Myoelectric Signals Research Articles

Myoelectric signal and machine learning computing in gait pattern recognition for flat fall prediction

Myoelectric signal and machine learning computing in gait pattern recognition for flat fall prediction

A simplified adversarial architecture for cross-subject silent speech recognition using electromyography

Objective. The decline in the performance of electromyography (EMG)-based silent speech recognition is widely attributed to disparities in speech patterns, articulation habits, and individual physiology among speakers. Feature alignment by learning a discriminative network that resolves domain offsets across speakers is an effective method to address this problem. The prevailing adversarial network with a branching discriminator specializing in domain discrimination renders insufficiently direct contribution to categorical predictions of the classifier.Approach. To this end, we propose a simplified discrepancy-based adversarial network with a streamlined end-to-end structure for EMG-based cross-subject silent speech recognition. Highly aligned features across subjects are obtained by introducing a Nuclear-norm Wasserstein discrepancy metric on the back end of the classification network, which could be utilized for both classification and domain discrimination. Given the low-level and implicitly noisy nature of myoelectric signals, we devise a cascaded adaptive rectification network as the front-end feature extraction network, adaptively reshaping the intermediate feature map with automatically learnable channel-wise thresholds. The resulting features effectively filter out domain-specific information between subjects while retaining domain-invariant features critical for cross-subject recognition.Main results. A series of sentence-level classification experiments with 100 Chinese sentences demonstrate the efficacy of our method, achieving an average accuracy of 89.46% tested on 40 new subjects by training with data from 60 subjects. Especially, our method achieves a remarkable 10.07% improvement compared to the state-of-the-art model when tested on 10 new subjects with 20 subjects employed for training, surpassing its result even with three times training subjects.Significance. Our study demonstrates an improved classification performance of the proposed adversarial architecture using cross-subject myoelectric signals, providing a promising prospect for EMG-based speech interactive application.

Fall-related gait pattern recognition based on surface electromyography using a hybrid neural network with transfer learning

Gait analysis across different individuals presents significant challenges due to individual variability. In this study, we developed a gait analysis system to enable continuous decoding of gait patterns based on surface electromyography (EMG). Our objective was to address the long-term challenges associated with neural networks, particularly their limited generalization capability and the heavy training burden on new subjects in gait pattern recognition. Fifteen healthy subjects were recruited to imitate two fall-related gait patterns and collect myoelectric signals from eight lower limb muscles. We proposed a transfer learning-based framework and investigated eight adaptation schemes using varying quantities of target training samples. In the cross-subject evaluation, our framework demonstrated robust generalization capability and reduced training burden. Even with a limited number of target training samples, the framework outperformed state-of-the-art machine learning models and discriminative neural networks that have previously shown excellent recognition performance in subject-specific evaluation. This study highlights the promising potential of using transfer learning in conjunction with neural networks for gait pattern recognition across different individuals. It also provides valuable insights into the diagnosis, monitoring, and treatment of various medical conditions using surface EMG-based gait analysis systems.

Movements classification system for transhumeral amputees using myoelectric signals

The extent of loss of functionality in people with transhumeral amputation or elbow disarticulation is considered highly compromised. The person with this impairment loses the primary muscle involved in the movement of the hand and fingers, and the elbow flexion/extension. In this sense, the development of myoelectric prostheses must include mechanisms that replicate these movements. Moreover, the control system for controlling a prosthesis must be robust and intuitive, where pattern recognition and artificial intelligence techniques represent an important and increasingly explored alternative. This study aims to develop a movement intention classification system based on myoelectric signals (MES) obtained from an elbow disarticulation amputee. Different features were extracted from the MES as the Mean absolute value (MAV), zero crossings (ZC), slope sign changes (SSC), waveform length (WL), and autoregressive (AR) coefficients. Machine learning classifiers (Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Random Forests (RF), and Multilayer Perceptron (MLP)) were used to predict seven gestures: elbow flexion (EF), elbow extension (EE), forearm pronation (FP), forearm supination (FS), hand opening (HO), hand closing (HC), and rest (R). The results obtained with LDA, QDA, KNN, MLP, SVM, and RF were 60.84%, 71.05%, 77.10%, 78.06%, 78.57%, and 79.72% of accuracy, respectively. These results are promising and will allow the development of a myoelectric prosthesis control system for people with transhumeral amputation or elbow disarticulation.

