Cognitive NeurodynamicsPub Date : 2025-12-01Epub Date: 2025-03-22DOI: 10.1007/s11571-025-10239-9
Hongze Sun, Shifeng Mao, Wuque Cai, Yan Cui, Duo Chen, Dezhong Yao, Daqing Guo
{"title":"BISNN: bio-information-fused spiking neural networks for enhanced EEG-based emotion recognition.","authors":"Hongze Sun, Shifeng Mao, Wuque Cai, Yan Cui, Duo Chen, Dezhong Yao, Daqing Guo","doi":"10.1007/s11571-025-10239-9","DOIUrl":"10.1007/s11571-025-10239-9","url":null,"abstract":"<p><p>Spiking neural networks (SNNs), known for their rich spatio-temporal dynamics, have recently gained considerable attention in EEG-based emotion recognition. However, conventional model training approaches often fail to fully exploit the capabilities of SNNs, posing challenges for effective EEG data analysis. In this work, we propose a novel bio-information-fused SNN (BISNN) model to enhance EEG-based emotion recognition. The BISNN model incorporates biologically plausible intrinsic parameters into spiking neurons and is initialized with a structurally equivalent pre-trained ANN model. By constructing a bio-information-fused loss function, the BISNN model enables simultaneous training under dual constraints. Extensive experiments on benchmark EEG-based emotion datasets demonstrate that the BISNN model achieves competitive performance compared to state-of-the-art methods. Additionally, ablation studies investigating various components further elucidate the mechanisms underlying the model's effectiveness and evolution, aligning well with previous findings.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"52"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929665/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143699844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multi-level cognitive state classification of learners using complex brain networks and interpretable machine learning.","authors":"Xiuling He, Yue Li, Xiong Xiao, Yingting Li, Jing Fang, Ruijie Zhou","doi":"10.1007/s11571-024-10203-z","DOIUrl":"https://doi.org/10.1007/s11571-024-10203-z","url":null,"abstract":"<p><p>Identifying the cognitive state can help educators understand the evolving thought processes of learners, and it is important in promoting the development of higher-order thinking skills (HOTS). Cognitive neuroscience research identifies cognitive states by designing experimental tasks and recording electroencephalography (EEG) signals during task performance. However, most of the previous studies primarily concentrated on extracting features from individual channels in single-type tasks, ignoring the interconnection across channels. In this study, three learning activities (i.e., video watching activity, keyword extracting activity, and essay creating activity) were designed based on a revised Bloom's taxonomy and the Interactive-Constructive-Active-Passive framework and used with 31 college students. The EEG signals were recorded when they were engaged in these activities. First, whole-brain network temporal dynamics were characterized by EEG microstate sequence analysis. Such dynamic changes rely on learning activity and corresponding functional brain systems. Subsequently, phase locking value was used to construct synchrony-based functional brain networks. The network characteristics were extracted to be inputted into different machine learning classifiers: Support Vector Machine, K-Nearest Neighbour, Random Forest, and eXtreme Gradient Boosting (XGBoost). XGBoost showed superior performance in the classification of cognitive states, with an accuracy of 88.07%. Furthermore, SHapley Additive exPlanations (SHAP) was adopted to reveal the connections between different brain regions that contributed to the classification of cognitive state. SHAP analysis reveals that the connections in the frontal, temporal, and central regions are most important for the high cognitive state. Collectively, this study may provide further evidence for educators to design cognitive-guided instructional activities to enhance learners' HOTS.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"5"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11699182/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142930821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ufuoma Akpojotor, Olubusayo Oluwole, Olaniyi Oyatomi, Rajneesh Paliwal, Michael Abberton
