Luping Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Luping Song has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
Shu Xu
School of Rehabilitation, Capital Medical University, Neurorehabilitation Center, Beijing Boai Hospital, China Rehabilitation Research Center, Beijing, China
3 shared publicationsJing Wang
Department of Neurobiology, School of Basic Medical Sciences, Capital Medical University, Beijing, China
2 shared publications- Yanbo Zhang
The Second Affiliated Hospital of Shandong First Medical University, Taian, CHINA
2 shared publications Zhiqing Xu
School of Rehabilitation, Capital Medical University, Neurorehabilitation Center, Beijing Boai Hospital, China Rehabilitation Research Center, Beijing, China
2 shared publicationsBin Jing
School of Biomedical Engineering, Capital Medical University, Beijing 100069, China
1 shared publication- Chenhui Zhang
School of Information and Communication Technology, Shenzhen City Polytechnic (Shenzhen Institute of Technology), Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 11 November 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (17) , 1-13
A time series long-short term codec for compression and representation
- 11 November 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (17) , 1-13
Open AccessA time series long-short term codec for compression and representation
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 483-487
Decoding Electromyographic Signal With Multiple Labels for Hand Gesture Recognition
Surface electromyography (sEMG) is a significant interaction signal in the fields of human-computer interaction and rehabilitation assessment, as it can be used for hand gesture recognition. This paper proposes a novel MLHG model to improve the robustness of sEMG-based hand gesture recognition. The model utilizes multiple labels to decode the sEMG signals from two different perspectives. In the first view, the sEMG signals are transformed into motion signals using the proposed FES-MSCNN (Feature Extraction of sEMG with Multiple Sub-CNN modules). Furthermore, a discriminator FEM-SAGE (Feature Extraction of Motion with graph SAmple and aggreGatE model) is employed to judge the authenticity of the generated motion data. The deep features of the motion signals are extracted using the FEM-SAGE model. In the second view, the deep features of the sEMG signals are extracted using the FES-MSCNN model. The extracted features of the sEMG signals and the generated motion signals are then fused for hand gesture recognition. To evaluate the performance of the proposed model, a dataset containing sEMG signals and multiple labels from 12 subjects has been collected. The experimental results indicate that the MLHG model achieves an accuracy of $99.26\%$ for within-session hand gesture recognition, $78.47\%$ for cross-time, and $53.52\%$ for cross-subject. These results represent a significant improvement compared to using only the gesture labels, with accuracy improvements of $1.91\%$ , $5.35\%$ , and $5.25\%$ in the within-session, cross-time and cross-subject cases, respectively.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 483-487
Decoding Electromyographic Signal With Multiple Labels for Hand Gesture Recognition
Surface electromyography (sEMG) is a significant interaction signal in the fields of human-computer interaction and rehabilitation assessment, as it can be used for hand gesture recognition. This paper proposes a novel MLHG model to improve the robustness of sEMG-based hand gesture recognition. The model utilizes multiple labels to decode the sEMG signals from two different perspectives. In the first view, the sEMG signals are transformed into motion signals using the proposed FES-MSCNN (Feature Extraction of sEMG with Multiple Sub-CNN modules). Furthermore, a discriminator FEM-SAGE (Feature Extraction of Motion with graph SAmple and aggreGatE model) is employed to judge the authenticity of the generated motion data. The deep features of the motion signals are extracted using the FEM-SAGE model. In the second view, the deep features of the sEMG signals are extracted using the FES-MSCNN model. The extracted features of the sEMG signals and the generated motion signals are then fused for hand gesture recognition. To evaluate the performance of the proposed model, a dataset containing sEMG signals and multiple labels from 12 subjects has been collected. The experimental results indicate that the MLHG model achieves an accuracy of $99.26\%$ for within-session hand gesture recognition, $78.47\%$ for cross-time, and $53.52\%$ for cross-subject. These results represent a significant improvement compared to using only the gesture labels, with accuracy improvements of $1.91\%$ , $5.35\%$ , and $5.25\%$ in the within-session, cross-time and cross-subject cases, respectively.
