Precise Recognition Research Articles

All‐in‐One: Photo‐Responsive Lanthanide‐Organic Framework for Simultaneous Sensing, Adsorption, and Photocatalytic Reduction of Uranium

AbstractThe selective removal and immobilization of uranyl ions from aqueous solutions is essential for the sustainable development of nuclear energy. Herein, a robust lanthanide‐organic framework material (IHEP‐24) is developed for simultaneous fluorescence sensing, selective adsorption, and photocatalytic reduction of uranium, integrating three different functions in one material. The confined space formed by the coordination assembly of viologen derivative ligands and metal‐oxygen clusters can act as precise recognition sites for uranyl, allowing IHEP‐24 to efficiently detect and capture uranyl ions. In addition, the presence of a viologen‐based radical ligand enables IHEP‐24 to a further photocatalytic reduction of the adsorbed uranyl to amorphous UO2. The mechanisms of adsorption and photocatalysis are revealed by batch experiments, photoelectrochemical characterizations, and theoretical calculations. This study provides a reference for the construction of robust multi‐functional MOF materials and also provides support for the deep removal and immobilization of radionuclides from aqueous solution.

Dual Sensing Signal Decoupling Based on Thermoelectric Polymer Aerogels for Precise Temperature and Pressure Recognition

AbstractThe capability to emulate skin‐like temperature and pressure sensing is fundamental for next‐generation artificial intelligence products. However, detecting temperature and pressure simultaneously with a single sensor without signal interference is challenging. Herein, a novel PCC aerogel sensor composed of PEDOT:PSS, CNTs, and CNF via directional freezing technology is developed. The PCC sensor can decouple temperature and pressure stimuli into individual voltage and resistance signals. It exhibits high‐precision temperature sensing capabilities, boasting an exceptionally high Seebeck coefficient of 30.4 µV K‐1 and the ability to detect temperature variations as low as 0.1 K. PCC sensors show excellent sensitivity and fast response times for detecting static and dynamic pressures, as well as high stability after 1000 cycles. Its maximum pressure sensitivity can reach 159.1% kPa−1, and the lowest detection limit is 10 Pa. Additionally, its excellent thermoelectric properties also enable to generating thermopower from human skin for self‐powered pressure sensing. A 3×3 PCC sensor array has been proposed to simulate the unique features of human skin in temperature and pressure recognition. This work provides a scalable manufacturing strategy for multi‐functional tactile sensors.

Deep Sea Fisherman’s App using WWSN

In this study, we present a method for recognizing daily living activities using Doppler sensors with extended detection ranges, addressing key challenges in cost, accuracy, user convenience, and privacy preservation. We highlight the importance of accurate and affordable activity recognition for enabling advanced services in energy-saving home appliance control and other daily life applications. The proposed method leverages Doppler sensors' capabilities to detect dynamic objects and achieve precise recognition of a wide range of activities, including location-independent tasks like reading. Our evaluation includes optimizing recognition accuracy through logistic regression and assessing ensemble methods to enhance performance. Additionally, we explore the impact of sensor reduction strategies on recognition accuracy, demonstrating the potential of this approach to streamline sensor deployment while maintaining effectiveness. This research contributes to advancing sensor-based technologies for improving everyday life services, emphasizing practical solutions that prioritize cost-effectiveness and user experience

A novel approach for identification of zoonotic trypanosome utilizing deep metric learning and vector database-based image retrieval system

