A Comparative Study of Machine Learning Algorithms for EEG Signal Classification
Improving Long Term Myoelectric Decoding, Using an Adaptive Classifier with Label Correction
1. Improving Long Term Myoelectric Decoding, Using an Adaptive
Classifier with Label Correction
Sarthak Jain, Girish Singhal, Ryan J. Smith, Rahul Kaliki and Nitish Thakor
Abstract— This study presents a novel adaptive myoelectric
decoding algorithm for control of upper limb prosthesis. Myo-
electric decoding algorithms are inherently subject to decay in
decoding accuracy over time, which is caused by the changes
occurring in the muscle signals. The proposed algorithm relies
on an unsupervised and on demand update of the training
set, and has been designed to adapt to both the slow and fast
changes that occur in myoelectric signals. An update in the
training data is used to counter the slow changes, whereas
an update with label correction addresses the fast changes in
the signals. We collected myoelectric data from an able bodied
user for over four and a half hours, while the user performed
repetitions of eight wrist movements. The major benefit of the
proposed algorithm is the lower rate of decay in accuracy;
it has a decay rate of 0.2 per hour as opposed to 3.3 for
the non adaptive classifier. The results show that, long term
decoding accuracy in EMG signals can be maintained over
time, improving the performance and reliability of myoelectric
prosthesis.
I. INTRODUCTION
Over the past few years there has been a significant ad-
vance in the capabilities offered by prosthetic devices. Today,
prosthetic devices more closely resemble human hands, and
have dramatically improved from the previously available
hooks. With the advances made in the capability of the me-
chanical parts and the various additional degrees of freedom
offered, there is an increased interest in pattern recognition
based devices, which promise to offer users control over
various additional degrees of freedom. However, despite the
limited functionality offered by proportional control based
devices, as compared to pattern recognition based devices
[1], proportional control based devices are still preferred by
amputees since pattern recognition of EMG signals has not
yet achieved clinical impact.
Pattern recognition based systems focus on creating a
classification system, which is used to separate the incoming
muscle signals into various discrete positions. This allows
users the freedom to perform various discrete gestures with
their prosthetic limb. Such techniques have been shown to
demonstrate decoding accuracies over 90% for five or more
distinct gestures [2]–[6].
This research was supported in part by National Institutes of Health R44
NS065495.
Sarthak Jain (email: sarthak@iitgn.ac.in) and Girish Singhal are with
the Department of Electrical Engineering, Indian Institute of Technology
Gandhinagar, Gujarat India 382424
Ryan J. Smith and Nitish V. Thakor are with the Department of Biomedi-
cal Engineering, The Johns Hopkins University, Baltimore, Maryland, USA.
Rahul Kaliki is with the Infinite Biomedical Technologies LLC, Balti-
more, Maryland, USA.
However, these experiments were performed for a short
duration, under strict laboratory settings and fail to to con-
sider the long term effects. Most studies assume that the
signal process remains stationary over time, therefore, they
neglect modeling changes in the signals over time. A major
reason for the lack of stable decoding performance, for such
applications, is the change in the underlying probabilistic
distributions generating the data. A change in the statistics
of the signal is referred to as concept drift [7]–[10].
Two forms of concept drift have been described in litera-
ture, (1) gradual concept drift and (2) sudden (also referred
to as fast, abrupt and instantaneous) concept drift. It is
important to model both these kinds of drift with respect
to the classifier, since both are detrimental towards the
performance of the system [10], [11].
Concept drift in myoelectric coding may be caused due to
variations in electrode conductivity (perspiration, humidity),
electro-physiological factors (muscle fatigue, atrophy, or
hypertrophy), spatial orientation (electrode movement on the
skin or soft tissue fluid fluctuations), user intent (cognitive
intent variations or contraction intensity changes), and po-
tentially other factors [12].
To achieve a significant improvement in long term decod-
ing accuracies, it is important to counteract the changes in
the myoelectric signals. One of the first barriers in tackling
changes in the underlying signal process is to detect when
changes occur, known as concept drift detection [9], [13].
