Human Pattern Recognition Research Articles

Ultrasensitive electrospinning fibrous strain sensor with synergistic conductive network for human motion monitoring and human-computer interaction

With the rapid development of wearable electronic skin technology, flexible strain sensors have shown great application prospects in the fields of human motion and physiological signal detection, medical diagnostics, and human-computer interaction owing to their outstanding sensing performance. This paper reports a strain sensor with synergistic conductive network, consisting of stable carbon nanotube dispersion (CNT) layer and brittle MXene layer by dip-coating and electrostatic self-assembly method, and breathable three-dimensional (3D) flexible substrate of thermoplastic polyurethane (TPU) fibrous membrane prepared through electrospinning technology. The MXene/CNT@PDA-TPU (MC@p-TPU) flexible strain sensor had excellent air permeability, wide operating range (0–450 %), high sensitivity (Gauge Factor, GFmax = 8089.7), ultra-low detection limit (0.05 %), rapid response and recovery times (40 ms/60 ms), and excellent cycle stability and durability (10,000 cycles). Given its superior strain sensing capabilities, this sensor can be applied in physiological signals detection, human motion pattern recognition, and driving exoskeleton robots. In addition, MC@p-TPU fibrous membrane also exhibited excellent photothermal conversion performance and can be used as a wearable photo-heater, which has far-reaching application potential in the photothermal therapy of human joint diseases.

Research on exoskeleton compliance control strategy based on dual interaction torque split phase control method.

Human gait pattern recognition and compliance control are key technologies for achieving high coordination and assistance between exoskeleton robots and human movements. In order to improve the adaptability of exoskeleton robots to the human body, this paper proposes an exoskeleton compliance control strategy based on dual interaction torque phase separation control method. A support phase swing phase split control strategy based on dual interaction torque is proposed. Utilize the interaction force of human joints and adopt a model-based method to control the support phase. By utilizing the interaction force of exoskeleton joints and using a torque closed-loop method to control the swing phase, a multi-state control method of motion is achieved. A lower limb exoskeleton knee joint testing platform is built to verify the proposed human gait recognition The effectiveness of human-machine interaction force identification and human-machine coupling system compliance control technology. The proposed control method can effectively adjust joint torque, enabling the exoskeleton robot to maintain balance and stability during the entire walking phase.

Solving puzzles using knowledge-based automation: biomimicry of human solvers

The human brain’s remarkable efficiency in solving puzzles through pictorial information processing serves as a valuable inspiration for computational puzzle solving. In this study, we present a nucleation algorithm for automated puzzle solving, developed based on statistical analysis of an empirical database. This algorithm effectively solves puzzles by choosing pieces with infrequent and iridescent edges as nucleation centers, followed by the identification of neighboring pieces with high resemblances from the remaining puzzle pieces. For the 8 different pictures examined in this study, both empirical data and computer simulations consistently demonstrate a power-law relationship between solving time and the number of puzzle pieces, with an exponent less than 2. We explain this relationship through the nucleation model and explore how the exponent is influenced by the color pattern of the puzzle picture. Moreover, our investigation of puzzle-solving processes reveals distinct principal pathways, akin to protein folding behavior. Our study contributes to the development of a cognitive model for human puzzle solving and color pattern recognition.

Biosensor-Driven IoT Wearables for Accurate Body Motion Tracking and Localization.

The domain of human locomotion identification through smartphone sensors is witnessing rapid expansion within the realm of research. This domain boasts significant potential across various sectors, including healthcare, sports, security systems, home automation, and real-time location tracking. Despite the considerable volume of existing research, the greater portion of it has primarily concentrated on locomotion activities. Comparatively less emphasis has been placed on the recognition of human localization patterns. In the current study, we introduce a system by facilitating the recognition of both human physical and location-based patterns. This system utilizes the capabilities of smartphone sensors to achieve its objectives. Our goal is to develop a system that can accurately identify different human physical and localization activities, such as walking, running, jumping, indoor, and outdoor activities. To achieve this, we perform preprocessing on the raw sensor data using a Butterworth filter for inertial sensors and a Median Filter for Global Positioning System (GPS) and then applying Hamming windowing techniques to segment the filtered data. We then extract features from the raw inertial and GPS sensors and select relevant features using the variance threshold feature selection method. The extrasensory dataset exhibits an imbalanced number of samples for certain activities. To address this issue, the permutation-based data augmentation technique is employed. The augmented features are optimized using the Yeo-Johnson power transformation algorithm before being sent to a multi-layer perceptron for classification. We evaluate our system using the K-fold cross-validation technique. The datasets used in this study are the Extrasensory and Sussex Huawei Locomotion (SHL), which contain both physical and localization activities. Our experiments demonstrate that our system achieves high accuracy with 96% and 94% over Extrasensory and SHL in physical activities and 94% and 91% over Extrasensory and SHL in the location-based activities, outperforming previous state-of-the-art methods in recognizing both types of activities.