Trypanosomiasis, a significant health concern in South America, South Asia, and Southeast Asia, requires active surveys to effectively control the disease. To address this, we have developed a hybrid model that combines deep metric learning (DML) and image retrieval. This model is proficient at identifying Trypanosoma species in microscopic images of thin-blood film examinations. Utilizing the ResNet50 backbone neural network, a trained-model has demonstrated outstanding performance, achieving an accuracy exceeding 99.71 % and up to 96 % in recall. Acknowledging the necessity for automated tools in field scenarios, we demonstrated the potential of our model as an autonomous screening approach. This was achieved by using prevailing convolutional neural network (CNN) applications, and vector database based-images returned by the KNN algorithm. This achievement is primarily attributed to the implementation of the Triplet Margin Loss function as 98 % of precision. The robustness of the model demonstrated in five-fold cross-validation highlights the ResNet50 neural network, based on DML, as a state-of-the-art CNN model as AUC >98 %. The adoption of DML significantly improves the performance of the model, remaining unaffected by variations in the dataset and rendering it a useful tool for fieldwork studies. DML offers several advantages over conventional classification model to manage large-scale datasets with a high volume of classes, enhancing scalability. The model has the capacity to generalize to novel classes that were not encountered during training, proving particularly advantageous in scenarios where new classes may consistently emerge. It is also well suited for applications requiring precise recognition, especially in discriminating between closely related classes. Furthermore, the DML exhibits greater resilience to issues related to class imbalance, as it concentrates on learning distances or similarities, which are more tolerant to such imbalances. These contributions significantly make the effectiveness and practicality of DML model, particularly in in fieldwork research.

The potential and promise for clinical application of adoptive T cell therapy in cancer.

Adoptive cell therapy has revolutionized cancer treatment, especially for hematologic malignancies. T cells are the most extensively utilized cells in adoptive cell therapy. Currently, tumor-infiltrating lymphocytes, T cell receptor-transgenic T cells and chimeric antigen receptor T cells are the three main adoptive T cell therapies. Tumor-infiltrating lymphocytes kill tumors by reinfusing enlarged lymphocytes that naturally target tumor-specific antigens into the patient. T cell receptor-transgenic T cells have the ability to specifically destroy tumor cells via the precise recognition of exogenous T cell receptors with major histocompatibility complex. Chimeric antigen receptor T cells transfer genes with specific antigen recognition structural domains and T cell activation signals into T cells, allowing T cells to attack tumors without the assistance of major histocompatibility complex. Many barriers have been demonstrated to affect the clinical efficacy of adoptive T cell therapy, such as tumor heterogeneity and antigen loss, hard trafficking and infiltration, immunosuppressive tumor microenvironment and T cell exhaustion. Several strategies to improve the efficacy of adoptive T cell therapy have been explored, including multispecific chimeric antigen receptor T cell therapy, combination with immune checkpoint blockade, targeting the immunosuppressive tumor microenvironment, etc. In this review, we will summarize the current status and clinical application, followed by major bottlenecks in adoptive T cell therapy. In addition, we will discuss the promising strategies to improve adoptive T cell therapy. Adoptive T cell therapy will result in even more incredible advancements in solid tumors if the aforementioned problems can be handled.

Imaging Review of Pediatric Monogenic CNS Vasculopathy with Genetic Correlation.

Monogenic cerebral vasculopathy is a rare but progressively recognizable cause of pediatric cerebral vasculopathy manifesting as early as fetal life. These monogenic cerebral vasculopathies can be silent or manifest variably as fetal or neonatal distress, neurologic deficit, developmental delay, cerebral palsy, seizures, or stroke. The radiologic findings can be nonspecific, but the presence of disease-specific cerebral and extracerebral imaging features can point to a diagnosis and guide genetic testing, allowing targeted treatment. The authors review the existing literature describing the frequently encountered and rare monogenic cerebral vascular disorders affecting young patients and describe the relevant pathogenesis, with an attempt to categorize them based on the defective step in vascular homeostasis and/or signaling pathways and characteristic cerebrovascular imaging findings. The authors also highlight the role of imaging and a dedicated imaging protocol in identification of distinct cerebral and extracerebral findings crucial in the diagnostic algorithm and selection of genetic testing. Early and precise recognition of these entities allows timely intervention, preventing or delaying complications and thereby improving quality of life. It is also imperative to identify the specific pathogenic variant and pattern of inheritance for satisfactory genetic counseling and care of at-risk family members. Last, the authors present an image-based approach to these young-onset monogenic cerebral vasculopathies that is guided by the size and predominant radiologic characteristics of the affected vessel with reasonable overlap. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Captcha Recognition Using CNN

Abstract: Tests that are automated and intended to tell humans from machines are called CAPTCHAs. Computers find it harder to solve them, which prevents programs from abusing online services and consuming internet resources, but humans can solve them with ease. Convolutional neural nets could be used to efficiently and automatically complete the CAPTCHA tests. The highly precise CAPTCHA recognition techniques currently in use can be structurally complex. Consequently, our group investigated an alternative method for resolving CAPTCHAs: enhancing accuracy by using image processing and a Convolutional Neural Network, which is more efficient in terms of run time and structural complexity. Our networks were also evaluated using CAPTCHA datasets that included background noise and character adhesion.