Design of a Real-Time Monitoring System for Electroencephalogram and Electromyography Signals in Cerebral Palsy Rehabilitation via Wearable Devices

Cerebral palsy is a disorder of central motor and postural development, resulting in limited mobility. Cerebral palsy is often accompanied by cognitive impairment and abnormal behavior, significantly impacting individuals and society. Time, energy, and economic investment in the rehabilitation process is substantial, yet the rehabilitation outcomes often remain unsatisfactory. Additionally, some patients have limited sensory perception during rehabilitation training, making it challenging to effectively regulate exercise intensity. Traditional evaluation methods are mostly based on recovery performance, lack guidance at the neurophysiological level, and have an unequal distribution of medical rehabilitation resources, which pose great challenges to the rehabilitation of patients. Based on the issues mentioned above, this paper proposes a real-time cerebral signal monitoring system based on wearable devices. This system can monitor and store blood oxygen, heart rate, myoelectric, and EEG signals during cerebral palsy rehabilitation, and it can track and monitor signals during the rehabilitation treatment process. The system includes two parts: hardware design and software design. The hardware design includes a data signal acquisition module, a main control chip (ESP32), a muscle electrical sensor module, a brain electrical sensor module, a blood/heart rate acquisition module, etc. It is primarily for real-time signal data acquisition, processing, and uploading to the cloud server. The software design includes functions such as data receiving, data processing, data storage, network configuration, and remote communication and enables the visual monitoring of data signals. The system can achieve real-time monitoring of electromyography, electroencephalography, and blood oxygen levels, as well as the heart rate of patients with cerebral palsy, and adjust rehabilitation training in real-time during the rehabilitation process. At the same time, based on the real-time storage of the original electromyography and electroencephalography data, it can provide auxiliary guidance for later rehabilitation evaluation and effective data support for the entire rehabilitation treatment process.

Effects of hand dominance on myoelectric signal of non‑fatigued lumbar multifidus muscle during single arm lifts.

Some evidence indicates that lower back muscles located at the non‑dominant side of the body are more fatigue resistant than their opposite counterparts presumably due to preferential use of the dominant hand. The aim of the study was to determine if any distinction exists in the surface electromyographic activity of corresponding contralateral non‑fatigued lumbar multifidus (LM) muscles as a function of hand dominance. The relative to maximum root mean square, the median frequency (MdF) and spike shape parameters were computed from the surface myoelectric signals of ipsilateral and contralateral lumbar multifidus muscle of 46 adult healthy subjects (27 right‑handed, 19 left‑handed) during voluntary contractions evoked by the single arm lifts in prone position. Activation of LM as a contralateral muscle to lifted arm was greater than as ipsilateral muscle, independently of handedness. Regardless if LM performed ipsi‑ or contralateral action to the lifted arm, the mean spike amplitude, slope, number of peaks per spike and spike duration were greater and mean spike frequency as well as MdF were smaller in the muscle of dominant than non‑dominant side. Combined changes of spike shape measures indicate increased recruitment, lower firing rates and higher synchronization of motor units in the LM of dominant side as compared to its counterpart.

The Posterior Insular Cortex is Necessary for Feeding-Induced Jejunal Myoelectrical Activity in Male Rats

The gastrointestinal tract exhibits coordinated muscle motility in response to food digestion, which is regulated by the central nervous system through autonomic control. The insular cortex is one of the brain regions that may regulate the muscle motility. In this study, we examined whether, and how, the insular cortex, especially the posterior part, regulates gastrointestinal motility by recording jejunal myoelectrical signals in response to feeding in freely moving male rats. Feeding was found to induce increases in jejunal myoelectrical signal amplitudes. This increase in the jejunal myoelectrical signals was abolished by vagotomy and pharmacological inhibition of the posterior insular cortex. Additionally, feeding induced a decrease and increase in sympathetic and parasympathetic nervous activities, respectively, both of which were eliminated by posterior insular cortical inhibition. These results suggest that the posterior insular cortex regulates jejunal motility in response to feeding by modulating autonomic tone.

