Explore the vast range of titles available.

The task of modeling and analyzing intercepted multifunction radars (MFRs) pulse trains is vital for cognitive electronic reconnaissance. Existing methodologies predominantly rely on prior information or heavily constrained models, posing challenges for non-cooperative applications. This paper introduces a novel approach to model MFRs using a Bayesian network, where the conditional probability density function is approximated by an autoregressive kernel mixture network (ARKMN). Utilizing the estimated probability density function, a dynamic programming algorithm is proposed for denoising and detecting change points in the intercepted MFRs pulse trains. Simulation results affirm the proposed method's efficacy in modeling MFRs, outperforming the state-of-the-art in pulse train denoising and change point detection.

Basketball games, real-time adjustment of defense strategy according to the changes on the court can greatly improve the team's chance of success in defense and thus win the game. In sophisticated team sports, it can be particularly difficult to judge these kinds of talents. This study attempted to develop an accurate and dependable video-based decision-making evaluation for young basketball in order to solve this problem. In this manuscript, Progressive Graph Convolutional Networks based onreal-time decision modeling of basketball game tactics based on video analytics (RDBGT-PGCN-GOA) is proposed. First, the image is taken from the NBA basketball video collection, and the pre-processing section receives the acquired data after that. When preparing, Unsharp Structure Guided Filtering (USGF) is used to remove background noise from the image. Then the preprocessed output is fed to Progressive Graph Convolutional Networks (PGCNs) is successfully used to classify the game tactics such as the Body Postures, Player Positions and Player Actions. Progressive Graph Convolutional Networks (PGCNs) classifiers, in general, do not express adaptive optimisation procedures to find the best parameters to guarantee accurate classification of player positions, player actions, and body postures. Hence, proposed GOOSE Optimization Algorithm (GOA) enhances Progressive Graph Convolutional Networks (PGCNs), accurately classify game tactics such as Body Postures, Player Positions and Player Actions. The weight parameter of the PGCN optimized with GOOSE Optimization Algorithm (GOA) for accurate prediction. The proposed RDBGT-PGCN-GOA proposed is implemented on the Python working platform. The performance of proposed method examined utilizing performance metrics likes Accuracy, Precision, Recall,F1 score, Error rate, and specificity were looked at. The proposed RDBGT-PGCN-GOA approach contains 23.52%, 22.72% and 24.92% higher accuracy; 23.52%, 24.72% and 21.92% lower Error rate compared with existing methods, such as Basketball video analysis using deep learning algorithms for technical features (TFBV-DNN), offline reinforcement learning for tactical strategies in professional basketball games (TSPBG-RNN), and real-time defensive strategy optimization using motion tracking and deep learning (RTBDS-CNN) are the three approaches that are being examined.

In order to systematically explore and understand the structure–activity relationship (SAR) of a lesinurad-based hit (1c) derived from the replacement of the S atom in lesinurad with CH2, 18 compounds (1a–1r) were designed, synthesized and subjected to in vitro URAT1 inhibitory assay. The SAR exploration led to the discovery of a highly potent flexible URAT1 inhibitor, 1q, which was 31-fold more potent than parent lesinurad (IC50 = 0.23 μM against human URAT1 for 1q vs 7.18 μM for lesinurad). The present study discovered a flexible molecular scaffold, as represented by 1q, which might serve as a promising prototype scaffold for further development of potent URAT1 inhibitors, and also demonstrated that the S atom in lesinurad was not indispensable for its URAT1 inhibitory activity.