- Open Access
- 21 December 2021
- Published by Frontiers Media SA in Frontiers in Psychiatry
- Vol. 12, 824725
Corrigendum: Effect of the cPKCγ-Ng Signaling System on Rapid Eye Movement Sleep Deprivation-Induced Learning and Memory Impairment in Rats
Corrigendum: Effect of the cPKCγ-Ng Signaling System on Rapid Eye Movement Sleep Deprivation-Induced Learning and Memory Impairment in Rats
- 21 December 2021
- Published by Frontiers Media SA in Frontiers in Psychiatry
- Vol. 12, 824725
Open AccessCorrigendum: Effect of the cPKCγ-Ng Signaling System on Rapid Eye Movement Sleep Deprivation-Induced Learning and Memory Impairment in Rats
Corrigendum: Effect of the cPKCγ-Ng Signaling System on Rapid Eye Movement Sleep Deprivation-Induced Learning and Memory Impairment in Rats
- Open Access
- 29 October 2021
- Published by Frontiers Media SA in Frontiers in Psychiatry
- Vol. 12
Effect of the cPKCγ-Ng Signaling System on Rapid Eye Movement Sleep Deprivation-Induced Learning and Memory Impairment in Rats
Objective: Rapid eye movement sleep deprivation (REM-SD) can cause a decline in learning and memory and lead to changes in behavior. Therefore, REM sleep plays a key role in processes that govern learning and memory. However, the mechanism underlying REM-SD-induced learning and memory impairment is unclear and the underlying molecular signaling still needs to be identified. In the present study, we investigated the role of the cPKCγ-Ng signaling pathway in REM-SD-induced learning and memory impairment.Method: Sixty male rats were divided into Control, REM-SD, REM-SD+cPKCγ activator PMA, REM-SD+cPKCγ inhibitor H-7, and sleep revival (SR) groups. The Morris water maze was used to assess spatial learning and memory. Western blot analysis was used to detect cPKCγ total protein expression and membrane translocation levels, and Ng total protein expression and phosphorylation levels.Results: The REM-SD group performed worse on the Morris water maze test than the control group. Western blot analysis showed that cPKCγ membrane translocation and Ng phosphorylation levels were significantly lower in the REM-SD group. SR following REM-SD restored learning and memory ability, cPKCγ transmembrane translocation, and Ng phosphorylation levels, but not to levels observed before REM-SD. PMA and H-7 significantly improved/disrupted task ability as well as cPKCγ transmembrane translocation and Ng phosphorylation levels in REM-SD rats.Conclusion: The REM-SD induced learning and memory impairment in rats and may be associated with the cPKCγ-Ng signaling pathway. Specifically, activation of the cPKCγ-Ng signaling pathway may protect against REM-SD.
- 29 October 2021
- Published by Frontiers Media SA in Frontiers in Psychiatry
- Vol. 12
Open AccessEffect of the cPKCγ-Ng Signaling System on Rapid Eye Movement Sleep Deprivation-Induced Learning and Memory Impairment in Rats
Objective: Rapid eye movement sleep deprivation (REM-SD) can cause a decline in learning and memory and lead to changes in behavior. Therefore, REM sleep plays a key role in processes that govern learning and memory. However, the mechanism underlying REM-SD-induced learning and memory impairment is unclear and the underlying molecular signaling still needs to be identified. In the present study, we investigated the role of the cPKCγ-Ng signaling pathway in REM-SD-induced learning and memory impairment.Method: Sixty male rats were divided into Control, REM-SD, REM-SD+cPKCγ activator PMA, REM-SD+cPKCγ inhibitor H-7, and sleep revival (SR) groups. The Morris water maze was used to assess spatial learning and memory. Western blot analysis was used to detect cPKCγ total protein expression and membrane translocation levels, and Ng total protein expression and phosphorylation levels.Results: The REM-SD group performed worse on the Morris water maze test than the control group. Western blot analysis showed that cPKCγ membrane translocation and Ng phosphorylation levels were significantly lower in the REM-SD group. SR following REM-SD restored learning and memory ability, cPKCγ transmembrane translocation, and Ng phosphorylation levels, but not to levels observed before REM-SD. PMA and H-7 significantly improved/disrupted task ability as well as cPKCγ transmembrane translocation and Ng phosphorylation levels in REM-SD rats.Conclusion: The REM-SD induced learning and memory impairment in rats and may be associated with the cPKCγ-Ng signaling pathway. Specifically, activation of the cPKCγ-Ng signaling pathway may protect against REM-SD.