{"title":"Research and developmental strategies to hasten the improvement of orphan crops.","authors":"Ufuoma Akpojotor, Olubusayo Oluwole, Olaniyi Oyatomi, Rajneesh Paliwal, Michael Abberton","doi":"10.1080/21645698.2024.2423987","DOIUrl":"https://doi.org/10.1080/21645698.2024.2423987","url":null,"abstract":"<p><p>To feed the world's expanding population, crop breeders need to increase agricultural productivity and expand major crops base. Orphan crops are indigenously important crops with great potential because they are climate resilient, highly nutritious, contain nutraceutical compounds, and can improve the livelihood of smallholder farmers and consumers, but they have received little or no scientific attention. This review article examines several research and developmental strategies for hastening the improvement of these crops so that they can effectively play their role in securing food and nutrition. The integration of both research and developmental approaches will open up modern opportunities for crop improvement. We summarized ways in which advanced tools in phenotyping and genotyping, using high-throughput processes, can be used to accelerate their improvement. Finally, we suggest roles the genebanks can play in improving orphan crops, as the utilization of plant genetic resources is important for the genetic improvement of a crop.</p>","PeriodicalId":54282,"journal":{"name":"Gm Crops & Food-Biotechnology in Agriculture and the Food Chain","volume":"16 1","pages":"46-71"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142883650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cognitive NeurodynamicsPub Date : 2025-12-01Epub Date: 2025-01-09DOI: 10.1007/s11571-024-10190-1
K G Shanthi, A Mary Joy Kinol, S Rukmani Devi, K Kannan
{"title":"Cognitive neurodynamic approaches to adaptive signal processing in wireless sensor networks.","authors":"K G Shanthi, A Mary Joy Kinol, S Rukmani Devi, K Kannan","doi":"10.1007/s11571-024-10190-1","DOIUrl":"10.1007/s11571-024-10190-1","url":null,"abstract":"<p><p>In recent years, Wireless Sensor Networks (WSN) have become vital because of their versatility in numerous applications. Nevertheless, the attain problems like inherent noise, and limited node computation capabilities, result in reduced sensor node lifespan as well as enhanced power consumption. To tackle such problems, this study develops a Modified-Distributed Arithmetic-Offset Binary Coding-based Adaptive Finite Impulse Response (MDA-OBC based AFIR) framework. By leveraging Modified Distributed Arithmetic (MDA) which optimizes arithmetic operations by replacing the multipliers with lookup tables (LUT) hence minimizing energy consumption as well as computational complexity. Offset Binary Coding (OBC) enhanced the efficiency of data transmission by minimizing the data representation overhead. In addition to this, the adaptive strategy is incorporated with the Adaptive Finite Impulse Response (AFIR) framework permitting the filters to dynamically adjust to varying signal characteristics, thus offering high noise suppression and low distortion rates. Comprehensive simulations and comparative analysis validate the effectiveness of the proposed MDA-OBC-based AFIR method. The proposed method attained a lower energy consumption of 1.5 J and 130 W power consumption than the traditional implementations, resulting in significant energy efficiency and data transmission in signal preprocessing and noise suppression in WSNs.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"11"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11717781/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142969905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cognitive NeurodynamicsPub Date : 2025-12-01Epub Date: 2025-01-24DOI: 10.1007/s11571-025-10220-6
Long Chen, Yihao Hu, Zhongpeng Wang, Lei Zhang, Chuxiang Jian, Shengcui Cheng, Dong Ming