MES-FES Interface Enhances Quadriceps Muscle Response in Sitting Position in Incomplete Spinal Cord Injury: Pilot Study

Purpose: In incomplete spinal cord injury (SCI), there is a partial decrease in motor or sensory or autonomic function. Mainly due to the motor impairment in SCI, a muscle–machine interface is a tool that can bring functional benefits to this population. Objective: To investigate the feasibility of the non-invasive myoelectric signal–functional electrical stimulation (MES-FES) interface on the response of the quadriceps muscle in an individual with incomplete SCI. Methods: This is a quasi-experimental, uncontrolled, longitudinal case report study carried out with an individual with incomplete SCI in the chronic phase. The assessments performed before (pre) and after eight (post8) interventions were neuromuscular assessment (surface electromyography (EMG) in rectus femoris (RF) and vastus lateralis (VL) muscles); muscle strength (load cell); knee extension range of motion (goniometry); spasticity (Modified Ashworth Scale); and quality of life (Spinal Cord Injury Quality-of-Life Questionnaire (SCI-QoL.Br)). The MES-FES interface was associated with physical therapy exercises on the extension knee joint muscle group. Results: Improvement in neuromuscular activation (normalized increase in EMGRMS of 2% (RF) and 3.3% (VL)) and synchronism of the motor units (normalized reduction in EMGMDF of 22.8% (RF) and 5.9% (VL)); 1.4 kgf increase in quadriceps strength; 10.6° increase in knee joint extension amplitude; 1 point spasticity reduction; improved quality of life, confirmed by a 12-point reduction in the SCI-QoL.Br score. Moreover, along with interventions, the participant increased the correct FES activation rate, indicating a user learning curve (ρ = 0.78, p-value = 0.04). Conclusions: The MES-FES interface associated with physical therapy promotes neuromuscular and quality of life improvements in the SCI participant.

DistaNet: grasp-specific distance biofeedback promotes the retention of myoelectric skills

Objective. An active myoelectric interface responds to the user’s muscle signals to enable movements. Machine learning can decode user intentions from myoelectric signals. However, machine learning-based interface control lacks continuous, intuitive feedback about task performance, needed to facilitate the acquisition and retention of myoelectric control skills. Approach. We propose DistaNet as a neural network-based framework that extracts smooth, continuous, and low-dimensional signatures of the hand grasps from multi-channel myoelectric signals and provides grasp-specific biofeedback to the users. Main results. Experimental results show its effectiveness in decoding user gestures and providing biofeedback, helping users retain the acquired motor skills. Significance. We demonstrates myoelectric skill retention in a pattern recognition setting for the first time.

A distributed, high-channel-count, implanted bidirectional system for restoration of somatosensation and myoelectric control

Objective. We intend to chronically restore somatosensation and provide high-fidelity myoelectric control for those with limb loss via a novel, distributed, high-channel-count, implanted system. Approach. We have developed the implanted Somatosensory Electrical Neurostimulation and Sensing (iSens®) system to support peripheral nerve stimulation through up to 64, 96, or 128 electrode contacts with myoelectric recording from 16, 8, or 0 bipolar sites, respectively. The rechargeable central device has Bluetooth® wireless telemetry to communicate to external devices and wired connections for up to four implanted satellite stimulation or recording devices. We characterized the stimulation, recording, battery runtime, and wireless performance and completed safety testing to support its use in human trials. Results. The stimulator operates as expected across a range of parameters and can schedule multiple asynchronous, interleaved pulse trains subject to total charge delivery limits. Recorded signals in saline show negligible stimulus artifact when 10 cm from a 1 mA stimulating source. The wireless telemetry range exceeds 1 m (direction and orientation dependent) in a saline torso phantom. The bandwidth supports 100 Hz bidirectional update rates of stimulation commands and data features or streaming select full bandwidth myoelectric signals. Preliminary first-in-human data validates the bench testing result. Significance. We developed, tested, and clinically implemented an advanced, modular, fully implanted peripheral stimulation and sensing system for somatosensory restoration and myoelectric control. The modularity in electrode type and number, including distributed sensing and stimulation, supports a wide variety of applications; iSens® is a flexible platform to bring peripheral neuromodulation applications to clinical reality. ClinicalTrials.gov ID NCT04430218.

Intelligent Human-Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition.

