通过检索关键词,指定一个或多个类别标签实现文本的高效组织和自动分类,是发现文档中的隐含关系、推动知识传播和创新的重要途径。然而,检索关键词的获取位置、词性以及选取是否全面等因素,会导致关键词语义信息缺失和关键词识别准确性...通过检索关键词,指定一个或多个类别标签实现文本的高效组织和自动分类,是发现文档中的隐含关系、推动知识传播和创新的重要途径。然而,检索关键词的获取位置、词性以及选取是否全面等因素,会导致关键词语义信息缺失和关键词识别准确性较差;这两大问题,正是影响文档高效、精准自动分类的突出障碍。基于此,论文构建了一个融合TF-IDF(Term Frequency-Inverse Document Frequency)和GloVe(Global Vectors for Word Representation)的文本自动分类系统。该系统首先就词性影响因子和位置权重系数对TF-IDF算法进行改进,以弥补传统TF-IDF算法在关键词识别和语义分析上的不足;其次,使用GloVe模型对关键词集进一步扩充,使文本自动分类的准确率和召回率分别达到92.6%和90.9%;最后,通过实验比对,进一步验证该系统在处理多类别文本自动分类任务中的有效性。展开更多
Background With the increasing prominence of hand and finger motion tracking in virtual reality(VR)applications and rehabilitation studies,data gloves have emerged as a prevalent solution.In this study,we developed an...Background With the increasing prominence of hand and finger motion tracking in virtual reality(VR)applications and rehabilitation studies,data gloves have emerged as a prevalent solution.In this study,we developed an innovative,lightweight,and detachable data glove tailored for finger motion tracking in VR environments.Methods The glove design incorporates a potentiometer coupled with a flexible rack and pinion gear system,facilitating precise and natural hand gestures for interaction with VR applications.Initially,we calibrated the potentiometer to align with the actual finger bending angle,and verified the accuracy of angle measurements recorded by the data glove.To verify the precision and reliability of our data glove,we conducted repeatability testing for flexion(grip test)and extension(flat test),with 250 measurements each,across five users.We employed the Gage Repeatability and Reproducibility to analyze and interpret the repeatable data.Furthermore,we integrated the gloves into a SteamVR home environment using the OpenGlove auto-calibration tool.Conclusions The repeatability analysis revealed an aggregate error of 1.45 degrees in both the gripped and flat hand positions.This outcome was notably favorable when compared with the findings from assessments of nine alternative data gloves that employed similar protocols.In these experiments,users navigated and engaged with virtual objects,underlining the glove's exact tracking of finger motion.Furthermore,the proposed data glove exhibited a low response time of 17-34 ms and back-drive force of only 0.19 N.Additionally,according to a comfort evaluation using the Comfort Rating Scales,the proposed glove system is wearable,placing it at the WL1 level.展开更多
With the rapid development of flexible electronics,the tactile systems for object recognition are becoming increasingly delicate.This paper presents the design of a tactile glove for object recognition,integrating 243...With the rapid development of flexible electronics,the tactile systems for object recognition are becoming increasingly delicate.This paper presents the design of a tactile glove for object recognition,integrating 243 palm pressure units and 126 finger joint strain units that are implemented by piezoresistive Velostat film.The palm pressure and joint bending strain data from the glove were collected using a two-dimensional resistance array scanning circuit and further converted into tactile images with a resolution of 32×32.To verify the effect of tactile data types on recognition precision,three datasets of tactile images were respectively built by palm pressure data,joint bending strain data,and a tactile data combing of both palm pressure and joint bending strain.An improved residual convolutional neural network(CNN)model,SP-ResNet,was developed by light-weighting ResNet-18 to classify these tactile images.Experimental results show that the data collection method combining palm pressure and joint bending strain demonstrates a 4.33%improvement in recognition precision compared to the best results obtained by using only palm pressure or joint bending strain.The recognition precision of 95.50%for 16 objects can be achieved by the presented tactile glove with SP-ResNet of less computation cost.The presented tactile system can serve as a sensing platform for intelligent prosthetics and robot grippers.展开更多
