Semantic Features Research Articles

Automating Abercrombie: Machine‐learning trademark distinctiveness

AbstractTrademark law protects marks to enable firms to signal their products' qualities to consumers. To qualify for protection, a mark must be able to identify and distinguish goods. US courts typically locate a mark on a “spectrum of distinctiveness”—known as the Abercrombie spectrum—that categorizes marks as fanciful, arbitrary, or suggestive, and thus as “inherently distinctive,” or as descriptive or generic, and thus as not inherently distinctive. This article explores whether locating trademarks on the Abercrombie spectrum can be automated using current natural‐language processing techniques. Using about 1.5 million US trademark registrations between 2012 and 2019 as well as 2.2 million related USPTO office actions, the article presents a machine‐learning model that learns semantic features of trademark applications and predicts whether a mark is inherently distinctive. Our model can predict trademark actions with 86% accuracy overall, and it can identify subsets of trademark applications where it is highly certain in its predictions of distinctiveness. Using an eXplainable AI (XAI) algorithm, we further analyze which features in trademark applications drive our model's predictions. We then explore the practical and normative implications of our approach. On a practical level, we outline a decision‐support system that could, as a “robot trademark clerk,” assist trademark experts in their determination of a trademark's distinctiveness. Such a system could also help trademark experts understand which features of a trademark application contribute the most toward a trademark's distinctiveness. On a theoretical level, we discuss the normative limits of the Abercrombie spectrum and propose to move beyond Abercrombie for trademarks whose distinctiveness is uncertain. We discuss how machine‐learning projects in the law not only inform us about the aspects of the legal system that may be automated in the future, but also force us to tackle normative tradeoffs that may be invisible otherwise.

Classification of Dog Breeds Using Convolutional Neural Network Models and Support Vector Machine

When classifying breeds of dogs, the accuracy of classification significantly affects breed identification and dog research. Using images to classify dog breeds can improve classification efficiency; however, it is increasingly challenging due to the diversities and similarities among dog breeds. Traditional image classification methods primarily rely on extracting simple geometric features, while current convolutional neural networks (CNNs) are capable of learning high-level semantic features. However, the diversity of dog breeds continues to pose a challenge to classification accuracy. To address this, we developed a model that integrates multiple CNNs with a machine learning method, significantly improving the accuracy of dog images classification. We used the Stanford Dog Dataset, combined image features from four CNN models, filtered the features using principal component analysis (PCA) and gray wolf optimization algorithm (GWO), and then classified the features with support vector machine (SVM). The classification accuracy rate reached 95.24% for 120 breeds and 99.34% for 76 selected breeds, respectively, demonstrating a significant improvement over existing methods using the same Stanford Dog Dataset. It is expected that our proposed method will further serve as a fundamental framework for the accurate classification of a wider range of species.

Machine learning prediction of brain metastasis invasion pattern on brain MRI scans

Abstract Background Brain metastasis invasion pattern (BMIP) is an emerging biomarker associated with recurrence-free and overall survival in patients, and differential response to therapy in preclinical models. Currently, BMIP can only be determined from the histopathological examination of surgical specimens, precluding its use as a biomarker prior to therapy initiation. The aim of this study was to investigate the potential of machine learning (ML) approaches to develop a non-invasive magnetic resonance imaging (MRI)-based biomarker for BMIP determination. Methods From an initial cohort of 329 patients, a subset of 132 patients met inclusion criteria for this retrospective study. We evaluated the ability of an expert neuroradiologist to reliably predict BMIP. Thereafter, the dataset was randomly divided into training/validation (80% of cases) and test subsets (20% of cases). Ground truth for BMIP was histopathologic evaluation of resected specimens. Following MRI sequence co-registration, advanced feature extraction techniques deriving hand-crafted radiomic features with traditional ML classifiers and convolution-based deep learning (CDL) models were trained and evaluated. Different ML approaches were used individually or using ensembling techniques to determine the model with the best performance for BMIP prediction. Results Expert evaluation of brain MRI scans could not reliably predict BMIP, with an accuracy of 44-59% depending on the semantic feature used. Among the different ML and CDL models evaluated, the best performing model achieved an accuracy of 85% and an F1-score of 90%. Conclusion ML approaches can effectively predict BMIP, representing a non-invasive MRI-based approach to guide management of patients with brain metastases.

