the original electrode array position were first initialized to train a neural network for pattern recognition. A part of decomposed MUs could be tracked and paired with MUs obtained at the original position based on spatial distribution of their MUAP waveforms, so as to determine the shift vector (describing both the orientation and distance of the shift) implicated consistently by these multiple MU pairs. Given the known shift vector, the features of the after-shift decomposed MUs were corrected accordingly and then fed into the network to finalize the MPR task. The performance of the proposed method was evaluated with data recorded by a 16 × 8 electrode array placed over the finger extensor muscles of 8 subjects performing 10 finger movement patterns. ResultsThe proposed method achieved a shift detection accuracy of 100 % and a pattern recognition accuracy approximating to 100 %, significantly outperforming the conventional methods with lower shift detection accuracies and lower pattern recognition accuracies (p < 0.05). ConclusionsOur method demonstrated the feasibility of using decomposed MUAP waveforms’ spatial distributions to calibrate electrode shift. This study provides a new tool to enhance the robustness of myoelectric control systems via microscopic neural drive information at an individual MU level.

Semi-supervised learning for gas insulated switchgear partial discharge pattern recognition in the case of limited labeled data

Semi-supervised learning has better and more efficient performance than supervised algorithms in the case of limited labeled data. Existing methods for diagnosing partial discharge (PD) insulation defects in gas-insulated switchgear (GIS) equipment can only be effective if there is sufficient labeled data. However, in the actual working conditions of GIS equipment, insulation defect data is very scarce, where labeled data is more expensive to obtain and most of the data is unlabeled. In the case of limited PD labeled data, it is still a serious challenge to achieve higher classification accuracy of GIS PD pattern recognition. Therefore, we propose a semi-supervised self-training algorithm based on density peaks of local neighbor Information. Firstly, an improved density peak clustering algorithm based on local neighbor information is proposed, which no longer depends on the truncation distance, and considers the local information to better reflect the local density. Secondly, using local neighbor Information of labeled data, the criterion of confidence of unlabeled data is improved. Then, the PD unlabeled data with pseudo-labels are used to build a strong classifier for GIS PD pattern recognition. The experimental results show that the proposed algorithm has higher classification accuracy than other semi-supervised algorithms. When the proportion of labeled data is 10 %, the recognition accuracy can reach 65.98 %, which is the highest in the comparison algorithm. The proposed algorithm provides a feasible solution for GIS PD pattern recognition in the case of limited labeled data.

Optically and electrically modulated artificial synapses based on MoS2/PZT ferroelectric field-effect transistor for neuromorphic computing system

To present an advanced device scheme of high-performance optoelectronic synapses, herein, we demonstrated the electrically- and/or optically-drivable multifaceted synaptic capabilities on the 2D semiconductor channel-based ferroelectric field-effect transistor (FeFET) architecture. The device was fabricated in the form of the MoS2/PZT FeFET, and its synaptic weights were effectively controlled by dual stimuli (i.e., both electrical and optical pulses simultaneously) as well as single stimuli (i.e., either electrical or optical pulses alone). This could be attributed to the electrical pulse-tunable strong ferroelectric polarization in PbZrxTi1−xO3 (PZT) as well as the polarization field-enhanced persistent photoconductivity effect in MoS2. Additionally, it was confirmed that the proposed device possesses substantial activity, achieving approximately 95 % pattern recognition accuracy. The results substantiate the great potential of the 2D semiconductor channel-based FeFET device as a high-performance optoelectronic synaptic platform, marking a pivotal stride towards the realization of advanced neuromorphic computing systems.

