Journal of Medical Engineering and Technology最新文献

An integrated deep learning model combining 1D-UNet and LSTM for speech emotion classification. 结合1D-UNet和LSTM的语音情感分类集成深度学习模型。

Journal of Medical Engineering and Technology Pub Date : 2026-10-22 DOI: 10.1080/03091902.2026.2737129

Wang Yun, Wu Jing

{"title":"An integrated deep learning model combining 1D-UNet and LSTM for speech emotion classification.","authors":"Wang Yun, Wu Jing","doi":"10.1080/03091902.2026.2737129","DOIUrl":"https://doi.org/10.1080/03091902.2026.2737129","url":null,"abstract":"Speech emotion detection is crucial for various applications, including audio monitoring, clinical research, e-learning, entertainment, lie detection, gaming, and customer service centres. Classifying sentimental states from speech data necessitates advanced methods to achieve optimal predictive performance. Deep learning (DL) approaches have revealed efficacy in recording high-level traits of speech data and addressing categorisation challenges. This investigation aims to predict different sentimental states using speech signal exploration and DL frameworks. Specifically, we introduce two network types: (i) the 1D-UNet framework, which consists solely of deep one-dimensional CNN (1D-CNN), and (ii) the 1D-UNet-long short-term memory (1D-UNet-LSTM), which integrates the 1D-UNet construction with the LSTM recurrent network. Three databases namely RML, RAVDESS, IEMOCAP and SAVEE are utilised in the empirical analyses to assess the efficacy of the recommended networks. The 1D-UNet-LSTM outperformed the 1D-UNet framework for speech emotion detection in all databases. The 1D-UNet-LSTM network obtained 95.90%, 97.85%, 90.11%, and 86.23% mean accuracy rates achieved for RML, RAVDESS, SAVEE, and IEMOCAP databases, accordingly; whereas, the 1D-UNet framework yielded 95.19%, 96.77%, 88.82%, and 83.51% mean precision rates were achieved for RML, RAVDESS, SAVEE, and IEMOCAP databases, accordingly. The recommended networks demonstrate notable efficiency, resulting in improved accuracy rates compared to previously published outcomes when tested on the relevant databases.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-14"},"PeriodicalIF":0.0,"publicationDate":"2026-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149246595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Electrophoretic deposition of CaP-TiSiN composite coatings on 316L stainless steel: corrosion resistance and in vitro cytocompatibility. 316L不锈钢表面CaP-TiSiN复合涂层的电泳沉积：耐蚀性和体外细胞相容性。

Journal of Medical Engineering and Technology Pub Date : 2026-10-07 DOI: 10.1080/03091902.2026.2741144

Ahmed S Abbas, Ahmed Hafedh Mohammed, Mohammed Dakhil Abbas, Zaid Kareem, Mohammed Ali Abdulrehman, Ali M Flayyih

{"title":"Electrophoretic deposition of CaP-TiSiN composite coatings on 316L stainless steel: corrosion resistance and in vitro cytocompatibility.","authors":"Ahmed S Abbas, Ahmed Hafedh Mohammed, Mohammed Dakhil Abbas, Zaid Kareem, Mohammed Ali Abdulrehman, Ali M Flayyih","doi":"10.1080/03091902.2026.2741144","DOIUrl":"https://doi.org/10.1080/03091902.2026.2741144","url":null,"abstract":"The EPD technique was used to synthesize CaP-TiSiN composite coatings on 316 L stainless steel to enhance its surface mechanical, electrochemical, and biological properties. The fabricated coatings were characterized by SEM, EDS, XRD, water contact-angle determination, Vickers microhardness test, scratch adhesion test, potentiodynamic polarization, and in vitro MTT test on MC3T3-E1 osteoblast-like cells. The CaP-TiSiN composite coating possessed a dense, relatively homogeneous microstructure with uniform distribution of the constituents. The microhardness value rose from 177.0 HV of bare 316 L to 602.4 HV of the CaP-TiSiN coating, and the scratch critical load was 18.8 N. Corrosion rate dropped from 0.00057 to 0.00007 mm/year, and the water contact angle became 54.3°, which indicates improvement in wettability. In MTT test, the CaP-TiSiN-coated samples showed maximum metabolic activity at all times, which was achieved as high as 116.3% on day 5 and significantly higher than TiSiN coating (p < 0.05) and HA coating on day 5 (p = 0.041). This suggests that EPD-synthesized CaP-TiSiN composite coatings could be employed as efficient surface modifications of 316 L stainless steel in biomedicine.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-17"},"PeriodicalIF":0.0,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149128535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Validity of the garmin Forerunner 265 to predict VO2max and race performance times. garmin先行者265预测最大摄氧量和比赛成绩时间的有效性。