The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situati...The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.展开更多
Progress is described regarding the development of a new electrotactile feedback glove designed for application to dexterous robot. The sensitivity of operator's finger against electrical stimulus pulse is conside...Progress is described regarding the development of a new electrotactile feedback glove designed for application to dexterous robot. The sensitivity of operator's finger against electrical stimulus pulse is considered. It is found that frequency, duty ratio, and voltage amplitude of electrical stimulus pulse determine the sensitivity of finger. The effects of materials, sizes, arrangements and shapes of electrodes on sensitivity of finger are analyzed. Finally, the tactile tele presence system is designed to experimentally confirm that the robot with electrotactile feedback glove can manipulate dexterous robotic multi fingered hand and identify and classify three sorts of objects.展开更多
Yarn sensors have shown promising application prospects in wearable electronics owing to their shape adaptability, good flexibility, and weavability. However, it is still a critical challenge to develop simultaneously...Yarn sensors have shown promising application prospects in wearable electronics owing to their shape adaptability, good flexibility, and weavability. However, it is still a critical challenge to develop simultaneously structure stable, fast response, body conformal, mechanical robust yarn sensor using full microfibers in an industrial-scalable manner. Herein, a full-fiber auxetic-interlaced yarn sensor(AIYS) with negative Poisson’s ratio is designed and fabricated using a continuous, mass-producible, structure-programmable, and low-cost spinning technology. Based on the unique microfiber interlaced architecture, AIYS simultaneously achieves a Poisson’s ratio of-1.5, a robust mechanical property(0.6 c N/dtex), and a fast train-resistance responsiveness(0.025 s), which enhances conformality with the human body and quickly transduce human joint bending and/or stretching into electrical signals. Moreover, AIYS shows good flexibility, washability, weavability, and high repeatability. Furtherly, with the AIYS array, an ultrafast full-letter sign-language translation glove is developed using artificial neural network. The sign-language translation glove achieves an accuracy of 99.8% for all letters of the English alphabet within a short time of 0.25 s. Furthermore, owing to excellent full letter-recognition ability, real-time translation of daily dialogues and complex sentences is also demonstrated. The smart glove exhibits a remarkable potential in eliminating the communication barriers between signers and non-signers.展开更多
Humans can sense, weigh and grasp different objects, deduce their physical properties at the same time, and exert appropriate forces – a challenging task for modern robots. Studying the mechanics of human grasping ob...Humans can sense, weigh and grasp different objects, deduce their physical properties at the same time, and exert appropriate forces – a challenging task for modern robots. Studying the mechanics of human grasping objects will play a supplementary role in visual-based robot object processing. These tools require large-scale tactile data sets with high spatial resolution. However, there is no large human-grasped tactile data set covering the whole hand, because dense coverage of the human hand with tactile sensors is challenging. Hence, the capability of observing and learning from successful daily humanobject interactions is the long-term goal of aiding the development of robots and prosthetics.展开更多
