Higher thermal plasticity in flowering phenology increases flowering output.

Ongoing climate change poses an increasing threat to biodiversity. To avoid decline or extinction, species need to either adjust or adapt to new environmental conditions or track their climatic niches across space. In sessile organisms such as plants, phenotypic plasticity can help maintain fitness in variable and even novel environmental conditions and is therefore likely to play an important role in allowing them to survive climate change, particularly in the short term. Understanding a species' response to rising temperature is crucial for planning well-targeted and cost-effective conservation measures. We sampled seeds of three Hypericum species (H. maculatum, H. montanum, and H. perforatum), from a total of 23 populations originating from different parts of their native distribution areas in Europe. We grew them under four different temperature regimes in a greenhouse to simulate current and predicted future climatic conditions in the distribution areas. We measured flowering start, flower count, and subsequent seed weight, allowing us to study variations in the thermal plasticity of flowering phenology and its relation to fitness. Our results show that individuals flowered earlier with increasing temperature, while the degree of phenological plasticity varied among species. More specifically, the plasticity of H. maculatum varied depending on population origin, with individuals from the leading range edge being less plastic. Importantly, we show a positive relationship between higher plasticity and increased flower production, indicating adaptive phenological plasticity. The observed connection between plasticity and fitness supports the idea that plasticity may be adaptive. This study underlines the need for information on plasticity for predicting species' potential to thrive under global change and the need for studies on whether higher phenotypic plasticity is currently being selected as natural populations experience a rapidly changing climate.

Estimation of Genotype by Environmental Interaction for Litter Traits by Reaction Norm Model in Taiwan Landrace Sows.

The negative effects of heat stress on swine reproduction have been well documented and the recent global warming trend caused by climate change is leading to more days with high temperatures every year. This has caused a reduction in litter trait performance of Landrace sows in Taiwan, a country extending across tropical and subtropical oceanic zones. Therefore, this study developed a modified model to determine which stages of pregnancy, before, early, middle, and late, had the largest impacts of heat stress on litter traits. A reaction norm model (RNM) was used to identify sows with high resilience to heat stress for litter traits followed by analysis of the modified model. Data from Landrace sows were collected from two farms in Taiwan between 2008 and 2021. A total of 11,059 records were collected for total number born (TNB), number born alive (NBA), and stillborn rate (STBR). The results showed that the heritabilities of TNB, NBA, and STBR were 0.170, 0.115, and 0.077, respectively. These results were similar between the conventional model and the modified model. In the modified model, the before and early stages of sow pregnancy were the significant periods for TNB and NBA (p<0.05), while the early and middle stages were significant for STBR (p<0.05). According to the RNM results, the heritability estimates for TNB, NBA, and STBR were 0.23-0.11, 0.18-0.08, and 0.10-0.04, respectively, showing a decrease from low temperature-humidity index (THI) to high THI. The minimum genetic correlations between the highest and the lowest THI for TNB, NBA, and STBR were 0.85, 0.64, and 0.80, respectively. The results of the RNM for breeding value showed re-ranking across THI values. In conclusion, similar results were obtained for heritability when the model was modified for heat stress estimation. Yet re-ranking of breeding values across THI could help farmers to select not only for improved litter trait performance but also for heat stress resilience of Landrace sows in Taiwan.

Hematological and neurological impact studies on the exposure to naturally occurring radioactive materials.

Naturally Occurring Radioactive Materials (NORM) contribute to everyone's natural background radiation dose. The technologically advanced activities of the gas and oil sectors produce considerable amounts of radioactive materials as industrial by-products or waste products. The goal of the current study is to estimate the danger of long-term liability to Technologically Enhanced Naturally Occurring Radioactive Materials (TE-NORM) on blood indices, neurotransmitters, oxidative stress markers, and ß-amyloid in the cerebral cortex of rats' brains. Twenty adult male albino rats were divided into two equal groups (n = 10): control and irradiated. Irradiated rats were exposed to a total dose of 0.016 Gy of TE-NORM as a whole-body chronic exposure over a period of two months. It should be ''The results showed no significant changes in RBC count, Hb concentration, hematocrit percentage (HCT%), and Mean Corpuscular Hemoglobin Concentration (MCHC). However, there was a significant increase in the Mean Corpuscular Volume of RBCs (MCV) and a significant decrease in cell distribution width (RDW%) compared to the control. Alteration in neurotransmitters is noticeable by a significant increase in glutamic acid and significant decreases in serotonin and dopamine. Increased lipid peroxidation, decreased glutathione content, superoxide dismutase, catalase, and glutathione peroxidase activities indicating oxidative stress were accompanied by increased ß-amyloid in the cerebral cortex of rats' brains. The findings of the present study showed that chronic radiation liability has some harmful effects, that may predict the risks of future health problems in occupational radiation exposure in the oil industries. Therefore, the control of exposure and application of sample dosimetry is recommended for health and safety.