Once concept drift has been detected, the changes need to
be categorized into slow or fast concept drift. If slow concept
drift has occurred, an update in the classifier is performed
based on the newly encountered data, retraining the classifier,
making it capable of classifying recently encountered data
with high accuracy. In the case where fast concept drift has
occurred, the classifier does not have access to the correct
labels for the recently processed data, as true labels are
unavailable in an unsupervised setting. Fast concept drift is
more likely to produce mislabeling in the new training set
due to the sudden movement of data in the feature space. This
leads to a significant problem, as updating the classifier based
on mislabeled data leads to a badly trained classifier, which
is sure to propagate error over time. However, if corrected
labels are assigned to the mislabeled instances, it is possible
to deal with the problem by updating the classifier based
on recent data in the same way in which slow concept drift
is dealt with.Various studies, in different fields, dealing with
such phenomena have proposed schema for relabeling which
provides the classifier with an improved label set as opposed
to the case where there are misclassifications in the labels of
2. Distribution
Underlying
t=0
t=T
Class 1 Class 2 Decision Boundary
(a) Slow Concept Drift
Distribution
Underlying
t=0
t=T
Class 1 Class 2 Decision Boundary
(b) Fast Concept Drift
Fig. 1: The figures show the plot of time versus a particular dimension in which the classifier can seperate the data. The
figure shows the two types of concept drift, figure 1a shows the change in the distribution from t=0 where the classifier was
trained to t=T when the classifier is used to make a prediction. As a result of slow concept drift, the data has moved but
can still be classified correctly, as well as be used to train a new classifier as we have the correct labels avaialable. In figure
1b demonstrates fast concept drift where the data moves a considerable distance and part of the data is missclassified and
hence cannote be used to train a new classifier. Both the images are created using simulated data, using unimodal gaussian
distributions.
the data that the classifier is trained on [14]–[17].
We propose a novel classification architecture which mod-
els both slow and fast changes in the data. By updating
the classifier once concept drift is detected we mitigate the
effects of slow concept drift. To battle fast concept drift,
we propose label correction algorithm, which corrects the
labels to be used in the new training set, helping maintain a
consistently accurate classifier all throughout our experiment.
II. METHODS
A. Experimental Procedure
The study involved muscle signal data collection from
a single able bodied user. The study was performed with
the approval of the Johns Hopkins University Institutional
Review Board, with prior consent of all the subjects.
We used 16 electrodes, in 8 bipolar pairs. the electrodes
used were 3/8” stainless steel dome electrodes with snap
connectors (Liberating Technologies INC., Holliston, MA)
each of which were embedded inside a silicon cuff, placed on
the dominant arm of the able-bodied subject. The electrode
pairs were place equidistantly over the cross section of the
subjects arm. An additional Cleartrace LT electrode (Conmed
Corporation, Utica, NY), used as a ground electrode, was
placed on the subjects olecranon.
B. Recording Setup and Data Collection
Differential signal from the electrodes were sent to mod-
ified Otto Bock EMG Amplifiers (MYOBOCK, Otto Bock
Healthcare, Minneapolis, MN), whose output was sent to a
computer using a 16-bit data acquisition card (PCI-6040E,
National Instruments, Austin, TX) using a custom-made
electrical isolation board and I/O connector block (SCC-68,
National Instruments, Austin, TX), the system sampled the
EMG signals at 1 kHz.
The subject performed the various gestures as directed
by cues appearing on a computer screen. The labels
corresponded to eight distinct gestures: hand open/close
(HO/HC), wrist flexion/extension (WF/WE), forearm prona-
tion/supination (FP/FS), precision grasp (PG) and index
finger point (IP). All subjects performed gestures on the limb
ipsilateral to the electrode location.
The four and a half hour data collection period was
broken down into fifteen separate sessions, the user was given
fifteen minute breaks between sessions. The user continued
to wear the silicon cuff with the electrodes for the entire
experimental period. Each of these sessions comprised of the
user performing 10 repetitions of each of the eight gestures,
which appeared in a random order. The user was directed to
hold the gesture for between 2.5 and 3.5 seconds, following
a rest period of between 2.5 and 3.5 seconds as well.