An explainable spatial interpolation method considering spatial stratified heterogeneity

Spatial interpolation is essential for handling sparsity and missing spatial data. Current machine learning-based spatial interpolation methods are subject to the statistical constraints of spatial stratified heterogeneity (SSH), normally involving separate modeling of each stratum and simple weighted averaging to integrate intra-stratum and inter-strata features. However, these models overlook the different contributions of inter-strata features to different locations within a stratum (heterogeneous inter-strata associations, HIA) and the explanation of spatial effects on the interpolation process, leading to suboptimal and unreliable interpolation outcomes. This article proposes a novel explainable spatial interpolation method considering SSH (X-SSHM). Spatial and environmental features are utilized to describe intra-stratum and inter-strata information, which are fed into random forest-based learners to achieve high-level semantic feature mapping. Geographically weighted regression is employed to integrate intra-stratum and inter-strata features to achieve a unified expression of SSH and HIA, obtaining the final interpolation result. Geographically weighted Shapley (GSHAP) is proposed to decompose the marginal contributions of intra-stratum and inter-strata features. Model performance is evaluated on simulated and soil organic matter datasets. X-SSHM outperformed five baselines regarding interpolation accuracy. Moreover, statistical methods validated X-SSHM’s ability to elucidate the mechanisms by which SSH, spatial autocorrelation and HIA affect the model interpolation process.

Radiomics-guided generative adversarial network for automatic primary target volume segmentation for nasopharyngeal carcinoma using computed tomography images.

Automatic primary gross tumor volume (GTVp) segmentation for nasopharyngeal carcinoma (NPC) is a quite challenging task because of the existence of similar visual characteristics between tumors and their surroundings, especially on computed tomography (CT) images with severe low contrast resolution. Therefore, most recently proposed methods based on radiomics or deep learning (DL) is difficult to achieve good results on CT datasets. A peritumoral radiomics-guided generative adversarial network (PRG-GAN) was proposed to address this challenge. A total of 157 NPC patients with CT images was collected and divided into training, validation, and testing cohorts of 108, 9, and 30 patients, respectively. The proposed model was based on a standard GAN consisting of a generator network and a discriminator network. Morphological dilation on the initial segmentation results from GAN was first conducted to delineate annular peritumoral region, in which radiomics features were extracted as priori guide knowledge. Then, radiomics features were fused with semantic features by the discriminator's fully connected layer to achieve the voxel-level classification and segmentation. The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD) were used to evaluate the segmentation performance using a paired samples t-test with Bonferroni correction and Cohen's d (d) effect sizes. A two-sided p-value of less than 0.05 was considered statistically significant. The model-generated predictions had a high overlap ratio with the ground truth. The average DSC, HD95, and ASSD were significantly improved from 0.80±0.12, 4.65±4.71mm, and 1.35±1.15mm of GAN to 0.85±0.18 (p=0.001, d=0.71), 4.15±7.56mm (p=0.002, d=0.67), and 1.11±1.65mm (p<0.001, d=0.46) of PRG-GAN, respectively. Integrating radiomics features into GAN is promising to solve unclear border limitations and increase the delineation accuracy of GTVp for patients with NPC.

Semantic and distributional patterns of Spanish negation with nouns and adjectives: A Lexical-Realizational Functional Grammar approach

This study examines the semantic and distributional characteristics of the Spanish negation no when it occurs before nouns and adjectives, specifically, whether these instances diverge from sentential negation, but also from negation via prefixes such as des- ‘dis-’ or in- ‘in-, un-’. Using data from the Spanish Web 2011 corpus, it is shown that the use of no before adjectives aligns with other forms of constituent negation, often resulting in a contradictory interpretation, that is similar to that of sentential negation. However, the interpretation of no preceding nouns exhibits a broader range of interpretations, depending on whether the noun refers to an eventuality, quality, or entity. In such instances, no shows parallels to negative prefixes, frequently indicating privation rather than contradiction. Consequently, no can be analyzed as a building block of phrases, expressing syntactic negation, behaving similarly to other adverbs, as well as a building block of words, expressing lexical negation, resembling Spanish prefix-like elements like cuasi ‘almost’ or ex ‘ex-’. The analysis is couched within the framework of Lexical-Realizational Functional Grammar (LRFG), integrating aspects of Lexical Functional Grammar and Distributed Morphology. This approach does not treat morphology and syntax as separate modules, thus allowing us to account for the variable distribution and interpretation of no by means of a single representation in vocabulary structure, drawing on constituent structure representations which are needed on independent grounds for adverbs and for prefix-like elements.

