Recognition Function Research Articles

Development of an automatic medium exchange system using a compact general-purpose robot equipped with image recognition functionality．

Development of an automatic medium exchange system using a compact general-purpose robot equipped with image recognition functionality．

THE USE OF SPEECHRECOGNITION TO FIND OUT READING ERRORS ON GOOGLE TRANSLATE

This study aims to find out what are the errors in reading 50 Arabic vocabularies using speech recognition found on google translate. This research is descriptive qualitative research, with collection techniques using observation and documentation techniques. Data used in this research is 50 vocabularies prepared for reading by 20 students. Data analysis techniques used in research it is an interactive data analysis. The research result obtained is that several vocabularies that have many errors, in the accuracy of letters, and there is also a vocabulary that has the correct letter and vowel accuracy. Errors found in using speech recognition very diverse, such as the arrangement of letters that do not match up with what is captured by the speech recognition function from google translate. Common reading errors in the vocabulary prepared by the researcher an error in the vocabulary ending in the letter Ta’ Marbutah “ة”. This is due to the arrangement of letters and vowels in the vocabulary prepared by the researcher is not by the result captures by google translate when students read it.

Photoelectrochemical sensor for the detection of Escherichia coli O157:H7 based on TPA-NO2 and dual-functional polythiophene films

The detection of Escherichia coli (E. coli) is of great significance for the environment and human health. Herein, a photoelectrochemical (PEC) detection strategy based on molecularly imprinted polymers (MIPs) was proposed for the sensitive detection of E. coli. 4,4′,4″-Trinitrotriphenylamine (TPA-NO2) was prepared using a simple nitration reaction. Subsequently, MIP films were polymerized on the surface of TPA-NO2 using 1,3-dihydrothieno[3,2-d]pyrimidine-2,4-dione as the functional monomer with the dual functions of specific recognition and sensitization. The linear range was 10–108 CFU/mL and the limit of detection was 10 CFU/mL. It showed favorable recoveries in real sample tests of milk, orange juice and tomato. Additionally, the ability of functional monomers to bind excellently with E. coli was verified using molecular docking techniques. This research provided broader possibilities for constructing MIPs-PEC sensors and analyzing the interaction mechanism between E. coli and functional monomers.

Largemouth bass galectin, MsGal-9: Mediating various functions as a pattern recognition receptor and a potential damage-associated molecular pattern

Galectins are lectins that bind to β-galactose and are widely expressed in immune system tissues, playing pivotal roles in innate immunity through their conserved carbohydrate-recognition domains (CRDs). In this present investigation, a tandem-repeat galectin was discovered in the largemouth bass, Micropterus salmoides (designated as MsGal-9). The open reading frame of MsGal-9 encodes two CRDs, each containing two consensus motifs that are essential for ligand binding. MsGal-9 is expressed in various tissues of the largemouth bass, with particularly high expression levels in the liver and spleen. The full-length form of MsGal-9, as well as the N-terminal (MsGal-9-N) and C-terminal (MsGal-9-C) CRDs, were individually recombined. Their ability for nonself recognition was studied. The three recombinant proteins were able to bind to glucan (GLU), peptidoglycan (PGN), and lipopolysaccharide (LPS), with MsGal-9 displaying the highest binding activity. Furthermore, rMsGal-9-N exhibited higher binding activity towards GLU in comparison to rMsGal-9-C. Further investigations revealed that the full-length rMsGal-9 could significantly bind to Gram-positive bacteria, Gram-negative bacteria, and fungi, while rMsGal-9-C specifically bound to Escherichia coli. However, rMsGal-9-N did not exhibit significant binding activity towards any microbes. These findings indicate that MsGal-9 requires both CRDs to cooperate in order to fulfill its nonself recognition function. All three recombinant proteins demonstrated agglutination activity towards various microbes, with MsGal-9 and MsGal-9-N displaying a similar broad binding spectrum, while MsGal-9-C agglutinated three types of bacteria. Moreover, both MsGal-9 and MsGal-9-N were capable of coagulating largemouth bass red blood cells, whereas MsGal-9-C lacked this ability. However, MsGal-9-C played a significant role in enhancing the encapsulation of leukocytes in comparison to MsGal-9-N. All three proteins acted as potential damage-associated molecular patterns (DAMPs), inducing apoptosis in leukocytes.

