Search Results (104)

In recent years, research on human activity recognition (HAR) on smartphones has received extensive attention due to its portability. However, the discrimination issues between similar activities such as leaning forward and walking forward, as well as going up and down stairs, are hard to deal with. This paper conducts HAR based on the sensors of smartphones, i.e., accelerometers and gyroscopes. First, a feature extraction method for sensor data from both the time domain and frequency domain is designed to obtain more than 300 features, aiming to enhance the accuracy and stability of recognition. Then, the LightGBM (version 4.5.0) algorithm is utilized to comprehensively analyze the above-mentioned extracted features, with the goal of improving the accuracy of similar activity recognition. Through simulation experiments, it is demonstrated that the feature extraction method proposed in this paper has improved the accuracy of HAR. Compared with classical machine learning algorithms such as random forest (version 1.5.2) and XGBoost (version 2.1.3), the LightGBM algorithm shows improved performance in terms of the accuracy rate, which reaches 94.98%. Moreover, after searching for the model parameters using grid search, the prediction accuracy of LightGBM can be increased to 95.35%. Finally, using feature selection and dimensionality reduction, the efficiency of the model is further improved, achieving a 70.14% increase in time efficiency without reducing the accuracy rate. Full article

Objectives: Interval block resistance training (IBRT) and circuit resistance training (CRT) are periodization models aimed at enhancing neuromuscular and metabolic adaptations. This study aims to evaluate the effects of a 12-week IBRT program compared to CRT on body composition, muscle strength, speed, functional capacity, and autonomic recovery in young Chilean adults. Methods: A randomized, parallel, double-blind study was conducted with 30 participants assigned to IBRT (n = 15) or CRT (n = 15). Assessments included body mass index (BMI), waist circumference, right-hand grip strength, the running anaerobic sprint test (RAST), the 6 min walk test (6 MWT), and heart rate variability (HRV) indices: low-frequency to high-frequency ratio (LF/HF) and root mean square of successive differences (RMSSD, a time-domain HRV metric reflecting parasympathetic activity). Statistical analyses included t-tests and ANCOVA. Results: Groups were similar in age (IBRT: 25.2 ± 3.19; CRT: 23.27 ± 3.69, p = 0.14) and BMI (IBRT: 21.56 ± 2.22; CRT: 22.36 ± 1.70 kg/m², p = 0.40). Both groups improved significantly in waist circumference (IBRT: −1.85%; CRT: −2.37%), grip strength (IBRT: +5.47%; CRT: +4.02%), RAST (IBRT: −2.67%; CRT: −1.04%), 6 MWT (IBRT: +4.53%; CRT: +2.17%), LF/HF (IBRT: −11.43%; CRT: −5.11%), and RMSSD (IBRT: +5.36%; CRT: +3.81%) (all p ≤ 0.01). IBRT produced significantly greater gains in 6 MWT (B = 19.51, 95% CI: 0.79 to 38.23, p = 0.04). Conclusions: Both IBRT and CRT effectively improved body composition, muscle strength, speed, functional capacity, and autonomic recovery. However, IBRT demonstrated a superior effect on aerobic capacity. Full article

This systematic review, conducted in accordance with PRISMA guidelines and registered in PROSPERO (CRD42024619693), aimed to evaluate the effects of physical exercise interventions on muscle function and fall risk in older adults with and without sarcopenia. Methods: A comprehensive search of PubMed and Web of Science databases identified 11 randomized controlled trials (RCTs) published between 2015 and 2025. A total of 792 participants (mean age 75.13 ± 4.71 years; 65.53% women, 34.47% men) were included. Interventions varied in type—strength, balance, aerobic, and multi-component programs—with a minimum duration of 8 weeks. Results: The reviewed studies showed that physical exercise interventions significantly improved neuromuscular function, physical performance, and postural control in older adults. Positive effects were observed in gait speed, stair-climbing ability, grip strength, muscle mass, and bone density. Specific modalities such as Tai Chi improved postural control and neuromuscular response; dynamic resistance and functional training increased muscle strength and improved posture; Nordic walking reduced postural sway; and multi-component and combined walking-resistance training enhanced mobility and force efficiency. Programs integrating strength and balance components yielded the most consistent benefits. However, reporting on FITT (Frequency, Intensity, Time, Type) principles was limited across studies. Conclusions: Exercise interventions are effective in improving neuromuscular outcomes and reducing fall risk in older adults, both with and without sarcopenia. The findings support the need for tailored, well-structured programs and greater methodological standardization in future research to facilitate broader clinical application and maximize health outcomes. Full article