C. Classifier: Linear Discriminant Analysis
The classifier used for this study was Linear Discrimi-
nant Analysis, which has been proven to be effective for
myoelectric decoding through previous studies [18], [19].
Discrimination is done by projecting the incoming data
into the dimension in which the inter class distance is
maximized while minimizing the intra class variance. The
feature extraction technique used was Time Domain Auto
Regressive (TDAR) as demonstrated by [2], [20]. A total of
56 features were used, seven features per channel, including
four coefficients of forth order auto regressive model and
three time domain feature values, namely mean absolute
value, variance and slope sign changes. We use a window of
length 250ms and slide size of 25ms for extracting features.
While using Linear Discriminant Analysis as a classifier
the posterior probability is given as a vector:
Φ = [φ1, φ2, ...φp] (1)
3. If
Slow Drift
If
Fast Drift
Majority
Relabeling
PCA
Relabeling
Feature
Extraction
Classification
Entropy
Yes
No
Yes
Relabeling
Concept Drift
Detection
Output
Classifier
Update
Retraining
Onset
Detection
Fig. 3: Block Diagram of the Proposed System.
where φi represents the probability of an instance belong-
ing to a particular class i, each φi is given by:
φi =
1
1 + exp− 8
j=1,j=i wT
i,j x
(2)
where wi,j is the projection vector of the LDA to separate
class i from j, x is the original input vector.
D. Concept Drift Detection
Concept drift is detected when the data moves away from
its previously observed statistical state. This can be quantified
as data moving closer to the decision boundary or crossing it.
The probability function for a Linear Discriminant Analysis
based classifier is shown to be a monotonic function in
the distance from the decision boundary, given by wT
i,jx.
Therefore, we can use the probabilities directly as measure of
concept drift. Entropy gives us a measure of the uncertainty
associated with a random variable, which is a better indicator
of how far data is from a decision boundary. Entropy is given
by:
η = − logn Φ × ΦT
(3)
Where n is the number of distinct labels that can be
assigned to the data point.
We use the entropy to predict whether concept drift has
occurred, using two separate threshold based criteria. The
detection of concept drift is done at defined intervals of
time; by summation of entropy in windows, of length τ, and
comparing this value to the predefined thresholds. α is the
threshold for slow concept drift, which if crossed, we retrain
the classifier based on recently encountered data, using labels
as predicted by the classifier output. If the entropy crosses β
we detect fast concept drift for which we retrain the classifier
after having performed relabeling. We perform relabeling
on the instances constituting the new training set, this is
described in a later section. We set these thresholds based
on previously observed statistics of the entropy for the user
as given by:
µ = 1
τ j ηj
σ = 1
τ j(ηj − µ)2
α = µ + σ
β = µ + 4 ∗ σ
(4)
Where ηk represents the entropy for the kth
instance, µ
and σ are calculated based on the entropy of the training
set. Values of α and β can be empirically determined offline.
The value of τ chosen for this study was set to 48 gestures,
which corresponded to 6 repetitions of each gesture; this
corresponds to approximately 4 minutes of data collection.
We check for an increase in entropy after every λ number of
movements, for our experiment we selected λ as 24 gestures.
E. Update for Slow Concept Drift
A small increase in entropy implies slow concept drift
has occurred. At this time we update the classifier by
retraining it on the recently encountered data, this ensures
the classifier can classify the data after concept drift has
occurred. Constant update allows us to maintain a classifier
which is capable of classifying the most recently encountered
data with high accuracy. In its current version the algorithm
does not have any inclusion rules for the new training set.
We currently include the last τ encountered points where
τ is size of the training set. The previous training set is
completely discarded, however the rules for data inclusion
and exclusion can be modified if required.