Pattern recognition of control charts based on data feature enhancement and ensemble learning of classifiers for dimensional accuracy of products

Product quality in manufacturing is directly related to the reliability, durability and safety of the product. Product quality can be controlled by building a product control chart pattern recognition model. The complexity and temporal sequence of product quality data make it difficult to extract effective control chart features, and it is difficult for common classifiers to play an effective role for each control chart pattern category, thus affecting the accuracy of pattern recognition. Therefore, this paper proposes a data feature enhancement processing method that combines Smote algorithm and smooth shift processing. This method reveals data features by performing feature enhancement processing on raw data and extracts statistical and shape features for dimensionality reduction to improve recognition accuracy and efficiency. Based on this approach, this paper also proposes an ensemble learning model based on the Stacking method, which incorporates BP, ELM, PNN and SVM classifiers for control chart pattern recognition. Through extensive experimental validation, the data feature enhancement method improves the accuracy of the weak classifier normal pattern recognition by 30%, and effectively reduces the misclassification in the quality control process. The ensemble learning model is stronger than the weak classifier, and its recognition accuracy can reach 97.31%.

Image analysis by fractional-order weighted spherical Bessel-Fourier moments

Moment and moment invariants as effective feature descriptors have been widely applied in image analysis, pattern recognition and computer vision applications. Scholars have demonstrated that fractional-order orthogonal moments outperform their corresponding moments in representing the fine details of a given image. To this end, we propose a new fractional-order orthogonal moments based on fractional-order weighted spherical Bessel polynomial in this paper, which is named as Fractional-order weighted Spherical Bessel-Fourier Moments (FrSBFMs). Moreover, to address the issue of color image analysis, FrSBFMs are integrated with quaternion theory to develop Quaternion FrSBFMs (QFrSBFMs). In addition, the rotation invariance and parameter α analysis of FrSBFMs and QFrSBFMs are discussed in detail. The experimental results show the effectiveness of the proposed FrSBFMs and QFrSBFMs in terms of image reconstruction capability, pattern recognition accuracy and zero-watermark verification.

A liquid optical memristor using photochromic effect and capillary effect

In the era of the Internet of Things, photonic neuromorphic computing presents a promising method for real-time, local processing of vast quantities of data. However, the rigidity of materials used in such devices can considerably impact performance and longevity when subjected to mechanical deformation. In this study, we introduce a liquid optical memristor (LOM) based on an organic-inorganic hybrid in a liquid state. This novel approach offers programmable optical properties and significant mechanical flexibility thanks to the robust photochromic and capillary effects. We have developed a LOM with a 24 dB cm−1 modulation depth and over 3-bit nonvolatile memory states. By controlling the droplet morphology to mimic a synapse-like shape, the LOM can withstand strains over 400% and endure misalignment and bending. Furthermore, our findings substantiate the application of LOM for photonic neuromorphic computing systems, yielding 100% accuracy in pattern recognition. The easily-integratable LOM paves the way for the creation of flexible and wearable photonic neuromorphic computing systems.

Maximizing the Synaptic Efficiency of Ferroelectric Tunnel Junction Devices Using a Switching Mechanism Hidden in an Identical Pulse Programming Learning Scheme

Memristors play a pivotal role in advanced computing, with memristor‐based crossbar arrays showing promise for various artificial neural networks. Among these, HfO2‐based ferroelectric tunnel junctions (FTJs) stand out as ideal synaptic devices for neuromorphic computing. Their compatibility with the complementary metal oxide semiconductor process and intrinsic energy efficiency make them particularly appealing. While an increasing number of studies adopt identical pulse programming (IPP) with short width to update the conductance of HfO2‐based FTJs synaptic devices, conventional ferroelectric switching models fall short in describing updates the conductance with the IPP scheme. Consequently, studies achieving conductance updates via IPP lack an underlying mechanism explanation, potentially limiting the application of HfO2‐based FTJs as synaptic devices. This study explores the potential of ferroelectric Zr‐doped HfO2 (HZO) FTJs to undergo learning through the IPP scheme. Synaptic characteristics, including the number of conductance states, symmetry, linearity, write energy, and latency by modulating IPP scheme conditions are optimized. Finally, the applicability of HZO FTJ as a synaptic device by assessing learning accuracy in pattern recognition through artificial neural network simulation based on the optimized synaptic characteristics is evaluated.