Study of Aerial Image Classification

Abstract: Classifying images captured through remote sensing is necessary for various reasons, including monitoring the environment and assessing agriculture. The progress in thisfield has been greatly enhanced by the integration of advancements in machine learning, especially deep learning, and also accessibility of high-definition images obtained through remote sensing. CNNs are now necessary instruments for precise recognition and classificationof objects in aerial imaging. These models use convolution and pooling operations to capture local patterns and relationships, enhancing image classification accuracy. This review paper presents a comprehensive look at the most recent techniques for categorising remote sensing images. It emphasises the significance of accurate classification in the constantly evolving contemporary society and investigates new progress made possible by deep learning methods.The article explores problems in pinpointing unique and important areas in remote sensing images and illustrates how deep learning models tackle these problems through comprehendingrelationships among objects and other elements in the scene. The article assesses the advantagesand disadvantages of various techniques in relation to accuracy, computational efficiency, andscalability through a comparison between traditional methods and deep learning-based methods.

Use of Fluorescence Imaging in Liver Transplant Surgery.

Liver transplant surgery is a complex procedure that demands high knowledge of surgical anatomy and the precise recognition and preservation of structures. To address this, the use of fluorescence imaging has facilitated the identification of anatomical structures such as biliary ducts, arteries, and liver segmentation. Indocyanine green is among the most commonly utilized fluorescent agents, not just during surgery but also in the pre- and postoperative phases, where it is used to assess graft failure by measuring the plasma disappearance rate. New advancements such as artificial intelligence paired with fluorescence imaging have the potential to enhance patient outcomes. Additionally, technologies such as augmented reality and mixed reality could be integrated into surgical procedures, broadening the scope of possibilities for improving patient safety.

Accuracy Assessment of Geometric-Distortion Identification Methods for Sentinel-1 Synthetic Aperture Radar Imagery in Highland Mountainous Regions.

SAR imagery plays a crucial role in geological and environmental monitoring, particularly in highland mountainous regions. However, inherent geometric distortions in SAR images often undermine the precision of remote sensing analyses. Accurately identifying and classifying these distortions is key to analyzing their origins and enhancing the quality and accuracy of monitoring efforts. While the layover and shadow map (LSM) approach is commonly utilized to identify distortions, it falls short in classifying subtle ones. This study introduces a novel LSM ground-range slope (LG) method, tailored for the refined identification of minor distortions to augment the LSM approach. We implemented the LG method on Sentinel-1 SAR imagery from the tri-junction area where the Xiaojiang, Pudu, and Jinsha rivers converge at the Yunnan-Sichuan border. By comparing effective monitoring-point densities, we evaluated and validated traditional methods-LSM, R-Index, and P-NG-against the LG method. The LG method demonstrates superior performance in discriminating subtle distortions within complex terrains through its secondary classification process, which allows for precise and comprehensive recognition of geometric distortions. Furthermore, our research examines the impact of varying slope parameters during the classification process on the accuracy of distortion identification. This study addresses significant gaps in recognizing geometric distortions and lays a foundation for more precise SAR imagery analysis in complex geographic settings.

Survey on the convergence of learning techniques for precise pattern identification in fingerprint analysis

Fingerprint analysis has been an essential component of forensic science and biometric authentication systems. The precise recognition of fingerprint patterns is critical for solving crimes, confirming identities and assuring the security of numerous applications. In recent years, the convergence of learning approaches, particularly machine learning and deep learning, has played an essential part in improving the accuracy and efficiency of fingerprint pattern recognition. In this paper, we discuss recent advancements in physiological-based biometric multimodalities, with a particular focus on the field of precise pattern identification in fingerprint analysis. Additionally, we assume the task of summarizing and examining a range of physiological-based biometric modalities, encompassing both traditional and deep learning approaches. A detailed review of several biometric measurements across many modalities is presented, encompassing various phases, including preprocessing, feature extraction and classification, which are thoroughly discussed. We provide a comprehensive analysis of the challenges and future developments associated with conventional and deep learning methodologies. The objective is to enable investigators to recognize these problems. A review is conducted to evaluate the standard and deep learning approaches employed in different physiological-based biometric systems. The comparative analysis of this review suggests that more advancement is necessary for the development of a reliable physiological-based approach to enhance and optimize the functionality of the fingerprint system.