Numerical Analysis of an Autonomous Emergency Braking System for Rear-End Collisions of Electric Bicycles.

The rapid growth in the number of electric bicycles (e-bicycles) has greatly improved daily commuting for residents, but it has also increased traffic collisions involving e-bicycles. This study aims to develop an autonomous emergency braking (AEB) system for e-bicycles to reduce rear-end collisions. A framework for the AEB system composed of the risk recognition function and collision avoidance function was designed, and an e-bicycle following model was established. Then, numerical simulations were conducted in multiple scenarios to evaluate the effectiveness of the AEB system under different riding conditions. The results showed that the probability and severity of rear-end collisions involving e-bicycles significantly decreased with the application of the AEB system, and the number of rear-end collisions resulted in a 68.0% reduction. To more effectively prevent rear-end collisions, a low control delay (delay time) and suitable risk judgment criteria (TTC threshold) for the AEB system were required. The study findings suggested that when a delay time was less than or equal to 0.1 s and the TTC threshold was set at 2 s, rear-end collisions could be more effectively prevented while minimizing false alarms in the AEB system. Additionally, as the deceleration rate increased from 1.5 m/s2 to 4.5 m/s2, the probability and average severity of rear-end collisions also increased by 196.5% and 42.9%, respectively. This study can provide theoretical implications for the design of the AEB system for e-bicycles. The established e-bicycle following model serves as a reference for the microscopic simulation of e-bicycles.

A Multi‐Module Sensing and Bi‐Directional HMI Integrating Interaction, Recognition, and Feedback for Intelligent Robots

AbstractRapid advances in robotics have placed urgent demands on more intelligent human‐machine interaction technologies. Specifically, the way of establishing dual‐way intuitive communication with a consistent sensory system can greatly enhance efficiency and reliability. Here, a bi‐directional human‐machine interface (HMI) is designed by applying starch‐based hydrogel sensors. The whole system consists of a multi‐modal wearable sensory exoskeleton with a haptic feedback module and sensory robotic hand. The sensory exoskeleton with strain‐sensing glove and rotation‐sensing arm can capture and project the motion of the entire upper limb. The system offers object recognition functions by utilizing a sensing array on the robotic hands and machine learning algorithms, which can identify the shape and hardness information. The recognized results can be delivered back to the operator via vision and vibrational haptic feedback, respectively. This dual‐way intelligent sensory system shows potential application in many key fields such as the Internet of Things, teleoperation, and medical robotics.

Tailoring tumor-recognizable hyaluronic acid–lipid conjugates to enhance anticancer efficacies of surface-engineered natural killer cells

Natural killer (NK) cells have clinical advantages in adoptive cell therapy owing to their inherent anticancer efficacy and their ability to identify and eliminate malignant tumors. However, insufficient cancer-targeting ligands on NK cell surfaces often inhibit their immunotherapeutic performance, especially in immunosuppressive tumor microenvironment. To facilitate tumor recognition and subsequent anticancer function of NK cells, we developed hyaluronic acid (HA, ligands to target CD44 overexpressed onto cancer cells)-poly(ethylene glycol) (PEG, cytoplasmic penetration blocker)-Lipid (molecular anchor for NK cell membrane decoration through hydrophobic interaction) conjugates for biomaterial-mediated ex vivo NK cell surface engineering. Among these major compartments (i.e., Lipid, PEG and HA), optimization of lipid anchors (in terms of chemical structure and intrinsic amphiphilicity) is the most important design parameter to modulate hydrophobic interaction with dynamic NK cell membranes. Here, three different lipid types including 1,2-dimyristoyl-sn-glycero-3-phosphati-dylethanolamine (C14:0), 1,2-distearoyl-sn-glycero-3-phosphatidylethanolamine (DSPE, C18:0), and cholesterol were evaluated to maximize membrane coating efficacy and associated anticancer performance of surface-engineered NK cells (HALipid-NK cells). Our results demonstrated that NK cells coated with HA-PEG-DSPE conjugates exhibited significantly enhanced anticancer efficacies toward MDA-MB-231 breast cancer cells without an off-target effect on human fibroblasts specifically via increased NK cell membrane coating efficacy and prolonged surface duration of HA onto NK cell surfaces, thereby improving HA-CD44 recognition. These results suggest that our HALipid-NK cells with tumor-recognizable HA-PEG-DSPE conjugates could be further utilized in various cancer immunotherapies.Graphical

