Background: The past 2 decades have seen rapid development in the use of robots for rehabilitation. Research on rehabilitation robots involves interdisciplinary activities, making it a great challenge to obtain comprehensive insights in this research field. Objective: We performed a bibliometric study to understand the characteristics of research on rehabilitation robots and emerging trends in this field in the last 2 decades. Methods: Reports on the topic of rehabilitation robots published from January 1, 2001, to December 31, 2020, were retrieved from the Web of Science Core Collection on July 28, 2022. Document types were limited to “article” and “meeting” (excluding the “review” type), to ensure that our analysis of the evolution over time of this research had high validity. We used CiteSpace to conduct a co-occurrence and co-citation analysis and to visualize the characteristics of this research field and emerging trends. Landmark publications were identified using metrics such as betweenness centrality and burst strength. Results: Through data retrieval, cleaning, and deduplication, we retrieved 9287 publications and 110,619 references cited in these publications that were on the topic of rehabilitation robots and were published between 2001 and 2020. Results of the Mann-Kendall test indicated that the numbers of both publications (P<.001; St=175.0) and citations (P<.001; St=188.0) related to rehabilitation robots exhibited a significantly increasing yearly trend. The co-occurrence results revealed 120 categories connected with research on rehabilitation robots; we used these categories to determine research relationships. The co-citation results identified 169 co-citation clusters characterizing this research field and emerging trends in it. The most prominent label was “soft robotic technology” (the burst strength was 79.07), which has become a topic of great interest in rehabilitative recovery for both the upper and lower limbs. Additionally, task-oriented upper-limb training, control strategies for robot-assisted lower limb rehabilitation, and power in exoskeleton robots were topics of great interest in current research. Conclusions: Our work provides insights into research on rehabilitation robots, including its characteristics and emerging trends during the last 2 decades, providing a comprehensive understanding of this research field.
Rehabilitation robots, as representative advanced modern rehabilitation devices, are automatically operated machines used for improving the motor functions of patients. Research on rehabilitation robots is typically multidisciplinary research involving technical engineering, clinical medicine, neural science, and other disciplines. Understanding the emerging trends and high-impact publications is important for providing an overview of rehabilitation robot research for interested researchers. Bibliometric analysis is the use of statistical methods to analyze publications over a period of time, which can provide visual insights into the relationships between studies and their publications. In this study, we used “rehabilitation robot*” as a topic term to collect 3527 papers from Web of Science in 127 subject categories published between 2000 and 2019. Rehabilitation robot research has increased rapidly over the past 20 years, 10 key clusters of which were analyzed in this narrative review: improving functional ability after stroke, spinal cord injury, universal haptic drive, robotic-assisted treadmill therapy, treadmill training, increasing productivity, custom-designed haptic training, physical treatment strategies, arm movement therapy, and rehabilitation robotics. Based on this database, we constructed co-citation and co-occurrence networks that were characterized by betweenness centrality values of more than 0.08 and citation bursts with strengths of more than 23, thereby visualizing the emerging trends in the research of rehabilitation robots.
The advent of Large Language Models (LLMs) has revolutionized Natural Language Processing (NLP), offering unprecedented capabilities for understanding and generating human-like texts. However, the effectiveness of these models in specific domains often requires fine-tuning, which can be computationally expensive and increases the risk of overfitting. To address these challenges, we introduce Task-Agnostic Adaptive Activation Scaling Network (TAAS-Net), a novel multi-task learning model architecture designed to adapt pre-trained LLMs to new tasks with minimal computational and storage overhead. TAAS-Net leverages an adaptive activation scaling network to enhance parameter efficiency and prevent overfitting, thereby improving model generalization. It incorporates a task-agnostic adaptive activation scaling layer that introduces task-specific, learnable activation scaling vectors, enhancing the model’s adaptability across various tasks. In addition, Low-Rank Adaptation within the attention modules facilitates the transfer of knowledge across different tasks. TAAS-Net’s integration of multi-task learning and parameter-efficient fine-tuning schemes enables efficient fine-tuning in multi-task scenarios, with a reduced parameter count compared to existing methods such as MoE-LoRA and X-LoRA. Our model also handles mixed-task batches during inference, thereby enhancing versatility and operational efficiency. Through a series of experiments on benchmark datasets, including the General Language Understanding Evaluation (GLUE), IMDB, and Agnews, TAAS-Net demonstrated superior performance over existing baselines, underscoring its potential for applications requiring rapid deployment and high accuracy. The architectural design of TAAS-Net streamlines the model adaptation process and reduces resource demands, offering a scalable and resource-efficient solution for adapting LLMs to new tasks.
BACKGROUND The past 2 decades have seen rapid development in the use of robots for rehabilitation. Research on rehabilitation robots involves interdisciplinary activities, making it a great challenge to obtain comprehensive insights in this research field. OBJECTIVE We performed a bibliometric study to understand the characteristics of research on rehabilitation robots and emerging trends in this field in the last 2 decades. METHODS Reports on the topic of rehabilitation robots published from January 1, 2001, to December 31, 2020, were retrieved from the Web of Science Core Collection on July 28, 2022. Document types were limited to “article” and “meeting” (excluding the “review” type), to ensure that our analysis of the evolution over time of this research had high validity. We used CiteSpace to conduct a co-occurrence and co-citation analysis and to visualize the characteristics of this research field and emerging trends. Landmark publications were identified using metrics such as betweenness centrality and burst strength. RESULTS Through data retrieval, cleaning, and deduplication, we retrieved 9287 publications and 110,619 references cited in these publications that were on the topic of rehabilitation robots and were published between 2001 and 2020. Results of the Mann-Kendall test indicated that the numbers of both publications (P<.001; St=175.0) and citations (P<.001; St=188.0) related to rehabilitation robots exhibited a significantly increasing yearly trend. The co-occurrence results revealed 120 categories connected with research on rehabilitation robots; we used these categories to determine research relationships. The co-citation results identified 169 co-citation clusters characterizing this research field and emerging trends in it. The most prominent label was “soft robotic technology” (the burst strength was 79.07), which has become a topic of great interest in rehabilitative recovery for both the upper and lower limbs. Additionally, task-oriented upper-limb training, control strategies for robot-assisted lower limb rehabilitation, and power in exoskeleton robots were topics of great interest in current research. CONCLUSIONS Our work provides insights into research on rehabilitation robots, including its characteristics and emerging trends during the last 2 decades, providing a comprehensive understanding of this research field.