Search

All existing physiological tremor filtering algorithms, developed for robotic microsurgery, use nonlinear phase prefilters to isolate the tremor signal. Such filters cause phase distortion to the filtered tremor signal and limit the filtering accuracy. We revisited this long-standing problem to enable filtering of the physiological tremor without any phase distortion. We developed a combined estimation-prediction paradigm that offers zero-phase type filtering. The estimation is achieved with the mathematically modified recursive singular spectrum analysis algorithm, and the prediction is delivered with the standard extreme learning machine. In addition, to limit the computational cost, we developed two moving window versions of this structure, which are appropriate for real-time implementation. The proposed paradigm preserved the natural phase of the filtered tremor. It achieved the key performance index of error limitation below 10\mum, yielding the estimation accuracy larger than 70%, at a time delay of 36 ms only. Both moving window versions of the proposed approach restricted the computational cost considerably while offering the same performance. It is the first time that the effective estimation of the physiological tremor is achieved, without any prefiltering and phase distortion. This proposed method is feasible for real-time implantation. Clinical translation of the proposed paradigm can significantly enhance the outcome in hand-held surgical robotics.

In recent years, the usage of portable electroencephalogram (EEG) devices are becoming popular for both clinical and non-clinical applications. In order to provide more comfort to the subject and measure the EEG signals for several hours, these devices usually consists of fewer EEG channels or even with a single EEG channel. However, electrooculogram (EOG) signal, also known as eye-blink artifact, produced by involuntary movement of eyelids, always contaminate the EEG signals. Very few techniques are available to remove these artifacts from single channel EEG and most of these techniques modify the uncontaminated regions of the EEG signal. In this paper, we developed a new framework that combines unsupervised machine learning algorithm (k-means) and singular spectrum analysis (SSA) technique to remove eye blink artifact without modifying actual EEG signal. The novelty of the work lies in the extraction of the eye-blink artifact based on the time-domain features of the EEG signal and the unsupervised machine learning algorithm. The extracted eye-blink artifact is further processed by the SSA method and finally subtracted from the contaminated single channel EEG signal to obtain the corrected EEG signal. Results with synthetic and real EEG signals demonstrate the superiority of the proposed method over the existing methods. Moreover, the frequency based measures [the power spectrum ratio ($$\Gamma $$ Γ ) and the mean absolute error (MAE)] also show that the proposed method does not modify the uncontaminated regions of the EEG signal while removing the eye-blink artifact.

Recently, the study of designing multi-objective evolutionary algorithms (MOEAs) to solve multi and many-objective optimization has received lot of recognition. In this paper, we have proposed an indicator based MOEA (I gSDE -MOEA) in which the information from the shift based density estimation is utilized to a greater extent. In the past, the shift based density estimation (SDE) is employed in conjunction with the other indicators and metrics. However, in this work, we employ the indicator based on SDE solely to approximate the Pareto front. The indicator proposed in this paper is adaptively controlled over the generations. The performance of the proposed I gSDE -MOEA is evaluated by performing experiments on 14 benchmark problems and 7 real-world problems. The experimental results demonstrate that the proposed I gSDE -MOEA exhibits better performance in comparison with the state-of-art algorithms.

The challenges existing under the category of fully autonomous systems call for a need of human automation interaction to ensure safety and trust. Motivated by the above, this paper deals with the design of a shared control framework that enables the interaction between the human driver and automation. Further, the potential of game theory in a cooperative framework is employed to model the strategic interaction between the human driver and automation. The lateral dynamics of the vehicle model is taken into consideration with an incomplete information of all states. Lateral displacement and Yaw angle are measured whereas lateral velocity and Yaw rate are the unavailable states. A higher Order sliding Mode (HOSM) observer is designed to estimate the unknown states. With the availability of the estimated states, the interaction between the human driver and automation is carried out to generate a shared control law based on cooperative game theory. Model predictive control (MPC) approach is employed to design the control action for the human driver and autonomous subsystem separately. Then, the proposed shared lateral control scheme is analyzed and examined through simulation to evaluate the driver performance in this cooperative game theoretic approach.

Fault detection in a Direct Current (DC) microgrid with multiple interconnections of distributed generation units (DGUs) is an interesting topic of research. The occurrence of any sensor fault in the DC microgrid should be detected immediately by the fault detection network to achieve an overall stable performance of the system. This work focuses on sensor fault diagnosis of voltage and current sensors in interconnected DGUs of the microgrid. Two separate higher order sliding mode observers (HOSM) based on model dynamics are designed to estimate the voltage and current and generate the residuals for detecting the faulty sensors in DGUs. Multiplicative single and multiple sensor faults are considered in voltage and current sensors. By appropriate selection of threshold, single and multiple sensor fault detection strategies are formulated. A hierarchical controller is designed to ensure equal sharing of current among the DGUs of the DC microgrid and stabilize the system. Simulations are performed to validate the proposed approach for various configurations of the DC microgrid under various load and off noise conditions.