F. Relabeling for Fast Concept Drift
To tackle the problem of incorrectly labeled data, we
present a relabeling algorithm which removes the misclassifi-
cations from the data, based on the knowledge of the updated
statistics, along with information available about when the
gestures were performed through the Teager Kaiser Energy
Operator (TKEO) as described in [21]. The algorithm has
three different parts, which are described as follows:
1) Majority Label Correction: Based on the assumption
that a user performs only a particular gesture between gesture
onset and gesture offset as determined by the TKEO operator,
we correct for the spurious misclassifications that occur in
between an isolated gesture. This information regarding the
gesture allows us to easily correct for mislabeled instances in
the duration of a gesture. We determine the most frequently
occurring class for this gesture and assign it to the entire
duration of the gesture.
In the case where abrupt concept drift occurs, it is possible
that a part of the gesture is correctly labeled and a part,
of comparable size, is mislabeled. In such a case we use a
separate criteria, this is if the number of occurrences of the
modal class are not sufficiently higher than the number of
instances of the another class, in such a case, we assign
the gesture two labels. We call such a case competitive
relabeling, which assumes two labels for the data which are
corrected through an additional step.
4. 0 1 2 3 4
Cue
Onset
Channel 1
Channel 2
Channel 3
Channel 4
Channel 5
Channel 6
Channel 7
Channel 8
Filtered EMG, 30-300Hz
Time in Seconds
0 1 2 3 4
EMG post TKEO Operator
Time in Seconds
0 1 2 3 4
EMG post TKEO with 10 Hz LPF
Time in Seconds
Fig. 2: The figure shows the use of the Teager Keiser Energy Operator to detect movement onset and offset. The Raw signal
after filtering, the signal after applying the TKEO and the signal after further low pass filtering are shown. As can be seen
from the figure there is a delay caused due to response time of the subject which needs to be accounted for as well as the
a delay caused by the TKEO based detection scheme.
2) Statistics based Relabeling, using PCA based cross
validation: Our given training data is now corrected for
jitter and spurious misclassifications within gestures. It is
however, still subject to misclassified instances which now
occur over entire gestures, along with multiple labels for a
single gesture. To recover from such a scenario we consider
each individual gesture and attempt to relabel it based on the
statistics of the available data belonging to the same class.
It has been demonstrated in various studies that given the
statistics of correctly labeled data it is possible to create
a model based on these statistics and reassign labels to
misclassified instances [14], [15], [17]. Considering a two
class problem, we first project all of the data belonging to the
two classes into m dimensional space from the original 56 di-
mensions, with the objective of capturing maximum variance.
For such a projection we use a Principal Component Analysis
as the preferred method for dimensionality reduction. It is
preferred over Linear Discriminant Analysis since it is class
independent [22], which is essential for class reallocation. A
dimensionality reduction technique is required to maintain
real-time performance as this step needs to be performed
multiple times, once for each of the gestures.
We then select all the gestures belonging to the selected
two classes (i, j), we refer to this data as Yi,Yj, this data
excludes the selected gesture k, Xk
. We create a logistic
regression model to separate the two selected classes based
on data Yi, Yj which allows us to predict which class does
Xk
belongs to. If the gesture in question (Xk
) initially
belonged to the class i, we perform this analysis for all j
1, .., 8 j = i. Such an analysis produces a score for each class
j, based on the number of points output by the regression
model belonging to class j. We reassign the label to gesture
Xk
with the maximum score, if it is above a certain threshold
δ. This process is carried out for all of the gestures and the
entire analysis is repeated till no further relabeling occurs.
dk
i,j,n = uT
i,jXk
n
mk
i,j,n =
1 if
1
1 + e−(vk
i,j
T
dk
i,j,n)
> 0.5
0 otherwise
sk
i,j =
offest
n=onset(mk
i,j,n)
if(maxj sk
i,j) > α : C (Xk
) = arg maxj sk
i,j
(5)
where C (Xk
) are the class labels corresponding to the
gesture Xk
, sk
i,j is the score attached with each class j,
ui,j is the projection vector as determined by the principle
component analysis, vk
i,j is the projection vector given by the
logistic regression model. n is the instance between onset and
offset, mk
i,j,n is the score output of the logistic regression
model while considering gesture k.