Recent studies have highlighted the possibility of using surface electromyographic (EMG) signals to develop human-computer interfaces that are also able to recognize complex motor tasks involving the hand as the handwriting of digits. However, the automatic recognition of words from EMG information has not yet been studied. The aim of this study is to investigate the feasibility of using combined forearm and wrist EMG probes for solving the handwriting recognition problem of 30 words with consolidated machine-learning techniques and aggregating state-of-the-art features extracted in the time and frequency domains. Six healthy subjects, three females and three males aged between 25 and 40 years, were recruited for the study. Two tests in pattern recognition were conducted to assess the possibility of classifying fine hand movements through EMG signals. The first test was designed to assess the feasibility of using consolidated myoelectric control technology with shallow machine-learning methods in the field of handwriting detection. The second test was implemented to assess if specific feature extraction schemes can guarantee high performances with limited complexity of the processing pipeline. Among support vector machine, linear discriminant analysis, and K-nearest neighbours (KNN), the last one showed the best classification performances in the 30-word classification problem, with a mean accuracy of 95% and 85% when using all the features and a specific feature set known as TDAR, respectively. The obtained results confirmed the validity of using combined wrist and forearm EMG data for intelligent handwriting recognition through pattern recognition approaches in real scenarios.

Spectral characterization of human leg EMG signals from an open access dataset for the development of computational models.

Large-scale neuromusculoskeletal models have been used for predicting mechanisms underlying neuromuscular functions in humans. Simulations of such models provide several types of signals of practical interest, such as surface electromyographic signals (EMG), which are compared with experimental data for interpretations of neurophysiological phenomena under study. Specifically, realistic characterization of spectral properties of simulated EMG signals is important for achieving powerful inferences, whereas considerations should be taken for myoelectric signals of different muscles. In this study, we characterized spectral properties of surface interference pattern EMG signals and motor unit action potentials (MUAP) acquired from three plantar flexor muscles: Soleus (SO), Medial Gastrocnemius (MG), and Lateral Gastrocnemius (LG); and one dorsiflexor muscle: Tibialis Anterior (TA). Surface EMG signals were acquired from 20 participants using the same convention for electrode placement. Specifically, interference pattern EMG signals were obtained during isometric constant force contractions at 5%, 10% and 20% of maximum voluntary contraction (MVC), whereas surface MUAPs were decomposed from surface EMG signals obtained at low contraction forces. We compared the spectrum median frequency (MDF) estimated from interference pattern EMG signals across muscles and contraction intensities. Additionally, we compared MDF and durations of MUAPs between muscles. Our results showed that MDF of interference pattern EMG signals acquired from TA were higher compared to SO, MG, and LG for all contraction intensities i.e., 5%, 10%, and 20% MVC. Consistently, MUAPs acquired from TA also had higher MDF values and shorter durations compared to the other leg muscles. We provide herein a dataset with the surface MUAPs waveforms and interference pattern EMG signals obtained for this study, which should be useful for implementing and validating the simulation of myoelectrical signals of leg muscles. Importantly, these results indicate that spectral properties of myoelectrical signals should be considered for improving EMG modeling in large-scale neuromusculoskeletal models.

Mechanisms of electroacupuncture relieves uterine smooth muscle spasm in dysmenorrhea rats based on Rho/ROCK signaling pathway.