Background Alzheimer's disease (AD) is a leading cause of dementia, and traditional diagnostic methods like cerebrospinal fluid testing and PET imaging are invasive, costly, and limit early detection. Language biomarker analysis offers a non‐invasive, efficient alternative to detect cognitive impairments through speech. However, in Chinese, the presence of homophones often leads to transcription errors, which may reduce model accuracy. Converting text to Pinyin sequences can minimize ambiguity, enhancing detection. This study proposes a novel speech‐based method to improve cognitive impairment detection accuracy with greater efficiency. Method This study utilized a systematic approach to differentiate individuals with cognitive impairment from healthy controls (HC). With approval from the hospital ethics committee, data from 300 participants in the China Preclinical Alzheimer's Disease Study (C‐PAS) cohort were extracted. Audio data were transcribed using iFLYTEK's speech recognition tool and converted into Pinyin sequences. Acoustic features, such as pause frequency and silent time, were extracted using OpenSMILE, and MFCC features were also incorporated. These features, along with demographic variables, formed comprehensive digital signatures for model training. To address the small sample size, data augmentation techniques such as introducing noise to numerical features and simulating word omissions, repetitions, and replacements in Pinyin sequences were applied. A Bi‐directional LSTM model, known for capturing context and semantic relevance, was employed to fuse Pinyin sequences with numerical features and optimize classification performance. Result The proposed method achieved an accuracy of 93.80% and an Area Under the Curve (AUC) of 0.93, demonstrating its superior performance compared to models trained solely on acoustic features or cognitive test scores. Ablation experiments revealed that combining pinyin sequences with acoustic features significantly enhanced model performance, emphasizing the importance of integrating both linguistic and acoustic data for detecting Alzheimer's disease in Chinese. Conclusion This study demonstrates the feasibility and effectiveness of integrating Pinyin sequences and acoustic features for non‐invasive Alzheimer's detection in Chinese. These findings providing a practical tool for early screening and paves the way for larger‐scale studies and potential clinical application.

Alzheimer's disease (AD) is a prevalent neurodegenerative condition, and its early diagnosis is critical for timely intervention and treatment. Current diagnostic methods, such as biomarker detection and neuroimaging, are costly and reliant on specialized resources, limiting their accessibility. Non-invasive cognitive screening, while promising, is often influenced by subjective and environmental factors, reducing its accuracy in practical use. Language biomarker analysis has emerged as a stable and convenient alternative. Advancements in machine learning, particularly the Bidirectional Encoder Representations from Transformers (BERT) model, provide robust support for speech-based AD screening and hold promise for breakthroughs in early diagnosis. This study adopted a systematic and scientific method to accurately distinguish between people with cognitive impairment and healthy controls (HC). In terms of data processing, with the approval of the hospital ethics committee, 300 subjects were selected from the C - PAS cohort and the data sets were reasonably divided. Semantic features were obtained through Shanghai cognitive screening (SCS) test, and audio features were extracted using BERT and OpenSMILE. During model training, an SCS score of 84.75 was determined as the classification boundary. For text, a CNN model was constructed, and for audio, five models such as RF and XGBoost were trained. The hard voting method was used for result fusion, and professional indicators such as Specificity were used for evaluation to ensure the reliability and validity of the study. The proposed framework achieved an accuracy of 91.80%, surpassing the 77.17% accuracy of the MoCA-Basic test for identifying people with cognitive impairment. Additionally, it attained an F1-score of 91.85%. Feature importance analysis revealed key biomarkers linked to cognitive impairment, including increased pause time and spectral changes in acoustic features, along with reduced semantic complexity in translated text. The proposed multimodal framework offers a highly accurate, cost-effective, and non-invasive method for the early detection of cognitive impairment. The identified biomarkers provide valuable insights into early functional deficits associated with cognitive decline, advancing our understanding of the disease and enabling the development of more effective screening tools.

Background Alzheimer's disease (AD) is a prevalent neurodegenerative condition, and its early diagnosis is critical for timely intervention and treatment. Current diagnostic methods, such as biomarker detection and neuroimaging, are costly and reliant on specialized resources, limiting their accessibility. Non‐invasive cognitive screening, while promising, is often influenced by subjective and environmental factors, reducing its accuracy in practical use. Language biomarker analysis has emerged as a stable and convenient alternative. Advancements in machine learning, particularly the Bidirectional Encoder Representations from Transformers (BERT) model, provide robust support for speech‐based AD screening and hold promise for breakthroughs in early diagnosis. Method This study adopted a systematic and scientific method to accurately distinguish between people with cognitive impairment and healthy controls (HC). In terms of data processing, with the approval of the hospital ethics committee, 300 subjects were selected from the C ‐ PAS cohort and the data sets were reasonably divided. Semantic features were obtained through Shanghai cognitive screening (SCS) test, and audio features were extracted using BERT and OpenSMILE. During model training, an SCS score of 84.75 was determined as the classification boundary. For text, a CNN model was constructed, and for audio, five models such as RF and XGBoost were trained. The hard voting method was used for result fusion, and professional indicators such as Specificity were used for evaluation to ensure the reliability and validity of the study. Result The proposed framework achieved an accuracy of 91.80%, surpassing the 77.17% accuracy of the MoCA‐Basic test for identifying people with cognitive impairment. Additionally, it attained an F1‐score of 91.85%. Feature importance analysis revealed key biomarkers linked to cognitive impairment, including increased pause time and spectral changes in acoustic features, along with reduced semantic complexity in translated text. Conclusion The proposed multimodal framework offers a highly accurate, cost‐effective, and non‐invasive method for the early detection of cognitive impairment. The identified biomarkers provide valuable insights into early functional deficits associated with cognitive decline, advancing our understanding of the disease and enabling the development of more effective screening tools.