Identification and processing of in-ear acoustic signals

Hearing is the sound depiction of the world for human beings. The ear, or in other world, the peripheral organ of hearing, is an important physiological structure and basis to produce hearing. In order to learn more about hearing organs, the first thing required to know is how hearing is formed, as well as how sound is perceived by us. For this purpose, this paper will examine the matter of identification and processing of in-ear acoustic signals. The main content of this paper are principles of sound, hearing, and signal encoding, as well as their usage in a model which describes the neuron system in cochlear nucleus. In addition, this paper puts forward an application of in-ear signal identifying in hearing aids and cochlear implants by using the convolution signal encoding mode to improve the sound recognition function of these devices and further improve the lives of the hearing impaired. In the end, basic conceptions and related knowledge are organized in this paper. The meanings and problems of this paper are also mentioned in the last section.

A study on the recognition of monkeypox infection based on deep convolutional neural networks.

The World Health Organization (WHO) has assessed the global public risk of monkeypox as moderate, and 71 WHO member countries have reported more than 14,000 cases of monkeypox infection. At present, the identification of clinical symptoms of monkeypox mainly depends on traditional medical means, which has the problems of low detection efficiency and high detection cost. The deep learning algorithm is excellent in image recognition and can extract and recognize image features quickly and reliably. Therefore, this paper proposes a residual convolutional neural network based on the λ function and contextual transformer (LaCTResNet) for the image recognition of monkeypox cases. The average recognition accuracy of the neural network model is 91.85%, which is 15.82% higher than that of the baseline model ResNet50 and better than the classical convolutional neural networks models such as AlexNet, VGG16, Inception-V3, and EfficientNet-B5. This method realizes high-precision identification of skin symptoms of the monkeypox virus to provide a fast and reliable auxiliary diagnosis method for monkeypox cases for front-line medical staff.

StairWave Transformer: For Fast Utilization of Recognition Function in Various Unmanned Vehicles

Newly introduced vehicles come with various added functions, each time utilizing data from different sensors. One prominent related function is autonomous driving, which is performed in cooperation with multiple sensors. These sensors mainly include image sensors, depth sensors, and infrared detection technology for nighttime use, and they mostly generate data based on image processing methods. In this paper, we propose a model that utilizes a parallel transformer design to gradually reduce the size of input data in a manner similar to a stairway, allowing for the effective use of such data and efficient learning. In contrast to the conventional DETR, this model demonstrates its capability to be trained effectively with smaller datasets and achieves rapid convergence. When it comes to classification, it notably diminishes computational demands, scaling down by approximately 6.75 times in comparison to ViT-Base, all the while maintaining an accuracy margin of within ±3%. Additionally, even in cases where sensor positions may exhibit slight misalignment due to variations in data input for object detection, it manages to yield consistent results, unfazed by the differences in the field of view taken into consideration. The proposed model is named Stairwave and is characterized by a parallel structure that retains a staircase-like form.