Recently, developing efficient multi-objective evolutionary algorithms (MOEAs) for detect communities in complex networks has received immense recognition. Employing MOEAs for community detection provide a set of Pareto-optimal solutions (PS) where each solution in PS represent different network partition. In literature, majority of existing approaches proposed for detecting community structures focus on obtaining disjoint communities (each node belongs to a unique community). However, communities in real-world networks often overlap with each other and thus it is essential to develop algorithms for overlapping community detection. Hence, in this paper, we propose a MOEA based on ensemble of initializations for overlapping community detection (OCD-enMOEA). In OCD-enMOEA, we employ an ensemble of initialization procedure, where the individuals are encoded by an indirect representation based on permutation. Then, a decoding procedure based on community fitness is employed to transform the individuals into communities. The community fitness metrics adopted for decoding is associated with a resolution parameter $\alpha$ , which allows exploration of community structures at different levels of granularity. However, the community fitness metric is very sensitive to the parameter $\alpha$ and adapting the parameter to achieve better performance is very difficult. Hence, in this paper, we employ a set of values for the parameter $\alpha$ as an ensemble and transform the individuals into communities. To validate the performance of proposed OCD-enMOEA, we have employed five real-world networks and compared with six baseline algorithms to detect overlapping communities. The experimental results demonstrate that the proposed method exhibit better performance in comparison with the baseline algorithms.

To communicate efficiently with a prospective user, auditory interfaces are employed in mobile communication devices. Diverse sounds in different volumes are used to alert the user in various devices such as mobile phones, modern laptops and domestic appliances. These alert noises behave erroneously in dynamic noise environments, leading to major annoyances to the user. In noisy environments, as sounds can be played quietly, this leads to the improper masked rendering of the necessary information. To overcome these issues, a multi-model sensing technique is developed as a smartphone application to achieve automatic volume control in a smart phone. Based on the ambient environment, the volume is automatically controlled such that it is maintained at an appropriate level for the user. By identifying the average noise level of the ambient environment from dynamic microphone and together with the activity recognition data obtained from the inertial sensors, the automatic volume control is achieved. Experiments are conducted with five different mobile devices at various noise-level environments and different user activity states. Results demonstrate the effectiveness of the proposed application for active volume control in dynamic environments.

Network perspective studies of the human brain are rapidly increasing due to the advances in the field of network neuroscience. In several brain network based applications, recognition of event-associated brain functional networks (BFNs) can be crucial to understand the event processing in the brain and can play a significant role to characterize and quantify the complex brain networks. This paper presents a framework to identify the event-associated BFNs using phase locking value (PLV) in EEG. Based on the PLV dissimilarities during the rest and event tasks, we identify the reactive band and the event-associated most reactive pairs (MRPs). With the MRPs identified, the event-associated BFNs are formed. The proposed method is employed on ‘database for emotion analysis using physiological signals (DEAP)‘ data set to form the BFNs associated with several emotions. With the emotion-associated BFNs as features, comparable state-of-the-art multiple emotion classification accuracies are achieved. Results show that, with the proposed method, event-associated BFNs can be identified and can be used in brain network based applications.

International audience; The nonlinear active suspension control design can be analyzed as a multiobjective control problem that caters to the enhancement in ride comfort levels while ensuring that road holding is maintained with the constrained suspension displacement movement. In this article, a robust constrained output feedback approach employing sliding mode controllers is proposed for the nonlinear active suspension system equipped with hydraulic actuators. Adhering to mechanical design limitations, the suspension displacement and the corresponding displacement rate are constrained using asymmetric barrier Lyapunov functions. Consequently, a nonlinear control law that incorporates the first-order sliding mode control is then formulated to regulate the hydraulic valve and thereby provide an active control effort. The robust control performance with high-performance improvements for ride comfort in the presence of parametric uncertainties, sensor noise, and over variable driving velocities for different road conditions is established using simulation studies.

In the past few years, the study on functional connectivity of the human brain has led to various innovations in neuroscience. Functional connectivity reveals the simultaneity between the electrode pairs while performing neurophysiological activities. In this paper, the functional connectivity networks of healthy subjects, mild cognitive impairment (MCI), Alzheimer's disease (AD), and dementia patients were analysed by measuring the irregularity of the signals through wavelet spectral entropy (WSE) and were quantified using network measures. Depending on the discordance between the networks of all the four conditions, significant electrode pairs and their reactive networks were identified. These networks demonstrate the importance of most reactive electrode pairs that show significant variations. The identified functional connectivity networks that respond to the different pathologies shows the progression of the disease in patients. Further, the quantification of networks with graph theory network measures highlight differences between various progressive stages of the AD and its potential for development of EEG network biomarker in future.

Accurate prediction of tumor motion for motion adaptive radiotherapy has been a challenge as respiration-induced motion is non-stationary in nature and often subjected to irregularities. Despite having a plethora of works for predicting this motion, their tracking capabilities are usually prone to large prediction errors due to the time-varying irregularities and intra-trace variabilities. To overcome this, prediction models are re-trained at regular intervals. This solution however demands a trade-off between the re-training interval and prediction accuracy in estimating the future tumor location. This is because re-training with small interval increases the computational requirements whereas a larger interval hampers the prediction performance. To address these issues, a prediction model that relies on random convolution nodes (RCN) governed by local receptive fields (LRFs) is proposed for respiratory motion prediction. The innate nature of LRFs extracts the features that contribute to the local-patterns as well as the non-stationary patterns in recent samples and subsequently learn them using extreme learning machine (ELM) theories. To address the re-training issue, we propose an online sequential learning framework (OS-fRCN) that can update the model parameters at regular intervals. Suitability of the proposed OS-fRCN for respiratory motion prediction is evaluated on 304 respiratory motion traces. Performance analysis conducted at four prediction horizons (in-line with the commercially available radiotherapy systems) demonstrated that the proposed OS-fRCN method requires less computational complexity and yields robust, accurate prediction performance when compared with existing prediction methods. This research was supported by the National Natural Science Foundation of China under No. 81701787, the Natural Science Basic Research Plan in Shaanxi Province of China (2019JQ-138), and 2019GHY112041 Primary RD Program of Shandong Province (Public welfare). The research was also supported in part by the National Research Foundation (NRF) of Korea through the Ministry of Education, Science and Technology under Grant NRF2018R1A6A1A03025109.