Novel Deep Learning Approach for Predicting Stock Market Trends

Stock Market Prediction a Major Achievement in financial markets is precisely forecasting stock market trends, which remains a considerable hurdle. Deep learning, a subset of machine learning, has grown to be a potent tool for untangling complex relationships within data. What distinguishes deep learning is its capacity to handle large amounts of data, unwrinkle difficult characteristics, and adapt to dynamic structures, all while unearthing concealed truths. Deep learning, at its core, is predicated on artificial neural networks that simulate human brain learning and pattern recognition capabilities, making it ideal for analyzing financial data. Through novel profound neural systems, the strategy applies a varied collection of the distributed showcase information, including, but not limited to, authentic stock costs, trading volumes, and calculations extracted from news sources. Keywords— stock advertise patterns, back, profound learning, designs, authentic information, design acknowledgment, sentiments.

Retracted: Human Motion Representation and Motion Pattern Recognition Based on Complex Fuzzy Theory

Retracted: Human Motion Representation and Motion Pattern Recognition Based on Complex Fuzzy Theory

Deep Learning for Electromyographic Lower-Limb Motion Signal Classification Using Residual Learning.

Electromyographic (EMG) signals have gained popularity for controlling prostheses and exoskeletons, particularly in the field of upper limbs for stroke patients. However, there is a lack of research in the lower limb area, and standardized open-source datasets of lower limb EMG signals, especially recording data of Asian race features, are scarce. Additionally, deep learning algorithms are rarely used for human motion intention recognition based on EMG, especially in the lower limb area. In response to these gaps, we present an open-source benchmark dataset of lower limb EMG with Asian race characteristics and large data volume, the JJ dataset, which includes approximately 13,350 clean EMG segments of 10 gait phases from 15 people. This is the first dataset of its kind to include the nine main muscles of human gait when walking. We used the processed time-domain signal as input and adjusted ResNet-18 as the classification tool. Our research explores and compares multiple key issues in this area, including the comparison of sliding time window method and other preprocessing methods, comparison of time-domain and frequency-domain signal processing effects, cross-subject motion recognition accuracy, and the possibility of using thigh and calf muscles in amputees. Our experiments demonstrate that the adjusted ResNet can achieve significant classification accuracy, with an average accuracy rate of 95.34% for human gait phases. Our research provides a valuable resource for future studies in this area and demonstrates the potential for ResNet as a robust and effective method for lower limb human motion intention pattern recognition.

Arabic Character Recognition Using CNN LeNet-5

The human handwriting pattern is one of the research areas of pattern recognition; it is very complex. Therefore, research in this field has become quite popular. Moreover, human handwriting pattern recognition is needed for several things, one of them being character recognition. Recognition of Arabic handwriting is complex because everyone has different characteristics in writing and Arabic characters have quite abstract shapes and patterns. From previous research, Convolutional Neural Network (CNN), a deep learning-based algorithm, has a fairly high accuracy value when used for public datasets such as AHDB and private datasets. In this study, private datasets are used with a fairly high level of complexity because the respondents appointed to write Arabic letters come from different age categories. The CNN architecture used in this research is the architecture developed by Yan LeCun known as LeNet-5. The local dataset used was 8400 images, with details of 6720 for training data (each letter has 240 images) and 1680 for testing data (each letter has 60 images). The total respondents who wrote Arabic script were 30 people, and each person wrote each letter ten times. The accuracy obtained is 81% higher than in previous studies. The following study will test a number of additional CNN architectures to increase the accuracy of the results. In addition to accuracy, this study will also calculate the misclassification rate, root mean square error, and mean absolute error.

