Recognition Evaluation Research Articles

A Method of Intelligent Driving-Style Recognition Using Natural Driving Data

At present, achieving efficient, sustainable, and safe transportation has led to increasing attention on driving behavior recognition and advancements in autonomous driving. Identifying diverse driving styles and corresponding types is crucial for providing targeted training and assistance to drivers, enhancing safety awareness, optimizing driving costs, and improving autonomous driving systems responses. However, current studies mainly focus on specific driving scenarios, such as free driving, car-following, and lane-changing, lacking a comprehensive and systematic framework to identify the diverse driving styles. This study proposes a novel, data-driven approach to driving-style recognition utilizing naturalistic driving data NGSIM. Specifically, the NGSIM dataset is employed to categorize car-following and lane-changing groups according to driving-state extraction conditions. Then, characteristic parameters that fully represent driving styles are optimized through correlation analysis and principal component analysis for dimensionality reduction. The K-means clustering algorithm is applied to categorize the car-following and lane-changing groups into three driving styles: conservative, moderate, and radical. Based on the clustering results, a comprehensive evaluation of the driving styles is conducted. Finally, a comparative evaluation of SVM, Random Forest, and KNN recognition indicates the superiority of the SVM algorithm and highlights the effectiveness of dimensionality reduction in optimizing characteristic parameters. The proposed method achieves over 97% accuracy in identifying car-following and lane-changing behaviors, confirming that the approach based on naturalistic driving data can effectively and intelligently recognize driving styles.

Beyond body image: Self-face recognition and negative self-face evaluations in women at high risk for an eating disorder.

Although one's face represents a core aspect of one's physical appearance, it remains underexplored in eating disorder (ED) populations. The current study examined whether self-face recognition accuracy and evaluations differ in those at high (vs. low) ED risk. We also explored whether recognition accuracy and evaluations are related, and whether this relationship is moderated by ED risk status. Participants included 222 women of East/Southeast Asian (61%) and Caucasian (39%) ethnicity, stratified into low-ED-risk (n=124) and high-ED-risk (n=98). Participants completed measures of self-face recognition accuracy (difficulty recognizing their face and sensitivity to seeing their facial image) and evaluations (including perceived facial adiposity and attractiveness, and head dissatisfaction). Partially consistent with hypotheses, regression analyses revealed that participants at high (vs. low) risk showed poorer self-face recognition accuracy (greater difficulty) and more negative self-face evaluations (higher perceived adiposity, lower perceived attractiveness, greater head dissatisfaction). However, ED risk was not significantly associated with self-face recognition sensitivity. Inconsistent with expectations, whilst greater self-face recognition difficulty was associated with more negative self-face evaluations, ED risk failed to moderate such effects. Findings suggest the potential value of considering face and body image disturbances in ED research and interventions. Further research is encouraged.

Remote Infant Studies of Early Learning (RISE): Scalable online replications of key findings in infant cognitive development.

The current article describes the Remote Infant Studies of Early Learning, a battery intended to provide robust looking time measures of cognitive development that can be administered remotely to inform our understanding of individual developmental trajectories in typical and atypical populations, particularly infant siblings of autistic children. This battery was developed to inform our understanding of early cognitive and language development in infants who will later receive a diagnosis of autism. Using tasks that have been successfully implemented in lab-based paradigms, we included assessments of attention, memory, prediction, word recognition, numeracy, multimodal processing, and social evaluation. This study reports results on the feasibility and validity of administration of this task battery in 55 infants who were recruited from the general population at age 6 months (n = 29; 14 female, 15 male) or 12 months (n = 26; 14 female, 12 male; 62% White, 13% Asian, 1% Black, 1% Pacific Islander, 22% more than one race; 6% Hispanic). Infant looking behavior was recorded during at-home administration of the battery on the family's home computer and automatically coded for attention to stimuli using iCatcher+, an open-access software that assesses infant gaze direction. Results indicate that while some tasks replicated lab-based findings (attention, memory, prediction, and numeracy), others did not (word recognition, multimodal processing, and social evaluation). These findings will inform efforts to refine the battery as we continue to develop a robust set of tasks to improve the understanding of early cognitive development at the individual level in general and clinical populations. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