In general, permanent magnet synchronous motor (PMSM) drives require four sensors (one position, one dc-link voltage, and at least two current sensors) to obtain good dynamic control performance. If an unpredictable fault occurs in any of these sensors, the performance of the drive deteriorates or even becomes unstable. Most of the existing works are limited to fault diagnosis of one or two sensors due to complexity. Therefore, to provide a continuous drive operation regardless of any of the sensor faults, an advanced fault-tolerant control (FTC) scheme that comprises of higher order sliding mode (HOSM) based observers and controllers is proposed. Two HOSM observers and one Luenberger observer are designed to generate the respective residuals and provide the detection of all sensor faults. Moreover, HOSM controllers are developed to ensure finite-time convergence of the error trajectories after the fault reconfiguration. The proposed FTC scheme reduces the existing chattering phenomenon with good performance in terms of convergence speed and steady-state error. Evaluation results on a three-phase PMSM are presented to validate the effectiveness of the proposed FTC approach.

Independent component analysis with reference (ICA-R), a paradigm of constrained ICA (cICA), incorporates textita priori information about the desired sources as reference signals into the contrast function of ICA. Reference signals direct the search toward the separation of desired sources more efficiently and accurately than the ICA. The penalized contrast function of ICA-R is non-smooth everywhere and the ICA-R algorithm does not always reach the global optimum due to the Newton-like learning used. In this paper, we propose a constrained differential evolutionary algorithm with an improved initialization strategy to solve the constrained optimization problem of ICA-R that can asymptotically converge to the optimum. It completely avoids the formulation of a penalized contrast function and scaling (due to the Lagrangian multipliers) by incorporating the ICA contrast function and the violation of the closeness constraint into the selection process of the evolution. Experiments with synthetic data and isolation of $\mu $ rhythmic activity from EEG showed improved source extraction performance over ICA-R and its recent enhancements.

This paper presents an analysis of the tradeoff between repeated communications and computations for a fast distributed computation of global decision variables in a model-predictive-control (MPC)-based coordinated control scheme. We consider a coordinated predictive control problem involving uncertain and constrained subsystem dynamics and employ a formulation that presents it as a distributed optimization problem with sets of local and global decision variables where the global variables are allowed to be optimized over a longer time interval. Considering a modified form of the dual-averaging-based distributed optimization scheme, we explore convergence bounds under ideal and non-ideal wireless communications and determine the optimal choice of communication cycles between computation steps in order to speed up the convergence per unit time of the algorithm. We apply the algorithm for a class of dynamic-policy based stochastic coordinated control problems and illustrate the results with a simulation example.

For monitoring and diagnostics of the cardiovascular health, Electrocardiogram (ECG)is considered as a standard modality. However, direct contact of electrodes with skin, and signal corruption due to sweat and the daily-activity induced motion limits the use of conventional ECG in wearable-sensor based long term health monitoring devices. Accelerometers are light-weight, inexpensive and can be used simultaneously in multiple applications. Therefore, we propose an approach for generating pseudo-ECG from a chest-worn accelerometer. First a non-linear regression is identified between the chest surface acceleration and the conventional ECG signals. Based on the identified regression model, a pseudo-ECG signal is generated from the chest acceleration signal. The proposed method was validated on 15 trials data recorded from 3 human subjects. Results show that the generated ECG matches well with the real ECG with an average correlation coefficient of 0.8.

The lateral motion of an Automated Vehicle (AV) is highly affected by the model’s uncertainties and unknown external disturbances during its navigation in adverse environmental conditions. Among the variety of controllers, the sliding mode controller (SMC), known for its robustness towards disturbances, is considered to generate a robust control signal under uncertainties. However, conventional SMC suffers from the issue of high frequency oscillations, called chattering. To address the issue of chattering and reduce the effect of unknown external disturbances in the absence of precise model information, a radial basis function neural network (RBFNN) is employed to estimate the equivalent control. Further, a higher order sliding mode (HOSM) based switching control is proposed in this paper to compensate for the effect of external disturbances. The effectiveness of the proposed controller in terms of lane-keeping and lateral stability is demonstrated through simulation in a high-fidelity Carsim-Matlab Simulink environment under a variety of road and environmental conditions.

Vehicular ad hoc networks (VANETs) has received significant attention in the research domain of intelligent transportation system (ITS) as they provide safety and security to drivers and passengers. As compared to mobile ad hoc networks (MANETs), VANETs are mainly different in terms of characteristics, and system architecture. Security in VANET has been an important issue as it effects the communication between both (V-2-V) vehicles-to-vehicle and (V-2-I) vehicle to infrastructure. In VANET, malicious attacks affect the security of the networks, and it is necessary to identify and prevent such security attacks. In VANET network, any node can function as a router for the others nodes, and a malicious node connected to the network may inject spoofed routing tables to the other nodes thereby affecting the operation of the network. To overcome this issue, a secure AODV routing protocol is developed for detection of black hole attack in this paper. The proposed method is a modified version of the original AODV routing protocol with improvements in the RREQ packet and RREP packet protocols. For added security, a cryptography function-based encryption and decryption is included to verify the source and destination nodes. The proposed approach is demonstrated on a NS-2.33 simulator using different network parameters like drop packets, end-to-end delay, and packet delivery ratio (PDR) and routing request overhead. Results demonstrate that the proposed method outperforms existing AODV routing protocol under black hole attack and improves the network performance.