{"title":"Effects of transcutaneous auricular vagus nerve stimulation (taVNS) on motor planning: a multimodal signal study.","authors":"Long Chen, Yihao Hu, Zhongpeng Wang, Lei Zhang, Chuxiang Jian, Shengcui Cheng, Dong Ming","doi":"10.1007/s11571-025-10220-6","DOIUrl":"10.1007/s11571-025-10220-6","url":null,"abstract":"<p><p>Motor planning plays a pivotal role in daily life. Transcutaneous auricular vagus nerve stimulation (taVNS) has been demonstrated to enhance decision-making efficiency, illustrating its potential use in cognitive modulation. However, current research primarily focuses on behavioral and single-modal electrophysiological signal, such as electroencephalography (EEG) and electrocardiography (ECG). To investigate the effect of taVNS on motor planning, a total of 21 subjects were recruited for this study and were divided into two groups: active group (n = 10) and sham group (n = 11). Each subject was required to be involved in a single-blind, sham-controlled, between-subject end-state comfort (ESC) experiment. The study compared behavioral indicators and electrophysiological features before and following taVNS. The results indicated a notable reduction in reaction time and an appreciable increase in the proportion of end-state comfort among the participants following taVNS, accompanied by notable alterations in motor-related cortical potential (MRCP) amplitude, low-frequency power of HRV (LF), and cortico-cardiac coherence, particularly in the parietal and occipital regions. These findings show that taVNS may impact the brain and heart, potentially enhancing their interaction, and improve participants' ability of motor planning.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"35"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11759740/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143045764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An integrated <i>in vitro</i> and <i>in silico</i> approach to assess targeted cytotoxicity against MDA-MB-231 triple-negative breast cancer cells with <i>Psidium guajava</i> peel-derived chitosan nanoparticles.","authors":"Vino Udappusamy, Rajan Thinagaran, Vijayakumar Mayakrishnan, Janani Balakarthikeyan, Priya Kannappan, Sameer Al-Ghamdi, Naif Abdurhman Alrudian, Mohammed Saad Alqahtani, Khalid Albasheer, Chandrabose Sureka, Mahmoud H El-Bidawy, Nesreen Alsanousi, Sahar Gamil, Thiyagarajan Ramesh","doi":"10.1080/21691401.2025.2462333","DOIUrl":"10.1080/21691401.2025.2462333","url":null,"abstract":"<p><p>Triple-negative breast cancer (TNBC) is a significant global health issue, with high mortality rates. The chemotherapeutic drugs currently used for TNBC have significant side effects, impacting both normal and cancer cells. In this study, we investigated a potential use of fruit peel extract of <i>Psidium guajava</i> (PGP) encapsulated with chitosan nanoparticles (CSNPs) to combat TNBC. The synthesized PGP-CSNPs were characterized using UV-vis spectroscopy, Fourier transform infra-red (FTIR) spectroscopy, TEM and GC-MS. The maximum loading capacity and encapsulation efficacy of PGP-CSNPs were found to be 72.5 ± 0.49% and 92.9 ± 0.10%, respectively. Furthermore, <i>in vitro</i> cytotoxicity was assessed, and the IC<sub>50</sub> value for PGP-CSNPs was 50.13 µg/mL. It was observed that PGP-CSNPs could induce apoptosis in MDA-MB-231 cells in dose-dependent manner. Furthermore, molecular docking was performed for bioactive compounds retrieved from PGP-CSNPs against human tumour suppressor proteins Bcl2, and results showed that the PGP-CSNPs had lower binding energy than cisplatin. This suggests that, the synthesized PGP-CSNPs have the potential to serve as a therapeutic agent for tackling TNBC. However, to validate its efficacy in human therapy, furthermore pre-clinical and clinical procedures should be examined, as this is an ongoing and significant step towards developing an effective and safe anticancer drug.</p>","PeriodicalId":8736,"journal":{"name":"Artificial Cells, Nanomedicine, and Biotechnology","volume":"53 1","pages":"43-55"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shiyao Liao, Kai Zhou, Yao Kang, Tingxiao Zhao, Yicheng Lin, Jun Lv, Danjie Zhu