III. RESULTS
A. Overall Performance and Decay
The first major improvement is the decay in decoding
accuracy of the system, which significantly improves for the
adaptive system as compared to the non adaptive system.
The decay in accuracy per hour for an adaptive system is
0.2 as opposed to a decay in accuracy of 3.3 for a non
adaptive system. These results were determined by fitting a
linear model through the available data. The improvement
5. 2 4 6 8 10 12 14
75
80
85
90
Non Adaptive
Adaptive
(a) Mean Decoding Accuracy Vs Sessions Since Initial
Training.
2 4 6 8 10 12 14
75
80
85
90
95
100
Without Relabeling
With Relabeling
(b) Mean Accuracy Training Set Vs Sessions Since
Initial Training
Fig. 4: The figures show the key results of the proposed algorithm, 4a is the plot of the mean accuracy over a session
versus the session after supervised training. It shows the improvement due to the adaptive system can be seen from the
significant difference between the two methods towards the end. 4b shows the plot of the mean accuracy of the training set
(the accuracy of the data used to create the classifier). The improvement in the accuracy of the training set over the sessions
shows the reason why the decoding accuracy is higher for the proposed algorithm.
in performance due to the proposed method can be seen
from the plot of the decoding accuracy vs the session after
training 4a. In the figure the gap between the non adaptive
and adaptive classifier is seen to widen in later sessions.
The mean decoding accuracy over the entire four and a half
hours, for the proposed method is 86.8±2.57%, as opposed
to 78.4±2.33% for a non adaptive system. Table I shows the
improvement in decoding accuracy for each of the 8 classes,
along with the decay in accuracy per hour for each of the
classes.
B. Movement Specific Analysis
There is a significant improvement shown in decoding the
accuracy of Index Point which has a decay rate of 10%
per for the non adaptive system but is significantly reduced
and even improves after the initial training. In terms of
overall improvement there is a 42% improvement in absolute
decoding accuracy of the Index Point, which corresponds
to about 60 repitions of the grip Index Point decoded
correctly which were previously incorrectly decoded. There
is a minor reduction in accuracy for two classes because,
in later sessions, the non adpative classifier became biased
towards those, which led to very poor decoding accuracies
for other classes.
C. Improvement by Relabeling
The addition of relabeling to the training set causes a mean
absolute improvement of 7.05±2.35% in the mean accuracy
of the training set calculated over the entire experiment for
all subjects. The improvement in the accuracy of the training
set helps maintain a suitable classifier, which can decode
the incoming data with a higher accuracy, the % accuracy
of the training set as a function of sessions after the initial
supervised training set can be seen from the figure 4b.
TABLE I: Results
Improvement in Decay per Hour
Movement Decoding Accuracy Non Adaptive Adaptive
HO 2.98 -0.54 0
HC -4.28 -1.2 -4.8
FP 8.35 -1.65 0.45
FS 7.19 -2.97 -0.21
WF 0.48 -0.39 -0.48
WE 10.22 -5.52 -0.15
IP 41.98 -9.45 4.08
PG -1.32 -1.2 -0.48
Overall 8.2 3.3 0.2
IV. DISCUSSION
In this study we have proposed a novel decoding algorithm
for use with myoelectric prosthesis, the proposed algorithm
consists of an Adaptive Linear Discriminant Analysis Clas-
sifier which had update rules based on the entropy of the
current samples. Along with the adaptive classifier, we also
proposed a relabeling mechanism which corrects for spuri-
ous labels that are output by the classifier. The relabeling
occurs when the entropy levels cross a particular threshold
after which retraining occurs. Such a method is considered
unsupervised since we do not have access to the true labels
and the only access we have to the true data is through the
initial training session, which makes this algorithm suitable
for real time implementation. The user would not be required
to provide any input to the system after the initial training
session which is essential for real time usage. The proposed
algorithm significantly improved the stability of the decoding
accuracies over time, which has been a major concern. The
decay in accuracies over time has prevented prevalent use of
pattern recognition based myoelectric prosthesis.