Recent works on brain functional analysis have accentuated the importance of distributed functional networks and synchronized activity between networks in mediating cognitive functions. The network perspective is important to relate mechanisms of brain functions and the basis for classifying brain states. In this work, the network patterns related to neural tasks based on synchronization measure phase-locking value (PLV) in an electroencephalogram (EEG) are analyzed. Based on network dissimilarities between the rest and motor imagery tasks, important nodes and channel pairs corresponding to motor tasks are identified. A framework is developed to identify these most reactive channel pairs that form the subject-specific functional network. The identified functional network corresponding to tasks demonstrate significant PLV variation in line with the experiment protocol. With the selection of subject-specific reactive band, these channel pairs provide even higher variation corresponding to tasks. To demonstrate the potential of the developed framework to brain–computer interface, identified network patterns are employed as features for classification of tasks. Analysis performed with the two classes (left-hand and right-hand motor imagery EEG data) showed that the proposed approach yielded better classification results compared to earlier band-power based approaches for single trial analysis.

Due to the significant growth in transportation industries, the importance of interactions between vehicle technologies and humans from the safety aspect plays an important role in the new developments of complex vehicle systems. Therefore, from academic and industrial viewpoints, increasing attention has been paid to complex vehicle correlative technologies with full consideration of issues like safety, robust performance, impact analysis, optimization, automation, motion control, etc. All aforementioned issues provide a basis for the design and operation of practical vehicle systems in order to achieve desired complex tasks.

Respiratory motion exhibits non-linear and non-stationary behavior in nature and this has been a great hindrance to the accurate prediction of tumor in motion adaptive radiotherapy. Accurate prediction of respiratory motion and subsequent tracking of tumor has been a challenge due to the irregularities and intra-trace variabilities. In order to overcome this issue, prediction models can be trained by using neural networks. However due to the burden of large training data, computational efficacy of existing neural networks can be affected. Moreover, training of neural networks using conventional methods like back-propagation (BP) may result in local minima and it may slow down the learning rate and convergence respectively. As a solution, in this paper, we employed random vector function link (RVFL) based neural networks to train the model in a very efficient way to achieve high accuracy in respiratory motion prediction. In RVFL, the direct link from input features to output layer acts as regularization to prevent the network from overfitting. The proposed method is tested with real respiratory motion traces acquired from 31 patients. Results show that RVFL with the use of direct link performs quite better than without direct link.

Better understanding of human balance control is pivotal for applications such as bipedal robots and medical technologies/therapies targeting human locomotion. Despite the inverted pendulum model being popular for describing bipedal locomotion, it does not properly capture the step-to-step transition dynamics. The major drawback has been the requirement for both feet to be on the ground which generates a discontinuity along the intersection of the potential energy surfaces produced by the two legs. To overcome this problem, we propose a generalized inverted pendulum-based model that can describe both single and double support phases. The full characterization of the system's potential energy allows the proposed model to drop the main limitation. This framework also enables optimal strategies to be designed for the transition between the two feet without the optimization algorithms. The proposed theory has been validated by comparing the human locomotor strategies output of our planner with real data from multiple experimental studies. The results show that our model generates trajectories consistent with human variability and performs better than existing well-known methods.

The motor control of human locomotion is still an open issue, and it may be the leading cause of the low effectiveness of lower limbs rehabilitation therapies. Locomotion motor control has proved to be fundamentally different from the upper limbs reaching task strategies, which have been used for the development of current motor control computational models used to define rehabilitation protocols. The main difference between these two tasks is the relevance of the environmental dynamics in task planning and execution. Reaching movements are dominated by the intrinsic impedance of the human body. On the other hand, locomotion is determined by the interaction between the human body and Earth's gravity. The dynamic primitives have been recently proposed to explain how humans account for the environmental dynamics during motor control; however, it is not yet possible to explain how the nervous system combines the information. This paper proposes and validates with human data that the brain controls locomotion to have the centre of mass moving between the two legs as a harmonic oscillator. This finding has enabled us to propose a control architecture that can explain how the motor primitives can be described as a special type of dynamics primitives.

In smart grid, energy resource management is highly complex large-scale optimization problem where the aim is to maximize the incomes while minimizing operational costs. Due to presence of mixed-integer variables and non-linear constraints, recently the use of evolutionary algorithms as a tool to find optimal and near-optimal solutions is becoming popular. The energy resource management problem further gets complicated if the uncertainty associated with the renewable generation, load forecast errors, electric vehicles scheduling and market prices are considered. Therefore, in a real-world scenario, it is essential to address the issues brought by the variability of demand, renewable energy, electric vehicles, and market price variations while maximizing the incomes and minimizing the total operation costs. In this paper, we analyze the performance of Differential Evolution with a stochastic selection on a large-scale energy resource management problem with uncertainty designed for competition at CEC 2018. The system comprises of a 25-bus microgrid representing a residential area with high penetration of Distributed Energy Resources (DER), Electric Vehicles (EVs), Demand Response (DR) programs etc.

Mobility impairment is a major challenge for the healthcare systems of developed countries. Balance deterio-ration is a physiological consequence of the ageing process, which makes it an endemic problem in ageing societies. Despite the importance of this issue, the development of appropriate therapies and protocols is challenging due to our limited understanding of human locomotion and equilibrium. This paper presents a technique that can track the BoS geometry from the feet' posture and its validation with healthy subjects. The proposed model uses a posture dependent reference frame called Saddle Space, which is aligned to the principal direction of the potential energy surface. The target application for the model described in this paper is the development of sensors for the evaluation of balance during activity of daily living. However, the proposed methodology can also be applied to bipedal robots, and the saddle space can also be employed to describe other posture dependent variables.