Synchronous gesture recognition and muscle force estimation based on piezoelectric micromachined ultrasound transducer

Early prosthetic control research mainly focused on motion intention recognition, but in recent years, study on control force has emerged. The simultaneous integration of motion intention recognition and control force estimation has significant practical value. This paper proposes an ultrasound control scheme using wearable device that enables synchronous intention recognition and accurate control force estimation. Eleven gestures abstracted from daily life are selected, with a force range of 0–100 % maximum voluntary contraction (MVC). The wearable device employed for muscle morphology monitoring consists of a piezoelectric micromachined ultrasound transducer (PMUT) and polymer encapsulation. It is small, lightweight, and eliminates the need for ultrasound gel, enhancing its practicality. Ultrasound echogenicity of two forearm muscles and corresponding output forces are simultaneously collected. We propose peak and location (PKL) feature and combine it with mean and standard deviation (MSD) feature to improve the accuracy of pattern recognition and force estimation. Experimental results show that during dynamic muscle contraction forces, the classification accuracy achieves 95.84 ± 1.48 %, while the synchronous estimation of forces yields a R2 correlation coefficient of 0.919 and a normalized root-mean-square deviation of 0.127. This scheme demonstrates the feasibility of PMUT-based ultrasound control for supporting synchronous gesture recognition and force estimation, and is expected to contribute to the practicality of prosthesis control.

Engineering of TiN/ZnO/SnO2/ZnO/Pt multilayer memristor with advanced electronic synapses and analog switching for neuromorphic computing

The two-terminal memristor is a promising neuromorphic artificial electronic device, mirroring biological synapses in structure and replicating various synaptic functions. Despite its advantages, challenges in achieving high reliability, gradual switching, and low energy consumption hinder progress in neuromorphic devices. This study explores electronic synapses and simulates analog switching in a Pt/TiN/ZnO/SnO2/ZnO/Pt multilayer (ML) configuration, featuring a ∼3 nm SnO2 layer between ZnO layers. Results show enhanced cycling endurance (more than 250 cycles), resistance window (102), tunable synaptic plasticity, and multilevel switching. ML memristors exhibit low coefficient of variation (4.5 %) in set voltage, low energy consumption (set = ∼0.12 nj, reset = ∼0.1 nj), and fast switching speeds (set = 300 ns, reset = 200 ns), suitable for high-density memory and neuromorphic systems. They successfully emulate synaptic functions, including paired-pulse facilitation (PPF), spike voltage-dependent plasticity (SVDP), spike width-dependent plasticity (SWDP), spike frequency-dependent plasticity (SFDP), and post-tetanic potentiation (PTP). Modulating pulse amplitude and width achieves multilevel conductance in long-term potentiation (LTP) and long-term depression (LTD). Using nonlinear conductance data, a 96.5 % image pattern recognition accuracy is achieved in a deconvolution neural network (DNN) simulation. These results highlight the ML memristor's potential in efficient neuromorphic computing systems.

Volatile memory characteristics of CMOS-compatible HZO ferroelectric layer for reservoir computing

Recently, ferroelectric memory utilizing hafnium oxide has emerged as an attractive option compared to existing memory technologies, primarily due to its scalability and energy-efficient advantages. Among them, hafnium zirconium oxide (HZO) is examined for its short-term memory characteristics to achieve a reservoir computing system known to exhibit remarkable polarization properties, being able to switch between distinct polarization states under the influence of an electric field. These unique properties are of utmost importance in ferroelectric memory applications, where they play a pivotal role in the storage and retrieval of binary data. In this study, we identify and experiment with the electrical characteristics of a ferroelectric tunnel junction (FTJ) device with a metal-ferroelectric-semiconductor (MFS) structure using TiN as the top electrode and HZO as the ferroelectric layer. Moreover, we assess the performance of the device by evaluating its maximum 2Pr (remnant polarization) and tunneling electro resistance (TER) values in different conditions of cell area. Furthermore, we analyze and show short-term memory (STM) characteristics and synaptic properties with 5 cycles of potentiation and depression under conditions of stable dynamic range by coordinating identical and incremental pulses. In the case of incremental pulses (>95 %), the MNIST pattern recognition accuracy is higher than in the case of identical pulses (>94 %). Through a sequence of procedures, the synaptic characteristics of FTJs are confirmed to assess their suitability for use as an artificial synaptic device.