This study proposes a novel parallel denoising and temperature compensation fusion algorithm for MEMS ring gyroscopes. First, the particle swarm optimization (PSO) algorithm is used to optimize the time-varying filter-based empirical mode decomposition (TVFEMD), obtaining optimal decomposition parameters. Then, TVFEMD decomposes the gyroscope output signal into a series of product function (PF) signals and a residual signal. Next, sample entropy (SE) is employed to classify the decomposed signals into three categories: noise segment, mixed segment, and feature segment. According to the parallel model structure, the noise segment is directly discarded. Meanwhile, time–frequency peak filtering (TFPF) is applied to denoise the mixed segment, while the feature segment undergoes compensation. For compensation, the football team training algorithm (FTTA) is used to optimize the parameters of the long short-term memory (LSTM) neural network, forming a novel FTTA-LSTM architecture. Both simulations and experimental results validate the effectiveness of the proposed algorithm. After processing the MEMS gyroscope output signal using the PSO-TVFEMD-SE-TFPF denoising algorithm and the FTTA-LSTM temperature drift compensation model, the angular random walk (ARW) of the MEMS gyroscope is reduced to 0.02°/√h, while the bias instability (BI) decreases to 2.23°/h. Compared to the original signal, ARW and BI are reduced by 99.43% and 97.69%, respectively. The proposed fusion-based temperature compensation method significantly enhances the temperature stability and noise performance of the gyroscope. Full article

Background/Objectives: After spinal cord injury (SCI), poor dorsiflexor control and involuntary plantar-flexor contraction impair walking. As whole-body vibration (WBV) improves voluntary muscle activation and modulates reflex excitability, it may improve ankle control. In this study, the dosage effects of WBV on walking speed, dorsiflexion, and spinal reflex excitability were examined. Methods: Sixteen people with chronic motor-incomplete SCI participated in this randomized sham-control wash-in study. Two weeks of sham stimulation (wash-in phase) were followed by either 2 weeks of eight repetitions (short bout) or sixteen repetitions of WBV (long bout; intervention phase) per session. Walking speed, ankle angle at mid-swing, and low-frequency depression of the soleus H-reflex were measured before and after the wash-in phase and before and after the intervention phase. Results: A significant dosage effect of WBV was not observed on any of the measures of interest. There were no between-phase or within-phase differences in ankle angle during the swing phase or in low-frequency depression. When dosage groups were pooled together, there was a significant change in walking speed during the intervention phase (mean = 0.04 m/s, standard deviation = 0.06, p = 0.02). There was not a significant correlation between overall change in walking speed and dorsiflexion angle or low-frequency depression during the study. Conclusions: Whole-body vibration did not have a dosage-dependent effect on dorsiflexion during the swing phase or on spinal reflex excitability. Future studies assessing the role of corticospinal tract (CST) descending drive on increased dorsiflexor ability and walking speed are warranted. Full article

The aging population has created a significant challenge affecting the world; social and healthcare systems need to ensure elderly individuals receive the necessary care services to improve their quality of life and maintain their independence. In response to this need, developing integrated digital solutions, such as IoT based wearable devices combined with artificial intelligence applications, offers a technological platform for creating Ambient Intelligence (AI) and Assisted Living (AAL) environments. These advancements can help reduce hospital admissions and lower healthcare costs. In this context, this article presents an IoT application based on MEMS (micro electro-mechanical systems) sensors integrated into a state-of-the-art microcontroller (STM55WB) for recognizing the movements of older individuals during daily activities. human activity recognition (HAR) is a field within computational engineering that focuses on automatically classifying human actions through data captured by sensors. This study has multiple objectives: to recognize movements such as grasping, leg flexion, circular arm movements, and walking in order to assess the motor skills of older individuals. The implemented system allows these movements to be detected in real time, and transmitted to a monitoring system server, where healthcare staff can analyze the data. The analysis methods employed include machine learning algorithms to identify movement patterns, statistical analysis to assess the frequency and quality of movements, and data visualization to track changes over time. These approaches enable the accurate assessment of older people’s motor skills, and facilitate the prompt identification of abnormal situations or emergencies. Additionally, a user-friendly technological solution is designed to be acceptable to the elderly, minimizing discomfort and stress associated with using technology. Finally, the goal is to ensure that the system is energy-efficient and cost-effective, promoting sustainable adoption. The results obtained are promising; the model achieved a high level of accuracy in recognizing specific movements, thus contributing to a precise assessment of the motor skills of the elderly. Notably, movement recognition was accomplished using an artificial intelligence model called Random Forest. Full article