Application of Multi-sensory interaction design Based on Machine Learning in Virtual Reality

Virtual reality (VR) technology is well-known to the public for its unparalleled sense of environmental immersion, which is accompanied by a large amount of human-computer interaction between users and objects in the virtual environment. Users transmit and obtain information through their senses, so the processing mechanism of information in various senses under the background of VR technology has become the foundation of research. In the process of natural information dissemination, users’ senses are synergistically involved, so whether there is a correlation between various senses that affects users’ final perception has become an important theoretical support for studying multi-sensory interaction. Facial expression recognition is an important component of multi-sensory interaction technology. Therefore, this article mainly uses machine learning algorithms to achieve real-time detection of facial targets in images or videos, as well as classification and recognition of facial expressions. To meet the task requirements of the expression recognition module, this article selects the DeepID network model based on deep learning in the field of facial recognition as the basic model for the expression recognition function. This study utilizes the excellent feature extraction ability of the original network for facial images and introduces residual modules and attention mechanisms, making the modified network model more suitable for facial expression multi classification recognition tasks. The recognition accuracy of the facial expression classification algorithm proposed by this work reaches 97.2%.

Engineering an Antifouling Electrochemical Sensing Platform Based on an All-in-One Peptide and a Hierarchical β-Bi2O3-Au Microsphere for Vancomycin Detection in Food.

Challenges associated with interference aroused by nonspecific attachment of foulants in the food matrix steered the development of sensor surfaces capable of antifouling capacity. In this study, an antifouling electrochemical sensing platform based on an all-in-one peptide (DOPA3-PPPPEKDQDKKaa) with anchoring, antifouling, and recognition functions and a hierarchical β-Bi2O3-Au microsphere was proposed for vancomycin (Van) detection in food. The β-Bi2O3-Au with excellent conductivity was synthesized and introduced as an electrode modifier to accelerate electron transfer on the sensor surface, enhancing sensing response. Mussel organism-inspired oligo DOPA, that is, oligo 3,4-dihydroxyphenylalanine, was employed as the anchoring segment of the all-in-one peptide, which is versatile for surfaces with different materials. PPPPEKDQDK and Kaa as antifouling and recognition segments confer abilities to resist nonspecific adsorption of foulants and specifically bind Van on the sensor surface, respectively. Notably, the excellent antifouling performance of the proposed sensor has been verified in protein solutions, carbohydrate solutions, and even in diluted milk and honey. Molecular dynamics simulation was carried out to explain the antifouling mechanism of the all-in-one peptide. The proposed sensor can detect Van sensitively and selectively with a relatively wide linear range (0.1-100 ng mL-1) and a limit of detection (LOD) as low as 0.038 ng mL-1 and support the quantification of Van in milk, milk powder, and honey samples with satisfactory recoveries within 105.3-110.8%. This antifouling electrochemical sensing platform offers a feasible strategy to reduce matrix interference, which guarantees the accurate detection of Van in food samples.

Highly sensitive quantitative detection of glycans on exosomes in renal disease serums using fluorescence signal amplification strategies

Exosomal glycoproteins play a significant role in many physiological and pathological processes. However, the detection of exosome surface glycans is currently challenged by the complexity of biological samples or the sensitivity of the methods. Herein, we prepared a novel fluorescent probe of biotin-functionalized nanocrystals (denoted as CdTe@cys-biotin) and applied it for the first time for the detection of the expression of exosomal surface glycans using a fluorescence amplification strategy. First, the dual affinity of TiO2 and CD63 aptamers of Fe3O4@TiO2-CD63 was utilized to rapidly and efficiently capture exosomes within 25 min. In this design, interference from other vesicles and soluble impurities can be avoided due to the dual recognition strategy. The chemical oxidation of NaIO4 oxidized the hydroxyl sites of exosomal surface glycans to aldehydes, which were then labeled with aniline-catalyzed biotin hydrazide. Using the high affinity between streptavidin and biotin, streptavidin-FITC and probes were successively anchored to the glycans on the exosomes. The fluorescent probe achieved the dual function of specific recognition and fluorescent labeling by modifying biotin on the surface of nanocrystals. This method showed excellent specificity and sensitivity for exosomes at concentrations ranging from 3.30 × 102 to 3.30 × 106 particles/mL, with a detection limit of 121.48 particles/mL. The fluorescent probe not only quantified exosomal surface glycans but also distinguished with high accuracy between serum exosomes from normal individuals and patients with kidney disease. In general, this method provides a powerful platform for sensitive detection of exosomes in cancer diagnosis.