Background Multi‐domain non‐pharmacological interventions, such as cognitive training and physical exercise, have been widely recognized for their effectiveness in improving cognitive function in older adults. However, adherence to such programs, particularly online programs, remains low. This study examines the role of different types of emotional support in relation to adherence to such interventions. Method A quasi‐experimental design recruited 524 participants (mean age: 68.4 years, 94.1% female) join in the Brain and Body Rehab Training (BBRT) program (Figure 1), a multi‐domain non‐pharmacological online intervention, for 240 days. Participants were divided into high‐adherence (≥70% task completion, n = 250), low‐adherence (30%–70% task completion, n = 145), and control (<30% task completion, n = 129) groups. Emotional support metrics included community‐based group chat, topic discussion, live classes, one‐on‐one trainer interactions etc. Cognitive performance was measured using the G3 (a three‐minute gamified cognitive screen tool) at baseline, 4 months, and 8 months. Repeated measures analysis evaluated G3 score changes over time, while the Kruskal‐Wallis test compared group differences. Binary logistic regression examined the relationship between emotional support metrics and adherence levels. Result Baseline G3 scores did not differ significantly across groups (p > 0.05). At 4 months, all groups showed significant G3 score improvements compared to baseline (p < 0.05). By 8 months, both the high‐adherence (p = 0.029) and low‐adherence (p = 0.035) groups exhibited significantly greater G3 score improvements than the control group. Emotional support was significantly associated with adherence. Sharing of check‐in status on the social media (OR = 6.431, p = 0.004), participating in community topic discussions (OR = 1.231, p = 0.035) and live classes attended (OR = 1.197, p = 0.007) were positively associated with adherence, while number of topics shared (OR = 0.393, p = 0.015) was negatively associated with adherence. Conclusion Emotional support is significantly associated with adherence to online multi‐domain non‐pharmacological interventions among older adults. Tailored strategies, such as live classes and community engagement, are crucial for completing cognitive training and improving cognitive outcomes. Further research is needed to refine these strategies for diverse populations.

Alzheimer's disease (AD) is a leading cause of dementia, and traditional diagnostic methods like cerebrospinal fluid testing and PET imaging are invasive, costly, and limit early detection. Language biomarker analysis offers a non-invasive, efficient alternative to detect cognitive impairments through speech. However, in Chinese, the presence of homophones often leads to transcription errors, which may reduce model accuracy. Converting text to Pinyin sequences can minimize ambiguity, enhancing detection. This study proposes a novel speech-based method to improve cognitive impairment detection accuracy with greater efficiency. This study utilized a systematic approach to differentiate individuals with cognitive impairment from healthy controls (HC). With approval from the hospital ethics committee, data from 300 participants in the China Preclinical Alzheimer's Disease Study (C-PAS) cohort were extracted. Audio data were transcribed using iFLYTEK's speech recognition tool and converted into Pinyin sequences. Acoustic features, such as pause frequency and silent time, were extracted using OpenSMILE, and MFCC features were also incorporated. These features, along with demographic variables, formed comprehensive digital signatures for model training. To address the small sample size, data augmentation techniques such as introducing noise to numerical features and simulating word omissions, repetitions, and replacements in Pinyin sequences were applied. A Bi-directional LSTM model, known for capturing context and semantic relevance, was employed to fuse Pinyin sequences with numerical features and optimize classification performance. The proposed method achieved an accuracy of 93.80% and an Area Under the Curve (AUC) of 0.93, demonstrating its superior performance compared to models trained solely on acoustic features or cognitive test scores. Ablation experiments revealed that combining pinyin sequences with acoustic features significantly enhanced model performance, emphasizing the importance of integrating both linguistic and acoustic data for detecting Alzheimer's disease in Chinese. This study demonstrates the feasibility and effectiveness of integrating Pinyin sequences and acoustic features for non-invasive Alzheimer's detection in Chinese. These findings providing a practical tool for early screening and paves the way for larger-scale studies and potential clinical application.