Spectral CT-based nomogram for preoperative prediction of Lauren classification in locally advanced gastric cancer: a prospective study.

To develop a nomogram based on clinical features and spectral quantitative parameters to preoperatively predict the Lauren classification for locally advanced gastric cancer (LAGC). Patients diagnosed with LAGC by postoperative pathology who underwent abdominal triple-phase enhanced spectral computed tomography (CT) were prospectively enrolled in this study between June 2023 and December 2023. All the patients were categorized into intestinal- and diffuse-type groups according to the Lauren classification. Traditional characteristics, including demographic information, serum tumor markers, gastroscopic pathology, and image semantic features, were collected. Spectral quantitative parameters, including iodine concentration (IC), effective atomic number (Zeff), and slope of the energy spectrum curve from 40 keV to 70 keV (λ), were measured three times for each patient by two blinded radiologists in arterial/venous/delayed phases (AP/VP/DP). Differences in traditional features and spectral quantitative parameters between the two groups were compared using univariable analysis. Independent predictors of the Lauren classification of LAGC were screened using multivariable logistic regression analysis. Receiver operating characteristic (ROC) curve analysis was used to assess the discriminating capability. Ultimately, the nomogram, including clinical features and spectral CT quantitative parameters, was developed. Gender, nIC in AP (APnIC), and λ in DP (λd) were independent predictors for Lauren classification. The nomogram based on these indicators produced the best performance with an area under the curve of 0.841 (95% confidence interval: 0.749-0.932), specificity of 85.3%, accuracy of 76.4%, and sensitivity of 68.4%. The nomogram based on clinical features and spectral CT quantitative parameters exhibits great potential in the preoperative and non-invasive assessment of Lauren classification for LAGC. Question Can the proposed nomogram, integrating clinical features and spectral quantitative parameters, preoperatively predict the Lauren classification in locally advanced gastric cancer (LAGC)? Findings The nomogram, based on gender, arterial phase normalized iodine concentration, and slope of the energy spectrum curve in the delayed phase showed satisfactory predictive ability. Clinical relevance The established nomogram could contribute to guiding individualized treatment strategies and risk stratification in patients by predicting the Lauren classification for LAGC before surgery.

Design of judicial public opinion supervision and intelligent decision-making model based on Bi-LSTM

Fuzzy preference modeling in intelligent decision support systems aims to improve the efficiency and accuracy of decision-making processes by incorporating fuzzy logic and preference modeling techniques. While network public opinion (NPO) has the potential to drive judicial reform and progress, it also poses challenges to the independence of the judiciary due to the negative impact of malicious public opinion. To tackle this issue within the context of intelligent decision support systems, this study provides an insightful overview of current NPO monitoring technologies. Recognizing the complexities associated with handling large-scale NPO data and mitigating significant interference, a novel judicial domain NPO monitoring model is proposed, which centers around semantic feature analysis. This model takes into account time series characteristics, binary semantic fitting, and public sentiment intensity. Notably, it leverages a bidirectional long short-term memory (Bi-LSTM) network (S-Bi-LSTM) to construct a judicial domain semantic similarity calculation model. The semantic similarity values between sentences are obtained through the utilization of a fully connected layer. Empirical evaluations demonstrate the remarkable performance of the proposed model, achieving an accuracy rate of 85.9% and an F1 value of 87.1 on the test set, surpassing existing sentence semantic similarity models. Ultimately, the proposed model significantly enhances the monitoring capabilities of judicial authorities over NPO, thereby alleviating the burden on public relations faced by judicial institutions and fostering a more equitable execution of judicial power.

Unveiling user identity across social media: a novel unsupervised gradient semantic model for accurate and efficient user alignment

AbstractThe field of social network analysis has identified User Alignment (UA) as a crucial area of investigation. The objective of UA is to identify and connect user accounts across diverse social networks, even when there are no explicit interconnections. UA plays a pivotal role in synthesising coherent user profiles and delving into the intricacies of user behaviour across platforms. However, traditional approaches have encountered limitations. Singular embedding techniques have been found to fall short in fully capturing the semantic essence of user profile attributes. Furthermore, classification-based embedding methods lack definitive criteria for categorisation, thereby constraining both the efficacy and applicability of these models. This paper presents a novel unsupervised Gradient Semantic Model for User Alignment (GSMUA) for the purpose of identifying common user identities across social networks. GSMUA categorises user profile information into weak, sub, and strong gradients based on the semantic intensity of attributes. Different gradient semantic levels direct attention to literal features, semantic features, or a combination of both during feature extraction, thereby achieving a full semantic representation of user attributes. In the case of strongly semantic long texts, GSMUA employs Named Entity Recognition (ENR) technology in order to enhance the inefficient handling of such texts. Furthermore, GSMUA compensates for missing user profile attributes by utilising profile information from user neighbours, thereby reducing the negative impact of missing user profile attributes on model performance. Extensive experiments conducted on four pairs of real datasets demonstrate the superiority of our approach. In comparison to the most effective previously developed unsupervised methods, GSMUA demonstrates improvements in hit-precision ranging from 5.32 to 12.17%. When compared to supervised methods, the improvements range from 0.71 to 11.79%.

