Recognition Function Research Articles

Construct a garbage recognition model using automatic machine learning based on EasyDL

In modern times, machine learning has become an indispensable part of various industries. As the amount of data increases, reducing the time cost of manual annotation is crucial. AutoML emerges as a solution that effectively automates labor-intensive tasks like image annotation. In this article, we use Tencent's EasyDL to develop a garbage recognition function. The garbage recognition model completed through EasyDL achieved an average of over 90% in terms of accuracy and F1 score. This indicates that autoML can greatly reduce manual participation while ensuring a certain level of accuracy.

Emergence of syntax and word prediction in an artificial neural circuit of the cerebellum

The cerebellum, interconnected with the cerebral neocortex, plays a vital role in human-characteristic cognition such as language processing, however, knowledge about the underlying circuit computation of the cerebellum remains very limited. To gain a better understanding of the computation underlying cerebellar language processing, we developed a biologically constrained cerebellar artificial neural network (cANN) model, which implements the recently identified cerebello-cerebellar recurrent pathway. We found that while cANN acquires prediction of future words, another function of syntactic recognition emerges in the middle layer of the prediction circuit. The recurrent pathway of the cANN was essential for the two language functions, whereas cANN variants with further biological constraints preserved these functions. Considering the uniform structure of cerebellar circuitry across all functional domains, the single-circuit computation, which is the common basis of the two language functions, can be generalized to fundamental cerebellar functions of prediction and grammar-like rule extraction from sequences, that underpin a wide range of cerebellar motor and cognitive functions. This is a pioneering study to understand the circuit computation of human-characteristic cognition using biologically-constrained ANNs.

γδ T Cells: A Game Changer in the Future of Hepatocellular Carcinoma Immunotherapy.

Hepatocellular carcinoma (HCC) remains a global health challenge with limited treatment options and a poor prognosis for advanced-stage patients. Recent advancements in cancer immunotherapy have generated significant interest in exploring novel approaches to combat HCC. One such approach involves the unique and versatile subset of T cells known as γδ T cells. γδ T cells represent a distinct subset of T lymphocytes that differ from conventional αβ T cells in terms of antigen recognition and effector functions. They play a crucial role in immunosurveillance against various malignancies, including HCC. Recent studies have demonstrated that γδ T cells can directly recognize and target HCC cells, making them an attractive candidate for immunotherapy. In this article, we aimed to explore the role exerted by γδ T cells in the context of HCC. We investigate strategies designed to maximize the therapeutic effectiveness of these cells and examine the challenges and opportunities inherent in applying these research findings to clinical practice. The potential to bring about a revolutionary shift in HCC immunotherapy by capitalizing on the unique attributes of γδ T cells offers considerable promise for enhancing patient outcomes, warranting further investigation.

Large Field-of-View Nonlinear Holography in Lithium Niobate.

A nonlinear holographic technique is capable of processing optical information in the newly generated optical frequencies, enabling fascinating functions in laser display, security storage, and image recognition. One popular nonlinear hologram is based on a periodically poled lithium niobate (LN) crystal. However, due to the limitations of traditional fabrication techniques, the pixel size of the LN hologram is typically several micrometers, resulting in a limited field-of-voew (FOV) of several degrees. Here, we experimentally demonstrate an ultra-high-resolution LN hologram by using the laser poling technique. The minimal pixel size reaches 200 nm, and the FOV is extended above 120° in our experiments. The image distortions at large view angles are effectively suppressed through the Fourier transform. The FOV is further improved by combining multiple diffraction orders of SH fields. The ultimate FOV under our configuration is decided by a Fresnel transmission. Our results pave the way for expanding the applications of nonlinear holography to wide-view imaging and display.