KAZAKH SPEECH AND RECOGNITION METHODS: ERROR ANALYSIS AND IMPROVEMENT PROSPECTS

This study offers a detailed evaluation of automatic speech recognition (ASR) systems for the Kazakh, examining their performance in recognizing the phonetic and linguistic features unique to the language. The Kazakh language presents specific challenges for ASR due to its complex phonology, vowel harmony, and the presence of multiple regional dialects. To address these challenges, a comparative analysis of three leading ASR systems were conducted—Kaldi, Mozilla DeepSpeech, and Google Speech-to-Text API—using a dataset of 101 recordings of spoken the Kazakh text. This study focuses on the systems' word error rates (WER), identifying common misrecognitions, especially with the Kazakh-specific phonemes like "қ," "ң," and "ү." Kaldi and Mozilla DeepSpeech exhibited high WERs, particularly struggling with Kazakh’s vowel harmony and consonant distinctions, while Google Speech-to-Text achieved of the lowest WER among the three. However, none of the systems demonstrated accuracy levels sufficient for practical applications, as errors in recognizing Kazakh’s agglutinative morphology and case endings remained pervasive. To improve these outcomes, a series of enhancements are proposed, including adapting acoustic models to better reflect Kazakh’s phonetic and morphological traits, integrating dialect-specific data, and employing machine learning methods such as transfer learning and hybrid models. Additional steps include refining data preprocessing and increasing dataset diversity to capture Kazakh’s linguistic nuances more accurately. By addressing these limitations, the ASR systems can better handle complex sentence structures and regional speech variations. This research thus provides a foundation for advancing Kazakh ASR technologies and contributes insights that are vital for developing inclusive, effective ASR systems capable of supporting linguistically diverse users.

Implementation of a Whisper Architecture-Based Turkish Automatic Speech Recognition (ASR) System and Evaluation of the Effect of Fine-Tuning with a Low-Rank Adaptation (LoRA) Adapter on Its Performance

This paper focuses on the implementation of the Whisper architecture to create an automatic speech recognition (ASR) system optimized for the Turkish language, which is considered a low-resource language in terms of speech recognition technologies. Whisper is a transformer-based model known for its high performance across numerous languages. However, its performance in Turkish, a language with unique linguistic features and limited labeled data, has yet to be fully explored. To address this, we conducted a series of experiments using five different Turkish speech datasets to assess the model’s baseline performance. Initial evaluations revealed a range of word error rates (WERs) between 4.3% and 14.2%, reflecting the challenges posed by Turkish. To improve these results, we applied the low-rank adaptation (LoRA) technique, which is designed to fine-tune large-scale models efficiently by introducing a reduced set of trainable parameters. After fine-tuning, significant performance improvements were observed, with WER reductions of up to 52.38%. This study demonstrates that fine-tuned Whisper models can be successfully adapted for Turkish, resulting in a robust and accurate end-to-end ASR system. This research highlights the applicability of Whisper in low-resource languages and provides insights into the challenges of and strategies for improving speech recognition performance in Turkish.

Simulation and experimental analysis of traveling wave resonance of flexible spiral bevel gear system

Considering the traveling wave resonance (TWR) phenomenon of the spiral bevel gear system in the aero engine accessory casing, the flexible spiral bevel gear model is established by three-dimensional (3D) shell element and beam element. The dynamic model of flexible bevel gear system considering the change of meshing teeth pairs in the operating process is established by component mode synthesis (CMS) method and rotational modal projection method. The proposed model is verified by finite element (FE) solid model and experiment test results. On this basis, the TWR phenomenon of the bevel gear system is studied in combination with dynamic response and vibration stress experimental test. The results show that the bevel gear system has 3 nodal diameter resonance speeds within the actual operating speed range, which are one 1st nodal diameter resonance of pinion and two 1st nodal diameter resonance of gear. When the bevel gear system operates at TWR state, the amplitude corresponding to fm ± m·fr (fm is meshing frequency, m is nodal diameter number, fr is shaft rotational frequency) is larger than that corresponding to fm in the Fast Fourier transform (FFT) spectrum of the of the gear foundation vibration stress, and the vibration stress cloud map of the gear foundation shows the corresponding nodal diameter vibration shape. The research results provide a theoretical basis for feature recognition and influence law evaluation of TWR of bevel gear system.