Predicting Food Waste Avoidance: Analysis of an Extended Model of the Theory of Planned Behavior and of Relevant Beliefs.

This research adopted the Theory of Planned Behavior (TPB) to predict intention and behavior to avoid food waste. In a pilot study, behavioral, normative, and control beliefs were identified. In the main study, a TPB model extended with descriptive and moral norms was assessed using a two-wave design and applying SEM. The associations between beliefs and TPB constructs were analyzed by MIMIC models. Attitude, descriptive and moral norms, and perceived behavioral control were associated with intention to avoid food waste, which predicted behavior. Considering the most important beliefs in forming intentions has important implications for designing food waste prevention interventions.

The potential of incorporating norm-critical design objects as a pedagogical tool in sociology courses.

Previous research has raised challenges in teaching gender theory in sociology courses. While many students appreciate such theories, some students resist sociological approaches to gender, sexualities, and social inequalities. There is a growing body of research that has recognized and explored pedagogical tools aiming to help students engage with sociological insights and concepts related to gender. However, more studies and pedagogical frameworks are needed to guide higher education teachers. Consequently, this perspective article aims to introduce and present how norm-critical design objects can be used as a pedagogical tool to enhance student learning and engagement. The article demonstrates how such objects have been incorporated into sociology courses and provides a springboard for reflective, thorough, and problematizing approaches to gender issues in sociology. Further, the article encourages a broader sociological discussion about the potential of using norm-critical design objects in sociology courses.

Assessing students with dyslexia and other reading difficulties through multiple diagnostic assessments.

This article aims to assist practitioners in understanding dyslexia and other reading difficulties and assessing students' learning needs. We describe the essential components of language and literacy, universal screening, diagnostic assessments, curriculum-based measurement and eligibility determination. We then introduce four diagnostic assessments as examples, including norm-referenced assessments (i.e. the Comprehensive Test of Phonological Processing second edition and the Woodcock-Johnson IV Tests of Achievement) and criterion-referenced assessments (i.e. the Gallistel-Ellis Test of Coding Skills and the Dynamic Indicators of Basic Early Literacy Skills). Finally, We use a makeup case as a concrete example to illustrate how multiple diagnostic assessments are recorded and how the results can be used to inform intervention and eligibility for special education services.

Introgression affects Salmo trutta juvenile life-history traits generations after stocking with non-native strains.

Introgression of non-native conspecifics changes the genetic composition of wild populations, potentially leading to loss of local adaptations and fitness declines. However, long-term data from wild populations are still relatively few. Here, we studied the effects of introgression in a Danish brown trout (Salmo trutta, L.) population, subjected to intensive stocking with domesticated hatchery fish of non-native origin. We used wild-caught genetically wild and admixed trout as well as fish from the partly domesticated hatchery strain used for stocking the river up until ~15 years prior to this study, to produce 22 families varying in hatchery/wild admixture. Following a replicated common-garden experiment conducted in fish tanks from first feeding through 23 weeks at 7, 12, and 16°C, we observed a significant positive relationship between family admixture and fish size upon termination, an effect observed through all levels of admixture. Furthermore, the admixture effect was most distinct at the higher rearing temperatures. Although the hatchery strain used for stocking had been in culture for ~7 generations, it had not been deliberately selected for increased growth. These data thus demonstrate: (i) that growth had increased in the hatchery strain even in the absence of deliberate directional selection for this trait, (ii) that the increasing effect of admixture by temperature could represent inadvertent selection for performance in the hatchery strain at higher temperatures, and most significantly, (iii) that despite undergoing up to five generations of natural selection in the admixed wild population, the genetically increased growth potential was still detectable and thus persistent. Our findings suggest that altered growth patterns and potentially their cascading effects are of importance to the severity of hatchery/wild introgression, especially under changing-climate scenarios and are of general significance to conservation practitioners seeking to evaluate long-term effects of intra-specific hybridization including under recovery.