Fine semantic segmentation of hands for human functional pattern recognition in IADLs using deep learning

AbstractBackgroundAlzheimer’s Disease (AD) is an irreversible degenerative brain disease and the most common cause of dementia, in the elderly population (age 65 and above) although people younger may develop the disease (Clemmensen, 2020). AD is characterized by impairment in behavior and cognition which eventually obstruct the Instrumental Activities of Daily Living (IADL) (Kumar, 2022). Researchers have predicted functional capacity by assessing IADL as they are strongly associated with cognitive impairment. With the availability of big data and public repositories of multimedia data such as images and videos, artificial intelligence algorithms have been used in classifying and making informed decisions that could help in disease prediction and monitoring. In the context of early diagnosis of Alzheimer, researchers have worked with machine learning techniques applied to neuroimaging for AD classification (Lama, 2021). Researchers and practitioners often use Activity of Daily Living to monitor independent‐living senior citizens’ self‐care ability, wellness status, and disease progression (Zhu, 2021). Automating the assessments of IADL will ease the evaluation of functional and cognitive function and strengthen the prediction of AD.MethodOur work approaches the timely detection and diagnosis of AD by exploring the deficiency in hand dexterity and visuospatial skills while performing IADL using egocentric videos. Therefore, in this work, we propose a fine semantic segmentation of hands, optimizing the predictions at the level of the relationship between pixels in a deep learning method. We trained the optimized RefineNet‐Pix convolutional neural network, obtaining a higher accuracy in the segmentation of semantic maps of hands.ResultsWith the optimization of RefineNet‐Pix we obtained an accuracy higher than 87.9% (Urooj, 2018) in the semantic segmentation of hands. By integrating the RefineNet‐Pix results to the base model for human functional pattern recognition, we obtain an accuracy higher than 74% with respect to the base model (Yemisi, 2022).ConclusionThe optimized RefineNet‐Pix model segments pixel‐wise the hand regions in egocentric videos, providing hand motion information that can be used to classify impairment based on human functional patterns. Optimization of these models is a way forward in building a technological device for the support of Alzheimer’s diagnosis.

Fine semantic segmentation of hands for human functional pattern recognition in IADLs using deep learning

AbstractBackgroundAlzheimer’s Disease (AD) is an irreversible degenerative brain disease and the most common cause of dementia, in the elderly population (age 65 and above) although people younger may develop the disease (Clemmensen, 2020). AD is characterized by impairment in behavior and cognition which eventually obstruct the Instrumental Activities of Daily Living (IADL) (Kumar, 2022). Researchers have predicted functional capacity by assessing IADL as they are strongly associated with cognitive impairment. With the availability of big data and public repositories of multimedia data such as images and videos, artificial intelligence algorithms have been used in classifying and making informed decisions that could help in disease prediction and monitoring. In the context of early diagnosis of Alzheimer, researchers have worked with machine learning techniques applied to neuroimaging for AD classification (Lama, 2021). Researchers and practitioners often use Activity of Daily Living to monitor independent‐living senior citizens’ self‐care ability, wellness status, and disease progression (Zhu, 2021). Automating the assessments of IADL will ease the evaluation of functional and cognitive function and strengthen the prediction of AD.MethodOur work approaches the timely detection and diagnosis of AD by exploring the deficiency in hand dexterity and visuospatial skills while performing IADL using egocentric videos. Therefore, in this work, we propose a fine semantic segmentation of hands, optimizing the predictions at the level of the relationship between pixels in a deep learning method. We trained the optimized RefineNet‐Pix convolutional neural network, obtaining a higher accuracy in the segmentation of semantic maps of hands.ResultWith the optimization of RefineNet‐Pix we obtained an accuracy higher than 87.9% (Urooj, 2018) in the semantic segmentation of hands. By integrating the RefineNet‐Pix results to the base model for human functional pattern recognition, we obtain an accuracy higher than 74% with respect to the base model (Yemisi, 2022).ConclusionThe optimized RefineNet‐Pix model segments pixel‐wise the hand regions in egocentric videos, providing hand motion information that can be used to classify impairment based on human functional patterns. Optimization of these models is a way forward in building a technological device for the support of Alzheimer’s diagnosis.