A major reason for improvement is that the adaptive sys-
6. tem ensures a model, capable of accurately decoding newly
encountered data, is maintained throughout. The reason for
the improved model is the adaptive classifier; having an
adaptive system ensures the model is constantly updated to
fit newly encountered data well. Also the relabeling process
ensures the classifier is trained on correct data. Having an
adaptive model that is trained on correct data and models
recent data well is another major reason for the improved
decoding accuracy.
However the efficacy of the system can only be validated
through more experiments performed with both amputee
and able bodied subjects. A major question mark for any
myoelectric decoding system is the usability for amputees,
since experiments with amputees provide a unique problem
of lack of visual feedback. Since amputees do not receive
visual feedback due to a missing appendage, the way they
perform movements is likely to change as time progress, this
can be thought of as another form of concept of drift, which
is currently not captured in this experiment.
Another proposed challenge is modeling several kinds
of concept drift; this experiment has looked at long term
decoding accuracy, but is not an exhaustive set of all possible
causes of concept drift, a large amount of data will need to be
acquired from both amputee and able bodied subjects, which
should help us better understand all the possible causes of
concept drift. For example this experiment did not have any
electrode drop out or electrode displacement, such problems
can cause a major change in the signals which make it very
difficult for the model to accurately decode.
V. CONCLUSION
To be viable solutions for amputees, pattern recognition
based myoelectric devices require a significant increase in
robustness with respect to long term stability in decoding
accuracies. In this study we present an algorithm to solve
this problem, using an adaptive decoding algorithm which
using only training data provided at the beginning, adapts
to changes and presents stable decoding in an unsupervised
setting. The study demonstrates stable decoding accuracies
for more than four hours an able bodied subject. Such an
algorithm promises real time implementation, given the low
computational complexity of the algorithm, since it only
requires update of the classifier when an increase in the
systems entropy is detected. However, the efficacy of the
algorithm will need to be validated in future work through
amputee subjects.
REFERENCES
[1] B. Hudgins, P. Parker, and R. Scott, “A new strategy for multifunction
myoelectric control,” Biomedical Engineering, IEEE Transactions on,
vol. 40, no. 5, pp. 82 –94, jan. 1993.
[2] K. Englehart and B. Hudgins, “A robust, real-time control scheme
for multifunction myoelectric control,” Biomedical Engineering, IEEE
Transactions on, vol. 50, no. 7, pp. 848 –854, july 2003.
[3] M. Oskoei and H. Hu, “Support vector machine-based classification
scheme for myoelectric control applied to upper limb,” Biomedical
Engineering, IEEE Transactions on, vol. 55, no. 8, pp. 1956 –1965,
aug. 2008.
[4] K. Farry, I. Walker, and R. Baraniuk, “Myoelectric teleoperation of a
complex robotic hand,” Robotics and Automation, IEEE Transactions
on, vol. 12, no. 5, pp. 775 –788, oct 1996.
[5] J.-U. Chu, I. Moon, Y.-J. Lee, S.-K. Kim, and M.-S. Mun, “A super-
vised feature-projection-based real-time emg pattern recognition for
multifunction myoelectric hand control,” Mechatronics, IEEE/ASME
Transactions on, vol. 12, no. 3, pp. 282 –290, june 2007.
[6] R. Khushaba, A. Al-Ani, and A. Al-Jumaily, “Orthogonal fuzzy neigh-
borhood discriminant analysis for multifunction myoelectric hand
control,” Biomedical Engineering, IEEE Transactions on, vol. 57,
no. 6, pp. 1410 –1419, june 2010.
[7] L. Minku, A. White, and X. Yao, “The impact of diversity on online
ensemble learning in the presence of concept drift,” Knowledge and
Data Engineering, IEEE Transactions on, vol. 22, no. 5, pp. 730 –742,
may 2010.
[8] P. Rodrigues, J. Gama, and J. Pedroso, “Hierarchical clustering of
time-series data streams,” Knowledge and Data Engineering, IEEE
Transactions on, vol. 20, no. 5, pp. 615 –627, may 2008.