Digital filters are employed in hand-held robotic instruments to separate the concomitant involuntary physiological tremor motion from the desired motion of micro-surgeons. Inherent phase-lag in digital filters induces phase distortion (time-lag/delay) into the separated tremor motion and it adversely affects the final tremor compensation. Owing to the necessity of digital filters in hand-held instruments, multi-step prediction of physiological tremor motion is proposed as a solution to counter the induced delay. In this paper, a quaternion variant for extreme learning machines (QELMs) is developed for multi-step prediction of the tremor motion. The learning paradigm of the QELM integrates the identified underlying relationship from 3-D tremor motion in the Hermitian space with the fast learning merits of ELMs theories to predict the tremor motion for a known horizon. Real tremor data acquired from micro-surgeons and novice subjects are employed to validate the QELM for various prediction horizons in-line with the delay induced by the order of digital filters. Prediction inferences underpin that the QELM method elegantly learns the cross-dimensional coupling of the tremor motion with random quaternion neurons and hence obtained significant improvement in prediction performance at all prediction horizons compared with existing methods. Published version

The Cancer Genome Atlas (TCGA) cancer genomics dataset includes over 10,000 tumor-normal exome pairs across 33 different cancer types, in total >400 TB of raw data files requiring analysis. Here we describe the Multi-Center Mutation Calling in Multiple Cancers project, our effort to generate a comprehensive encyclopedia of somatic mutation calls for the TCGA data to enable robust cross-tumor-type analyses. Our approach accounts for variance and batch effects introduced by the rapid advancement of DNA extraction, hybridization-capture, sequencing, and analysis methods over time. We present best practices for applying an ensemble of seven mutation-calling algorithms with scoring and artifact filtering. The dataset created by this analysis includes 3.5 million somatic variants and forms the basis for PanCan Atlas papers. The results have been made available to the research community along with the methods used to generate them. This project is the result of collaboration from a number of institutes and demonstrates how team science drives extremely large genomics projects. The MC3 is a variant calling project of over 10,000 cancer exome samples from 33 cancer types. Over three million somatic variants were detected using seven different methods developed from institutions across the United States. These variants formed the basis for the PanCan Atlas papers.

This paper proposes a human implicit intent recognition system based on electroencephalography (EEG) signals, for developing an advanced interactive web service engine. We focus on identifying brain state transitions between intentions, and classifying a user's implicit intentions while viewing an image on a web page, based on an EEG experiment. We measure brain state changes between a navigational intention and an informational intention by using phase synchrony; i.e., the phase locking value (PLV) in an EEG. Comparing PLVs that correspond to the two intention states is useful for determining a human's implicit intention. In order to discriminate between a user's implicit intentions using a PLV, we must extract features based on an EEG analysis. For this purpose, we identify the most reactive band within the full band of brain signals. Theta (4-7 Hz), alpha (8-13 Hz), beta-1 (14-22 Hz), and beta-2 (23-30 Hz) bands are used to extract the EEG features from the most reactive EEG band. Subsequently, we select the most significant pairs (MSPs) that are highly reactive and correspond to the intention. According to the proposed method, these features are useful for: (i) showing the brain state transitions regarding intentions, and (ii) classifying a human's implicit intention using several classifiers such as a support vector machine (SVM), Gaussian Mixture Model (GMM), and Naive Bayes. We then compare the results of these classifiers. This study demonstrates the potential uses of these identified brain electrode pairs for cognitive detection and task classification in future brain-computer interface (BCI) applications. We propose a human intent recognition based on EEG signals.In order to classify human's implicit intentions, we extract some features using EEG analysis.The most reactive band and the most significant electrode pairs in the brain.We distinguish between human's implicit intentions based on phase locking values (PLV).

For effective tremor compensation in robotics assisted hand-held device, accurate filtering of tremulous motion is necessary. The time-varying unknown phase delay that arises due to both software (filtering) and hardware (sensors) in these robotics instruments adversely affects the device performance. In this paper, moving window-based least squares support vector machines approach is formulated for multistep prediction of tremor to overcome the time-varying delay. This approach relies on the kernel-learning technique and does not require the knowledge of prediction horizon compared to the existing methods that require the delay to be known as a priori . The proposed method is evaluated through simulations and experiments with the tremor data recorded from surgeons and novice subjects. Comparison with the state-of-the-art techniques highlights the suitability and better performance of the proposed method.

In Pareto-Dominance based multi-objective evolutionary algorithms (PDMOEAs), nondominated sorting (NDS) procedure plays significantly important role in mating and environmental selection of the solutions. However, NDS is computationally expensive as each solution needs to be compared on all objectives with all solutions in the population. Therefore, the complexity increases with increase in the number of objectives (M) and the number of individuals in the population (N). Therefore, designing an efficient NDS algorithm plays a prominent role in reducing the computational complexity of the MOEAs. In this paper, we propose a NDS algorithm that assigns solutions to the fronts in the ascending order of sum of objectives; by comparing with only solutions that are better than the respective solution in the sum of objectives. To demonstrate the effectiveness, we compared the proposed method with the existing efficient nondominated sorting (ENS) algorithm and Corner Sort (CS). The experimental results indicate the effectiveness of the proposed method in reducing the number of comparisons and runtimes as the number of objectives increases.