- 24 February 2021
- Published by Elsevier in Neuromodulation: Technology at the Neural Interface
- Vol. 24 (5) , 923-929
Effect of Anodic Transcranial Direct Current Stimulation Combined With Speech Language Therapy on Nonfluent Poststroke Aphasia
- 24 February 2021
- Published by Elsevier in Neuromodulation: Technology at the Neural Interface
- Vol. 24 (5) , 923-929
Effect of Anodic Transcranial Direct Current Stimulation Combined With Speech Language Therapy on Nonfluent Poststroke Aphasia
- Open Access
- 1 February 2020
- Published by Elsevier in Brain and Language
- Vol. 201, 104721
The left inferior longitudinal fasciculus supports orthographic processing: Evidence from a lesion-behavior mapping analysis
- 1 February 2020
- Published by Elsevier in Brain and Language
- Vol. 201, 104721
Open AccessThe left inferior longitudinal fasciculus supports orthographic processing: Evidence from a lesion-behavior mapping analysis
- 28 April 2019
- Published by Taylor & Francis in Neurological Research
- Vol. 41 (8) , 714-721
Application of functional near-infrared spectroscopy to explore the neural mechanism of transcranial direct current stimulation for post-stroke depression
Objectives: We investigated the neural mechanism of transcranial direct current stimulation (tDCS) in the treatment of post-stroke depression (PSD) using functional near-infrared spectroscopy (fNIRS). Methods: Twenty-six patients with PSD were randomly divided into an experimental group receiving tDCS and a control group receiving sham stimulation. The anode and cathode were placed on the left and right dorsolateral prefrontal cortex (PFC). Patients underwent fNIRS before and after treatment, combined with an emotional face sex judgment task and a ‘1-back’ working memory task to assess reaction times and relative concentration changes of oxyhemoglobin (Oxy-Hb) in the PFC. Results: Reaction times for faces showing positive emotions decreased after treatment in the experimental group (P < 0.05). For faces showing negative emotions, relative Oxy-Hb concentration changes in the PFC were higher after treatment (P < 0.05), but there was no significant difference between the experimental and the control group. Reaction times during the working memory task in the experimental group were shorter after treatment (P < 0.05), and there was a significant difference between the groups (P < 0.05). Relative Oxy-Hb concentration changes in the left PFC were significantly higher after treatment in the experimental group (P < 0.05), and concentration changes in the right PFC after treatment were significantly higher in the experimental than in the control group (P < 0.05). Discussion: tDCS may improve the processing of negative emotions and working memory in patients with PSD by enhancing aerobic metabolism in the PFC, thereby improving depressive symptoms.
- 28 April 2019
- Published by Taylor & Francis in Neurological Research
- Vol. 41 (8) , 714-721
Application of functional near-infrared spectroscopy to explore the neural mechanism of transcranial direct current stimulation for post-stroke depression
Objectives: We investigated the neural mechanism of transcranial direct current stimulation (tDCS) in the treatment of post-stroke depression (PSD) using functional near-infrared spectroscopy (fNIRS). Methods: Twenty-six patients with PSD were randomly divided into an experimental group receiving tDCS and a control group receiving sham stimulation. The anode and cathode were placed on the left and right dorsolateral prefrontal cortex (PFC). Patients underwent fNIRS before and after treatment, combined with an emotional face sex judgment task and a ‘1-back’ working memory task to assess reaction times and relative concentration changes of oxyhemoglobin (Oxy-Hb) in the PFC. Results: Reaction times for faces showing positive emotions decreased after treatment in the experimental group (P < 0.05). For faces showing negative emotions, relative Oxy-Hb concentration changes in the PFC were higher after treatment (P < 0.05), but there was no significant difference between the experimental and the control group. Reaction times during the working memory task in the experimental group were shorter after treatment (P < 0.05), and there was a significant difference between the groups (P < 0.05). Relative Oxy-Hb concentration changes in the left PFC were significantly higher after treatment in the experimental group (P < 0.05), and concentration changes in the right PFC after treatment were significantly higher in the experimental than in the control group (P < 0.05). Discussion: tDCS may improve the processing of negative emotions and working memory in patients with PSD by enhancing aerobic metabolism in the PFC, thereby improving depressive symptoms.