[9] G. Widmer and M. Kubat, “Learning in the presence of
concept drift and hidden contexts,” Machine Learning, vol. 23,
pp. 69–101, 1996, 10.1023/A:1018046501280. [Online]. Available:
http://dx.doi.org/10.1023/A:1018046501280
[10] A. Tsymbal, “The problem of concept drift: Definitions and related
work,” Tech. Rep., 2004.
[11] S. K.O., “Learning concept drift with a committee of decision trees,”
Department of Computer Sciences, University of Texas at Austin,
USA, Tech. Rep. UT-AI-TR-03-302, 2003.
[12] J. Sensinger, B. Lock, and T. Kuiken, “Adaptive pattern recognition
of myoelectric signals: Exploration of conceptual framework and
practical algorithms,” Neural Systems and Rehabilitation Engineering,
IEEE Transactions on, vol. 17, no. 3, pp. 270 –278, june 2009.
[13] J. Gama, P. Medas, G. Castillo, and P. Rodrigues, “Learning with
drift detection,” in Advances in Artificial Intelligence SBIA 2004, ser.
Lecture Notes in Computer Science, A. Bazzan and S. Labidi, Eds.
Springer Berlin / Heidelberg, vol. 3171, pp. 66–112.
[14] M. Nagendra Prasad and A. Sowmya, “Multi-class unsupervised
classification with label correction of hrct lung images,” in Intelligent
Sensing and Information Processing, 2004. Proceedings of Interna-
tional Conference on, 2004, pp. 51 – 56.
[15] S. Lallich, F. Muhlenbach, and D. A. Zighed, “Improving classification
by removing or relabeling mislabeled instances,” in Proceedings of the
13th International Symposium on Foundations of Intelligent Systems,
ser. ISMIS ’02. London, UK, UK: Springer-Verlag, 2002, pp. 5–15.
[Online]. Available: http://dl.acm.org/citation.cfm?id=646360.759041
[16] F. Muhlenbach, S. Lallich, and D. A. Zighed, “Identifying and
handling mislabelled instances,” Journal of Intelligent Information
Systems, vol. 22, pp. 89–109, 2004, 10.1023/A:1025832930864.
[Online]. Available: http://dx.doi.org/10.1023/A:1025832930864
[17] C.B. and Chittineni, “Estimation of probabilities of label
imperfections and correction of mislabels,” Pattern Recognition,
vol. 13, no. 3, pp. 257 – 268, 1981. [Online]. Available:
http://www.sciencedirect.com/science/article/pii/0031320381901035
[18] L. Hargrove, E. Scheme, K. Englehart, and B. Hudgins, “Multiple
binary classifications via linear discriminant analysis for improved
controllability of a powered prosthesis,” Neural Systems and Reha-
bilitation Engineering, IEEE Transactions on, vol. 18, no. 1, pp. 49
–57, feb. 2010.
[19] H. Huang, P. Zhou, G. Li, and T. Kuiken, “An analysis of emg
electrode configuration for targeted muscle reinnervation based neural
machine interface,” Neural Systems and Rehabilitation Engineering,
IEEE Transactions on, vol. 16, no. 1, pp. 37 –45, feb. 2008.
[20] L. Hargrove, K. Englehart, and B. Hudgins, “The effect of electrode
displacements on pattern recognition based myoelectric control,” in
Engineering in Medicine and Biology Society, 2006. EMBS ’06. 28th
Annual International Conference of the IEEE, 30 2006-sept. 3 2006,
pp. 2203 –2206.
[21] S. Solnik, P. Rider, K. Steinweg, P. DeVita, and T. Hortobgyi,
“Teagerkaiser energy operator signal conditioning improves emg
onset detection,” European Journal of Applied Physiology, vol. 110,
pp. 489–498, 2010, 10.1007/s00421-010-1521-8. [Online]. Available:
http://dx.doi.org/10.1007/s00421-010-1521-8
[22] A. Martinez and A. Kak, “Pca versus lda,” Pattern Analysis and
Machine Intelligence, IEEE Transactions on, vol. 23, no. 2, pp. 228
–233, feb 2001.