Forming-less flexible memristor crossbar array for neuromorphic computing applications produced using low-temperature atomic layer deposition

The rapid development of wearable artificial intelligence devices based on memristor crossbar arrays has increased the demand for flexible electronics. However, fabricating crossbar arrays on flexible substrates faces inherent challenges, notably due to the complex fabrication process at low temperatures. Moreover, ensuring the stability and reliability of memristor device remains a crucial issue. To address these issues, this study introduced N-doped TaOx (N:TaOx) as a flexible memristor crossbar array fabricated via atomic layer deposition directly on a flexible substrate at an exceptionally low temperature (150 °C). The flexible PET/ITO/N:TaOx/TiN memristor device exhibited forming-less bipolar resistive switching properties with analog memory characteristics. This was accomplished by increasing the nitrogen doping concentration and effectively reducing oxygen-related defects in TaOx. The amorphous-phase flexible N:TaOx memristor demonstrated remarkable stability, enduring 500 switching cycles and retaining its state for 24 h during bending tests involving 104 bending cycles at 2.5 mm bending radius. Furthermore, a 6 × 6 flexible memristor crossbar array was fabricated successfully, with all 36 devices exhibiting well-defined memristor behavior and minimal variation attributed to the film's uniformity achieved through ALD process. Additionally, by programming the tunable conductance of each device in the array, characters of desired shapes can be formed and read. Regarding their synaptic behavior via long-term potentiation and depression, the proposed flexible memristor device showed an outstanding accuracy of 96.44 % in image recognition tasks under extreme bending conditions, employing the MNIST and Fashion-MNIST datasets. The N:TaOx memristor deposited at low temperatures thus exhibits significant potential for use in wearable neuromorphic hardware applications due to its high density, high performance, reliability, and precise image recognition.

Utilizing Deep Neural Networks for Chrysanthemum Leaf and Flower Feature Recognition

Chrysanthemums, a significant genus within the Asteraceae, hold a paramount position in the global floricultural industry, second only to roses in market demand. The proliferation of diverse chrysanthemum cultivars presents a formidable challenge for accurate identification, exacerbated by the abundance of varieties, intricate floral structures, diverse floret types, and complex genetic profiles. Precise recognition of chrysanthemum phenotypes is indispensable to navigating these complexities. Traditional methods, including morphology studies, statistical analyses, and molecular markers, have fallen short due to their manual nature and time-intensive processes. This study presents an innovative solution employing deep learning techniques for image-based chrysanthemum phenotype recognition. Leveraging machine learning, our system autonomously extracts key features from chrysanthemum images, converting morphological data into accessible two-dimensional representations. We utilized Support Vector Machine (SVM) and Multilayer Perceptron (MLP) algorithms to construct frameworks for processing image data and classifying chrysanthemum cultivars based on color, shape, and texture. Experimental results, encompassing 10 cultivars, 10 flower colors, and five flower shapes, consistently demonstrated recognition accuracy ranging from 79.29% up to 97.86%. This tool promises streamlined identification of flower traits, and we anticipate its potential for real-time identification enhancements in future iterations, promising advances in chrysanthemum cultivation and exportation processes. Our approach offers a novel and efficient means to address the challenges posed by the vast diversity within chrysanthemum species, facilitating improved management, breeding, and marketing strategies in the floricultural industry.

