Fractal Dimension Features Research Articles

Co-effects of epichlorohydrin-dimethylamine and polyferric on humic acid elimination and membrane resistance in hybrid process

The effective coagulation aid epichlorohydrin-dimethylamine was synthesized, its co-effect with three ferric iron species in polyferric chloride on humic acid elimination and membrane pollution in coagulation-ultrafiltration hybrid technique were appraised to improve the hybrid water treatment technology and generate cleaner water production by this research. To be specific, dosages of polyferric chlorides 2 and polyferric chlorides&epichlorohydrin-dimethylamine were adjusted according to their coagulation performance in jar tests. Furthermore, properties of generated flocs such as floc size (median particle diameter), strength/recovery factor and fractal dimension feature were monitored and combined with results of membrane fouling resistance under various shear forces to understand the mechanism of membrane fouling. Results indicated that epichlorohydrin-dimethylamine can observably enhance the coagulation performance of all polyferric chlorides, especially at low dosage of 4 mg/L. The higher the epichlorohydrin-dimethylamine dosage, the higher removal efficiencies achieved. In particular, for polyferric chloride with basicity of 1.5, the removal efficiency for dissolved organic carbon raised approximately from 15% to 32% as epichlorohydrin-dimethylamine dosage increased from zero to 1.5 mg/L. Meanwhile, for ultra-membrane 3 applied in this study, addition of the epichlorohydrin-dimethylamine also significantly reduced the total membrane fouling resistance of all coagulated water samples by forming cake layer of low compactness and reducing residual micro-particles, 4 even when shearing forces was introduced. Thereinto, the total membrane fouling resistance reduction of polyferric chloride with basicity of 1.5 was the most obvious, which dropped from 2.8 × 10 8 m −1 to 2.3 × 10 8 m −1 , approximately. • Epichlorohydrin-dimethylamine was beneficial to form large floc. • External fouling resistance dominated membrane fouling resistance. • High floc recovery ability was crucial for membrane fouling reduction. • Residual micro-particles determines internal fouling resistance.

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features.

K-complexes identification is a challenging task in sleep research. The detection of k-complexes in electroencephalogram (EEG) signals based on visual inspection is time consuming, prone to errors, and requires well-trained knowledge. Many existing methods for k-complexes detection rely mainly on analyzing EEG signals in time and frequency domains. In this study, an efficient method is proposed to detect k-complexes from EEG signals based on fractal dimension (FD) of time frequency (T-F) images coupled with undirected graph features. Firstly, an EEG signal is partitioned into smaller segments using a sliding window technique. Each EEG segment is passed through a spectrogram of short time Fourier transform (STFT) to obtain the T-F images. Secondly, the box counting method is applied to each T-F image to discover the FDs in EEG signals. A vector of FD features are extracted from each T-F image and then mapped into an undirected graph. The structural properties of the graphs are used as the representative features of the original EEG signals for the input of a least square support vector machine (LS-SVM) classifier. Key graphic features are extracted from the undirected graphs. The extracted graph features are forwarded to the LS-SVM for classification. To investigate the classification ability of the proposed feature extraction combined with the LS-SVM classifier, the extracted features are also forwarded to a k-means classifier for comparison. The proposed method is compared with several existing k-complexes detection methods in which the same datasets were used. The findings of this study shows that the proposed method yields better classification results than other existing methods in the literature. An average accuracy of 97% for the detection of the k-complexes is obtained using the proposed method. The proposed method could lead to an efficient tool for the scoring of automatic sleep stages which could be useful for doctors and neurologists in the diagnosis and treatment of sleep disorders and for sleep research.