A wearable force-feedback glove is a promising way to enhance the immersive sensation when a user interacts with virtual objects in virtual reality scenarios.Design challenges for such a glove include allowing a large...A wearable force-feedback glove is a promising way to enhance the immersive sensation when a user interacts with virtual objects in virtual reality scenarios.Design challenges for such a glove include allowing a large fingertip workspace,providing a desired force sensation when simulating both free-and constrained-space interactions,and ensuring a lightweight structure.In this paper,we present a forcefeedback glove using a pneumatically actuated mechanism mounted on the dorsal side of the user’s hand.By means of a triple kinematic paired link with a curved sliding slot,a hybrid cam-linkage mechanism is proposed to transmit the resistance from the pneumatic piston rod to the fingertip.In order to obtain a large normal component of the feedback force on the user’s fingertip,the profile of the sliding slot was synthesized through an analysis of the force equilibrium on the triple kinematic paired link.A prototype five-fingered glove with a mass of 245 g was developed,and a wearable force-measurement system was constructed to permit the quantitative evaluation of the interaction performance in both free and constrained space.The experimental results confirm that the glove can achieve an average resistance of less than 0.1 N in free-space simulation and a maximum fingertip force of 4 N in constrained-space simulation.The experiment further confirms that this glove permits the finger to move freely to simulate typical grasping gestures.展开更多
Two prototype pneumatic boxing gloves of different design were compared against conventional 10?oz (Std 10?oz) and 16?oz (Std 16?oz) gloves in terms of ability to reduce impact forces delivered to a target. One of the...Two prototype pneumatic boxing gloves of different design were compared against conventional 10?oz (Std 10?oz) and 16?oz (Std 16?oz) gloves in terms of ability to reduce impact forces delivered to a target. One of the pneumatic gloves (SBLI) contained a sealed air bladder inflated to a pressure of 2?kPa. The other (ARLI) incorporated a bladder that allowed release of air to the external environment upon contact with a target, followed by rapid air reuptake. Each glove was placed on to a mechanical fist and dropped 10 times on to an in-floor force plate from each of nine heights ranging from 1.0 to 5.0 metres, with the 5-metre drop generating a peak pre-impact glove velocity close to the reported maximum for elite boxers. Compared to the conventional gloves, the ARLI glove substantially reduced peak impact forces at all drop heights, with the reduction exceeding 30% even at the 5-metre level. The SBLI glove was as effective as the ARLI glove in reducing peak impact forces at drop heights of up to 2.5 metres, but its performance then progressively diminished, and at drop heights of 4.0, 4.5 and 5.0 metres it produced peak force readings similar to those recorded for the Std 10?oz and Std 16?oz gloves. The superiority of the ARLI glove was even more evident in relation to peak rate of force development, with reductions relative to the Std 10?oz glove being ~60% at drop heights up to 3.5 metres and still ~47% at 5 metres. Peak rate of force development for the SBLI glove exceeded that for the ARLI glove for all drop heights of 2.0 metres and above, and at 4.0, 4.5 and 5.0 metres it was higher than the readings for the Std 10 oz and 16?oz gloves. The protective effect of the ARLI glove was?associated with an increase in impact compliance and prolongation of contact time between glove and target. It is concluded that a pneumatic boxing glove that provides for air exchange with the external environment can greatly reduce impact magnitudes across the whole range of pre-impact glove velocities likely to be encountered in boxing, thereby mitigating risks associated with the sport. While acceptance of the gloves by the boxing community is uncertain, opportunity may exist for almost immediate uptake in modified boxing programs.展开更多
文摘通过检索关键词,指定一个或多个类别标签实现文本的高效组织和自动分类,是发现文档中的隐含关系、推动知识传播和创新的重要途径。然而,检索关键词的获取位置、词性以及选取是否全面等因素,会导致关键词语义信息缺失和关键词识别准确性较差;这两大问题,正是影响文档高效、精准自动分类的突出障碍。基于此,论文构建了一个融合TF-IDF(Term Frequency-Inverse Document Frequency)和GloVe(Global Vectors for Word Representation)的文本自动分类系统。该系统首先就词性影响因子和位置权重系数对TF-IDF算法进行改进,以弥补传统TF-IDF算法在关键词识别和语义分析上的不足;其次,使用GloVe模型对关键词集进一步扩充,使文本自动分类的准确率和召回率分别达到92.6%和90.9%;最后,通过实验比对,进一步验证该系统在处理多类别文本自动分类任务中的有效性。
基金Supported by the Sirindhorn International Institute of Technology,Thammasat University,EFS-G(Excellent foreign Student-Graduate)research fund.