Accurate power load forecasting plays an important role in smart grid analysis. To improve the accuracy of forecasting through the three-level “decomposition–optimization–prediction” innovation, this study proposes a prediction model that integrates complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the improved sparrow search algorithm (ISSA), a convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM). A series of simpler intrinsic mode functions (IMFs) with different frequency characteristics can be decomposed by CEEMDAN from data, then each IMF is reconstructed based on calculating the sample entropy of each IMF. The ISSA introduces three significant enhancements over the standard sparrow search algorithm (SSA), including that the initial distribution of the population is determined by the optimal point set, the position of the discoverer is updated by the golden sine strategy, and the random walk of the population is enhanced by the Lévy flight strategy. By the optimization of the ISSA to the parameters of the CNN-BiLSTM model, integrating the prediction results of the reconstructed IMFs in the sub-models can obtain the final prediction result of the data. Through the performance indexes of the designed prediction model, the application case results show that the proposed combined prediction model has a smaller prediction error and higher prediction accuracy than the eight comparison models. Full article

The issue of personal safety for crime prevention has become a significant societal concern. Existing software on smartwatches developed for personal protection might provide GPS location tracking and emergency reporting, but this is limited to proactively detecting and responding to actual at-risk situations. This paper presents a real-time motion detection algorithm for smartwatches that utilizes an accelerometer to identify at-risk movements when a wearer is under threat. Daily activities, including walking, running, desk work, and being threatened, are distinguished by a machine learning-based alarm application. A total of 5534 data points across four classes were collected from experiments. The proposed 1D-CNN model exhibited the highest performance in comparison with SVM, k-NN, random forest, SGD. Additionally, our comparative analysis of using time-domain versus frequency-domain data in machine learning revealed that frequency-domain features offer advantages in both accuracy and real-time performance. Finally, the proposed inference model was implemented as a smartwatch application that can detect at-risk situations in real time. The application was tested in real-world scenarios, showcasing the effectiveness of personal safety. Full article

In the last decade, substantial progress has been made to improve the performance of optical gyroscopes for inertial navigation applications in terms of critical parameters such as bias stability, scale factor stability, and angular random walk (ARW). Specifically, resonant fiber optic gyroscopes (RFOGs) have emerged as a viable alternative to widely popular interferometric fiber optic gyroscopes (IFOGs). In a conventional RFOG, a single-wavelength laser source is used to generate counter-propagating waves in a ring resonator, for which the phase difference is measured in terms of the resonant frequency shift to obtain the rotation rate. However, the primary limitation of RFOG performance is the bias drift, which can be attributed to nonreciprocal effects such as Rayleigh backscattering, back-reflections, polarization instabilities, Kerr nonlinearity, and environmental fluctuations. In this paper, we review the challenges and opportunities of achieving performance enhancement in RFOGs. Full article

The evaluation of gait biomechanics using portable inertial measurement units (IMUs) offers real-time feedback and has become a crucial tool for detecting gait disorders. However, many of these devices have not yet been fully validated. The aim of this study was to assess the concurrent validity and relative reliability of the RunScribe™ system for measuring spatiotemporal gait parameters during walking. A total of 460 participants (age: 36 ± 13 years; height: 173 ± 9 cm; body mass: 70 ± 13 kg) were asked to walk on a treadmill at 5 km·h⁻¹. Spatiotemporal parameters of step frequency (SF), step length (SL), step time (ST), contact time (CT), swing time (SwT), stride time (StT), stride length (StL) and normalized stride length (StL%) were measured through RunScribe™ and OptoGait™ systems. Bland–Altman analysis indicated small systematic biases and random errors for all variables. Pearson correlation analysis showed strong correlations (0.70–0.94) between systems. The intraclass correlation coefficient supports these results, except for contact time (ICC = 0.64) and swing time (ICC = 0.34). The paired t-test showed small differences in SL, StL and StL% (≤0.25) and large in CT and SwT (1.2 and 2.2, respectively), with no differences for the rest of the variables. This study confirms the accuracy of the RunScribe™ system for assessing spatiotemporal parameters during walking, potentially reducing the barriers to continuous gait monitoring and early detection of gait issues. Full article