Efficient Mixed-Type Wafer Defect Pattern Recognition Based on Light-Weight Neural Network.

Wafer defect pattern recognition can help engineers improve the production process of semiconductor chips. In real industrial scenarios, the recognition of mixed-type wafer defects is difficult and the production scale of semiconductor wafers is large, which requires high accuracy and speed in wafer defect pattern recognition. This study proposes a light-weight neural network model to efficiently recognize mixed-type wafer defects. The proposed model is constructed via inverted residual convolution blocks with attention mechanisms and large kernel convolution downsampling layers. The inference speed of the inverted residual convolution block is fast, and the attention mechanism can enhance feature extraction capabilities. Large kernel convolutions help the network retain more important feature information during downsampling operations. The experimental results on the real Mixed-type WM38 dataset show that the proposed model achieves a recognition accuracy of 98.69% with only 1.01 M parameters. Compared with some popular high-performance models and light-weight models, our model has advantages in both recognition accuracy and inference speed. Finally, we deploy the model as a TensorRT engine, which significantly improves the inference speed of the model, enabling it to process more than 1300 wafer maps per second.

Synaptic plasticity and associative learning in IGZO-based synaptic transistor

The increasing demand for efficient data access in high-performance computing systems has emphasized the limitations of the traditional von Neumann architecture, particularly due to the von Neumann bottleneck. This bottleneck arises from the significant power and time consumption required for data transfer between the central processing units and memory, impeding overall system efficiency. Neuromorphic computing offers a promising alternative. Neuromorphic systems emulate biological neurons and synapses, enabling parallel data processing and potentially overcoming the limitations of traditional computing architectures. This study focuses on synaptic transistors with In–Ga–Zn-O (IGZO) channels and TaOx charge trapping layers (Ox-CTL) to enhance neuromorphic computing capabilities. The devices were fabricated using reactive sputtering and atomic layer deposition, followed by comprehensive structural and compositional analyses. Experimental results demonstrated significant hysteresis, high on/off ratios, and multibit conductance states, suggestive of effective charge trapping and detrapping mechanisms. Evaluation through potentiation, depression, and excitatory postsynaptic current (EPSC) measurements, along with simulations using the Modified National Institute of Standards and Technology (MNIST) database, revealed improved pattern recognition accuracy. Additionally, associative learning experiments modeled after Pavlov’s dog conditioning emphasized the device's capability for both long- and short-term memory retention. These findings suggest that IGZO-based synaptic transistors are promising candidates for next-generation neuromorphic computing systems, offering enhanced data processing efficiency and adaptability.

Adaptive Processing Enabled by Sodium Alginate Based Complementary Memristor for Neuromorphic Sensory System.

Adaptive processing allows sensory systems to autonomically adjust their sensitivity with exposure to a constant sensory stimulus and thus organisms to adapt to environmental variations. Bioinspiredelectronics with adaptive functions are highly desirable for the development of neuromorphic sensory systems (NSSs). Herein, the functions of desensitization and sensitivity changing with background intensity (i.e., Weber's law), as two fundamental cues of sensory adaptation, are biorealistically demonstrated in an Ag nanowire (NW)-embedded sodium alginate (SA) based complementary memristor. In particular, Weber's law is experimentally emulated in a single complementary memristor. Furthermore, three types of adaptive NSS unit are constructed to realize a multiple perceptual capability that processes the stimuli of illuminance, temperature, and pressure signals. Taking neuromorphic vision as an example, scotopic and photopic adaptation functions are well reproduced for image enhancement against dark and bright backgrounds. Importantly, an NSS system with multisensory integration function is demonstrated by combining light and pressure spikes, where the accuracy of pattern recognition is obviously enhanced relative to that of an individual sense. This work offers a new strategy for developing neuromorphic electronics with adaptive functions and paves the way toward developing a highly efficient NSS.