The feasibility, acceptability, appropriateness and impact of implementing person-centered communication for prevention of female genital mutilation in antenatal care settings in Guinea, Kenya and Somalia.

BACKGROUND: There is limited evidence on how to engage health workers as advocates in preventing female genital mutilation (FGM). This study assesses the feasibility, acceptability, appropriateness and impact of a person-centered communication (PCC) approach for FGM prevention among antenatal care (ANC) providers in Guinea, Kenya and Somalia. METHODS: Between August 2020 and September 2021, a cluster randomised trial was conducted in 180 ANC clinics in three countries testing an intervention on PCC for FGM prevention. A process evaluation was embedded, comprising in-depth interviews (IDIs) with 18 ANC providers and 18 ANC clients. A qualitative thematic analysis was conducted, guided by themes identified a priori and/or that emerged from the data. RESULTS: ANC providers and clients agreed that the ANC context was a feasible, acceptable and appropriate entry point for FGM prevention counselling. ANC clients were satisfied with how FGM-related information was communicated by providers and viewed them as trusted and effective communicators. Respondents suggested training reinforcement, targeting other cadres of health workers and applying this approach at different service delivery points in health facilities and in the community to increase sustainability and impact. CONCLUSION: These findings can inform the scale up this FGM prevention approach in high prevalence countries.

Effectiveness and context dependency of social norm interventions: five field experiments on nudging pro-environmental and pro-social behavior.

Social norm interventions hold the potential to change people's behavior. Five field experiments (N = 1,163) examined the effects of a simple and easily realizable social norm nudge based on the social media format "Be like Bill." The nudge consisted of a stick figure named Toni that communicated descriptive and injunctive norms regarding pro-environmental or pro-social behaviors. Nudge conditions were compared to no-intervention control conditions. Experiment 1 (N = 179) focused on paper towel consumption in a women's restroom at a German university. The nudge condition used less paper towels than the control condition, d = 0.48. Experiment 2 (N = 183) replicated this result (d = 0.32) in a more diverse setting of a women's restroom at a German Christmas market. Experiment 3 (N = 250) examined differences in the effects of prescriptive (i.e., 'do-norm') versus proscriptive (i.e., 'do not-norm') social norms on paper towel consumption again in a university women's restroom. The effectiveness of both social norm nudge conditions was shown in comparison to the control condition (d = 0.46; d = 0.40), while the prescriptive and proscriptive social norm manipulations did not differ. Experiment 4 (N = 206) applied the nudging approach to the use of plastic lids in a coffee shop, where no effect was found. Finally, Experiment 5 (N = 345) focused on the pro-social behavior of mask wearing in a bakery toward the end of the Covid-19 pandemic restrictions in Germany. In the nudge condition, more visitors put on face masks compared to the control group, d = 0.39. Limitations and contextual factors regarding the applicability of our social norm nudge are discussed.

They approve but they don't act: promoting sustainable minority behavior with (conflicting) social norm appeals.

Background: Social norm appeals are effective in promoting sustainable majority behavior but could backfire when the target behavior is only performed by a minority of people. However, emphasizing that an increasing number of people have started engaging in the behavior or that the majority approve the behavior might prevent such negative effects. However, only a few studies have investigated the combination of descriptive minority and injunctive majority social norm appeals, with inconsistent results. Some studies of minority behavior suggest that the characteristics of recipients might determine the inconsistent results regarding the impact of minority social norm appeals and that social norm appeals could have a greater impact on individuals with weaker environment related dispositions. Method: Two two-wave studies investigated how descriptive minority appeals, injunctive majority appeals, and their combination can be used to motivate sustainable minority behavior and what role environment related dispositions play in this context. In the first part, perceived social norms, environment related dispositions, behavioral intentions, and pre-attitudes were measured. Two weeks later, respondents participated in a 3 (descriptive social norm appeal: static vs. dynamic vs. absent) × 2 (injunctive majority social norm appeal: present vs. absent) between-subjects experiment and watched an explainer video on voluntary carbon offsets that included various social norm appeals. Results: In both studies, we found that social norm appeals influenced perceived social norms. However, persuasive effects were only observed in the first study, and an injunctive majority appeal increased persuasive outcomes, but there were no differences between the descriptive conditions and no differences in their impact depending on individuals' environment related dispositions in either study. Discussion: A single exposure may be insufficient to exert persuasive effects and the change in perceived social norms may first need to be internalized. In online explainer videos, the effects of social norm appeals could be amplified by algorithm-based suggestions and when social norm appeals draw attention to norm-conforming content. However, further research is required on the long-term effects and their possible amplification via social media.