Human Activity Behavioural Pattern Recognition in Smart Home with Long-Hour Data Collection

Human Activity Behavioural Pattern Recognition in Smart Home with Long-Hour Data Collection

A new method proposed for realizing human gait pattern recognition: Inspirations for the application of sports and clinical gait analysis

BackgroundFinding the best subset of gait features among biomechanical variables is considered very important because of its ability to identify relevant sports and clinical gait pattern differences to be explored under specific study conditions. This study proposes a new method of metaheuristic optimization-based selection of optimal gait features, and then investigates how much contribution the selected gait features can achieve in gait pattern recognition. MethodsFirstly, 800 group gait datasets performed feature extraction to initially eliminate redundant variables. Then, the metaheuristic optimization algorithm model was performed to select the optimal gait feature, and four classification algorithm models were used to recognize the selected gait feature. Meanwhile, the accuracy results were compared with two widely used feature selection methods and previous studies to verify the validity of the new method. Finally, the final selected features were used to reconstruct the data waveform to interpret the biomechanical meaning of the gait feature. ResultsThe new method finalized 10 optimal gait features (6 ankle-related and 4-related knee features) based on the extracted 36 gait features (85 % variable explanation) by feature extraction. The accuracy in gait pattern recognition among the optimal gait features selected by the new method (99.81 % ± 0.53 %) was significantly higher than that of the feature-based sorting of effect size (94.69 % ± 2.68 %), the sequential forward selection (95.59 % ± 2.38 %), and the results of previous study. The interval between reconstructed waveform-high and reconstructed waveform-low curves based on the selected feature was larger during the whole stance phase. SignificanceThe selected gait feature based on the proposed new method (metaheuristic optimization-based selection) has a great contribution to gait pattern recognition. Sports and clinical gait pattern recognition can benefit from population-based metaheuristic optimization techniques. The metaheuristic optimization algorithms are expected to provide a practical and elegant solution for sports and clinical biomechanical feature selection with better economy and accuracy.

Human Motion Pattern Recognition Based on Nano-sensor and Deep Learning

A human motion pattern recognition algorithm based on Nano-sensor and deep learning is studied to recognize human motion patterns in real time and with high accuracy. First, human motion data are collected by micro electro mechanical system, and the noise in such data is filtered by smoothing filtering method to obtain high-quality motion data. Second, key time-domain features are extracted from high-quality motion data. Finally, after fusing and processing the key time-domain features, it is input into the deep long and short-term memory (LSTM) neural network to build a deep LSTM human motion pattern recognition model and complete human motion pattern recognition. The results show that the proposed algorithm can realize the recognition of various motion patterns with high accuracy of data acquisition, the average recognition accuracy is 94.8%, the average recall reaches 89.7%, and the F1 score of the algorithm are high, and the recognition time consuming is short, which can realize accurate and efficient human motion pattern recognition and provide guarantee for effective monitoring of the target human motion health.

Human motion pattern recognition based on the fused random forest algorithm

In this paper, a fused random forest algorithm named (PSO-RF)-(KNN-HC) is proposed for the recognition of seven human motion patterns, including flat walking, sitting, standing, going up the stairs, going down the stairs, going up the slope and going down the slope. A particle swarm optimization (PSO) method is used to find the optimal parameters of the random forest model and build the optimal classification model. In the decision process of the random forest, the algorithm of k-nearest neighbors-hierarchical clustering (KNN-HC) is applied to select the decision trees for new recognition samples and calculate the voting weights of each tree, which improves the classification accuracy of the random forest model for multi-classification problems. In the data processing stage, the motion data are analyzed from view of the frequency domain using the fast Fourier transform (FFT) to divide the data segments in cycles and perform feature extraction. Finally, the proposed algorithm is validated against other machine learning algorithms based on a self-constructed human motion dataset through a real motion data acquisition platform, and the effectiveness of the proposed method is also validated on an open source dataset.

Dual-Layer All-Textile Flexible Pressure Sensor Coupled by Silver Nanowires with Ti3C2-Mxene for Monitoring Athletic Motion during Sports and Transmitting Information.