{"title":"Enhanced cartilage repair using gelatin methacryloyl hydrogels combined with icariin and magnesium-doped bioactive glass.","authors":"Shiyao Liao, Kai Zhou, Yao Kang, Tingxiao Zhao, Yicheng Lin, Jun Lv, Danjie Zhu","doi":"10.1080/21691401.2025.2490677","DOIUrl":"https://doi.org/10.1080/21691401.2025.2490677","url":null,"abstract":"<p><p>Cartilage repair remains challenging due to limited self-healing, poor biocompatibility, and insufficient mechanical properties of current materials. To overcome these issues, we developed a multifunctional composite hydrogel by integrating gelatine methacrylate (GelMA) with magnesium-doped bioactive glass (Mg-BG) and icariin (ICA). SEM analysis revealed that pure GelMA exhibited a highly porous yet loosely organized structure, whereas the addition of Mg-BG and ICA produced a denser, more interconnected porous network that enhances cell adhesion and nutrient diffusion. <i>In vitro</i>, the ICA/Mg-BG/GelMA hydrogel achieved a swelling ratio up to 430% and maintained cell viability above 80% over 5 days. Moreover, qRT-PCR and immunohistochemical analyses demonstrated that the composite hydrogel upregulated chondrogenic markers (SOX9, ACAN, and COL2A1) compared with GelMA alone. Specifically, it downregulates M1 pro-inflammatory markers (CCR7, iNOS, CD86) and upregulates M2 anti-inflammatory markers (ARG1, CD163, CD206), thereby creating a regenerative microenvironment. These results indicate that the synergistic combination of GelMA, Mg-BG, and ICA not only improves the scaffold's mechanical support but also enhances its biological functionality, offering a promising strategy for cartilage repair. Future studies will focus on <i>in vivo</i> validation to further assess its clinical potential.</p>","PeriodicalId":8736,"journal":{"name":"Artificial Cells, Nanomedicine, and Biotechnology","volume":"53 1","pages":"181-193"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143959826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ClaPEPCK4: target gene for breeding innovative watermelon germplasm with low malic acid and high sweetness.","authors":"Congji Yang, Jiale Shi, Yuanyuan Qin, ShengQi Hua, Jiancheng Bao, Xueyan Liu, Yuqi Peng, Yige Gu, Wei Dong","doi":"10.1080/21645698.2025.2452702","DOIUrl":"10.1080/21645698.2025.2452702","url":null,"abstract":"<p><p>Malic acid markedly affects watermelon flavor. Reducing the malic acid content can significantly increase the sweetness of watermelon. An effective solution strategy is to reduce watermelon malic acid content through molecular breeding technology. In this study, we measured the TSS and pH of six watermelon varieties at four growth nodes. The TSS content was very low at 10 DAP and accumulated rapidly at 18, 26, and 34 DAP. Three phosphoenolpyruvate carboxykinase (<i>PEPCK</i>) genes of watermelon were identified and analyzed. The <i>ClaPEPCK4</i> expression was inversely proportional to malate content variations in fruits. In transgenic watermelon plants, overexpressing the <i>ClaPEPCK4</i> gene, malic acid content markedly decreased. In the knockout transgenic watermelon plants, two SNP mutations and one base deletion occurred in the <i>ClaPEPCK4</i> gene, with the malic acid content in the leaves increasing considerably and the PEPCK enzyme activity reduced to half of the wild-type. It is interesting that the <i>ClaPEPCK4</i> gene triggered the closure of leaf stomata under dark conditions in the knockout transgenic plants, which indicated its involvement in stomatal movement. In conclusion, this study provides a gene target <i>ClaPEPCK4</i> for creating innovative new high-sweetness watermelon varieties.</p>","PeriodicalId":54282,"journal":{"name":"Gm Crops & Food-Biotechnology in Agriculture and the Food Chain","volume":"16 1","pages":"156-170"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11734648/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cognitive NeurodynamicsPub Date : 2025-12-01Epub Date: 2025-06-05DOI: 10.1007/s11571-025-10269-3
Indu Dokare, Sudha Gupta