Efficient enhancement of low-rank tensor completion via thin QR decomposition.

Low-rank tensor completion (LRTC), which aims to complete missing entries from tensors with partially observed terms by utilizing the low-rank structure of tensors, has been widely used in various real-world issues. The core tensor nuclear norm minimization (CTNM) method based on Tucker decomposition is one of common LRTC methods. However, the CTNM methods based on Tucker decomposition often have a large computing cost due to the fact that the general factor matrix solving technique involves multiple singular value decompositions (SVDs) in each loop. To address this problem, this article enhances the method and proposes an effective CTNM method based on thin QR decomposition (CTNM-QR) with lower computing complexity. The proposed method extends the CTNM by introducing tensor versions of the auxiliary variables instead of matrices, while using the thin QR decomposition to solve the factor matrix rather than the SVD, which can save the computational complexity and improve the tensor completion accuracy. In addition, the CTNM-QR method's convergence and complexity are analyzed further. Numerous experiments in synthetic data, real color images, and brain MRI data at different missing rates demonstrate that the proposed method not only outperforms in terms of completion accuracy and visualization, but also conducts more efficiently than most state-of-the-art LRTC methods.

Genotype-by-gestational thermal environment interaction and its impact on the future performance of tropical composite beef cattle offspring.

With global warming, there are growing challenges for raising taurine and composite beef cattle populations in tropical regions, including elevated temperatures, limited forage availability, parasite infestation, and infectious diseases. These environmental factors can trigger specific physiological responses in the developing fetus, which may have long-term implications on its performance. Therefore, the main objective of this study was to assess the influence of naturally-induced thermal stress during the gestation period on the subsequent performance of tropical composite beef cattle progeny. Furthermore, we aimed to investigate the impact of genotype-by-gestational thermal environment interaction (G×Eg) on traits under selection pressure in the breeding population. A total of 157,414 animals from 58 farms located in various Brazilian states were recorded for birth weight (BW), pre-weaning weight gain (PWG), yearling weight (YW), hip height (HH), scrotal circumference (SC), and days to first calving (DFC). We first applied a linear regression model to the BW data, which revealed that the last 40 days of gestation were suitable for calculating the mean temperature humidity index (THIg). Subsequent regression analyses revealed that for every 10-unit increase in THIg, detrimental effects of approximately 1.13% to 16.34% are expected for all traits evaluated. Genetic parameters were estimated through a reaction norm model using THIg as the environmental descriptor. The posterior means of heritability estimates (standard deviation) were 0.35 (0.07), 0.25 (0.03), 0.31 (0.03), 0.37 (0.01), 0.29 (0.07), and 0.20 (0.09) for the direct effect of BW, PWG, YW, HH, SC, and DFC, respectively. These estimates varied along the range of THIg values, suggesting a variable response to selection depending on the thermal environment during gestation. Genetic correlation estimates between more divergent THIg values were low or negative for YW, PWG, and DFC, indicating that the best-performing individuals at low THIg values may not perform as well at high THIg values and vice versa. Overall, thermal stress during gestation impacts the future performance of beef cattle offspring. Our results indicate the need for developing effective breeding strategies that take into account G×Eg effects and the re-ranking of breeding animals along the THIg scale, particularly for traits such as DFC that are highly sensitive to thermal stress.

How ingroup norms of multiculturalism (and tolerance) affect intergroup solidarity: The role of ideology.