- 6 May 2015
- Published by Springer Nature
- p. 69-78
Heart Rate Variability Biofeedback Treatment for Post-Stroke Depression Patients: A Pilot Study
- 6 May 2015
- Published by Springer Nature
- p. 69-78
Heart Rate Variability Biofeedback Treatment for Post-Stroke Depression Patients: A Pilot Study
- 1 March 2015
- Published by Elsevier in Brain Research
- Vol. 1599, 93-102
Alteration of spontaneous neuronal activity within the salience network in partially remitted depression
- 1 March 2015
- Published by Elsevier in Brain Research
- Vol. 1599, 93-102
Alteration of spontaneous neuronal activity within the salience network in partially remitted depression
- 20 August 2009
- Vol. 122 (16) , 1901-6
Chinese word processing in nonfluent aphasic patients.
Chinese nonfluent aphasic patients experience apparent speech production deficit, but it remains less known in which part of Chinese speech production this deficit occurs. The present study aimed to examine the ability of nonfluent aphasic patients in Chinese orthography, phonological and semantic processing via two experiments. Experiment I disclosed the general pattern of deficit of Chinese nonfluent aphasic patients in speech production. Experiment II tested whether this deficit occurs in orthography, phonological or semantic processing. The present study adopted neuropsychological testing methods to compare speech production and Chinese word processing between nonfluent aphasic patients (the patient group) and normal individuals (the control group). Character reading and word reading tasks were used to test speech production. Chinese radical decision, rhyme decision and semantic decision tasks were used to examine word processing. Reaction time and the correct answer rate were collected. The patient group had a longer reaction time and was more prone to errors in both character reading and word reading tasks than was the control group. For the patient group, there was no difference between the reaction time of character reading and word reading, the error rate of the former was higher than the latter. In radical decision task the reaction time and error rate to the radical "mu " were higher in the patient group than in the control group. In the rhyme decision task, the reaction time and error rate to the rhyme "ang" were higher for the aphasic patients. In the semantic decision task the reaction time to characters in the category of animals was higher for the aphasic patients, yet the error rate was not significantly different between the two groups. Nonfluent aphasic patients seemingly have decreased speed of speech production and an increased error rate. There is a deficit in phonological processing of aphasic patients while their semantic processing may remain intact.
- 20 August 2009
- Vol. 122 (16) , 1901-6
Chinese word processing in nonfluent aphasic patients.
Chinese nonfluent aphasic patients experience apparent speech production deficit, but it remains less known in which part of Chinese speech production this deficit occurs. The present study aimed to examine the ability of nonfluent aphasic patients in Chinese orthography, phonological and semantic processing via two experiments. Experiment I disclosed the general pattern of deficit of Chinese nonfluent aphasic patients in speech production. Experiment II tested whether this deficit occurs in orthography, phonological or semantic processing. The present study adopted neuropsychological testing methods to compare speech production and Chinese word processing between nonfluent aphasic patients (the patient group) and normal individuals (the control group). Character reading and word reading tasks were used to test speech production. Chinese radical decision, rhyme decision and semantic decision tasks were used to examine word processing. Reaction time and the correct answer rate were collected. The patient group had a longer reaction time and was more prone to errors in both character reading and word reading tasks than was the control group. For the patient group, there was no difference between the reaction time of character reading and word reading, the error rate of the former was higher than the latter. In radical decision task the reaction time and error rate to the radical "mu " were higher in the patient group than in the control group. In the rhyme decision task, the reaction time and error rate to the rhyme "ang" were higher for the aphasic patients. In the semantic decision task the reaction time to characters in the category of animals was higher for the aphasic patients, yet the error rate was not significantly different between the two groups. Nonfluent aphasic patients seemingly have decreased speed of speech production and an increased error rate. There is a deficit in phonological processing of aphasic patients while their semantic processing may remain intact.