Journal of Medical Engineering and Technology Pub Date : 2026-10-01 DOI: 10.1080/03091902.2026.2741912

Jonathan Howard, Rebecca Ellis, C Kevin Fortner, J Andrew Doyle, Jeffrey Otis

{"title":"Validity of the garmin Forerunner 265 to predict VO2max and race performance times.","authors":"Jonathan Howard, Rebecca Ellis, C Kevin Fortner, J Andrew Doyle, Jeffrey Otis","doi":"10.1080/03091902.2026.2741912","DOIUrl":"https://doi.org/10.1080/03091902.2026.2741912","url":null,"abstract":"Advances in fitness tracker technology have led to increased measurements and predictions of physiological variables, such as VO2max and race prediction times. These data can help develop personalized exercise programs. The validity of wrist-based fitness trackers to estimate VO2max is mixed, and studies have not yet investigated race performance prediction. It was hypothesized that Garmin-estimated VO2max and race prediction times would fall within the INTERLIVE Network's consumer-level acceptability threshold (MAPE <10%), with accuracy improving after 12 weeks of use. Twenty subjects participated in 12 weeks of half-marathon training, wore a Garmin Forerunner 265 for the training program, and ran a half-marathon race. Garmin watch estimates of VO2max and race performance predictions were compared to criterion measures using paired samples t-test. Significance was set at p < 0.05. The initial mean VO2max estimate from Garmin (43.95 ± 7.99 ml/kg/min) was significantly higher than the criterion max test (41.10 ± 8.02 ml/kg/min), p = 0.009. After 12-weeks of training, estimated VO2max from Garmin (45.00 ± 7.21 ml/kg/min) was significantly higher than criterion (42.43 ± 8.54 ml/kg/min), p=.007. Garmin's race predictions for the half-marathon (129.97 ± 18.29 min) were significantly faster than the official race times (137.55 ± 21.03 min), p=.003. Despite this, mean absolute percent error of VO2max and race prediction were below 10%, indicating the Garmin Forerunner 265 may be suitable for tracking general fitness trends.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149116075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tetragrip: a functional electrical stimulation (FES) device for enhancing upper limb function in people with tetraplegia - development, technical evaluation, and pilot clinical investigation. Tetragrip：一种功能性电刺激（FES）装置，用于增强四肢瘫痪患者的上肢功能-开发，技术评估和试点临床研究。

Journal of Medical Engineering and Technology Pub Date : 2026-09-20 DOI: 10.1080/03091902.2026.2718865

Vinil Chackochan, Earl Merson, Paul Taylor, Catherine Whitmarsh, Ian Swain

{"title":"Tetragrip: a functional electrical stimulation (FES) device for enhancing upper limb function in people with tetraplegia - development, technical evaluation, and pilot clinical investigation.","authors":"Vinil Chackochan, Earl Merson, Paul Taylor, Catherine Whitmarsh, Ian Swain","doi":"10.1080/03091902.2026.2718865","DOIUrl":"https://doi.org/10.1080/03091902.2026.2718865","url":null,"abstract":"This paper describes the development and initial evaluation of Tetragrip, a five-channel functional electrical stimulation (FES) device designed to enhance upper limb function in people with C5-C7 spinal cord injury (SCI) resulting in tetraplegia. Tetragrip uses an inertial measurement unit (IMU) on the upper arm to control stimulation through opposite shoulder movements. A Finite State Machine enables users to start and stop stimulation, select grip patterns and adjust intensity. Reusable Etexsense fabric electrodes are embedded in custom Lycra sleeves and positioned over motor points to activate specific muscle groups. Clinicians preset stimulation levels, allowing users to perform \"Key\" and \"Power\" grips without complex adjustments. Initial testing with a healthy volunteer demonstrated reliable IMU control and highlighted the importance of accurate electrode placement. A pilot clinical investigation was subsequently conducted at the Duke of Cornwall Spinal Injuries Centre, Salisbury. Thirteen potential participants were identified and assessed; four met the inclusion criteria, but only two were able to meaningfully evaluate the system because of clinical factors. These participants provided positive feedback on its design and usability. The recruitment challenges encountered are discussed, while changes in SCI demographics are analysed in a companion paper.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2026-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149013143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Attention based noise-aware segmentation network (ANSN): leveraging attention mechanisms for noisy MR image segmentation. 基于注意的噪声感知分割网络（ANSN）：利用注意机制对带有噪声的MR图像进行分割。