At present, wearable flexible pressure sensors have broad application prospects in fields such as motion monitoring and information transmission. However, it is still a challenge to design flexible pressure sensors with high sensitivity over a large sensing range and simple fabrication. Here, we use a simple "dipping-drying" method to fabricate a fabric-based flexible pressure sensor by coupling silver nanowires (AgNWs) with Ti3C2-MXene. The interaction between MXene and AgNWs helps realize a dual-layer sensing network, achieving good synergistic effects between pressure sensitivity and sensing range. The effects of the material combination and dip-coating sequence on the sensor's performance are systematically studied. The results show that the sensor was impregnated sequentially with AgNWs solution, and the MXene solution has the highest sensitivity (0.168 kPa-1) over a wide range (190 kPa). Meanwhile, it has the advantages of low response hysteresis and detection limit, as well as good linearity and durability. We further demonstrate the application of this sensor in human physiological signal monitoring and motion pattern recognition. It can also encrypt and transmit information according to different pressing states. In addition, the proposed pressure sensor array exhibits spatial resolution detection capabilities, laying the foundation for applications in the fields of motion monitoring and human-computer interaction.

SECURE II: Unlocking the Potential of Artificial Intelligence for Entrepreneurial Success

This study investigates the potential of artificial intelligence (AI) techniques to aid novice entrepreneurs in evaluating their business models prior to launching new ventures. The proposed SECURE II framework integrates symbolic AI, neural AI and ensemble modeling to strengthen ex-ante assessment of business model designs and expected performance outcomes. Machine learning experiments demonstrate that AI modeling uncovers hidden patterns and relationships between pre-launch plans and post-launch results. This enables more informed entrepreneurial decision-making by providing data-driven evaluative feedback. Rather than relying solely on intuition, the interactive AI assessments offer entrepreneurs a simulation mechanism to systematically test assumptions and refine opportunities pre-launch. The ensemble approach combining complementary AI techniques outperforms individual models, underscoring the value of synthesized hybrid intelligence tailored to the entrepreneurial context. By compensating for limitations in human information processing, pattern recognition, and biases, the SECURE II framework augments entrepreneurial cognition during business model formulation. This study elucidates the mechanisms through which AI can expand mental capabilities for opportunity analysis and new venture creation. The proposed toolkit demonstrates strong predictiveness on real-world data, validating the utility of AI to minimize uncertainties and boost startup success.

Efficient Fabrication of TPU/MXene/Tungsten Disulfide Fibers with Ultra-Fast Response for Human Respiratory Pattern Recognition and Disease Diagnosis via Deep Learning.

Flexible wearable pressure sensors have received increasing attention as the potential application of flexible wearable devices in human health monitoring and artificial intelligence. However, the complex and expensive process of the conductive filler has limited its practical production and application on a large scale to a certain extent. This study presents a kind of piezoresistive sensor by sinking nonwoven fabrics (NWFs) into tungsten disulfide (WS2) and Ti3C2Tx MXene solutions. With the advantages of a simple production process and practicality, it is conducive to the realization of large-scale production. The assembled flexible pressure sensor exhibits high sensitivity (45.81 kPa-1), wide detection range (0-410 kPa), fast response/recovery time (18/36 ms), and excellent stability and long-term durability (up to 5000 test cycles). Because of the high elastic modulus of MXene and the synergistic effect between WS2 and MXene, the detection range and sensitivity of the piezoresistive pressure sensor are greatly improved, realizing the stable detection of human motion status in all directions. Meanwhile, its high sensitivity at low pressure allows the sensor to accurately detect weak signals such as weak airflow and wrist pulses. In addition, combining the sensor with deep-learning makes it easy to recognize human respiratory patterns with high accuracy, demonstrating its potential impact in the fields of ergonomics and low-cost flexible electronics.

Predicting mobile users' next location using the semantically enriched geo-embedding model and the multilayer attention mechanism

Predicting the next location of human mobility and its semantic information can support recommendations for location-based services and trajectory mining, such as human mobility pattern recognition and sequential anomaly detection. Previous studies have ignored the implicit correlation between location and spatiotemporal information thereby limiting the model performance in terms of location prediction accuracy. In this study, we propose a GEMA-BiLSTM (Geographical Embedding and Multilayer Attention -Bidirectional Long Short-Term Memory) model to predict the next-location in users' mobility. The model combines location and spatiotemporal information to extract the semantics of human mobility. The results show that the model can accurately predict the next location with a high accuracy of 87.63%. Compared with BiLSTM-CNN, LSTM, CNN, and Markov, the location prediction accuracy of the model improved by 2.28%, 9.72%, 11.53%, and 17.64%, respectively. In addition, the model has the highest semantic prediction accuracy (75.35%). Compared with the BiLSTM-CNN model, the our method improves the semantic prediction accuracy for residential and industrial function areas by 4.79% and 5.37%, respectively. The accuracy of location prediction for different time periods indicates that the next location of human activity during morning rush and evening rush hours is the most difficult to predict, which corresponds to the increase in human travel demand. Moreover, weekday human activity patterns indicate that the commercial area is still very active at night, which may be linked to nighttime economic policies. This study could improve the accuracy of recommendations for location-based service applications.