NonImmune hemolytic anemia secondary to vitamin B12 deficiency-A case report.

This case report emphasizes the crucial need to include vitamin B12 deficiency in the differential diagnosis of hemolytic anemia, despite its rarity as a presentation. The case illustrates that non-immune hemolytic anemia can occur secondary to severe vitamin B12 deficiency, which can be effectively treated with vitamin B12 supplementation. Early recognition and comprehensive evaluation are essential for identifying this uncommon yet significant cause of hemolysis, ensuring prompt and appropriate treatment to improve patient outcomes.

Characterization of Three-Dimensional Strong Force Chain Properties of Mineral Aggregate Mixtures Based on the Discrete Element Method

The skeleton structure composed of mineral aggregates is the main body to bear and transfer external loading in asphalt mixtures. To investigate the loading transfer mechanism of the mineral aggregate skeleton, the uniaxial penetration test and Discrete Element Method (DEM) were conducted for the Mineral Aggregate Mixture (MAM) to analyze its mechanical behavior. The three-dimensional strong force chain (SFC) was identified and evaluated based on the proposed recognition criterion and evaluation indices. The results indicate that 4.75 mm should be the boundary to distinguish the coarse and fine aggregates. The skeleton composed of aggregates located on SFCs has better bearing and transferring loading capacity due to its SFC number, average length, and total length decreasing with an increase in the aggregate size. Compared to SMA-16 and OGFC-16, AC-16 exhibits a higher number and total length of its SFC, a smaller average length of its SFC, and a lower average strength of its SFC. Consequently, AC-16 has a lower bearing and transferring loading capacity than that of SMA-16 and OGFC-16. In addition, approximately 90% of SFCs can only transfer external loading downward through 3–5 aggregates. The average direction angle of the SFC formed by fine aggregates is significantly higher than those formed by coarse aggregates. This indicates that the load transfer range of MAM composed of fine aggregates is noticeably larger, leading to lower loading transfer efficiency.

Accumbal Dopamine Responses Are Distinct between Female Rats with Active and Passive Coping Strategies.

There is a gap in existing knowledge of stress-triggered neurochemical and behavioral adaptations in females. This study was designed to explore the short-term consequences of a single social defeat (SD) on accumbal dopamine (DA) dynamics and related behaviors in female Wistar rats. During the SD procedure, rats demonstrated different stress-handling strategies, which were defined as active and passive coping. The "active" subjects expressed a significantly higher level of activity directed toward handling stress experience, while the "passive" ones showed an escalated freezing pattern. Remarkably, these opposite behavioral manifestations were negatively correlated. Twenty-four hours following the SD exposure, decreased immobility latency in the Porsolt test and cognitive augmentation in the new object recognition evaluation were evident, along with an increase in electrically evoked mesolimbic DA release in passive coping rats. Rats exhibiting an active pattern of responses showed insignificant changes in immobility and cognitive performance as well as in evoked mesolimbic DA response. Furthermore, the dynamics of the decline and recovery of DA efflux under the depletion protocol were significantly altered in the passive but not active female rats. Taken together, these data suggest that female rats with a passive coping strategy are more susceptible to developing behavioral and neurochemical alterations within 24 h after stress exposure. This observation may represent both maladaptive and protective responses of an organism on a short timescale.

NFT 미술작품 가치 평가 기반하의 랭크 프레임워크 연구

The objective of this study is to devise and propose a ranking framework for NFT artworks and artists, based on the valuation of NFT artworks. The findings of this study can be summarised as follows. Firstly, the results demonstrate that the cost production, S2F method, and quint algorithm approaches, which are commonly employed in classical economics, are the most effective models for valuing NFT artworks. Secondly, quantitative evaluation criteria for NFT artworks were proposed, including factors such as exhibitions and awards, copyrights, exhibition planning, career achievements and assigned weights. Additionally, qualitative evaluation criteria were put forth, encompassing aspects such as content, expression, originality, collectible value and assigned weights. The results of the recognition evaluation criteria were also derived. Furthermore, a framework was put forth to guarantee the rationality of the NFT artist ranking through verification. The anticipated outcomes of this research can be leveraged for the equitable utilisation of NFT artworks for purchase and sale, the establishment of guidelines for the calculation, settlement, and distribution of artworks, and the encouragement of new NFT art creation.