QOL-16. GLIOBLASTOMAS LOCATED IN THE RIGHT INFERIOR PARIETAL LOBE CAUSE A POOR POSTOPERATIVE PERFORMANCE LEVEL

Abstract OBJECTIVE Managing quality of life has become more important for patients with glioblastoma (GBM). Maintaining independence levels should be given attention while treating GBM. Postoperatively, non-dominant hemispheric GBMs often decrease the Karnofsky Performance Status (KPS) score. This study aimed to investigate the factors that lead to poor KPS scores after tumor resection in non-dominant hemispheric GBM. METHODS Forty-one patients newly diagnosed GBM in the right cerebral hemisphere who underwent resection were included. Brain functions were assessed preoperatively and postoperatively. First, the KPS scores before and after surgery were compared. Second, univariate and multiple regression analyses and voxel-based lesion-symptom mapping (VLSM) were performed to analyze the functions and brain regions related to KPS, respectively. Third, factors associated with prognosis were analyzed using the log-rank test. RESULTS Compared with the preoperative status, KPS significantly decreased after the surgery (81.0% vs. 73.6%, p = 0.020). Brain functions affecting KPS include general cognitive function, processing speed, attention, memory, visuospatial cognition, emotion recognition, and executive function. Among these, multiple regression analysis revealed visuospatial cognition and emotion recognition to be significantly influenced KPS in the chronic postoperative phase (p = 0.030 and 0.048, respectively). VLSM demonstrated that resection of the inferior parietal lobe caused a significant decline in KPS. Visuospatial cognition and emotion recognition were impaired with a higher probability (p = 0.035 and 0.048, respectively) in patients with tumors located in the inferior parietal lobe. In addition, lesions in the inferior parietal lobe were associated with shorter overall survival (p = 0.046). CONCLUSIONS GBMs in the right inferior parietal lobe are more likely to result in poor postoperative KPS due to impairment of visuospatial cognition and emotion recognition, which relate to a poor prognosis.

Assessments of Order-Picking Tasks Using a Paper List and Augmented Reality Glasses with Different Order Information Displays

This study investigated the effects of wearing AR devices on users’ performance and comfort ratings while performing order-picking (OP) tasks. In addition to a picking-by-paper list, two AR devices combined with three order information display designs were examined. Thirty adult participants joined. They searched for and found the boxes in the order list, picked them up, and returned to the origin. The time to complete the task and the number of incorrect boxes picked up were analyzed to assess the performance of the tasks. The subjective ratings of the participants on the comfort rating scale (CRS) and the simulator sickness questionnaire (SSQ) were collected to assess the designs of both the AR devices and the order information displays. It was found that the participants could complete the OP tasks faster when adopting the order map (4.97 ± 1.57 min) or the 3D graph display (4.87 ± 1.50 min) using either one of the AR devices than when using a paper list (6.03 ± 1.28 min). However, they needed more time to complete the OP tasks when wearing both types of AR glasses when the Quick Response (QR) code option was adopted (10.16 ± 4.30 min) than when using a paper list. The QR code scanning and display design using either one of the AR devices guaranteed 100% accuracy but sacrificed efficiency in task completion. The AR device with a binocular display and hand gesture recognition functions had a significantly lower CRS score in the dimensions of attachment and movement (5.6 and 6.3, respectively) than the corresponding dimensions (8.0 and 8.3, respectively) of the other device with a monocular and hand touch input design. There were complaints of eye strain after using both AR devices examined in this study. This implies that these AR devices may not be suitable to wear for extended periods of time. Users should take off the AR device whenever they do not need to view the virtual image to avoid eye strain and other discomfort symptoms.