Automated heartbeat classification and detection of arrhythmia using optimal orthogonal wavelet filters

Abstract Electrocardiogram (ECG) is commonly used to analyze heartbeats. Arrhythmia is a disturbance of the heartbeat that can potentially be lethal. Arrhythmia can be detected by identifying an individual abnormal heartbeat, which can occur in isolation or sequentially. Heartbeats can be classified into five types: non-ectopic (N), supra ventricular ectopic (S), ventricular ectopic (V), fusion (F) and unknown beats (Q). Automated classification of the incidence and pattern of abnormal heartbeats enables arrhythmia detection, triage and life-threatening arrhythmia. Therefore, it is vital to develop a tool for the classification of these classes. ECG signals are contaminated by noise rendering difficulty and challenging to discriminate between different types of heartbeats. In this work, we used noisy as well as denoised (clean) ECG signals to classify heartbeats. Using stop-band energy (SBE) minimized dyadic orthogonal filter bank, wavelet decomposition of the ECG signals was performed. After this, fuzzy entropy, Renyi entropy and fractal dimension features were extracted for easier and accurate classification into the five classes. These features were then fed to classifiers, achieving maximum accuracy (MAAC) of 98%, maximum sensitivity (MASE) of 85.33% and maximum specificity (MASP) of 98.22% for noisy data, and MAAC of 98.1%, MASE of 85.63% and MASP of 98.27% for clean data, with KNN classifier. Our developed system can be used in intensive care units to assist the clinicians to aid in their diagnosis.

Evaluation of filters over different stimulation models in evoked potentials

Filtering is a key process which removes unwanted parts of signals. During signal recording, various forms of noises distort data. Physiological signals are highly noise sensitive and to evaluate them powerful filtering approaches must be applied. The aim of this study is to compare modern filtering approaches on scalp signals. Brain activities were generally examined by brain signals like EEG and evoked potentials (EP). In this study, data were recorded from university students whose age between 18 and 25 years with visual and auditory stimuli. Discrete wavelet transforms, singular spectrum analysis, empirical mode decomposition and discrete Fourier transform based filters were used and compared with raw data on classification performance. Higuchi fractal dimension and entropy features were extracted from EEG; P300 features were extracted from EP signals. Classification was applied with support vector machines. All filtered data gave better scores than raw data. Empirical mode decomposition (EMD) and Fourier-based filter yielded lower results than the discrete wavelet-based filter. Singular spectrum analysis gave the best result at 84.32%. The current study suggests that singular spectrum analysis removes noise from sensitive physiological signals, and EMD requires new mode selection procedures before resynthesizing.

Development of a radiomic signature for prediction of pathological complete response following neoadjuvant chemoradiotherapy in esophageal cancer.

106 Background: Pivotal to personalized therapy is accurate pre-treatment patient selection based on predictive biomarkers. We developed a radiomic signature model to predict pathological complete response (pCR) following neoadjuvant chemo-radiotherapy (NACRT) in esophageal cancers. Methods: We retrospectively identified 68 patients with esophageal cancer, treated with NACRT followed by esophagectomy, with baseline 18F-fluorodeoxyglucose Positron Emission Tomography (PET) and computed tomography (CT) scans performed at our institution. In-house data-characterization algorithm was used to extract 3D radiomics features from the segmented primary disease. Prediction models were constructed and internally validated (2/3rd training, 1/3rd validation) using machine learning software. Cox regression hazard used to assess association with relapse free survival (RFS). Results: pCR was observed in 34 (50%) patients. A total of 126 features were extracted individually from PET and CT scans. On univariate analysis, 16 PET and 14 CT features were found to independently predict pCR. Three separate predictive models were built for CT, PET and combined CT+PET. Individually, both CT and PET had a good predictive power with AUC 0.74 and 0.730, respectively. Combined CT+PET radiomic features resulted in a significant improvement of predicting power, with AUC 0.856. Good discrimination (82.6%) was observed in validation dataset. Final model was: 13.439-34.632(CT-eccentricity)-2.469(CT-LRLGE)+10.626(CT-Gnorm_HIE)-2.094(CT-SD_Lac2)-19.337(CT-FD_SD)-0.344(PET-Contrast), where eccentricity is shape feature, LRLGE a gray level run length feature, Gnorm_HIE gray-level size zone feature, SD_Lac2 a fractal dimension feature. Stratifying patients with low vs. high radiomic signature score predicted RFS: median RFS 80.1 vs. 40.1 months; and 2-year RFS 77.4% vs. 52.6% [Hazard Ratio: 2.24, 95% CI 1.01-5.58], respectively. Conclusions: The developed radiomics signature models were highly predictive of pCR following NACRT. Further validation in larger data sets is needed to determine whether the model can predict clinical outcomes.