Naked eye Fe(III) recognition and anticancer efficacy evaluation via diazenyl-propargyl appended imine functionalized moiety

The study delves into the synthesis of diazenyl-propargyl appended imine functionalized moiety (4) emphasizing its structural dynamic, Fe(III) sensitivity, and anticancer potential. The synthesized compound was characterized via NMR (1H,13C), TGA, mass spectrometry, and single-crystal X-ray crystallography. The color transition of the compound from yellow to red demonstrates naked-eye sensing for Fe (III), validated by UV–visible spectroscopy. The limit of detection (LOD) and Association Constant (Ka) were calculated from the linear calibration curve and the B–H plot come out to be 28.71 nM and 2.17 × 105 M−1, respectively. As per Job’s plot Fe(III) binds to probe (4) in 1:1 stoichiometry. The interaction of probe (4) with Fe(III) has been examined through VSM (vibrating spectrum magnetism) study, FT-IR, 1H NMR and mass spectrometry. The pharmacokinetic properties of the synthesized compound were assessed, emphasizing absorption, distribution, metabolism, excretion and toxicity. The cytotoxicity assay using SAF-1 cell line indicated that the compound is nontoxic. Also compound (4) showed positive response on cervical cancer cells line and this anti-cancer potential has been further explored through molecular docking analysis.

Particle tracking, recognition and LET evaluation of out-of-field proton therapy delivered to a phantom with implants

Objective. This study aims to assess the composition of scattered particles generated in proton therapy for tumors situated proximal to some titanium (Ti) dental implants. The investigation involves decomposing the mixed field and recording Linear Energy Transfer (LET) spectra to quantify the influence of metallic dental inserts located behind the tumor. Approach. A therapeutic conformal proton beam was used to deliver the treatment plan to an anthropomorphic head phantom with two types of implants inserted in the target volume (made of Ti and plastic, respectively). The scattered radiation resulted during the irradiation was detected by a hybrid semiconductor pixel detector MiniPIX Timepix3 that was placed distal to the Spread-out Bragg peak. Visualization and field decomposition of stray radiation were generated using algorithms trained in particle recognition based on artificial intelligence neural networks (AI NN). Spectral sensitive aspects of the scattered radiation were collected using two angular positions of the detector relative to the beam direction: 0° and 60°. Results. Using AI NN, 3 classes of particles were identified: protons, electrons & photons, and ions & fast neutrons. Placing a Ti implant in the beam’s path resulted in predominantly electrons and photons, contributing 52.2% of the total number of detected particles, whereas for plastic implants, the contribution was 65.4%. Scattered protons comprised 45.5% and 31.9% with and without metal inserts, respectively. The LET spectra were derived for each group of particles identified, with values ranging from 0.01 to 7.5 keV μm−1 for Ti implants/plastic implants. The low-LET component was primarily composed of electrons and photons, while the high-LET component corresponded to protons and ions. Significance. This method, complemented by directional maps, holds the potential for evaluating and validating treatment plans involving stray radiation near organs at risk, offering precise discrimination of the mixed field, and enhancing in this way the LET calculation.

Toxic Peptides from the Mexican Scorpion Centruroides villegasi: Chemical Structure and Evaluation of Recognition by Human Single-Chain Antibodies.