256 Effects of Lactobacillus Fermentate Replacing Bacitracin on Biomarkers Associated with Bacterial Cell Wall Recognition and Intestinal Integrity in Pigs

Abstract Two experiments were conducted to evaluate the efficacy of Lactobacillus fermentate (LBF) as postbiotic on immune response and barrier function in jejunal mucosa of nursery pigs challenged with F18+Escherichia coli. Sixty-four pigs (32 barrows and 32 gilts) weaned at 21 d of age with 7.9 ± 0.5 kg in Exp. 1 (n = 32) and 6.6 ± 0.7 kg in Exp. 2 (n = 32) were allotted based on a randomized complete block design with sex and initial BW as blocks. The treatments were NC: no challenge/no supplement; PC: E. coli challenge/no supplement; AGP: E. coli challenge/bacitracin (30 g/t feed); and PBT: E. coli challenge/postbiotic (2 kg/t feed). Pigs were fed a basal diet for 28 d, formulated to meet the nutrient requirements of NRC (2012). At d 7, the challenged pigs were orally inoculated with F18+E. coli. At d 28, pigs were euthanized to collect jejunal tissue to analyze gene expressions involved in bacterial cell wall recognition, immune response, and intestinal barrier function. Data were analyzed using the Proc MIXED of SAS 9.4. The PC tended to reduce (P = 0.097) the relative expression of PGLYRP2A (1.12 to 0.76) and increased (P < 0.05) TLR4 (0.98 to 1.67) and NOD1 (0.99 to 1.56) compared with NC. The AGP tended to increase (P = 0.074) PGLYRP2A (0.76 to 1.15) and tended to reduce (P = 0.099) PGLYRP3 (1.21 to 0.82) compared with PC. The PBT increased (P < 0.05) PGLYRP4 (0.86 to 1.53) compared with PC. The AGP tended to reduce (P = 0.085) TLR4 (1.67 to 0.98) compared with PC. The AGP and the PBT reduced (P < 0.05) NOD1 (1.56 to 0.98 and 0.97, respectively) compared with PC. The PC tended to increase (P = 0.079) CD14 (1.13 to 2.13) compared with NC, however, PBT tended to reduce (P = 0.091) it (2.13 to 1.27) compared with PC. The AGP increased (P < 0.05) interferon-γ (1.13 to 1.21) and the PBT tended to increase (P = 0.096) it (1.13 to 1.63) compared with PC. The AGP tended to increase (P = 0.082) claudin-1 (0.85 to 1.81) compared with PC. In conclusion, F18+E. coli challenge upregulated the expression of pathogen recognition genes, including TLR4, CD14, and NOD1, which can increase the production of cytokines associated with pro-inflammatory response. The AGP showed a trend towards increasing the intestinal barrier function, possibly by increasing the expression of interferon-γ and reducing the expression of genes associated with pathogen recognition. The PBT enhanced the immunocompetence of nursery pigs by increasing the expression of interferon-γ and PGLYRP4, and reducing the expression of genes associated with pathogen recognition including NOD1 and CD14, which may indicate a reduction of the pathogen invasion.

A DenseNet‐based feature weighting convolutional network recognition model and its application in industrial part classification

AbstractTraditional warehousing typically needs machine learning or manual tagging to classify objects. However, this method is less robust and consumes a lot of labour and material resources. Based on DenseNet, this work proposes a feature weighting convolutional network recognition model and designs a set of software and hardware for data acquisition, which is applied to the efficient classification of industrial parts in warehouse management. Firstly, this work modifies DenseNet by embedding SE‐Block, and replaces the cross‐entropy loss function with the focus loss function to optimize the model structure. Secondly, a multi‐view hardware and software acquisition system is designed to complete the functions of part image acquisition, image preprocessing, model training and part recognition. Finally, an industrial parts sorting experiment was designed. Compared with the original DenseNet model, the proposed weighted convolutional network identification model showed that the accuracy of the modified model was increased by 3.09% and the convergence rate was significantly improved. The modified model proposed in this work aims to improve the recognition accuracy of industrial parts in modern warehouse management, so as to modify the classification efficiency of warehouse parts in production.