Multiculturalism and tolerance, as two sets of normative beliefs about how to deal with intergroup diversity, have been recognized as effective at reducing outgroup negativity among majority group members. However, whether majority group members' normative beliefs regarding them might motivate their solidarity-based collective actions and how their political ideology might qualify this influence remained unclear. To answer these questions, we conducted two pre-registered experimental studies (N = 626), both zooming in on the multiculturalism issues in the context of the relationships between native Dutch citizens and citizens with a Moroccan background within Dutch university campuses (Study 1) and broader Dutch society (Study 2). In both studies, we found an ingroup norm of tolerance (vs. control) undermined majority group members' engagement in collective actions in support of ethnic minorities. Additionally, ideological leftists were more sensitive to norms than rightists: Study 1 showed a facilitative effect of the multiculturalism norm (vs. control) on solidarity-based collective action intentions particularly among leftists, whilst Study 2 revealed a dampening effect of the tolerance norm (vs. control) on these intentions particularly among leftists.

Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures.

This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).

A Novel Fast Iterative STAP Method with a Coprime Sampling Structure.

In space-time adaptive processing (STAP), the coprime sampling structure can obtain better clutter suppression capabilities at a lower hardware cost than the uniform linear sampling structure. However, in practical applications, the performance of the algorithm is often limited by the number of training samples. To solve this problem, this paper proposes a fast iterative coprime STAP algorithm based on truncated kernel norm minimization (TKNM). This method establishes a virtual clutter covariance matrix (CCM), introduces truncated kernel norm regularization technology to ensure the low rank of the CCM, and transforms the non-convex problem into a convex optimization problem. Finally, a fast iterative solution method based on the alternating direction method is presented. The effectiveness and accuracy of the proposed algorithm are verified through simulation experiments.

Distribution of natural radioactivity in different geological formations and their environmental risk assessment in Malaysia.

Labuan, Miri, Kundasang and Raub regions of Malaysia have very different geological formations and settings that could result in different levels of natural radioactivity. Hence, this study determines the influence of different geological formations on radioactivity in these locations using field measurements, petrology and geochemistry. A total of 141 gamma dose rates and 227 beta flux measurements were collected using Polimaster survey meters (PM1405) in these four regions. The gamma dose rate values range from 0.37 to 0.05 µSv/h with a mean value of 0.11 µSv/h. Beta flux values range from 3.46 to 0.12 CPS with a mean value of 0.57 CPS. Mineralogy and elemental composition of the different rock types were analysed using thin-section petrography, XRD, ICP and pXRF methods. Felsic igneous rocks such as syenite and granite have higher natural radioactivity and contain more radionuclide-bearing minerals such as apatite, zircon, allanite, K-feldspar, titanite, muscovite and biotite. Metamorphic rocks have the second highest natural radioactivity and contain fewer radioactive minerals. The natural radioactivity of sedimentary rocks mostly depends on their clay content. The gamma dose rate maps show that igneous and metamorphic regions around Raub have higher radioactivity compared to the sedimentary-dominated regions around Miri and Labuan. Annual effective dose (AED) and excess lifetime cancer risk (ELCR) were calculated to evaluate the potential health risk for inhabitants of these regions. Labuan and Miri are considered to be safe zones with respect to natural radioactivity as the results show little to no risk for the public, compared with the Raub region, which is medium to high risk.

Distinguishing fast change in social norms and slow change in personal norms in cooperative decision-making.

Psychological research on norms has shown that norms are highly relevant for individuals' decision-making. Yet, there is so far little understanding of how norms change over time. Knowledge about how norms change may help better understanding their potential for as well as limitations in guiding decision-making and changing behavior. The present work investigated change in individuals' cooperation norms. As an indicator of different underlying processes of norm change, the temporal dynamics of different types of norms were examined. It was assumed that participants' social norms are adapted quickly whenever the social situation changes, while personal norms change more slowly and gradually, abstracting part of the situational learning in interaction with one's personality. In an experimental study, participants played a repeated prisoner's dilemma game with artificial co-players representing a predominantly cooperative or uncooperative social setting, depending on the experimental condition. The condition was expected to affect slow learning of personal norms. Additionally, the cooperativeness of the social setting was varied repeatedly within conditions, expected to result in fast changes in social norms. Participants' personal and social norms were assessed throughout the game. As predicted, the temporal dynamics differed between norms with social norms changing quickly and personal norms more slowly. Personal norms strongly predicted behavioral decision-making and were predicted by situational and personality factors. Potential qualitative differences of the underlying norm change processes are discussed.