文摘Background With the increasing prominence of hand and finger motion tracking in virtual reality(VR)applications and rehabilitation studies,data gloves have emerged as a prevalent solution.In this study,we developed an innovative,lightweight,and detachable data glove tailored for finger motion tracking in VR environments.Methods The glove design incorporates a potentiometer coupled with a flexible rack and pinion gear system,facilitating precise and natural hand gestures for interaction with VR applications.Initially,we calibrated the potentiometer to align with the actual finger bending angle,and verified the accuracy of angle measurements recorded by the data glove.To verify the precision and reliability of our data glove,we conducted repeatability testing for flexion(grip test)and extension(flat test),with 250 measurements each,across five users.We employed the Gage Repeatability and Reproducibility to analyze and interpret the repeatable data.Furthermore,we integrated the gloves into a SteamVR home environment using the OpenGlove auto-calibration tool.Conclusions The repeatability analysis revealed an aggregate error of 1.45 degrees in both the gripped and flat hand positions.This outcome was notably favorable when compared with the findings from assessments of nine alternative data gloves that employed similar protocols.In these experiments,users navigated and engaged with virtual objects,underlining the glove's exact tracking of finger motion.Furthermore,the proposed data glove exhibited a low response time of 17-34 ms and back-drive force of only 0.19 N.Additionally,according to a comfort evaluation using the Comfort Rating Scales,the proposed glove system is wearable,placing it at the WL1 level.
基金supported by the Key Research and Development Program of Shaanxi Province(No.2024 GX-YBXM-178)the Shaanxi Province Qinchuangyuan“Scientists+Engineers”Team Development(No.2022KXJ032)。
文摘With the rapid development of flexible electronics,the tactile systems for object recognition are becoming increasingly delicate.This paper presents the design of a tactile glove for object recognition,integrating 243 palm pressure units and 126 finger joint strain units that are implemented by piezoresistive Velostat film.The palm pressure and joint bending strain data from the glove were collected using a two-dimensional resistance array scanning circuit and further converted into tactile images with a resolution of 32×32.To verify the effect of tactile data types on recognition precision,three datasets of tactile images were respectively built by palm pressure data,joint bending strain data,and a tactile data combing of both palm pressure and joint bending strain.An improved residual convolutional neural network(CNN)model,SP-ResNet,was developed by light-weighting ResNet-18 to classify these tactile images.Experimental results show that the data collection method combining palm pressure and joint bending strain demonstrates a 4.33%improvement in recognition precision compared to the best results obtained by using only palm pressure or joint bending strain.The recognition precision of 95.50%for 16 objects can be achieved by the presented tactile glove with SP-ResNet of less computation cost.The presented tactile system can serve as a sensing platform for intelligent prosthetics and robot grippers.
文摘The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.
文摘Progress is described regarding the development of a new electrotactile feedback glove designed for application to dexterous robot. The sensitivity of operator's finger against electrical stimulus pulse is considered. It is found that frequency, duty ratio, and voltage amplitude of electrical stimulus pulse determine the sensitivity of finger. The effects of materials, sizes, arrangements and shapes of electrodes on sensitivity of finger are analyzed. Finally, the tactile tele presence system is designed to experimentally confirm that the robot with electrotactile feedback glove can manipulate dexterous robotic multi fingered hand and identify and classify three sorts of objects.
基金supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (NRF-2020R1A2C3003344 and NRF-2020R1A4A2002728)
文摘Yarn sensors have shown promising application prospects in wearable electronics owing to their shape adaptability, good flexibility, and weavability. However, it is still a critical challenge to develop simultaneously structure stable, fast response, body conformal, mechanical robust yarn sensor using full microfibers in an industrial-scalable manner. Herein, a full-fiber auxetic-interlaced yarn sensor(AIYS) with negative Poisson’s ratio is designed and fabricated using a continuous, mass-producible, structure-programmable, and low-cost spinning technology. Based on the unique microfiber interlaced architecture, AIYS simultaneously achieves a Poisson’s ratio of-1.5, a robust mechanical property(0.6 c N/dtex), and a fast train-resistance responsiveness(0.025 s), which enhances conformality with the human body and quickly transduce human joint bending and/or stretching into electrical signals. Moreover, AIYS shows good flexibility, washability, weavability, and high repeatability. Furtherly, with the AIYS array, an ultrafast full-letter sign-language translation glove is developed using artificial neural network. The sign-language translation glove achieves an accuracy of 99.8% for all letters of the English alphabet within a short time of 0.25 s. Furthermore, owing to excellent full letter-recognition ability, real-time translation of daily dialogues and complex sentences is also demonstrated. The smart glove exhibits a remarkable potential in eliminating the communication barriers between signers and non-signers.