{"title":"Shap-driven explainable AI with simulated annealing for optimized seizure detection using multichannel EEG signal.","authors":"Indu Dokare, Sudha Gupta","doi":"10.1007/s11571-025-10269-3","DOIUrl":"10.1007/s11571-025-10269-3","url":null,"abstract":"<p><p>The aim of this research is to combine Explainable AI (XAI) with advanced optimization techniques to provide a unique framework for seizure detection. This proposed work investigates how to enhance patient-specific and patient-non-specific seizure detection models by combining multiband feature extraction, SHAP-based feature selection, SMOTE, and a metaheuristic algorithm for hyperparameter tuning.The discrete wavelet transform (DWT) is used to decompose EEG signals to retrieve entropy-based and statistical information. Simulated Annealing (SA) is employed to optimize the Random Forest (RF) classifier's hyperparameters, and SHAP (SHapley Additive exPlanations) values are utilized for feature selection. Furthermore, a novel technique SHAP-RELFR has been demonstrated to select patient-non-specific features. Additionally, SMOTE is employed to handle imbalanced data. The proposed methodology is evaluated on the CHB-MIT and Siena datasets using both patient-specific and patient-non-specific feature selection approaches. Experimental findings demonstrate that the proposed methodology significantly improves the performance of seizure detection. The average accuracy, precision, sensitivity, specificity, F1-score, and AUC obtained for a patient-non-specific case are 96.58%, 95.19%, 94.52%, 98.02%, 94.72%, and 0.9452, respectively, using the CHB-MIT dataset. For the Seina dataset, the average accuracy, precision, sensitivity, specificity, F1-score, and AUC obtained for a patient-non-specific case are 94.81%, 94.51%, 94.04%, 96.87%, 94.28%, and 0.9400, respectively. Explainable AI combined with SMOTE and a metaheuristic optimization algorithm facilitates an enhanced seizure detection. The novel SHAP-RELFR method provides an effective patient-non-specific feature selection, enabling this approach to be applicable across diverse patients. This proposed framework offers a step toward enhancing clinical decision-making by providing interpretable and versatile seizure detection models.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"85"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12141179/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144246797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cognitive NeurodynamicsPub Date : 2025-12-01Epub Date: 2025-06-30DOI: 10.1007/s11571-025-10294-2
Keyi Dong, April Burch, Kang Huang
{"title":"Application of deep learning for multi-scale behavioral analysis in SNCA E46K Parkinson's disease drosophila.","authors":"Keyi Dong, April Burch, Kang Huang","doi":"10.1007/s11571-025-10294-2","DOIUrl":"10.1007/s11571-025-10294-2","url":null,"abstract":"<p><p><i>Drosophila melanogaster</i> is widely used as a model organism in Parkinson's disease research. However, due to the complexity of motion capture and the challenges of quantitatively assessing spontaneous behavior in <i>Drosophila melanogaster</i>, it remains technically difficult to identify symptoms of Parkinson's disease within <i>Drosophila</i> based on objective spontaneous behavioral characteristics. Here, we present an automated multi-scale behavioral phenotyping pipeline that classifies phenotypes related to Parkinson's disease using motion features extracted from pose estimation data of wild-type and Synuclein Alpha E46K mutant <i>Drosophila melanogaster</i>. Locomotor activity was recorded in a custom-designed 3D-printed behavioral trap, and body kinematics were analyzed using a markerless pose estimation tool to extract numerical features such as movement speed, tremor-like oscillations, and limb motion patterns. Beyond kinematic analysis, we applied unsupervised clustering to the pose-derived trajectories to extract recurrent movement subtypes that characterize spontaneous behavioral sequences. We found that kinematic features alone were insufficient to distinguish mutant flies from normal individuals, whereas behavioral sequence patterns captured through unsupervised clustering enabled robust group separation. Combining both feature types further enhanced classification accuracy, with the best model achieving 85%. This system provides an objective and scalable approach for analyzing behavior related to Parkinson's disease in <i>Drosophila melanogaster</i>, with potential applications in monitoring disease progression and screening pharmaceutical compounds.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"105"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12209173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144552510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}