Journal of Medical Engineering and Technology Pub Date : 2026-09-18 DOI: 10.1080/03091902.2026.2733055

Anand Swaroop Srivastava, Rishi Prakash, Ved Prakash Dubey, Sumit Tripathi

{"title":"Attention based noise-aware segmentation network (ANSN): leveraging attention mechanisms for noisy MR image segmentation.","authors":"Anand Swaroop Srivastava, Rishi Prakash, Ved Prakash Dubey, Sumit Tripathi","doi":"10.1080/03091902.2026.2733055","DOIUrl":"https://doi.org/10.1080/03091902.2026.2733055","url":null,"abstract":"There is a need of accurately segmenting the magnetic resonance (MR) images for diagnosis as well as treatment planning. It is, however, difficult due to low contrast, indistinct borders, intensity inhomogeneity, as well as acquisition noise. Rician noise in MR images reduces accuracy and reliability of segmentation of structures in images that are clinically relevant. Yet it is still challenging to maintain robustness under noisy imaging conditions. To remedy this limitation, we propose an Attention-based Noise-aware Segmentation Network (ANSN) which extends Attention U-Net model by integrating a Noise Suppression Filter (NSF) in the encoder along with attention-guided feature refinement in the decoder. The ACDC, SCD and TCGA-LGG datasets are used to evaluate the proposed framework. With ACDC at 10% Rician noise, ANSN obtains an improvement in the metrics Dice Score and Mean IoU of 6.66% and 5.34% respectively compared to the Attention U-Net. Similarly robust results are observed on the SCD dataset, as ANSN gains 35.68% Dice Score and 15.07% Mean IoU on 10% level of noise. Despite these gains, ANSN requires only 7.40 million parameters, representing an 80.2% reduction compared with Attention U-Net, while maintaining a 50.6 ms inference time on a Tesla T4 GPU.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-19"},"PeriodicalIF":0.0,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149001642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A deep learning framework for arrhythmia classification: mitigating data leakage and class imbalance in ECG analysis. 心律失常分类的深度学习框架：减轻心电分析中的数据泄漏和分类不平衡。

Journal of Medical Engineering and Technology Pub Date : 2026-09-09 DOI: 10.1080/03091902.2026.2724902

Sudeshna Sani, Dipra Mitra, Pallab Banerjee, Durgesh Srivastava

{"title":"A deep learning framework for arrhythmia classification: mitigating data leakage and class imbalance in ECG analysis.","authors":"Sudeshna Sani, Dipra Mitra, Pallab Banerjee, Durgesh Srivastava","doi":"10.1080/03091902.2026.2724902","DOIUrl":"https://doi.org/10.1080/03091902.2026.2724902","url":null,"abstract":"Accurate and timely identification of cardiac abnormalities remains essential for reducing mortality associated with life-threatening cardiac arrhythmias. However, automated diagnostic systems often struggle with imbalanced clinical data and limited generalizability. In this work, we propose an efficient deep learning framework to classify the various ECG arrhythmias based on time-frequency features generated through Continuous Wavelet Transform (CWT) and efficient VGG16 transfer learning. By avoiding data leakage through a stratified split-then-augment partitioning method, the method achieved a test accuracy of 96.05% and stable performance across five-fold cross-validation (96.0% ± 0.4%). The model achieved a macro-average F1 score of 0.933 despite class imbalance with a sensitivity that supports real-world detection needs, including ventricular fusion beat recognition. CWT improved the multi-resolution representation of non-stationary ECG signals, while architectural changes, including batch normalization, global average pooling and dropout, improved model performance without increasing computational load. The system has only 166K trainable parameters with an inference latency of ∼25-30 ms, suggesting the possible application in emergency triage, bedside monitoring, and telemedicine-assisted decision support. These findings show the feasibility of the proposed method for early cardiac event detection and providing clinical patient assistance in high-risk environments.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-15"},"PeriodicalIF":0.0,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148921388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Changes in the incidence, cause and severity of cervical spinal cord injuries over the last 30 years and the implications for biomedical research - lessons learnt from the Tetragrip project. 过去30年来颈脊髓损伤的发生率、原因和严重程度的变化及其对生物医学研究的影响——从Tetragrip项目获得的经验教训。