Deep practice of internet of things image recognition technology based on deep learning in intelligent financial supervision system

With the deepening development of the financial market, the role of regulatory systems in ensuring green and safe financial environment is becoming increasingly prominent. The traditional intelligent financial regulatory systems on the market lack precise and effective real-time monitoring and recognition capabilities, making it difficult to effectively process and analyze large-scale financial data. In order to improve the real-time recognition of abnormal situations or potential risks, achieve automation and intelligence of supervision, this article combines deep learning technology to study the deep practice of IoT image recognition technology in intelligent financial supervision systems. In response to the “data silos” and cross regional linkage issues faced by financial industry regulation, this article designs and implements an intelligent regulatory system based on IoT image recognition technology through deep learning. Using Convolutional Neural Network (CNN) algorithm to classify and analyze system images for regulatory and risk control purposes. The research results indicate that the intelligent financial regulatory system constructed in this article has high stability and responsiveness, which can effectively meet the real-time regulatory needs of finance and help promote the healthy development of the financial market.

Skin‐Inspired Bimodal Receptors for Object Recognition and Temperature Sensing Simulation

AbstractSkin contacts with objects with different thermal conductivity and tactile perception will produce different temperature and tactile sensations. Here, an innovative creation is presented known as the BB‐Skin, a highly realistic bionic bimodal electronic skin, meticulously designed to mirror the thermal sensitivity and tactile perception found in human skin. This technology allows for precise object recognition and offers remote temperature sensing feedback. The BB‐Skin comprises temperature sensing, heating, and tribo‐electrode modules. Through the utilization of machine learning algorithms that measure the thermal conductivity and electronegativity of materials, a bimodal bionic robot object recognition system is developed, achieving an impressive accuracy rate exceeding 98.11%. The bimodal nature of the system, based on different types of electrical signals that operate independently, significantly enhances the reliability of the device. Moreover, harnessing the inherent capabilities of the BB‐Skin, a novel remote temperature sensing and feedback system is successfully implemented. This system adeptly replicates the temperature perception when remotely touching objects and provides users with feedback through gloves embedded with heating and cooling modules.

A Multi-Hyperspectral Image Collaborative Mapping Model Based on Adaptive Learning for Fine Classification

Hyperspectral (HS) data, encompassing hundreds of spectral channels for the same area, offer a wealth of spectral information and are increasingly utilized across various fields. However, their limitations in spatial resolution and imaging width pose challenges for precise recognition and fine classification in large scenes. Conversely, multispectral (MS) data excel in providing spatial details for vast landscapes but lack spectral precision. In this article, we proposed an adaptive learning-based mapping model, including an image fusion module, spectral super-resolution network, and adaptive learning network. Spectral super-resolution networks learn the mapping between multispectral and hyperspectral images based on the attention mechanism. The image fusion module leverages spatial and spectral consistency in training data, providing pseudo labels for spectral super-resolution training. And the adaptive learning network incorporates spectral response priors via unsupervised learning, adjusting the output of the super-resolution network to preserve spectral information in reconstructed data. Through the experiment, the model eliminates the need for the manual setting of image prior information and complex parameter selection, and can adjust the network structure and parameters dynamically, eventually enhancing the reconstructed image quality, and enabling the fine classification of large-scale scenes with high spatial resolution. Compared with the recent dictionary learning and deep learning spectral super-resolution methods, our approach exhibits superior performance in terms of both image similarity and classification accuracy.

Implementation of Intelligent Indoor Service Robot Based on ROS and Deep Learning

When faced with challenges such as adapting to dynamic environments and handling ambiguous identification, indoor service robots encounter manifold difficulties. This paper aims to address this issue by proposing the design of a service robot equipped with precise small-object recognition, autonomous path planning, and obstacle-avoidance capabilities. We conducted in-depth research on the suitability of three SLAM algorithms (GMapping, Hector-SLAM, and Cartographer) in indoor environments and explored their performance disparities. Upon this foundation, we have elected to utilize the STM32F407VET6 and Nvidia Jetson Nano B01 as our processing controllers. For the program design on the STM32 side, we are employing the FreeRTOS operating system, while for the Jetson Nano side, we are employing ROS (Robot Operating System) for program design. The robot employs a differential drive chassis, enabling successful autonomous path planning and obstacle-avoidance maneuvers. Within indoor environments, we utilized the YOLOv3 algorithm for target detection, achieving precise target identification. Through a series of simulations and real-world experiments, we validated the performance and feasibility of the robot, including mapping, navigation, and target detection functionalities. Experimental results demonstrate the robot’s outstanding performance and accuracy in indoor environments, offering users efficient service and presenting new avenues and methodologies for the development of indoor service robots.