EEG Based Emotion Classification Mechanism in BCI

Psychological changes in humans are the result of emotions which occur due to activities in daily life. To understand these changes in behavioral pattern, research on a ective computing has emerged. Emotions are an integral part of our daily lives, based on which in this paper an investigation have been made to analyze the impact of positive and negative emotions using Electroencephalogram (EEG). Three classes of emotions namely calm, anger and happiness have been studied. The EEG signals are recorded in real time from 10 subjects while watching di erent emotions video clips of 2 minutes each. Next, the fractal dimension feature has been extracted from raw EEG. To further detect emotional states, the extracted features have been classified using Support Vector Machine (SVM) with radial basis function (RBF) kernel with an average accuracy of 60%. The proposed methodology shows that emotions recognition is possible from EEG signals.

Research on leaf species identification based on principal component and linear discriminant analysis

A method of leaf species identification based on principal component and linear discriminant analysis is proposed in this paper. The method consists of four phases. Leaf images obtained by cameras or other devices typically have petioles and wormholes that affect the recognition rate. Hence, it is necessary to first preprocess the images before feature extraction. After preprocessing of the leaf samples, the binary image, grayscale image, and texture image of the leaves are output for feature extraction. Then, shape features and texture features are extracted to describe the leaves. The shape features can be divided into three groups: geometric characteristics, Hu moment invariants features, and structural characteristics. The texture features consists of gray level co-occurrence matrix features, fractal dimension features, Local Binary Patterns features, and Gabor features. Next, principal component analysis and linear discriminant analysis are combined to reduce the dimension of the features. Finally, Back Propagation Neural Network is used to classify the feature data. The proposed method was tested on two leaf image datasets: Flavia and ICL; the average accuracy of leaf species identification was 94.22 and 87.82%, respectively. The experiment demonstrated the effectiveness of the proposed method.

Fractal dimension pattern-based multiresolution analysis for rough estimator of speaker-dependent audio emotion recognition

As a general means of expression, audio analysis and recognition have attracted much attention for its wide applications in real-life world. Audio emotion recognition (AER) attempts to understand the emotional states of human with the given utterance signals, and has been studied abroad for its further development on friendly human–machine interfaces. Though there have been several the-state-of-the-arts auditory methods devised to audio recognition, most of them focus on discriminative usage of acoustic features, while feedback efficiency of recognition demands is ignored. This makes possible application of AER, and rapid learning of emotion patterns is desired. In order to make predication of audio emotion possible, the speaker-dependent patterns of audio emotions are learned with multiresolution analysis, and fractal dimension (FD) features are calculated for acoustic feature extraction. Furthermore, it is able to efficiently learn the intrinsic characteristics of auditory emotions, while the utterance features are learned from FDs of each sub-band. Experimental results show the proposed method is able to provide comparative performance for AER.

Real-Time Epileptic Seizure Detection Using EEG.

This paper proposes a novel patient-specific real-time automatic epileptic seizure onset detection, using both scalp and intracranial electroencephalogram (EEG). The proposed technique obtains harmonic multiresolution and self-similarity-based fractal features from EEG for robust seizure onset detection. A fast wavelet decomposition method, known as harmonic wavelet packet transform (HWPT), is computed based on Fourier transform to achieve higher frequency resolutions without recursive calculations. Similarly, fractal dimension (FD) estimates are obtained to capture self-similar repetitive patterns in the EEG signal. Both FD and HWPT energy features across all EEG channels at each epoch are organized following the spatial information due to electrode placement on the skull. The final feature vector combines feature configurations of each epoch within the specified moving window to reflect the temporal information of EEG. Finally, relevance vector machine is used to classify the feature vectors due to its efficiency in classifying sparse, yet high-dimensional data sets. The algorithm is evaluated using two publicly available long-term scalp EEG (data set A) and short-term intracranial and scalp EEG (data set B) databases. The proposed algorithm is effective in seizure onset detection with 96% sensitivity, 0.1 per hour median false detection rate, and 1.89 s average detection latency, respectively. Results obtained from analyzing the short-term data offer 99.8% classification accuracy. These results demonstrate that the proposed method is effective with both short- and long-term EEG signal analyzes recorded with either scalp or intracranial modes, respectively. Finally, the use of less computationally intensive feature extraction techniques enables faster seizure onset detection when compared with similar techniques in the literature, indicating potential usage in real-time applications.