Efficient indoor 3D object detection in point clouds using the Kinect sensor

Abstract Only using the point clouds collected by a Kinect sensor to perform 3D object detection is a very challenging task for indoor sense understanding. In this paper, we propose a novel point clouds based 3D object detection framework named Weighted VoteNet (W-VoteNet), which systematically enhances seed points, voting points, and proposal objects to varying degree, thereby enhancing the detection accuracy of indoor scene point clouds. Firstly, a new neighborhood feature enhancement module was designed to enhance the features of the seed point, which can better utilize the neighborhood feature of the seed point. Secondly, a weighted voting module is implemented to increase the accuracy of voting, allowing more prospect seed points to participate in voting. Finally, a new semantic relation reasoning module is proposed to get the semantic relationship features of the proposal object, which can further decrease false alarm rate. The three modules we proposed all contribute to more accurate voting and more effective proposals. The experimental results on two benchmark indoor 3D object detection datasets, SUN RGB-D and ScanNet V2, demonstrate the effectiveness of our approach. The source code is available at: https://github.com/Guo-JQ/W-VoteNet.

Semantic Features of the Word Qonyr (Brown): Conceptual Analysis of Two Separate Works

It is known that the Aesopian language was used in the works of many writers to convey the parable. This article shows how and why Kazakh writers used the Aesopian language during the Soviet era. The study analyzes the contextual and symbolic meanings of the word qonyr, one of the most important concepts of Kazakh cognition. The research material was taken from O. Bokey’s novel Kajdasyn, Kaska Kulynym? (Where Are You, My Foal with a Star on His Forehead?), and a poem by Zhumeken Nazhimedenov titled “Kyran-Kiya” (“Mountain Eagle”). A conceptual research method in modern linguistics was chosen for data analysis. As a result, new implicit meanings of the word qonyr (“brown”) were revealed, such as “longing”, “sadness”, and “nobility”. The juxtaposition of these meanings with Soviet ideology is presented. The results and conclusions of the study are a kind of contribution to studies in cognitive linguistics and decolonization.

DESENet: a bilateral network with detail-enhanced semantic encoder for real-time semantic segmentation

Abstract Real-time semantic segmentation is widely used in various domains such as autonomous driving. Most real-time semantic segmentation networks adopt an encoder-decoder structure. During encoding, feature maps undergo multiple downsampling stages to enhance computational efficiency and enlarge the receptive field. However, this process may lead to the loss of detailed information, which may not be fully recovered during upsampling. Moreover, upsampling semantic features may cause blurring due to the lack of spatial detail information. To mitigate these issues, we use spatially guided cross-resolution self-attention to improve the upsampling of the semantic features by supplementing detailed information from the spatial branch. Furthermore, we incorporate an inductive bias into the cross-resolution attention mechanism to enhance its ability to learn generalized features. Additionally, we design a semantic feature extraction block, and a spatial feature extraction branch to construct a lightweight backbone. The results on Cityscapes and CamVid show that the proposed model achieves a good balance between accuracy and efficiency. Specifically, it obtains 74.2 and 71.5 mIoU on the two test datasets with 1.31M parameters, respectively. Code is available on https://github.com/clearwater753/DECENet.