Compliant Iontronic Triboelectric Gels with Phase-Locked Structure Enabled by Competitive Hydrogen Bonding

HighlightsA bionic phase-locked structure-inspired iontronic triboelectric gel is proposed with good mechanical compliance for wearable haptic sensing applications.Competitive hydrogen bonding systems are constructed through polymer-solvent-nonsolvent interactions, and regeneration of polymers with weak hydrogen bond donors triggers controlled phase separation.Self-powered haptic skin constructed with iontronic triboelectric gel has a modulus (150.6 kPa) and stretchability (> 400%) similar to that of the human body, enabling fidelity transmission of haptic signals and precise recognition of sensing objects.

Survey on Silentinterpreter : Analysis of Lip Movement and Extracting Speech using Deep Learning

Lip reading is a complex but interesting path for the growth of speech recognition algorithms. It is the ability of deciphering spoken words by evaluating visual cues from lip movements. In this study, we suggest a unique method for lip reading that converts lip motions into textual representations by using deep neural networks. Convolutional neural networks are used in the methodology to extract visual features, recurrent neural networks are used to simulate temporal context, and the Connectionist Temporal Classification loss function is used to align lip features with corresponding phonemes. The study starts with a thorough investigation of data loading methods, which include alignment extraction and video preparation. A well selected dataset with video clips and matching phonetic alignments is presented. We select relevant face regions, convert frames to grayscale, then standardize the resulting data so that it can be fed into a neural network. The neural network architecture is presented in depth, displaying a series of bidirectional LSTM layers for temporal context understanding after 3D convolutional layers for spatial feature extraction. Careful consideration of input shapes, layer combinations, and parameter selections forms the foundation of the model's design. To train the model, we align predicted phoneme sequences with ground truth alignments using the CTC loss. Dynamic learning rate scheduling and a unique callback mechanism for training visualization of predictions are integrated into the training process. After training on a sizable dataset, the model exhibits remarkable convergence and proves its capacity to understand intricate temporal correlations. Through the use of both quantitative and qualitative evaluations, the results are thoroughly assessed. We visually check the model's lip reading abilities and assess its performance using common speech recognition criteria. It is explored how different model topologies and hyperparameters affect performance, offering guidance for future research. The trained model is tested on external video samples to show off its practical application. Its accuracy and resilience in lip-reading spoken phrases are demonstrated. By providing a deep learning framework for precise and effective speech recognition, this research adds to the rapidly changing field of lip reading devices. The results offer opportunities for additional development and implementation in various fields, such as assistive technologies, audio-visual communication systems, and human-computer interaction.

Rapid Production Method of Massive Thematic Maps Based on Geospatial Knowledge Extraction

<p>Geospatial knowledge in massive academic papers can provide knowledge services such as location-based research hotspot analysis, spatio-temporal data aggregation, research results recommendation, etc. However, geospatial knowledge often exists implicitly in literature resources in unstructured form, which is difficult to be directly accessed and mined and utilized for rapid production of massive thematic maps. In this paper, we take the geospatial knowledge of the area studied as an example and introduce its extraction method in detail. An integrated feature template matching and random forest classification algorithm is proposed for accurately identifying research areas from the abstract texts of academic papers and producing thematic maps. Firstly, the precise recognition of geographical names is achieved step by step based on BiLSTM-CRF algorithm and improved heuristic disambiguation method; then, the area studied is extracted by the designed integrated feature recognition template of area studied using random forest classification algorithm, and a fast thematic map is designed for the knowledge of area studied, topic and literature. The experimental results show that the area studied recognition accuracy can reach 97%, the F-value is 96%, and the recall rate reaches 96%, achieving high accuracy and high efficiency of area studied extraction in text. Based on the geospatial knowledge, the thematic map can achieve the effect of fast map formation and accurate expression.</p> <p> </p>