Mental Health of School-Aged Children Treated with Propranolol or Atenolol for Infantile Hemangioma and Their Parents

Background: Infants with infantile hemangioma (IH) have been effectively treated with propranolol or atenolol. Concerns were raised about the mental health of these children at school age, due to central nervous system effects of propranolol and visible nature of IH. Objective: This study aimed to compare the mental health at school age of children treated with propranolol to children treated with atenolol for IHs and their parents. Methods: This two-centered cross-sectional study included children aged ≥6 years and treated with either propranolol or atenolol for IH during infancy. Children’s outcomes were performance-based affect recognition (Dutch version of the Developmental Neuropsychological Assessment-II [NEPSY-II-NL]), parent-reported emotional and behavioral functioning (Child Behavioral Checklist [CBCL]), and health-related quality of life (KIDSCREEN-27). Parents’ outcome was parenting stress (Parenting Stress Questionnaire [OBVL]). Results: Data of 105 children (36 propranolol, 69 atenolol; 6.0–11.8 years) were analyzed. Mental health outcomes did not differ between both β-blocker groups. Although overall functioning was in line with norms, children presented specific problems concerning affect recognition, parent-reported attention, and social quality of life. Parents showed increased physical symptoms, depressive symptoms, and parent-child relationship problems. Conclusion: No difference in mental health at school age was found between children treated with propranolol or atenolol for IH. Although few overall mental health problems were found, specific problems require follow-up. Follow-up of children should be directed toward affect recognition, attention, and social functioning in daily life. Problems reported by parents could be ameliorated by mental health support during and after their infant’s β-blocker treatment.

Amplified and Specific Staining of Protein Dimerization on Cell Membrane Catalyzed by Responsively Installed DNA Nanomachines for Cancer Diagnosis.

In situ staining of protein dimerization on cell membrane has an important significance in accurate diagnosis during perioperative period, yet facile integration of specific recognition function and local signal conversion/amplification abilities on membrane surface remains a great challenge. Herein, a two-stage catalytic strategy is developed by installing DNA nanomachines and employing. Specifically, dual-aptamer-assisted DNA scaffold perform a "bispecific recognition-then-computing" operation and the output signal initiate a membrane-anchored biocatalysis for self-assembly of DNA catalytic converters, that is, G-quadruplex nanowire/hemin DNAzyme. Then, localized-deposition of chromogenic polydopamine is chemically catalyzed by horseradish peroxidase-mimicking DNAzyme and guided by supramolecular interactions between conjugate rigid plane of G-tetrad and polydopamine oligomer. The catalytic products exhibit nanofiber morphology with a diameter of 80-120nm and a length of 1-10µm, and one-to-one localize on DNA scaffold for amplified and specific staining of protein dimers. The bispecific staining leads to a higher (≈3.4-fold) signal intensity than traditional immunohistochemistry, which is beneficial for direct visualization. Moreover, an efficient discrimination ability of the bispecific staining strategy is observed in co-culture model staining. This study provides a novel catalytic method for controlling deposition of chromogens and paves a new avenue to sensitively stain of protein-protein interactions in disease diagnosis.

Miniaturized CAR knocked onto CD3ε extends TCR function with CAR specificity under control of endogenous TCR signaling cascade

Immunotherapy using TCR and especially CAR transgenic T cells is a rapidly advancing field with the potential to become standard of care for the treatment of multiple diseases. While all current FDA approved CAR T cell products are generated using lentiviral gene transfer, extensive work is put into CRISPR/Cas mediated gene delivery to develop the next generation of safer and more potent cell products. One limitation of all editing systems is the size restriction of the knock-in cargo. Targeted integration under control of an endogenous promotor and/or signaling cascades opens the possibility to reduce CAR gene size to absolute minimum. Here we demonstrate that a first-generation CAR payload can be reduced to its minimum component - the antigen-binding domain - by targeted integration under control of the CD3ε promoter generating a CAR-CD3ε fusion protein that exploits the endogenous TCR signaling cascade. Miniaturizing CAR payload in this way results in potent CAR activity while simultaneously retaining the primary antigen recognition function of the TCR. Introducing CAR-specificity using a CAR binder only while maintaining endogenous TCR function may be an appealing design for future autologous CAR T cell therapies.

Switching molecular recognition selectivities by temperature in a diffusion-regulatory porous material

Over the long history of evolution, nature has developed a variety of biological systems with switchable recognition functions, such as the ion transmissibility of biological membranes, which can switch their ion selectivities in response to diverse stimuli. However, developing a method in an artificial host-guest system for switchable recognition of specific guests upon the change of external stimuli is a fundamental challenge in chemistry because the order in the host-guest affinity of a given system hardly varies along with environmental conditions. Herein, we report temperature-responsive recognition of two similar gaseous guests, CO2 and C2H2, with selectivities switched by temperature change by a diffusion-regulatory mechanism, which is realized by a dynamic porous crystal featuring ultrasmall pore apertures with flip-flop locally-motive organic moiety. The dynamic local motion regulates the diffusion process of CO2 and C2H2 and amplifies their rate differences, allowing the crystal to selectively adsorb CO2 at low temperatures and C2H2 at high temperatures with separation factors of 498 (CO2/C2H2) and 181 (C2H2/CO2), respectively.