文摘Humans can sense, weigh and grasp different objects, deduce their physical properties at the same time, and exert appropriate forces – a challenging task for modern robots. Studying the mechanics of human grasping objects will play a supplementary role in visual-based robot object processing. These tools require large-scale tactile data sets with high spatial resolution. However, there is no large human-grasped tactile data set covering the whole hand, because dense coverage of the human hand with tactile sensors is challenging. Hence, the capability of observing and learning from successful daily humanobject interactions is the long-term goal of aiding the development of robots and prosthetics.
基金the National Key Research and Development Program(2016YFB1001200)the National Natural Science Foundation of China(61572055 and 61633004).
文摘A wearable force-feedback glove is a promising way to enhance the immersive sensation when a user interacts with virtual objects in virtual reality scenarios.Design challenges for such a glove include allowing a large fingertip workspace,providing a desired force sensation when simulating both free-and constrained-space interactions,and ensuring a lightweight structure.In this paper,we present a forcefeedback glove using a pneumatically actuated mechanism mounted on the dorsal side of the user’s hand.By means of a triple kinematic paired link with a curved sliding slot,a hybrid cam-linkage mechanism is proposed to transmit the resistance from the pneumatic piston rod to the fingertip.In order to obtain a large normal component of the feedback force on the user’s fingertip,the profile of the sliding slot was synthesized through an analysis of the force equilibrium on the triple kinematic paired link.A prototype five-fingered glove with a mass of 245 g was developed,and a wearable force-measurement system was constructed to permit the quantitative evaluation of the interaction performance in both free and constrained space.The experimental results confirm that the glove can achieve an average resistance of less than 0.1 N in free-space simulation and a maximum fingertip force of 4 N in constrained-space simulation.The experiment further confirms that this glove permits the finger to move freely to simulate typical grasping gestures.
文摘Two prototype pneumatic boxing gloves of different design were compared against conventional 10?oz (Std 10?oz) and 16?oz (Std 16?oz) gloves in terms of ability to reduce impact forces delivered to a target. One of the pneumatic gloves (SBLI) contained a sealed air bladder inflated to a pressure of 2?kPa. The other (ARLI) incorporated a bladder that allowed release of air to the external environment upon contact with a target, followed by rapid air reuptake. Each glove was placed on to a mechanical fist and dropped 10 times on to an in-floor force plate from each of nine heights ranging from 1.0 to 5.0 metres, with the 5-metre drop generating a peak pre-impact glove velocity close to the reported maximum for elite boxers. Compared to the conventional gloves, the ARLI glove substantially reduced peak impact forces at all drop heights, with the reduction exceeding 30% even at the 5-metre level. The SBLI glove was as effective as the ARLI glove in reducing peak impact forces at drop heights of up to 2.5 metres, but its performance then progressively diminished, and at drop heights of 4.0, 4.5 and 5.0 metres it produced peak force readings similar to those recorded for the Std 10?oz and Std 16?oz gloves. The superiority of the ARLI glove was even more evident in relation to peak rate of force development, with reductions relative to the Std 10?oz glove being ~60% at drop heights up to 3.5 metres and still ~47% at 5 metres. Peak rate of force development for the SBLI glove exceeded that for the ARLI glove for all drop heights of 2.0 metres and above, and at 4.0, 4.5 and 5.0 metres it was higher than the readings for the Std 10 oz and 16?oz gloves. The protective effect of the ARLI glove was?associated with an increase in impact compliance and prolongation of contact time between glove and target. It is concluded that a pneumatic boxing glove that provides for air exchange with the external environment can greatly reduce impact magnitudes across the whole range of pre-impact glove velocities likely to be encountered in boxing, thereby mitigating risks associated with the sport. While acceptance of the gloves by the boxing community is uncertain, opportunity may exist for almost immediate uptake in modified boxing programs.