Alternative recombinant sources of antivenoms have been successfully generated. The application of such strategies requires the characterization of the venoms for the development of specific neutralizing molecules against the toxic components. Five toxic peptides to mammals from the Mexican scorpion Centruroides villegasi were isolated by chromatographic procedures by means of gel filtration on Sephadex G-50, followed by ion-exchange columns on carboxy-methyl-cellulose (CMC) resins and finally purified by high-performance chromatography (HPLC) columns. Their primary structures were determined by Edman degradation. They contain 66 amino acids and are maintained well packed by four disulfide bridges, with molecular mass from 7511.3 to 7750.1 Da. They are all relatively toxic and deadly to mice and show high sequence identity with known peptides that are specific modifiers of the gating mechanisms of Na+ ion channels of type beta-toxin (β-ScTx). They were named Cv1 to Cv5 and used to test their recognition by single-chain variable fragments (scFv) of antibodies, using surface plasmon resonance. Three different scFvs generated in our laboratory (10FG2, HV, LR) were tested for recognizing the various new peptides described here, paving the way for the development of a novel type of scorpion antivenom.

Virtual entertainment robot based on artificial intelligence image capture system for sports and fitness posture recognition

Currently, artificial intelligence and virtual technology are widely used in motion monitoring. Virtual entertainment robots can provide adaptive and personalized fitness services for different user groups, allowing users to experience the exercise process in games. This article studies the virtual entertainment robot based on artificial intelligence image capture system for sports and fitness posture recognition. Firstly, this article explores deep learning methods for motion recognition. By constructing a generative adversarial network to obtain discrimination results, and calculating its anti-loss function. This approach can improve the efficiency of human body movement style conversion through adversarial training. Finally, through the evaluation of movement posture and action recognition, quantitative evaluation results and targeted guidance strategies can be provided to help correct incorrect movements and master correct techniques. Using motion capture systems to identify user movements during exercise not only accurately extracts user fitness movement information, but also makes it easier to use and reduces user costs. The system uses motion evaluation techniques for evaluation to help users correct incorrect fitness habits, prevent exercise losses, and exercise more safely and effectively.

Facial recognition for disaster victim identification

Mass disaster events can result in high levels of casualties that need to be identified. Whilst disaster victim identification (DVI) relies on primary identifiers of DNA, fingerprints, and dental, these require ante-mortem data that may not exist or be easily obtainable. Facial recognition technology may be able to assist. Automated facial recognition has advanced considerably and access to ante-mortem facial images are readily available. Facial recognition could therefore be used to expedite the DVI process by narrowing down leads before primary identifiers are made available. This research explores the feasibility of using automated facial recognition technology to support DVI. We evaluated the performance of a commercial-off-the-self facial recognition algorithm on post-mortem images (representing images taken after a mass disaster) against ante-mortem images (representing a database that may exist within agencies who hold face databases for identity documents (such as passports or driver's licenses). We explored facial recognition performance for different operational scenarios, with different levels of face image quality, and by cause of death. Our research is the largest facial recognition evaluation of post-mortem and ante-mortem images to date. We demonstrated that facial recognition technology would be valuable for DVI and that the performance varies by image quality and cause of death. We provide recommendations for future research.

Enhancing ANPR accuracy for staff car verification using convolutional neural networks and RegEX correction

This research paper presents the development and evaluation of an Automatic Number Plate Recognition (ANPR) system using Convolutional Neural Networks (CNN) with Regex correction. The aim is to enhance the accuracy and effectiveness of car verification and security processes at First Technical University, Ibadan. The ANPR system was implemented both without Regex correction and with Regex correction. The evaluation results demonstrate significant improvements in the system's performance when CNN with Regex correction is employed. The CNN-based ANPR system achieves a precision of 1.00, recall of 0.90, and F1-score of 0.95 in accurately identifying number plates. These scores indicate increased accuracy and reduce false positives compared to the system without Regex correction. The integration of CNN and Regex correction effectively handles variations and errors in the number plate data, leading to a reliable and efficient car verification process. Future work can focus on further refining the CNN model and optimizing the Regex correction algorithms to enhance the system's accuracy and robustness. The developed ANPR system, utilizing CNN with Regex correction, shows great potential for enhancing car verification and security in various domains, including law enforcement, parking management, and traffic monitoring

P.135 Automated awake brain mapping with eloquentaid: a novel tool for low-resource settings