Development of Supramolecular Systems Which Possesses Ion/Molecular Recognition Functions

Development of Supramolecular Systems Which Possesses Ion/Molecular Recognition Functions

Research on Reconstruction and Cultural Inheritance of Ancient Literature under Digital Expression

Abstract It is one of the ascendant research topics to study ancient literature by means of digital humanities technology, to construct the historical scene of literature, to restore the writer’s creative prosperity and to excavate the era value of ancient books. The digital reconstruction of ancient books has greatly impacted the preservation and inheritance of ancient literary resources. As an important carrier of ancient literature, ancient books have many texts that need to be identified, and it isn’t easy to disseminate in the information age due to their text form. This paper uses computer image processing methods to handle broken ancient text and obtain a more clearly visible digital form. At the same time, a method for document correction based on neural networks is proposed for certain texts that have occlusions and distortions. In several sets of experiments, it is shown that the document correction F1 value of the model in this paper is significantly ahead of the mainstream model with 0.903. Applying the digital platform for ancient books to the member groups of the Association for the Study of Ancient Literature, 81.5% of the respondents strongly agree with Q7, “I think the digital platform for ancient books is very conducive to cultural inheritance”, and the total of disagreeing and strongly disagreeing only accounts for 5%. It can be assumed that the ancient books digital platform designed in this paper and its document correction and recognition function have been widely recognized, and the ancient books digital platform can be applied to the digitization of ancient literature documents, daily reading, and storage of texts, text recognition, etc., contributing to the automation of ancient literature research, book storage and dissemination, and electronic reading. Based on this, the future database of ancient books should not only be a query and retrieval tool but also help scholars to make multidimensional statistics, comparisons, and analyses so as to generate new knowledge and ideas.

Design and realization of a small launch system with autonomous regulation and recognition guidance

A small launching system with autonomous regulation and recognition guidance is designed. Firstly, it ensures a solid and reliable transmission on the mechanical structure of the launcher and the small vehicle. Further, stepper motors and sensors are used to ensure precise control and effective feedback of the angle of the launcher. The small vehicle is equipped with the functions of guidance signal recognition and attitude adjustment, which have the advantages of strong real-time and high versatility. Finally, the practicality and accuracy of the designed launching system to a certain extent are verified through tests.

An all-in-one enzyme-free fluorescent aptasensor integrating localized catalyzed hairpin assembly for sensing antibiotics in food with improved detection efficiency.

Enzyme-free signal amplification fluorescent aptasensors depending on multi-component freely diffusing probes have become indispensable tools for antibiotic detection in food, but they suffer from low detection efficiency and tedious operation steps. Herein, an all-in-one enzyme-free fluorescent aptasensor integrating localized catalyzed hairpin assembly (L-CHA) was designed for antibiotic detection with improved detection efficiency. In the designed aptasensor, a double-stranded DNA reactant containing an antibiotic aptamer and a primer as well as two paired hairpin DNA reactants were immobilized on one spatial-confinement DNA scaffold (that is a DNA tetrahedron). Upon addition of the target antibiotic kanamycin, the activated primer initiated L-CHA, generating an amplified fluorescence signal. Compared with previously reported enzyme-free signal amplification fluorescent aptasensors, the designed aptasensor integrated the functions of target recognition, signal transduction, and L-CHA signal amplification into a single probe. In this all-in-one design, the reactants in this aptasensor were confined to a compact space for a higher local concentration, which improved detection efficiency. In particular, this aptasensor achieved sensitive detection of kanamycin within 60 min with a low detection limit of 0.019 ng mL-1. Additionally, the designed aptasensor depended on a single probe rather than multi-component probes, leading to simplified operation steps. Furthermore, this aptasensor was employed for detecting kanamycin in spiked milk samples with recoveries of 96.00% to 108.60%, indicating an acceptable accuracy. Therefore, this L-CHA-based all-in-one enzyme-free fluorescent aptasensor offers a prospective tool for antibiotic detection in the field of food safety.