Background Older adults with cognitive impairments will benefit from multicomponent interventions include cognitive training, exercise, and lifestyle modifications. However, many existing digital therapeutic products predominantly focus on computerized cognitive training, lacking effective approaches to other crucial interventions. We proposed a multidimensional comprehensive cognitive intervention training program – Brain and Body Rehab Training (BBRT), which integrates multidomain cognitive training with physical‐cognitive training and multidimensional lifestyle interventions and developed the digital therapeutic product – BBRT‐online based on WeChat mini‐program. The present study was to assess the effectiveness of BBRT in older adults with subjective memory impairments. Method Using the WeChat mini‐program platform, we developed the BBRT‐online digital therapeutics product. Prior to the intervention, users undergo Game‐based Cognitive Assessment – Three‐Minute Version (G3). Subsequently, an individualized training program is assigned consisting of completing four to five daily tasks, including cognitive training, physical‐cognitive training, lifestyle interventions, chronic disease/diet/sleep/emotion management, and traditional Chinese medicine non‐pharmacological interventions among others (Figure 1). The intervention duration ranges 15‐25 minutes per day, and task difficulty is dynamically adjusted based on individual task performance and periodic cognitive assessments. Additionally, remote online administration services and internet communities are strongly recommended to offer emotional support and enhance intervention effectiveness. Sixty older adults reporting subjective memory complaints were recruited, with 30 assigned to receive BBRT‐online training and the remainder serving as the control group. Cognitive function was evaluated using the G3 at baseline and three months later. T‐tests were conducted to assess the impact of BBRT‐online on cognitive function. Result At baseline, there was no significant difference in G3 scores between the BBRT group (53.5±10.87) and the control group (55.1±11.77, p = 0.583). Following three months of intervention, the BBRT group demonstrated a significantly higher G3 score (61.5±6.85) compared to baseline (p<0.001, Figure 2). Conversely, no such difference was observed in the control group (55.5 ± 9.34, p = 0.911). Conclusion The BBRT digital therapeutics enabled cognitive assessment and individualized cognitive interventions and significantly improved cognitive function in older adults. Further studies are required to evaluate its effectiveness.

Background Game‐based Cognitive Assessment – 3‐minute Version (G3) is a self‐administrated mobile screening tool for detecting early cognitive impairments among Chinses community‐dwelling older adults. Released as a WeChat and Alipay mini‐programs, G3 offers a convenient and cost‐free means for individuals to evaluate their cognitive functions online. This study aimed to investigate the cognitive performance of older adults in the Shanghai community with G3. Additionally, a comparison was made between the cognitive performance of older adults who participated in the screening offline and those who proactively participated online. Method Between June and October 2023, an offline cognitive screening with G3 tests was performed in Xiaodongmen subdistrict of Shanghai. And G3 results of 3344 participants aged 55‐89 years old were enrolled for restrictive analysis. Simultaneously, G3 online assessment records between January and December 2022 completed by 64535 individuals aged 55‐89 years old from various regions of China, were reviewed and compared to the offline screening results. Result Among older adults aged 55 to 89 in Xiaodongmen communities, the average G3 score (mean ± stand deviation) was 56.82±12.47. Furthermore, the mean G3 score for males and females was 57.23±12.29 (n = 1569) and 56.46±12.61(n = 1775), respectively, both of which exhibited a trend of cognitive decline with increasing age (Figure 1). Moreover, older adults with a high school education or higher demonstrated significantly better cognitive performance compared to those without (p<0.05, Figure 2). When comparing the online self‐administrated G3 results of age‐matched older adults, both cohorts displayed a similar trend of cognitive decline with increasing age. However, the average G3 score obtained from Xiaodongmen subdistrict was statistically lower than that of the online assessments (p<0.05, Figure 3). Conclusion This study characterized the cognitive function among older adults in Shanghai and enhanced the feasibility of G3 tool for large‐scale cognitive screening in Chinese communities. Nonetheless, due to the notable disparity between online and offline screening results, further investigations are warranted to explore the underlying mechanisms.