Sentiment analysis of Chinese ancient poetry based on multidimensional knowledge attention

Abstract Poetry was a unique literary genre in ancient China as an important way to express sentiments. Chinese ancient poetry not only has simple words, strict meters, and rich semantic relationships, but also widely use rhetorical techniques such as simile and personification, as well as metaphorical means such as allusion and imagery, which makes it difficult to understand their implicit sentiments quickly and accurately. Therefore, this article attempts to make full use of the semantic features of Chinese ancient poetry text and the knowledge feature of related domains under the guidance of the research paradigm of digital intelligence integration and, based on which, proposed Sentiment Analysis Model of Chinese Ancient Poetry based on Multidimensional Knowledge Attention. This model extracts semantic features from Chinese ancient poetry text, meanwhile designs a multidimensional knowledge attention to extract knowledge features from the knowledge base of Chinese ancient poetry. The recognition of Chinese ancient poetry sentiment is performed by integrating the textual feature and knowledge feature. Comparison experiments on the open ancient poetry corpus verified the effectiveness of the proposed model, and the ablation experiment explored the importance of different knowledge to the sentiment analysis result of Chinese ancient poetry.

AVR (advancing video retrieval): A new framework guided by multi-level fusion of visual and semantic Features for deep learning-based concept detection

AVR (advancing video retrieval): A new framework guided by multi-level fusion of visual and semantic Features for deep learning-based concept detection

STATISTICAL INDICATORS OF THE CORRESPONDENCE OF THE LANGUAGE OF REGIONAL NEWSPAPERS IN KOSTROMA REGION TO ALL-RUSSIAN STANDARDS: A SYNTACTIC APPROACH

The paper is devoted to the analysis of complex sentences with subordinate clauses of condition, cause, goal, concession, consequence in regional newspapers of Kostroma Region in comparison with the data of similar studies conducted on the material of all-Russian periodicals. The grammar of the language, which is the backbone of the entire language system, is the most stable, standardised, which should be manifested at the syntactic level. The description of linguistic phenomena in the materials of regional periodicals in comparison with the all-Russia’s ones contributes to the forming of a general picture of the syntax of the modern Russian language. This paper shows on quantitative research data the correspondence of the syntax of regional newspapers with the language of all-Russia’s periodicals in the following aspects – the distribution of complex sentences with various types of subordinate clauses in the general system of conditionality and the peculiarities of using the means of their construction. It is shown that in the texts of regional newspapers of Kostroma Region, at the syntactic level, there are all the structural and semantic features of complex sentences with the meaning of conditionality – distribution by their types, the use of typed and non-typed means of communication, the phenomena of gradation, inversion, parcellation, phraseologisation of subordinate clauses. On the example of functioning of the most popular, semantically capacious and significant complex sentences, it is concluded that the syntactic media image of Kostroma Region reflects the general picture in modern Russian journalism, which indicates the stability of the system of complex sentences at the current stage of language development.

&lt;b&gt;Contrastive Analysis of Similes with Dog Image in English and Vietnamese and Implications&lt;/b&gt;

Studies on dog images in idiomatic languages ​​in different languages ​​always receive a lot of attention from researchers. The present study examines the similarities of 21 English-Vietnamese dog similes and tries to account for the differences based on Hofstede’s model (2001). The analysis results show that the image of the dog in each language has unique cultural characteristics due to the influence of factors such as geographical circumstances and customs. While the image of a dog appearing in English similes has both positive meaning (38%) and negative meaning (62%), Vietnamese similes record a full dominance in negative meanings (100%). Besides, the semantic symbols of similes with dog elements in Vietnamese and English have interesting similarities. Understanding the semantic characteristics of words for dogs in English and Vietnamese similes contributes to discovering new things about the life, customs, practices, culture, and thinking of British and Vietnamese people.

Within- and cross-language generalization in narrative production of bilingual persons with aphasia following Semantic Feature Analysis therapy.

Semantic Feature Analysis therapy (SFA) is a widely used approach for single-word naming treatment in monolingual and bilingual persons with aphasia (BiPWAs). There is evidence that SFA leads to naming improvements in both treated and untreated languages of BiPWAs. However, research on the generalization effects of SFA to narrative production is scarce. This study investigated the within- and cross-language generalization effects of SFA on narrative production and their relationship to naming gains in a group of L1-Russian - L2-Hebrew chronic-stage BiPWAs. The study included two groups of BiPWAs. In the experimental group, ten individuals received one or two blocks of SFA, while ten participants who did not receive therapy served as a control group. We compared the changes in narrative production between the experimental and control groups and examined whether the narrative changes in the experimental group were related to naming gains. The results indicated that SFA generalized to narrative production in the experimental group. Within-language generalization was observed following SFA in L1, while cross-language generalization was found following SFA in both L1 and L2. Although SFA has the potential to generalize to narrative production in BiPWAs, this effect did not consistently align with the therapy gains in naming. To achieve greater within- and cross-language generalization effects, we recommend providing SFA in the L1 of BiPWAs.