Research on the Innovation of Enterprise Accounting Management under the Financial Shared Service Model

Abstract Financial shared services not only improve operational efficiency and reduce management costs but also realize auxiliary data analysis and management decision-making work, creating more value for enterprises. This paper builds a financial shared service system based on image recognition and extraction of financial bills to realize the functions of financial content recognition, voucher generation, application recognition, and administrative approval. We perform pre-processing tasks like binarization and edge detection on the financial bill image to identify the form lines. We then use the Hough transform to solve the function of the form lines, rotate, and correct the tilt angle. The form structure and financial text detection method are created based on the accurate form line detection. Analysis of two companies using the system of this paper reveals that the number of entered field information can be reduced by 91.48% of the entry workload after optimizing the system of this paper. The economic efficiency of labor costs can be significantly improved by reducing the time spent by reimbursement personnel in the reimbursement process by approximately 4,400 hours per month. By using the system in this paper, a new document can be created and submitted for approval in just 11 minutes, which reduces the document time by 86.25%. The constructed scores for the four first-level indicators, A, B, C, and D, range from 80 to 90 points, resulting in a total score of 87.417 points for the comprehensive evaluation. The construction of the financial shared service system in this paper consolidates the enterprise financial business into a centralized processing system, thereby enhancing the quality and efficiency of enterprise accounting management.

Convolutional Neural Network Activation Function Performance on Image Recognition of The Batak Script

Deep Learning is a sub-set of Machine learning, Deep Learning is widely used to solve problems in various fields. One of the popular deep learning architectures is The Convolutional Neural Network (CNN), CNN has a layer that transforms feature extraction automatically so it is widely used in image recognition. However, CNN's performance using the tanh function is still relatively low, therefore it is necessary to select the right activation function to improve accuracy performance. This study analyzes the use of the activation function in image recognition of the Batak script. The result of this study is that the CNN model using the ReLU and eLU functions produces the highest accuracy compared to the CNN model using the tanh function. The CNN model using eLU produces the best accuracy performance in the training process, which is 99.71% with an error value of 0.0108. Meanwhile, in the testing process, the highest accuracy value is generated by the CNN Model using the ReLU function with an accuracy of 94.11%, an error value of 0.3282, a precision value of 0.9411, a recall of 0.9411, and an f1-score of 0.9416.

Two-dimensional viologen-based lanthanide coordination polymers as multi-stimuli responsive materials to light and amines with a fluorescence response.

Integrating multi-stimuli response properties in one molecule is challenging. This study presents two 2D polymers, [(Bpydp)Ln(H2O)(BDC)]·NO3·2H2O (Ln = Eu(1), Tb(2)), exhibiting rapid photo-responsiveness and the ability to detect specific small-molecule amines. In particular, complex 1 combines the functions of inkless printing, amine detection, anti-counterfeiting, and fluorescence recognition.

DNA-functionalized metal or metal-containing nanoparticles for biological applications.

The conjugation of DNA molecules with metal or metal-containing nanoparticles (M/MC NPs) has resulted in a number of new hybrid materials, enabling a diverse range of novel biological applications in nanomaterial assembly, biosensor development, and drug/gene delivery. In such materials, the molecular recognition, gene therapeutic, and structure-directing functions of DNA molecules are coupled with M/MC NPs. In turn, the M/MC NPs have optical, catalytic, pore structure, or photodynamic/photothermal properties, which are beneficial for sensing, theranostic, and drug loading applications. This review focuses on the different DNA functionalization protocols available for M/MC NPs, including gold NPs, upconversion NPs, metal-organic frameworks, metal oxide NPs and quantum dots. The biological applications of DNA-functionalized M/MC NPs in the treatment or diagnosis of cancers are discussed in detail.