Assessing the diametrical model of schizotypal and autistic traits in emotion recognition and social functioning in a community sample.

Some research suggests that schizotypal and autistic traits can produce opposing effects on the mentalizing domain of social cognition. Although such findings support a diametrical model proposing that psychotic and autistic traits represent opposite extremes of the social brain continuum, results from recent studies have been more inconsistent, and the applicability of this model to other social cognition domains remains unclear. To test the diametrical model more broadly, this study examined the interactions between schizotypal and autistic traits on emotion recognition and social functioning. A total of 791 participants recruited from the general population self-reported schizotypal traits using the Schizotypal Personality Questionnaire-Brief Revised (SPQ-BR) and autistic traits using the Broad Autism Phenotype Questionnaire (BAPQ). Participants also completed the Emotion Recognition 40 task and the Specific Levels of Functioning (SLOF) scale. The SPQ subscales of interpersonal relationships and disorganized symptoms interacted significantly with social BAP on overall emotion recognition performance and the accuracy of identifying neutral faces. Supporting the diametrical model, elevated levels of both schizotypal and autistic traits contributed to higher emotion recognition accuracy compared to elevations on only one trait. For social functioning, however, the diametrical model was not supported. A main effect was found such that higher interpersonal relationship difficulties on SPQ predicted lower work skills on SLOF, and higher levels of both schizotypal and autistic traits combined to produce even lower social functioning. These findings suggest that the diametrical model may be more relevant to social cognition than to social functioning.

EMNGly: predicting N-linked glycosylation sites using the language models for feature extraction.

N-linked glycosylation is a frequently occurring post-translational protein modification that serves critical functions in protein folding, stability, trafficking, and recognition. Its involvement spans across multiple biological processes and alterations to this process can result in various diseases. Therefore, identifying N-linked glycosylation sites is imperative for comprehending the mechanisms and systems underlying glycosylation. Due to the inherent experimental complexities, machine learning and deep learning have become indispensable tools for predicting these sites. In this context, a new approach called EMNGly has been proposed. The EMNGly approach utilizes pretrained protein language model (Evolutionary Scale Modeling) and pretrained protein structure model (Inverse Folding Model) for features extraction and support vector machine for classification. Ten-fold cross-validation and independent tests show that this approach has outperformed existing techniques. And it achieves Matthews Correlation Coefficient, sensitivity, specificity, and accuracy of 0.8282, 0.9343, 0.8934, and 0.9143, respectively on a benchmark independent test set.

Determinants of Emotion Recognition System Adoption: Empirical Evidence from Malaysia

Emotion recognition systems (ERS) are an emerging technology with immense potential, exemplifying the innovative utilization of artificial intelligence (AI) within the context of the fourth industrial revolution (IR 4.0). Given that personalization is a key feature of the fifth industrial revolution (IR 5.0), ERS has the potential to serve as an enabler for IR 5.0. Furthermore, the COVID-19 pandemic has increased the relevance of this technology as work processes were adapted for social distancing and the use of face masks. Even in the post-pandemic era, many individuals continue to wear face masks. Therefore, ERS offers a technological solution to address communication challenges in a masked world. The existing body of knowledge on ERS primarily focuses on exploring modalities or modes for emotion recognition, system development, and the creation of applications utilizing emotion recognition functions. However, to enhance the development of impactful ERS, it is essential for researchers and innovators to understand the factors that influence its usage and adoption among the intended users. Therefore, this study presents a framework that combines technology adoption theories to identify the determinants of ERS adoption among Malaysian youth. Data for this study were collected through a survey involving 386 respondents. The findings revealed attitudes, subjective norms, perceived behavioral control, and awareness as significant determinants of ERS adoption. Additionally, the study found that technology aptitude plays a moderating role. These insights can inform the formulation of effective policies and programs to encourage and facilitate the development of innovative ERS solutions.