Self-Repairing and Energy-Harvesting Triboelectric Sensor for Tracking Limb Motion and Identifying Breathing Patterns.

The increasing prevalence of health problems stemming from sedentary lifestyles and evolving workplace cultures has placed a substantial burden on healthcare systems. Consequently, remote health wearable monitoring systems have emerged as essential tools to track individuals' health and well-being. Self-powered triboelectric nanogenerators (TENGs) have exhibited significant potential for use as emerging detection devices capable of recognizing body movements and monitoring breathing patterns. However, several challenges remain to be addressed in order to fulfill the requirements for self-healing ability, air permeability, energy harvesting, and suitable sensing materials. These materials must possess high flexibility, be lightweight, and have excellent triboelectric charging effects in both electropositive and electronegative layers. In this work, we investigated self-healable electrospun polybutadiene-based urethane (PBU) as a positive triboelectric layer and titanium carbide (Ti3C2Tx) MXene as a negative triboelectric layer for the fabrication of an energy-harvesting TENG device. PBU consists of maleimide and furfuryl components as well as hydrogen bonds that trigger the Diels-Alder reaction, contributing to its self-healing properties. Moreover, this urethane incorporates a multitude of carbonyl and amine groups, which create dipole moments in both the stiff and the flexible segments of the polymer. This characteristic positively influences the triboelectric qualities of PBU by facilitating electron transfer between contacting materials, ultimately resulting in high output performance. We employed this device for sensing applications to monitor human motion and breathing pattern recognition. The soft and fibrous-structured TENG generates a high and stable open-circuit voltage of up to 30 V and a short-circuit current of 4 μA at an operation frequency of 4.0 Hz, demonstrating remarkable cyclic stability. A significant feature of our TENG is its self-healing ability, which allows for the restoration of its functionality and performance after sustaining damage. This characteristic has been achieved through the utilization of the self-healable PBU fibers, which can be repaired via a simple vapor solvent method. This innovative approach enables the TENG device to maintain optimal performance and continue functioning effectively even after multiple uses. After integration with a rectifier, the TENG can charge various capacitors and power 120 LEDs. Moreover, we employed the TENG as a self-powered active motion sensor, attaching it to the human body to monitor various body movements for energy-harvesting and sensing purposes. Additionally, the device demonstrates the capability to recognize breathing patterns in real time, offering valuable insights into an individual's respiratory health.

Multimodal integrated flexible electronic skin for physiological perception and contactless kinematics pattern recognition

Multimodal integrated flexible electronic skin offers exceptional processing capability and versatility in various application scenarios. Researchers are devoting to developing nanomaterials or nano-devices with multidisciplinary functions. Herein, a trinary-mode integrated flexible electronic skin (E-Skin) was designed for physiological perception and contactless kinematics pattern recognition, which serves as real-time health monitor, electrode patch and contactless sensor. The composite film of liquid metal particles and thermoplastic polyurethane elastomers (LMPs@TPU) was prepared by a combination of electrostatic spinning, electrostatic spraying, and knife coating, which can be stretched up to 404.7 % at stress of 1Mpa. The film was endowed three functional modes through different forms of encapsulation, which allows for (1) detecting human arthrosis movements, muscle stretching, and inspiration, (2) achieving a real-time capture of Electrocardiogram (ECG) and surface electromyography (sEMG), and a Human-Machine Interaction (HMI) system for game control based on sEMG signals was also developed, (3) a contactless sensor combining with a machine learning model which realizes the recognition of human motion patterns with a receiver operating characteristic curve and area under curve score (ROC-AUC-score) of 0.99. The three models of this E-Skin highlight the significant potential for industrialization in various fields, such as HMI, physiological perception, virtual reality, and motion analysis.