Background/Objectives: This study aimed to assess and compare the effects of an adapted taekwondo (TKD) program, multicomponent training (MCT), walking exercise (WE), and inactive control group (CG) on blood pressure, morphological variables, frequency of food consumption, cognitive status, health-related quality of life (HRQoL), physical fitness tests, and postural balance in independent older females. Methods: A randomized controlled trial study was conducted with the following groups: TKD (n = 13), MCT (n = 12), WE (n = 12), and CG (n = 14), considering three/weekly 60-min/sessions for 16-weeks. A two-factor mixed analysis of the variance model with repeated measures was performed. Results: TKD improved significantly more in phonetic fluency (p = 0.021; ES = 1.89) than WE and in general health (p = 0.033; ES = 1.11) than CG. Both TKD and MCT improved significantly more than CG in the 30 s chair stand, arm curl, chair sit-and-reach, timed up-and-go, maximal isometric handgrip strength, and postural balance for the eyes closed condition in the area and anteroposterior velocity (p < 0.05). Conclusions: Only TKD improved the area (p = 0.008; ES = 1.00) and mediolateral velocity (p = 0.019; ES = 0.79) for the eyes open condition, and mediolateral velocity (p = 0.021; ES = 1.57) for the eyes closed condition. Blood pressure, morphological variables, and food consumption frequency showed no significant intragroup or intergroup interactions. TKD equivalently improved HRQoL and physical fitness to MCT, with better postural balance in older females. Full article

This paper presents a comprehensive optimization of an outer frame anchor disk resonator gyroscope (DRG) with enhanced resistance to vibration and shock, achieved by increasing the resonant frequency of the tub and translation modes. Furthermore, the wineglass mode retains a high quality factor, enhancing sensitivity and reducing the angle random walk (ARW). The performance of the proposed DRG is analyzed using dynamic equations, and its structural parameters are optimized through finite element analysis (FEA). The prototype device was fabricated using a two-mask silicon-on-insulator (SOI) process on (100) single-crystal silicon (SCS), which is better suited for complementary metal-oxide–semiconductor (CMOS) integration compared to (111) SCS. Experimental results show an ARW of $0.63°/\sqrt{\mathrm{h}}$ and a bias instability (BI) of $7.7°/\mathrm{h}$, with no significant performance degradation observed under vibrational environments, indicating potential for tactical-grade performance. Full article

Background: Motor impairments limit the functional abilities of patients after stroke; it is important to identify low-cost rehabilitation avenues. The aim of this study is to determine the effectiveness of thermal stimulation in addition to conventional therapy for functional recovery in post-stroke patients. Methods: An electronic search was performed in the MEDLINE, Scopus, Web of Science, EMBASE, CINAHL, SPORTDiscus, Epistemonikos, LILACS, and PEDro databases. The eligibility criterion was randomized clinical trials that analyzed the clinical effects of thermal stimulation plus conventional therapy. Two authors independently performed the search, study selection, data extraction, and risk of bias assessment. Results: Eight studies met the eligibility criteria, and six studies were included in the quantitative synthesis. For thermal stimulation plus conventional therapy versus conventional therapy alone, the mean difference (MD) for function was 6.92 points (95% CI = 4.36–9.48; p < 0.01), for motor function was 6.31 points (95% CI = 5.18–7.44; p < 0.01), for balance was 4.41 points (95% CI = −2.59–11.4; p = 0.22), and for walking was 1.01 points (95% CI = 0.33–1.69; p < 0.01). For noxious thermal stimulation versus innocuous thermal stimulation, the MD for activities of daily living was 1.19 points (95% CI = −0.46–2.84; p = 0.16). Conclusions: In the short term, adding thermal stimulation to conventional therapy showed statistically significant differences in functional recovery in post-stroke patients. The quality of evidence was high to very low according to GRADE rating. The studies included varied in the frequency and dosage of thermal stimulation, which may affect the consistency and generalizability of the results. A larger quantity and a better quality of clinical studies are needed to confirm our findings. PROSPERO registration: CRD42023423207. Full article