Extracranial robotic radiotherapy employs external markers and a correlation model to trace the tumor motion caused by the respiration. The real-time tracking of tumor motion however requires a prediction model to compensate the latencies induced by the software (image data acquisition and processing) and hardware (mechanical and kinematic) limitations of the treatment system. A new prediction algorithm based on local receptive fields extreme learning machines (pLRF-ELM) is proposed for respiratory motion prediction. All the existing respiratory motion prediction methods model the non-stationary respiratory motion traces directly to predict the future values. Unlike these existing methods, the pLRFELM performs prediction by modeling the higher-level features obtained by mapping the raw respiratory motion into the random feature space of ELM instead of directly modeling the raw respiratory motion. The developed method is evaluated using the dataset acquired from 31 patients for two horizons in-line with the latencies of treatment systems like CyberKnife. Results showed that pLRF-ELM is superior to that of existing prediction methods. Results further highlight that the abstracted higher-level features are suitable to approximate the nonlinear and non-stationary characteristics of respiratory motion for accurate prediction. Accepted version

To obtain a good dynamic control performance of permanent magnet synchronous motor (PMSM) drives, four sensors (one position, one DC-link voltage and at least two current sensors) are required for the control-loops. This paper deals with the unpredictable faults that occur in any one of the sensors using an advanced fault-tolerant control (FTC) scheme to provide continuous drive operation. The proposed FTC scheme comprises of two higher-order sliding mode (HOSM) observers and one Luenberger observer (LO) to generate the respective residuals, and provide the detection of all sensor faults. Moreover, HOSM controllers are designed to ensure finite-time convergence of the error trajectories. The designed scheme minimizes existing chattering phenomenon with good performance in terms of convergence speed and steady-state error. Evaluation results on a three-phase PMSM are presented to validate the effectiveness of the proposed FTC approach.

Physiological hand tremor causes undesirable vibration of hand-held surgical instruments which results in imprecisions and poor surgical outcomes. Existing tremor cancellation algorithms are based on detection of the tremulous component from the whole motion; then adding an anti-phase tremor signal to the whole motion to cancel it out. These techniques are based on adaptive filtering algorithms which need a reference signal that is highly correlated with the actual tremor signal. Hence, such adaptive approaches use a non-linear phase filter to pre-filter the tremor signal either offline or in real-time. However, pre-filtering causes unnecessary delays and non-linear phase distortions as the filter has frequency selective delays. Consequently, the anti-phase tremor signal cannot be generated accurately which results in poor tremor cancellation. In this paper, we present a new technique based on singular spectrum analysis (SSA) and its recursive version, that is, recursive singular spectrum analysis (RSSA). These algorithms decompose the whole motion into dominant voluntary components corresponding to larger eigenvalues and oscillatory tremor components having smaller eigenvalues. By selecting a group of specific decomposed signals based on their eigenvalues and spectral range, both voluntary and tremor signals can be reconstructed accurately. We test the SSA and RSSA algorithms using recorded tremor data from five novice subjects. This new approach shows the tremor signal can be estimated from the whole motion with an accuracy of up to 85% offline. In real-time, tolerating a delay of ≈ 72ms, the tremor signal can be estimated with at least 70% accuracy. This delay is found to be one-tenth of the delay caused by a conventional linear-phase bandpass filter to achieve similar performance in real-time. Accepted version

Chest surface motion is of significant importance as it contains information of respiratory and cardiac systems together with the complex coupling between these two systems. Chest surface motion is not only critical in radiotherapy, but also useful in personalized systems for continuous cardiorespiratory monitoring. In this dataset, a multimodal setup is employed to simultaneously acquire cardiorespiratory signals. These signals include high-density trunk surface motion (from 16 distinct locations) with VICON motion capture system, nasal breathing from a thermal sensor, respiratory effort from a strain belt and electrocardiogram in lead-II configuration. This dataset contains 72 trials recorded from 11 participants with a cumulative duration of approximately 215 min under various conditions such as normal breathing, breath-hold, irregular breathing and post-exercise recovery. The presented dataset is not only useful for evaluating prediction algorithms for radiotherapy applications, but can also be employed for the development of techniques to evaluate the cardio-mechanics and hemodynamic parameters of chest surface motion. Machine-accessible metadata file describing the reported data (ISA-Tab format)

BCI systems that rely on EEG signals usually employ Fourier based methods for time-frequency decomposition and for subsequent feature extraction. The band-limited multiple Fourier linear combiner is well suited for such band-limited signals due to its real-time applicability. Despite the improved performance of these techniques in two channel settings, its application in multiple-channel EEG is not straightforward and challenging. As more channels are available, a spatial filter will be required to eliminate the noise and preserve the required useful information. Moreover, multiple-channel EEG also adds the high dimensionality to the frequency feature space. Feature selection will be required to stabilize the performance of the classifier. In this paper, we develop a new method based on Evolutionary Algorithm (EA) to solve these two problems simultaneously. The real-valued EA encodes both the spatial filter estimates and the feature selection into its solution and optimizes it with respect to the classification error. Three Fourier based designs are tested in this paper. Our results show that the combination of Fourier based method with co-variance matrix adaptation evolution strategy (CMA-ES) has the best overall performance.

Particle swarm optimization (PSO) has gained significant attention for solving numerical optimization problems in different applications. However, the performance of PSO depends on the appropriate setting of inertia weight and the optimal setting changes with generations during the evolution. Therefore, different adaptive inertia weight strategies have been proposed. However, the best inertia weight adaptive strategy depends on the nature of the optimization problem. In this paper, different inertia weight strategies such as linear, Gompertz, logarithmic and exponential decreasing inertia weights as well as chaotic and oscillating inertia weight strategies are explored. Finally, PSO with an adaptive ensemble of linear & Gompertz decreasing inertia weights is proposed and compared with other strategies on a diverse set of benchmark optimization problems with different dimensions. Additionally, the proposed method is incorporated into heterogeneous comprehensive learning PSO (HCLPSO) to demonstrate its effectiveness.