Internet terminology in modern German: semantics and structure

Abstract The article presents an in-depth analysis of the formation of terminology in the professional language of the Internet in German and offers predictions about its future development, in line with the evolution of this area of knowledge. Drawing from a corpus of about 8,000 terms and term combinations, the authors explore the dynamics of German Internet terminology, propose a timeline for the emergence of these terms in relation to advancements in science and technology, and identify key methods of term formation along with their semantic characteristics. The primary source of expansion in German Internet terminology comes from Anglo-American borrowings, which, during their adaptation into German, have undergone structural and semantic assimilation. The main methods of term formation within the examined terminology are compounding (with a predominance of binary structures), derivation, and abbreviation. German Internet terminology is characterized by synonymy and polysemy, reflecting the dynamic nature of network technology development. A distinctive feature of this terminology is the formal redundancy in expressing a single concept, leading to the formation of synonymous sets. The uniqueness of the semantic paradigm of these terms lies in the extralinguistic factors that influence terminological synonymy, polysemy, and the broader system of structural relations in German Internet terminology.

SIFusion: Lightweight infrared and visible image fusion based on semantic injection.

The objective of image fusion is to integrate complementary features from source images to better cater to the needs of human and machine vision. However, existing image fusion algorithms predominantly focus on enhancing the visual appeal of the fused image for human perception, often neglecting their impact on subsequent high-level visual tasks, particularly the processing of semantic information. Moreover, these fusion methods that incorporate downstream tasks tend to be overly complex and computationally intensive, which is not conducive to practical applications. To address these issues, a lightweight infrared and visible light image fusion method known as SIFusion, which is based on semantic injection, is proposed in this paper. This method employs a semantic-aware branch to extract semantic feature information, and then integrates these features into the fused features through a Semantic Injection Module (SIM) to meet the semantic requirements of high-level visual tasks. Furthermore, to simplify the complexity of the fusion network, this method introduces an Edge Convolution Module (ECB) based on structural reparameterization technology to enhance the representational capacity of the encoder and decoder. Extensive experimental comparisons demonstrate that the proposed method performs excellently in terms of visual appeal and advanced semantics, providing satisfactory fusion results for subsequent high-level visual tasks even in challenging scenarios.

A lightweight deep-learning model for parasite egg detection in microscopy images.

Intestinal parasitic infections are still a serious public health problem in developing countries, and the diagnosis of parasitic infections requires the first step of parasite/egg detection of samples. Automated detection can eliminate the dependence on professionals, but the current detection algorithms require large computational resources, which increases the lower limit of automated detection. Therefore, we have designed a lightweight deep-learning model, YAC-Net, to achieve rapid and accurate detection of parasitic eggs and reduce the cost of automation. This paper uses the ICIP 2022 Challenge dataset for experiments, and the experiments are conducted using fivefold cross-validation. The YOLOv5n model is used as the baseline model, and then two improvements are made to the baseline model based on the specificity of the egg data. First, the neck of the YOLOv5n is modified to from a feature pyramid network (FPN) to an asymptotic feature pyramid network (AFPN) structure. Different from the FPN structure, which mainly integrates semantic feature information at adjacent levels, the hierarchical and asymptotic aggregation structure of AFPN can fully fuse the spatial contextual information of egg images, and its adaptive spatial feature fusion mode can help the model select beneficial feature and ignore redundant information, thereby reducing computational complexity and improving detection performance. Second, the C3 module of the backbone of the YOLOv5n is modified to a C2f module, which can enrich gradient information, improving the feature extraction capability of the backbone. Moreover, ablation studies are designed by us to verify the effectiveness of the AFPN and C2f modules in the process of model lightweighting. The experimental results show that compared with YOLOv5n, YAC-Net improves precision by 1.1%, recall by 2.8%, the F1 score by 0.0195, and mAP_0.5 by 0.0271 and reduces the parameters by one-fifth. Compared with some state-of-the-art detection methods, YAC-Net achieves the best performance in precision, F1 score, mAP_0.5, and parameters. The precision, recall, F1 score, mAP_0.5, and parameters of our method on the test set are 97.8%, 97.7%, 0.9773, 0.9913, and 1,924,302, respectively. Compared with the baseline model, YAC-Net optimizes the model structure and simplifies the parameters while ensuring the detection performance. It helps to reduce the equipment requirements for performing automated detection and can be used to realize the automatic detection of parasite eggs under microscope images.