Background: Detraining refers to the decline in physical fitness that occurs after the cessation of exercise, compromising the adaptations resulting from regular exercise training. To understand how long the benefits acquired from an exercise program can be maintained, the present study evaluated the detraining effects of a 4–week exercise cessation period in older adults who performed combined training at various weekly frequencies for 12 weeks. Methods: This randomized controlled trial assigned participants to one of two training programs: a combined training program twice a week (CT2) or four times a week (CT4) over a period of 12 weeks, followed by a four–week detraining period. The resistance training consisted of six bodyweight exercises, while the aerobic training involved either walking or running. Both the CT2 and CT4 groups completed the same total training volume and overload each week; the only difference was the number of training sessions per week. Assessments were conducted at baseline, after the training period, and after the detraining period, and included the 30–s and five–repetition chair–stand tests, isometric handgrip strength, body mass index (BMI), waist circumference, and waist–to–height ratio. Results: Thirty–one participants completed the study (CT2: 17 and CT4: 14). The groups presented similar attendance records during the training period (CT2: 96 ± 18% versus CT4: 94 ± 19%). After the 12–week training period, CT2 and CT4 improved lower limb strength, CT2 improved upper limb strength, and CT4 reduced waist circumference and waist–to–height ratio compared to baseline. After the 4–week detraining period, the lower limb strength remained improved in both groups (CT2: 4 ± 1 repetition; p < 0.001 and CT4: 4 ± 1 repetition; p < 0.001) when compared to the corresponding baseline values. The handgrip strength decreased in CT2 compared to post–training values. And the body composition benefit in CT4 was not sustained after detraining. Conclusions: The effects of 4 weeks of detraining after 12 weeks of training performed two or four times per week are similar on some but not all health-related physical fitness parameters. Full article

Background: Stroke survivors often experience autonomic nervous system (ANS) dysfunction. While Transcranial Direct Current Stimulation (tDCS) has been shown to modulate the ANS when applied to the left hemisphere, its effects on the right hemisphere remain unexplored. Objective: We aimed to compare the effects of tDCS applied to both the injured and the contralateral hemispheres on heart rate variability (HRV) and functional capacity in individuals post-stroke. Methods: Twenty individuals with cerebral hemisphere lesions (ten with right-hemisphere lesions and ten with left-hemisphere lesions) were randomized into four groups: anodal and sham tDCS on the left temporal cortex (T3) and anodal and sham tDCS on the right temporal cortex (T4). HRV was assessed before the intervention, after the six-minute walk test (6MWT), and following tDCS. HRV data were categorized into frequency ranges: low frequency (LF), high frequency (HF), and sympathovagal balance. The 6MWT (meters) was conducted both pre- and post-tDCS. Results: In individuals with right-hemisphere lesions, a higher global LF value was observed (right side: 71.4 ± 16.8 nu vs. left side: 65.7 ± 17.3 nu; p = 0.008), as well as lower values of the HF component (right side: 29.5 ± 18.9 nu vs. left side: 34.0 ± 17.4 nu; p = 0.047), consequently exhibiting higher global values of the low/high-frequency ratio (right side: 3.9 ± 2.8 vs. left side: 2.9 ± 2.4). Regarding the stimulation site, tDCS over T3 led to a lower overall value of the low/high-frequency ratio (left hemisphere: 3.0 ± 2.2 vs. right hemisphere: 3.7 ± 2.9; p = 0.040) regardless of the lesion location. A significant increase in the distance covered in the 6MWT was observed for individuals with lesions in both hemispheres after tDCS at T3. Conclusions: Participants with right-hemisphere lesions exhibited superior global sympathetic autonomic nervous system activity. When the tDCS was applied on the left hemisphere, it maintained lower sympathovagal balance values and improved functional capacity regardless of the hemisphere affected by the stroke. Full article