Continuous and non-invasive monitoring of hemodynamic parameters through unobtrusive wearable sensors can potentially aid in early detection of cardiac abnormalities, and provides a viable solution for long-term follow-up of patients with chronic cardiovascular diseases without disrupting the daily life activities. Electrocardiogram (ECG) and siesmocardiogram (SCG) signals can be readily acquired from light-weight electrodes and accelerometers respectively, which can be employed to derive systolic time intervals (STI). For this purpose, automated and accurate annotation of the relevant peaks in these signals is required, which is challenging due to the inter-subject morphological variability and noise prone nature of SCG signal. In this paper, an approach is proposed to automatically annotate the desired peaks in SCG signal that are related to STI by utilizing the information of peak detected in the sliding template to narrow-down the search for the desired peak in actual SCG signal. Experimental validation of this approach performed in conventional/controlled supine and realistic/challenging seated conditions, containing over 5600 heart beat cycles shows good performance and robustness of the proposed approach in noisy conditions. Automated measurement of STI in wearable configuration can provide a quantified cardiac health index for long-term monitoring of patients, elderly people at risk and health-enthusiasts.

Siemocardiography is a non-invasive technique for cardiomechanical assessment by analyzing the local vibrations on chest surface which can be readily acquired from cost-effective accelerometers. The peaks in siesmocardiogram (SCG) signal correspond to underlying mechanical events in heart cycle and have numerious potential clinical and health-awareness applications. However, utilization of SCG signal requires annotation of these peaks that is challenging due to variations in inter-subject morphology and noise prone characteristics of SCG signal. In this paper, we propose an approach to automatically annotate the desired peaks in SCG signal that are required for systolic time intervals (STI). The approach is based on formulating sliding template for the oncoming beat which is less noisier and hence desired peak detection is easier. The information of peak detected in the sliding template is then used to narrow-down the search of desired peak in actual signal.

Tremor is the root cause for human imprecision during microsurgery. Accurate filtering of physiological tremor is extremely important for compensation in robotics assisted microsurgical instruments/procedures. A study on several surgeons tremor is conducted and the characteristics of the tremor are analyzed. A double adaptive bandlimited multiple Fourier linear combiner is designed to estimate the modulated signals with multiple frequency components for filtering and compensation of tremor in real-time. A separation procedure to separate the intended motion/drift from the tremor portion is developed. The proposed methods are compared with the existing weighted-frequency Fourier linear combiner (WFLC) algorithm on the tremor data of surgeons/subjects. Critical validation of the algorithm is performed, experiments are conducted for 1-degree of freedom (DOF) cancellation of tremor. Our experiments showed that our newly developed algorithm has a tremor compensation of at least 65% compared to 46% for the WFLC algorithm.

IF=2.048; International audience; This paper focuses on the design of fixed-time consensus for first order multi-agent systems with unknown inherent nonlinear dynamics. A distributed control protocol, based on local information, is proposed to ensure the convergence of the tracking errors in finite time. Some conditions are derived to select the controller gains in order to obtain a prescribed convergence time regardless of the initial conditions. Simulations are performed to validate the theoretical results.

The brain functional network perspective forms the basis to relate mechanisms of brain functions. This work analyzes the network mechanisms related to human emotion based on synchronization measure - phase-locking value in EEG to formulate the emotion specific brain functional network. Based on network dissimilarities between emotion and rest tasks, most reactive channel pairs and the reactive band corresponding to emotions are identified. With the identified most reactive pairs, the subject-specific functional network is formed. The identified subject-specific and emotion-specific dynamic network pattern show significant synchrony variation in line with the experiment protocol. The same network pattern are then employed for classification of emotions. With the study conducted on the 4 subjects, an average classification accuracy of 62 % was obtained with the proposed technique.

The EEG signals employed for BCI systems are generally band-limited. The band-limited multiple Fourier linear combiner (BMFLC) with Kalman filter was developed to obtain amplitude estimates of the EEG signal in a pre-fixed frequency band in real-time. However, the high-dimensionality of the feature vector caused by the application of BMFLC to multi-channel EEG based BCI deteriorates the performance of the classifier. In this work, we apply evolutionary algorithm (EA) to tackle this problem. The real-valued EA encodes both the spatial filter and the feature selection into its solution and optimizes it with respect to the classification error. Three BMFLC based BCI configurations are proposed. Our results show that the BMFLC-KF with covariance matrix adaptation evolution strategy (CMAES) has the best overall performance.

Physiological tremor is an involuntary and rhythmic movement of the body specially the hands. The vibrations in hand-held surgical instruments caused by physiological tremor can cause unacceptable imprecision in microsurgery. To rectify this problem, many adaptive filtering-based methods have been developed to model the tremor to remove it from the tip of microsurgery devices. The existing tremor modeling algorithms such as the weighted Fourier Linear Combiner (wFLC) algorithm and its extensions operate on the x, y, and z dimensions of the tremor signals independently. These algorithms are blind to the dynamic couplings between the three dimensions. We hypothesized that a system that takes these coupling information into account can model the tremor with more accuracy compared to the existing methods. Tremor data was recorded from five novice subjects and modeled with a novel quaternion weighted Fourier Linear Combiner (QwFLC). We compared the modeling performance of the proposed QwFLC with that of the conventional wFLC algorithm. Results showed that QwFLC improves the modeling performance by about 20% at the cost of higher computational complexity.