To investigate the effect of electroacupuncture (EA) on Rho/Rho-associated coiled-coil-forming kinases (ROCK) signaling pathway of uterus tissue in rats with dysmenorrhea, so as to explore the underlying mechanism of EA treating primary dysmenorrhea (PD) and uterine smooth muscle spasm, and to observe whether there is a difference in the effect of meridian acupoints in Conception Vessel (CV) and Governer Vessel (GV). Sixty female SD rats were randomly divided into saline, model, CV, GV, and non-acupoint groups, with 12 rats in each group. The dysmenorrhea model was established by subcutaneous injection of estradiol diphenhydrate combined with intraperitoneal injection of oxytocin (OT). EA (2 Hz) was applied to "Qihai" (CV6) and "Zhongji" (CV3) for CV group, "Mingmen" (GV4) and "Yaoshu" (GV2) for GV group, "non-acupoint 1" and "non-acupoint 3" on the left side for non-acupoint group, and manual acupuncture was applied to "Guanyuan" (CV4) for CV group, "Yaoyangguan" (GV3) for GV group, "non-acupoint 2" on the left side for non-acupoint group. The treatment was conducted for 20 min each time, once daily for 10 days. The writhing score was evaluated. The smooth myoelectric signals of rats' uterus in vivo were recorded by multi-channel physiological recorder. The uterine histopathological changes were observed by HE staining. The contents of prostaglandin F2α (PGF2α), OT and calcium ion (Ca2+) in uterine tissue of rats were detected by ELISA. The protein and mRNA expression levels of smooth muscle 22-α (SM22-α), RhoA and ROCKⅡ in uterine tissue were detected by Western blot and fluorescence quantitative PCR, respectively. Compared with the saline group, the writhing score of rats in the model group was increased (P<0.01), the amplitude voltage of uterine smooth muscle in vivo was elevated (P<0.01), the contents of PGF2α, OT and Ca2+, the protein and mRNA expression of SM22-α, RhoA and ROCK Ⅱ in uterine tissue were all increased (P<0.01). Compared with the model and the non-acupoint groups, the writhing scores of the CV and the GV groups were decreased (P<0.01, P<0.05), the amplitude voltage of uterine smooth muscle was decreased (P<0.01), the contents of PGF2α, OT and Ca2+ in uterine tissue were decreased (P<0.01, P<0.05), and the protein expression and mRNA expression of SM22-α, RhoA and ROCKⅡ in uterine tissue were decreased (P<0.01, P<0.05). HE staining showed extensive exfoliation of uterine intima with severe edema and increased glandular secretion in the model group, which was alleviated in the CV and GV groups. EA at acupoints of CV and GV can significantly reduce the writhing score, uterine smooth muscle amplitude voltage, pathological injury degree of uterus, and relieve spasm of uterine smooth muscle in dysmenorrhea rats, which may be related to its effect in regulating PGF2α and OT contents, inhibiting the Rho/ROCK signaling pathway, and reducing the SM22-α, RhoA, ROCKⅡ protein and mRNA expression, and Ca2+ content in uterine tissue.

Functional and esthetic reconstruction of composite lower lip defects with a motor-innervated chimeric facial artery buccinator myomucosal-submental island flap

ObjectiveThis study aimed to assess the functional and esthetic outcomes of a chimeric innervated buccinator myomucosal-submental island flap (BMM-SIF) for large composite lower lip reconstruction. MethodsThis retrospective study included five patients who underwent lower lip tumor resection and BMM-SIF reconstruction at the Hospital of Stomatology, Sun Yat-sen University, between August 2021 and February 2023. Lip function was evaluated using water leakage, cheek puffing tests, and superficial electromyography. Lip appearance was observed using photographs and evaluated through subjective interviews. Donor-site conditions, including facial symmetry and mouth opening, were monitored. ResultsAll the BMM-SIFs survived. Drooling was the main complication observed shortly after surgery. The water leakage test showed complete oral competence for liquid holding in the 7th month; however, moderate air leakage was present in two patients. Electromyography revealed myoelectric signals from the innervated buccinator at the recipient site. Facial expression and food intake were typically managed. The shape and projection of the vermilion were harmonious and satisfactory for each patient. Neither microstomia nor mouth opening limitation was observed, with an average inter-incisor distance of 37.25±4.4 mm. ConclusionChimeric motor-innervated BMM-SIF effectively reconstructed large full-thickness lower-lip defects with satisfactory functional and esthetic outcomes.

Isoflurane anesthesia suppresses gastric myoelectric power in the ferret.

Gastric myoelectric signals have been the focus of extensive research; although it is unclear how general anesthesia affects these signals, and studies have often been conducted under general anesthesia. Here, we explore this issue directly by recording gastric myoelectric signals during awake and anesthetized states in the ferret and explore the contribution of behavioral movement to observed changes in signal power. Ferrets were surgically implanted with electrodes to record gastric myoelectric activity from the serosal surface of the stomach, and, following recovery, were tested in awake and isoflurane-anesthetized conditions. Video recordings were also analyzed during awake experiments to compare myoelectric activity during behavioral movement and rest. A significant decrease in gastric myoelectric signal power was detected under isoflurane anesthesia compared to the awake condition. Moreover, a detailed analysis of the awake recordings indicates that behavioral movement is associated with increased signal power compared to rest. These results suggest that both general anesthesia and behavioral movement can affect the signal power of gastric myoelectric recordings. In summary, caution should be taken in studying myoelectric data collected under anesthesia. Further, behavioral movement could have an important modulatory role on these signals, affecting their interpretation in clinical settings.