EEG-Based Affect and Workload Recognition in a Virtual Driving Environment for ASD Intervention.

To build group-level classification models capable of recognizing affective states and mental workload of individuals with autism spectrum disorder (ASD) during driving skill training. Twenty adolescents with ASD participated in a six-session virtual reality driving simulator-based experiment, during which their electroencephalogram (EEG) data were recorded alongside driving events and a therapist's rating of their affective states and mental workload. Five feature generation approaches including statistical features, fractal dimension features, higher order crossings (HOC)-based features, power features from frequency bands, and power features from bins () were applied to extract relevant features. Individual differences were removed with a two-step feature calibration method. Finally, binary classification results based on the k-nearest neighbors algorithm and univariate feature selection method were evaluated by leave-one-subject-out nested cross-validation to compare feature types and identify discriminative features. The best classification results were achieved using power features from bins for engagement (0.95) and boredom (0.78), and HOC-based features for enjoyment (0.90), frustration (0.88), and workload (0.86). Offline EEG-based group-level classification models are feasible for recognizing binary low and high intensity of affect and workload of individuals with ASD in the context of driving. However, while promising the applicability of the models in an online adaptive driving task requires further development. The developed models provide a basis for an EEG-based passive brain computer interface system that has the potential to benefit individuals with ASD with an affect- and workload-based individualized driving skill training intervention.

A cost-sensitive Bayesian combiner for reducing false positives in mammographic mass detection.

Mammography is the most widely used modality for early breast cancer detection. This work proposes a new computer-aided mass detection approach, in which a denoising method called BM3D is first applied to mammograms. Afterwards, using an adaptive segmentation algorithm, images are segmented to suspicious regions of interest (ROIs) and then a classifier is used to understand the features of true positive (TP) and false positive (FP) patterns. In this way, from selected suspicious ROIs, fractal dimension, texture and intensity features are extracted. Subsequently, a discretization approach followed by correlation-based feature selection (CFS) is combined with a genetic algorithm to obtain the most representative features. To neutralize the classifier's bias in favor of the major class in imbalanced datasets, an oversampling algorithm is used. In the next step, a cost-sensitive ensemble classifier based on a trainable combiner is proposed in order to reduce the number of FP samples. Finally, the presented method is validated on miniMIAS and INBreast datasets. The free-response receiver operating characteristic (FROC) analysis results prove the efficiency of the proposed approach. A sensitivity of 88% and false positive per image (FPpI) of 0.78 for miniMIAS and also a sensitivity of 86% and FPpI of 0.75 for INBreast dataset were obtained.

Fault Sensing Using Fractal Dimension and Wavelet

A new fusion sensing (FS) method was proposed by using the improved fractal box dimension (IFBD) and a developed maximum wavelet coefficient (DMWC) for fault sensing of an online power cable. There are four strategies that were used. Firstly, the traditional fractal box dimension was improved to enlarge the feature distances between the different fault classes. Secondly, the IFBD recognition algorithm was proposed by using the improved fractal dimension feature extracted from the three-phase currents for the first stage of fault recognition. Thirdly, the DMWC recognition algorithm was developed based on the K-transform and wavelet analysis to establish the relationship between the maximum wavelet coefficient and the fault class. Fourthly, the FS method was formed by combining the IFBD algorithm and the DMWC algorithm in order to recognize the 10 types of short circuit faults of online power. The designed test system proved that the FS method increased the fault recognition accuracy obviously. In addition, the parameters of the initial angle, transient resistance, and fault distance had no influence on the FS method.

Features of cerebral oxygenation detects brain injury in premature infants.

Babies born prematurely can develop brain injury within days after birth. Early identification of high-risk infants enables appropriate clinical care to mitigate potential lifelong disabilities. Near infra-red spectroscopy is an established technology that can provide continuous measurements of cerebral oxygen saturation (rcSO2) over this critical period. We develop a feature set of the rcSO2 signal for the purpose of detecting brain injury. Our feature set contains amplitude, spectral, and fractal dimension features within 5 frequency bands. Features are combined in a support vector machine (SVM) and performance is assessed within a cross-validation procedure. Using a cohort of 47 infants of <;32 weeks of gestation, we find significant (p <; 0.05) features of amplitude in the frequency band 0.9-3.6 mHz and a fractal dimension measure in the frequency band 1.8-3.6 mHz. The SVM has an area-under the receiver operator characteristic (AUC) of 0.75 with sensitivity-specificity values of 67-77%. These moderate results highlight the potential for quantitative analysis of rcSO2 to detect brain injury and thus enable early identification of high-risk infants.