Successful treatment of tumors with motion-adaptive radiotherapy requires accurate prediction of respiratory motion, ideally with a prediction horizon larger than the latency in radiotherapy system. Accurate prediction of respiratory motion is however a non-trivial task due to the presence of irregularities and intra-trace variabilities, such as baseline drift and temporal changes in fundamental frequency pattern. In this paper, to enhance the accuracy of the respiratory motion prediction, we propose a stacked regression ensemble framework that integrates heterogeneous respiratory motion prediction algorithms. We further address two crucial issues for developing a successful ensemble framework: (1) selection of appropriate prediction methods to ensemble (level-0 methods) among the best existing prediction methods; and (2) finding a suitable generalization approach that can successfully exploit the relative advantages of the chosen level-0 methods. The efficacy of the developed ensemble framework is assessed with real respiratory motion traces acquired from 31 patients undergoing treatment. Results show that the developed ensemble framework improves the prediction performance significantly compared to the best existing methods.

Prediction of respiratory motion to ablate tumors in chest and abdominal region is non-trivial because of the presence of intra-trace variabilities and irregularities. In recent past, several signal processing methods have been developed to model and predict respiratory motion. However, their prediction performance is susceptible to prediction horizons, irregularities and intra-trace variabilities. To counter these limitations and hence to enhance the prediction performance, in this paper, we proposed a moving window based online training approach for least squares support vector machines (LS-SVM) for respiratory motion prediction. To validate the proposed method, experiments have been conducted on ten real-respiratory motion traces. Results show that, the proposed online approach reduces prediction error compared to the conventional LS-SVM. Further, results demonstrate that the proposed approach provides better prediction performance than existing respiratory motion prediction methods.

IF=0.877; International audience; The suspension system is faced with nonlinearities from the spring, damper, and external excitations from the road surface. The objective of any control action provided to the suspension is to improve ride comfort while ensuring road holding for the vehicle. In this work, a robust higher order sliding mode algorithm combining the merits of the modified supertwisting algorithm and the adaptive supertwisting algorithm has been proposed for the nonlinear active suspension system. The proposed controller is robust to linearly growing perturbations and bounded uncertainties. Simulations have been performed for different classes of road excitations and the results are presented.

I t is often difficult to analyze biological signals because of their nonlinear and non-stationary characteristics. This necessitates the usage of time-frequency decomposition methods for analyzing the subtle changes in these signals that are often connected to an underlying phenomena. This paper presents a new approach to analyze the time-varying characteristics of such signals by employing a simple truncated Fourier series model, namely the band-limited multiple Fourier linear combiner (BMFLC). In contrast to the earlier designs, we first identified the sparsity imposed on the signal model in order to reformulate the model to a sparse linear regression model. The coefficients of the proposed model are then estimated by a convex optimization algorithm. The performance of the proposed method was analyzed with benchmark test signals. An energy ratio metric is employed to quantify the spectral performance and results show that the proposed method Sparse-BMFLC has high mean energy (0.9976) ratio and outperforms existing methods such as short-time Fourier transfrom (STFT), continuous Wavelet transform (CWT) and BMFLC Kalman Smoother. Furthermore, the proposed method provides an overall 6.22% in reconstruction error.

In this paper, we introduce a hybrid method for prediction of respiratory motion to overcome the inherent delay in robotic radiosurgery while treating lung tumors. The hybrid method adopts least squares support vector machine (LS-SVM) based ensemble learning approach to exploit the relative advantages of the individual methods local circular motion (LCM) with extended Kalman filter (EKF) and autoregressive moving average (ARMA) model with fading memory Kalman filter (FMKF). The efficiency the proposed hybrid approach was assessed with the real respiratory motion traces of 31 patients while treating with CyberKnife(TM). Results show that the proposed hybrid method improves the prediction accuracy by approximately 10% for prediction horizons of 460 ms compared to the existing methods.

Surface chest motion can be easily monitored with a wide variety of sensors such as pressure belts, fiber Bragg gratings and inertial sensors, etc. The current applications of these sensors are mainly restricted to respiratory motion monitoring/analysis due to the technical challenges involved in separation of the cardiac motion from the dominant respiratory motion. The contribution of heart to the surface chest motion is relatively very small as compared to the respiratory motion. Further, the heart motion spectrally overlaps with the respiratory harmonics and their separation becomes even more challenging. In this paper, we approach this source separation problem with independent component analysis (ICA) framework. ICA with reference (ICA-R) yields only desired component with improved separation, but the method is highly sensitive to the reference generation. Several reference generation approaches are developed to solve the problem. Experimental validation of these proposed approaches is performed with chest displacement data and ECG obtained from healthy subjects under normal breathing and post-exercise conditions. The extracted component morphologically matches well with the collected ECG. Results show that the proposed methods perform better than conventional band pass filtering.

The estimation of road excitation profile is important for evaluation of vehicle stability and vehicle suspension performance for autonomous vehicle control systems. In this work, the nonlinear dynamics of the active automotive system that is excited by the unknown road excitation profile are considered for modeling. To address the issue of estimation of road profile, we develop an adaptive supertwisting observer for state and unknown road profile estimation. Under Lipschitz conditions for the nonlinear functions, the convergence of the estimation error is proven. Simulation results with Ford Fiesta MK2 demonstrate the effectiveness of the proposed observer for state and unknown input estimation for nonlinear active suspension system.

Performance of robotics based hand-held surgical devices in real-time is mainly dependent on accurate filtering of physiological tremor. The presence of phase delay in sensors (hardware) and filtering (software) processes affects the cancellation accuracy. This paper focuses on developing an estimation algorithm to improve the estimation accuracy in the presence of phase delay for real-time implementations. Moving window based online training approach for least squares-support vector machines (LSSVM) is employed in this paper for tremor estimation. A study is conducted with tremor data recorded from the subjects to analyze the suitability of proposed approach for both single-step and multi-step prediction.