An Analysis of the Efficacy of L2-MT Mixed Modeling in Second Language Acquisition - A Cognitive Ability Perspective

Abstract Cognitive ability provides a new perspective for second language acquisition research, but there are still many problems to be solved. Therefore, after fully exploring the concept of cognitive synergy, this paper proposes two research methods: qualitative multimodal interaction and hybridization of cognitive synergy. The deep neural network algorithm is interpreted layer by layer, and the model is applied to the construction of bilingual language models. Based on this, the L2-MT hybrid model is introduced, and the generalization performance of the bilingual language model is improved using the joint approach. The model’s speech recognition function for monolingual multi-task learning is used to aid learners in learning a second language. The effectiveness of the L2-MT hybrid model in second language acquisition was tested through statistical correlation analysis. Under this model, the attention of the second language learners fluctuated twice in the first half of the learning process, with the fluctuation range between 80% and 100%, and finally stabilized at about 70%. The subjects were more concentrated in the second language acquisition process. In the second language achievement comparison experiment, class A performed better than class B in terms of speaking, writing, translation, and total achievement. The difference between the two classes is 7.83, 5.002, and 3.6, respectively. Meanwhile, the p-value is 0, which is less than 0.01, and there is a significant difference between the two classes. The L2-MT model has a higher value of application in second language acquisition, which provides a better method for learners.

Artificial Intelligence-Assisted Training and Skill Enhancement Strategies for Athletes

Abstract The continuous progress of science and technology promotes the continuous development of artificial intelligence, and digital intelligence empowerment has gradually become a focus topic of widespread social concern. Considering that traditional sports training is difficult to meet the higher requirements put forward by athletes on training methods, training load, and training equipment, this study combines artificial intelligence technology to explore the path of skill enhancement. In this paper, based on the skeletal key points for athlete training action recognition, the improved DHRNet network is optimized for the detection of skeletal key points and then for the complexity of the athlete’s training state, the occlusion of the skeletal points and the repair of motion information are carried out. On this basis, we construct an artificial intelligence-assisted training system composed of a video image input function system, action recognition function system, and behavior analysis function system. After completing the design, the core module of the system, the motion recognition system, was tested. The average recognition success rates of basic and sport movements were between 90.8~95.6% and 84.5~96.5%, respectively. The overall recognition correctness rate remained above 90% in the actual application test, which can meet the training needs of athletes. The average score for all abilities of the athletes using the AI-supported system is 85.242, which is 6.21 higher than that of the traditional training method. The AI-assisted system is of great help to athletes’ training, and it also enables the early realization of intelligent training.

Exploration of Intelligent Transformation Path of Traditional Cultural and Creative Products Based on Internet of Things Technology

Abstract More and more modern technology is applied to traditional cultural and creative industries, which enhances the technicality and novelty of traditional cultural products, and the fusion of culture and modern technology profoundly changes people’s way of life and learning. This paper explores the Internet of Things (IoT) technology and the intelligent transformation process of cultural and creative products and constructs cultural and creative products that integrate intelligent voice series. Specifically, a speech recognition model is integrated into the design process of cultural and creative products, and the designed model is applied to the design of intelligent cultural and creative products by analyzing the Hidden Markov Model (HMM), proposing a solution to the shortcomings of the HMM model, and choosing to perform noise reduction of speech signals through the fixed beam algorithm. Based on the speech recognition model designed in this paper, an intelligent cultural and creative product with a speech recognition function is designed, taking the ‘owl wine container’ from the Shanxi Museum as an example. The regression equation of the audience’s satisfaction with the product is Y (satisfaction) = -0.000263 + 0.208X1 (practicality) + 0.265X2 (innovation) + 0.253X3 (culture) + 0.271X4 (interactivity) - 0.296X5 (fun). This paper’s intelligent cultural and creative products have a greater impact on satisfaction due to their innovativeness and interactive function.

Impact and potential value of immunosenescence on solid gastrointestinal tumors.

Solid gastrointestinal tumors often respond poorly to immunotherapy for the complex tumor microenvironment (TME), which is exacerbated by immune system alterations. Immunosenescence is the process of increased diversification of immune genes due to aging and other factors, leading to a decrease in the recognition function of the immune system. This process involves immune organs, immune cells, and the senescence-associated secretory phenotype (SASP). The most fundamental change is DNA damage, resulting in TME remodeling. The main manifestations are worsening inflammation, increased immunosuppressive SASP production, decreased immune cell antitumor activity, and the accumulation of tumor-associated fibroblasts and myeloid-derived suppressor cells, making antitumor therapy less effective. Senotherapy strategies to remove senescent cells and block key senescence processes can have synergistic effects with other treatments. This review focuses on immunoenescence and its impact on the solid TME. We characterize the immunosenescent TME and discuss future directions for antitumor therapies targeting senescence.