FRACTAL DIMENSION AND LACUNARITY COMBINATION FOR PLANT LEAF CLASSIFICATION

Plants play important roles for the existence of all beings in the world. High diversity of plant’s species make a manual observation of plants classifying becomes very difficult. Fractal dimension is widely known feature descriptor for shape or texture. It is utilized to determine the complexity of an object in a form of fractional dimension. On the other hand, lacunarity is a feature descriptor that able to determine the heterogeneity of a texture image. Lacunarity was not really exploited in many fields. Moreover, there are no significant research on fractal dimension and lacunarity combination in the study of automatic plant’s leaf classification. In this paper, we focused on combination of fractal dimension and lacunarity features extraction to yield better classification result. A box counting method is implemented to get the fractal dimension feature of leaf boundary and vein. Meanwhile, a gliding box algorithm is implemented to get the lacunarity feature of leaf texture. Using 626 leaves from flavia, experiment was conducted by analyzing the performance of both feature vectors, while considering the optimal box size r. Using support vector machine classifier, result shows that combined features able to reach 93.92 % of classification accuracy.

Familiarity effects in EEG-based emotion recognition

Although emotion detection using electroencephalogram (EEG) data has become a highly active area of research over the last decades, little attention has been paid to stimulus familiarity, a crucial subjectivity issue. Using both our experimental data and a sophisticated database (DEAP dataset), we investigated the effects of familiarity on brain activity based on EEG signals. Focusing on familiarity studies, we allowed subjects to select the same number of familiar and unfamiliar songs; both resulting datasets demonstrated the importance of reporting self-emotion based on the assumption that the emotional state when experiencing music is subjective. We found evidence that music familiarity influences both the power spectra of brainwaves and the brain functional connectivity to a certain level. We conducted an additional experiment using music familiarity in an attempt to recognize emotional states; our empirical results suggested that the use of only songs with low familiarity levels can enhance the performance of EEG-based emotion classification systems that adopt fractal dimension or power spectral density features and support vector machine, multilayer perceptron or C4.5 classifier. This suggests that unfamiliar songs are most appropriate for the construction of an emotion recognition system.

Age Group Estimation by Combining Texture and Fractal Analysis

In this paper the age group estimation is presented based on combination of texture and fractal dimension features. The age of the human is used as one of the important key parameter for computer vision applications. The fractal dimension of the face image and the texture analysis is used to classify the age of the person into the three different groups such as child(10-20), young(21-50) and old(51 and above. The proposed approach of combing the fractal and texture features shows an effective estimation of the age group. The facial age groups are estimated with 90% average accuracy. General Terms Image Processing, Age Group Estimation, Texture Analysis, Fractal dimensions

A Novel Hepatocellular Carcinoma Image Classification Method Based on Voting Ranking Random Forests.

This paper proposed a novel voting ranking random forests (VRRF) method for solving hepatocellular carcinoma (HCC) image classification problem. Firstly, in preprocessing stage, this paper used bilateral filtering for hematoxylin-eosin (HE) pathological images. Next, this paper segmented the bilateral filtering processed image and got three different kinds of images, which include single binary cell image, single minimum exterior rectangle cell image, and single cell image with a size of n⁎n. After that, this paper defined atypia features which include auxiliary circularity, amendment circularity, and cell symmetry. Besides, this paper extracted some shape features, fractal dimension features, and several gray features like Local Binary Patterns (LBP) feature, Gray Level Cooccurrence Matrix (GLCM) feature, and Tamura features. Finally, this paper proposed a HCC image classification model based on random forests and further optimized the model by voting ranking method. The experiment results showed that the proposed features combined with VRRF method have a good performance in HCC image classification problem.