Robust myoelectric pattern recognition methods for reducing users' calibration burden: challenges and future.

Myoelectric pattern recognition (MPR) has evolved into a sophisticated technology widely employed in controlling myoelectric interface (MI) devices like prosthetic and orthotic robots. Current MIs not only enable multi-degree-of-freedom control of prosthetic limbs but also demonstrate substantial potential in consumer electronics. However, the non-stationary random characteristics of myoelectric signals poses challenges, leading to performance degradation in practical scenarios such as electrode shifting and switching new users. Conventional MIs often necessitate meticulous calibration, imposing a significant burden on users. To address user frustration during the calibration process, researchers have focused on identifying MPR methods that alleviate this burden. This article categorizes common scenarios that incur calibration burdens as based on data distribution shift and based on dynamic data categories. Then further investigated and summarized the popular robust MPR algorithms used to reduce the user's calibration burden. We categorize these algorithms as based on data manipulate, feature manipulation and, model structure. And describes the scenarios to which each method is applicable and the conditions required for calibration. Finally, this review is concluded with the advantages of robust MPR and the remaining challenges and future opportunities.

Electromyographic hand gesture recognition using convolutional neural network with multi-attention

Electromyographic hand gesture recognition can be used to develop myoelectric prosthetic hands for disabled people when the acquired myoelectric signals are accurately classified. Recently, the developed end-to-end deep learning methods are widely used in hand gesture recognition for their automatic extraction of features from raw signals. But not all extracted features are useful and unimportant information can impede gesture recognition. In this study, a deep learning model using multi-attention for electromyographic hand gesture recognition is proposed. The attention mechanism inspired by the biological system enables deep learning models to focus on the important parts of input data while ignoring unimportant information. At first, a convolutional neural network is employed as the feature extractor, enabling the learning of high-level discriminative features from input signals. Then, multi-attention blocks, including channel attention, spatial attention, and temporal attention, are integrated into the convolutional layers, enhancing the extraction of pertinent features by emphasizing critical information through weight recalibration. Finally, the proposed model is evaluated on both the public NinaPro dataset and the public Myo dataset, demonstrating superior performance compared to baseline models in terms of recognition accuracy. The experimental results reveal that the model with attention mechanism achieves an average recognition accuracy of 91.64%, representing a 1.1% improvement over the model without attention mechanism.

From Forearm to Wrist: Deep Learning for Surface Electromyography-Based Gesture Recognition

From Forearm to Wrist: Deep Learning for Surface Electromyography-Based Gesture Recognition

Lower-Limb Myoelectric Calibration Postures for Transtibial Prostheses.

The use of an agonist-antagonist muscle pair for myoelectric control of a transtibial prosthesis requires normalizing the myoelectric signals and identifying their co-contraction signature. Extensive literature has explored the relationship between body posture and lower-limb muscle activation level using surface electromyography (EMG), but it is unknown how these relationships hold after amputation. Using a virtual tracking task, this study compares the effect of three different calibration postures (seated, standing, dynamic) on user tracking ability while in two tracking postures (seated, standing) for 18 able-bodied (AB) subjects and 9 subjects with transtibial (TT) amputation. As expected, AB subjects produced statistically significant differences in muscle activation for gastrocnemius (GAS) when seated vs. standing during calibration (p = 8.8e-4), but not for tibialis anterior (TA) (p = 0.76). TT subjects, however, showed no significant differences in GAS or TA between seated and standing (p = 0.90, 0.60 respectively). It was also determined that normalizing EMG by the global maximum signal observed (standard in biomechanic analysis) is undesirable for myoelectric control. For best general results with this framework, calibration in both seated and dynamic postures is recommended, taking the normalization information from the seated posture and the narrowest co-contraction slopes from the two.

Recognition of Muscular Activity in Complex Noise-Contaminated Myoelectric Signals: An Adaptive Two-Step Approach

Recognition of Muscular Activity in Complex Noise-Contaminated Myoelectric Signals: An Adaptive Two-Step Approach