Spectral norm and energy of a digraph with respect to a VDB topological index.

The set of singular values of a digraph with respect to a vertex-degree based topological index is the set of all singular values of its general adjacency matrix. The spectral norm is the largest singular value and the energy the sum of the singular values. In this paper we characterize the digraphs which have exactly one singular value different from zero and the digraphs for which all singular values are equal. As a consequence, we deduce sharp upper and lower bounds for the spectral norm and energy of digraphs. In addition to being a natural generalization, proving the results in the general setting of digraphs allows us to deduce new results on graph energy.

EMCMDA: predicting miRNA-disease associations via efficient matrix completion.

Abundant researches have consistently illustrated the crucial role of microRNAs (miRNAs) in a wide array of essential biological processes. Furthermore, miRNAs have been validated as promising therapeutic targets for addressing complex diseases. Given the costly and time-consuming nature of traditional biological experimental validation methods, it is imperative to develop computational methods. In the work, we developed a novel approach named efficient matrix completion (EMCMDA) for predicting miRNA-disease associations. First, we calculated the similarities across multiple sources for miRNA/disease pairs and combined this information to create a holistic miRNA/disease similarity measure. Second, we utilized this biological information to create a heterogeneous network and established a target matrix derived from this network. Lastly, we framed the miRNA-disease association prediction issue as a low-rank matrix-complete issue that was addressed via minimizing matrix truncated schatten p-norm. Notably, we improved the conventional singular value contraction algorithm through using a weighted singular value contraction technique. This technique dynamically adjusts the degree of contraction based on the significance of each singular value, ensuring that the physical meaning of these singular values is fully considered. We evaluated the performance of EMCMDA by applying two distinct cross-validation experiments on two diverse databases, and the outcomes were statistically significant. In addition, we executed comprehensive case studies on two prevalent human diseases, namely lung cancer and breast cancer. Following prediction and multiple validations, it was evident that EMCMDA proficiently forecasts previously undisclosed disease-related miRNAs. These results underscore the robustness and efficacy of EMCMDA in miRNA-disease association prediction.

Revolutionizing breast cancer Ki-67 diagnosis: ultrasound radiomics and fully connected neural networks (FCNN) combination method.

PURPOSE: This study aims to assess the diagnostic value of ultrasound habitat sub-region radiomics feature parameters using a fully connected neural networks (FCNN) combination method L2,1-norm in relation to breast cancer Ki-67 status. METHODS: Ultrasound images from 528 cases of female breast cancer at the Affiliated Hospital of Xiangnan University and 232 cases of female breast cancer at the Affiliated Rehabilitation Hospital of Xiangnan University were selected for this study. We utilized deep learning methods to automatically outline the gross tumor volume and perform habitat clustering. Subsequently, habitat sub-regions were extracted to identify radiomics features and underwent feature engineering using the L1,2-norm. A prediction model for the Ki-67 status of breast cancer patients was then developed using a FCNN. The model's performance was evaluated using accuracy, area under the curve (AUC), specificity (Spe), positive predictive value (PPV), negative predictive value (NPV), Recall, and F1. In addition, calibration curves and clinical decision curves were plotted for the test set to visually assess the predictive accuracy and clinical benefit of the models. RESULT: Based on the feature engineering using the L1,2-norm, a total of 9 core features were identified. The predictive model, constructed by the FCNN model based on these 9 features, achieved the following scores: ACC 0.856, AUC 0.915, Spe 0.843, PPV 0.920, NPV 0.747, Recall 0.974, and F1 0.890. Furthermore, calibration curves and clinical decision curves of the validation set demonstrated a high level of confidence in the model's performance and its clinical benefit. CONCLUSION: Habitat clustering of ultrasound images of breast cancer is effectively supported by the combined implementation of the L1,2-norm and FCNN algorithms, allowing for the accurate classification of the Ki-67 status in breast cancer patients.