Motor-Imagery Task Classification using Mel-Cepstral and Fractal Fusion based Features

A brain-actuated wheelchair can be used to aid the movement of differentially enabled communities who face much difficulties while commuting from one place to another. In this research work, the active brain signals emanated from subjects while performing four different kinesthetic motor imagery tasks are recorded using Electroencephalography (EEG). Three different feature sets, namely, Fractal Dimension (FD), Mel-Frequency Cepstral Coefficients (MFCCs) and combined features of FD with MFCCs are extracted from the recorded EEG signals. The extracted features are then associated to classify the type of motor imagery tasks and three feedforward multi-layer Perceptrons trained with Levenberg-Marquardt method are developed. The performance of the three features are evaluated in term of classification rate and compared. Simple Elman network and NARX network models are then developed using the extracted features and evaluated. From the results, it is observed that the Elman network model trained with combined features of FD with MFCCs has yielded a higher classification accuracy for all the 5 subjects in the range of 98.98-100percent. The obtained result clearly indicates that the Elman network and combined features of FD with MFCCs has potential to classify the four different motor imagery tasks.

Classification of electromyography signals using relevance vector machines and fractal dimension

Surface electromyography (EMG) signals have been studied extensively in the last years aiming at the automatic classification of hand gestures and movements as well as the early identification of latent neuromuscular disorders. In this paper, we investigate the potentials of the conjoint use of relevance vector machines (RVM) and fractal dimension (FD) for automatically identifying EMG signals related to different classes of limb motion. The adoption of FD as the mechanism for feature extraction is justified by the fact that EMG signals usually show traces of self-similarity. In particular, four well-known FD estimation methods, namely box-counting, Higuchi's, Katz's and Sevcik's methods, have been considered in this study. With respect to RVM, besides the standard formulation for binary classification, we also investigate the performance of two recently proposed variants, namely constructive mRVM and top-down mRVM, that deal specifically with multiclass problems. These classifiers operate solely over the features extracted by the FD estimation methods, and since the number of such features is relatively small, the efficiency of the classifier induction process is ensured. Results of experiments conducted on a publicly available dataset involving seven distinct types of limb motions are reported whereby we assess the performance of different configurations of the proposed RVM+FD approach. Overall, the results evidence that kernel machines equipped with the FD feature values can be useful for achieving good levels of classification performance. In particular, we have empirically observed that the features extracted by the Katz's method is of better quality than the features generated by other methods.

SU-D-BRA-04: Fractal Dimension Analysis of Edge-Detected Rectal Cancer CTs for Outcome Prediction

Purpose: To extract the fractal dimension features from edge-detected rectal cancer CTs, and to examine the predictability of fractal dimensions to outcomes of primary rectal cancer patients. Methods: Ninety-seven rectal cancer patients treated with neo-adjuvant chemoradiation were enrolled in this study. CT images were obtained before chemoradiotherapy. The primary lesions of the rectal cancer were delineated by experienced radiation oncologists. These images were extracted and filtered by six different Laplacian of Gaussian (LoG) filters with different filter values (0.5–3.0: from fine to coarse) to achieve primary lesions in different anatomical scales. Edges of the original images were found at zero-crossings of the filtered images. Three different fractal dimensions (box-counting dimension, Minkowski dimension, mass dimension) were calculated upon the image slice with the largest cross-section of the primary lesion. The significance of these fractal dimensions in survival, recurrence and metastasis were examined by Student’s t-test. Results: For a follow-up time of two years, 18 of 97 patients had experienced recurrence, 24 had metastasis, and 18 were dead. Minkowski dimensions under large filter values (2.0, 2.5, 3.0) were significantly larger (p=0.014, 0.006, 0.015) in patients with recurrence than those without. For metastasis, only box-counting dimensions under a single filter value (2.5) showedmore » differences (p=0.016) between patients with and without. For overall survival, box-counting dimensions (filter values = 0.5, 1.0, 1.5), Minkowski dimensions (filter values = 0.5, 1.5, 2.0, 2,5) and mass dimensions (filter values = 1.5, 2.0) were all significant (p<0.05). Conclusion: It is feasible to extract shape information by edge detection and fractal dimensions analysis in neo-adjuvant rectal cancer patients. This information can be used to prognosis prediction.« less