Background: Intraoperative testing for awake craniotomies requires a multidisciplinary team which may not be available in low-resource settings. We explored the creation of an AI tool for automated testing. Methods: We developed a NodeJS application, EloquentAid (https://www.eloquentaid.com/), for language testing automation. The workflow was as follows: users select an image-based naming task and verbally identify the image in English. Then, the application transcribes the response using OpenAI’s Whisper transcription service. Finally, the application evaluates response correctness. Feedback is provided through auditory and color signals. To assess its reliability, we tested the EloquentAid versus a human rater using a 57-item test based on the Boston Naming Test. Participants were neurosurgery and neurology residents from the Philippines. Qualitative surveys were obtained post-test. Results: A total of 798 observations were recorded (N=14). Human-application agreement was 60.52%. Cohen’s kappa was 0.31 (fair agreement). There were no false positive identifications by EloquentAid. Noun-type was felt to affect human error (i.e. “knocker,” “yolk,” “trellis”). Accent and pronunciation were felt to affect EloquentAid errors. Conclusions: EloquentAid is a promising tool to facilitate intraoperative testing and brain mapping using AI for speech recognition and response evaluation. Preliminary data shows fair human-app agreements. Improvements in test items and pronunciation recognition may be made.

Use of transcranial magnetic stimulation (TMS) for studying cognitive control in depressed patients: A systematic review.

Major depressive disorder (MDD) is a debilitating mental disorder and the leading cause of disease burden. Major depressive disorder is associated with emotional impairment and cognitive deficit. Cognitive control, which is the ability to use perceptions, knowledge, and information about goals and motivations to shape the selection of goal-directed actions or thoughts, is a primary function of the prefrontal cortex (PFC). Psychotropic medications are one of the main treatments for MDD, but they are not effective for all patients. An alternative treatment is transcranial magnetic stimulation (TMS). Previous studies have provided mixed results on the cognitive-enhancing effects of TMS treatment in patients with MDD. Some studies have found significant improvement, while others have not. There is a lack of understanding of the specific effects of different TMS protocols and stimulation parameters on cognitive control in MDD. Thus, this review aims to synthesize the effectiveness of the TMS methods and a qualitative assessment of their potential benefits in improving cognitive functioning in patients with MDD. We reviewed 21 studies in which participants underwent a treatment of any transcranial magnetic stimulation protocol, such as repetitive TMS or theta-burst stimulation. One of the primary outcome measures was any change in the cognitive control process. Overall, the findings indicate that transcranial magnetic stimulation (TMS) may enhance cognitive function in patients with MDD. Most of the reviewed studies supported the notion of cognitive improvement following TMS treatment. Notably, improvements were predominantly observed in inhibition, attention, set shifting/flexibility, and memory domains. However, fewer significant improvements were detected in evaluations of visuospatial function and recognition, executive function, phonemic fluency, and speed of information processing. This review found evidence supporting the use of TMS as a treatment for cognitive deficits in patients with MDD. The results are promising, but further research is needed to clarify the specific TMS protocol and stimulation locations that are most effective.

The efficiency evaluation of image recognition and image segmentation methods for technical vision systems of small uavs

The efficiency evaluation of image recognition and image segmentation methods for technical vision systems of small uavs

Research on Oral English Learning System Integrating AI Speech Data Recognition and Speech Quality Evaluation Algorithm

The application of AI speech data recognition (SDR) and speech quality assessment algorithms in spoken English learning systems can help to realize the intelligence and automation of the process related to spoken English learning. To better assist the people concerned with the learning of spoken English, it is necessary to integrate AI speech data recognition technology in the process of learning spoken English to bring learners a learning environment and learning conditions that are not bound by time and space. As an important way to realize the natural communication of information between machines and people, AI speech recognition technology has significant application advantages and application values in eliminating the influence of the native language of English speaking learners and innovating the learning mode in the local area. In addition, the assessment of the reliability of spoken English language learning can be carried out in several dimensions. However, it is still difficult to unify the criteria of many sizes, bringing new application scenarios for AI SDR. Based on this, this paper first analyzes the theoretical basis of AI SDR. Then it investigates the speech data recognition method of the fused AI English-speaking learning mechanism and the process of fused AI English-speaking speech quality assessment. Finally, it designs and verifies the functions of the spoken English learning mechanism incorporating AI speech data identification and quality assessment.