Journal of Medical Engineering and Technology Pub Date : 2026-09-01 DOI: 10.1080/03091902.2026.2713709

Ian Swain, Catherine Whitmarsh, Vinil Chackochan, Earl Merson, Paul Taylor

引用次数: 0

A high-accuracy RFID system for efficient management of hospital textiles: design, implementation, and performance evaluation. 用于医院纺织品高效管理的高精度RFID系统：设计、实施和性能评估。

Journal of Medical Engineering and Technology Pub Date : 2026-08-21 DOI: 10.1080/03091902.2026.2718864

Kittisak Phaebua, Kiadtisak Salayong, Montree Saowadee, Titipong Lertwiriyaprapa, Prayoot Akkaraekthalin

{"title":"A high-accuracy RFID system for efficient management of hospital textiles: design, implementation, and performance evaluation.","authors":"Kittisak Phaebua, Kiadtisak Salayong, Montree Saowadee, Titipong Lertwiriyaprapa, Prayoot Akkaraekthalin","doi":"10.1080/03091902.2026.2718864","DOIUrl":"https://doi.org/10.1080/03091902.2026.2718864","url":null,"abstract":"This paper presents an RFID-based system for hospital textile management, addressing challenges of textile loss, inventory control, and infection prevention. The system integrates an RFID gate station, handheld RFID readers, and web/mobile software for real-time textile tracking. A cylindrical reflector structure is incorporated into the gate station to enhance electromagnetic field confinement and uniformity. Simulations and measurements demonstrate improved field distribution and reduced radiation leakage, with electric-field intensity behind the reflector reduced by approximately 94.4%. The system reliably processes up to 800 RFID-tagged textiles with a minimum reading accuracy of 99.8%. Thermogravimetric analysis confirms that the selected silicone RFID tag withstands repeated high-temperature laundry processes. The software platform supports real-time monitoring, inventory management, and textile lifecycle tracking. The proposed system offers a practical and scalable solution for improving operational efficiency, reducing textile losses, and supporting infection control in healthcare environments.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-15"},"PeriodicalIF":0.0,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MI recognition by subject specific localised frequency fusion. 通过受试者特定的局部频率融合来识别MI。

Journal of Medical Engineering and Technology Pub Date : 2026-08-20 DOI: 10.1080/03091902.2026.2720510

M K M Rahman, H M Tanvir Shuvo

{"title":"MI recognition by subject specific localised frequency fusion.","authors":"M K M Rahman, H M Tanvir Shuvo","doi":"10.1080/03091902.2026.2720510","DOIUrl":"https://doi.org/10.1080/03091902.2026.2720510","url":null,"abstract":"EEG-based motor imagery (MI) discrimination is widely utilised in real-life applications, such as brain-computer interfaces (BCIs), due to its non-invasive and comparatively cost-effective nature. However, traditional BCI systems typically rely on a uniform, broad frequency band or a standardised set of sub-bands to extract features. Consequently, they fail to account for distinct physiological variability across subjects, leading to significant classification performance degradation. To address this limitation, we propose a novel framework named subject-specific localised frequency fusion (SSLFF). The proposed method systematically searches for and selects optimal frequency sub-bands , while dynamically merging complementary spectral bands. In addition to this subject-specific frequency localisation, the framework integrates a time-localised feature extraction process. Unlike traditional approaches, the proposed method can operate effectively over a broader master frequency band without experiencing performance degradation, as it automatically isolates the optimal spectral parameters for each subject. Overall, the proposed framework achieves a statistically significant improvement in classification accuracy compared to alternative traditional methods, while maintaining exceptional robustness against variations in system parameters. In short, SSLFF try to address the fact that the learning of human brain varies from person to person and it incorporates subject specific tuning not only in the spatial filter and classifier, but also in frequency band selection and localised feature extraction, leading to a superior classification performance.","PeriodicalId":39637,"journal":{"name":"Journal of Medical Engineering and Technology","volume":" ","pages":"1-19"},"PeriodicalIF":0.0,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

News and product update. 新闻和产品更新。

Journal of Medical Engineering and Technology Pub Date : 2026-08-20 DOI: 10.1080/03091902.2026.2709922

John Fenner

引用次数: 0