Determination of the effect of preoperative knee joint function on postoperative quality of life in patients with total knee arthroplasty.

Primary total knee arthroplasty (TKA) is one of the most successful procedures for end-stage knee osteoarthritis. To determine the effect of preoperative knee joint function on postoperative quality of life in patients undergoing primary TKA. This descriptive cross-sectional study was conducted with a total of 208 patients in the orthopedics and traumatology clinic. Data were gathered with a personal information form, the Oxford Knee Score (OKS), and the EQ-5D-5L Quality Of Life Scale in the preoperative period, at postoperative 6th week, and at postoperative 3rd month. The data were analyzed using descriptive statistics, one-way analysis of variance (ANOVA), correlation analysis, and simple linear regression analysis. The mean age of the patients was 65.65 ± 7.01 years. Most patients (86.1%) were women, and 51.4% underwent left TKA. OKS scores indicated poor knee function preoperatively and gradually increased at postoperative 6th week and 3rd month. Preoperative OKS was a significant predictor of postoperative knee joint function and quality of life. This study shows that preoperative knee joint function significantly affects postoperative knee joint function and quality of life. These results demonstrate the importance of the surgery timing and suggest that performing surgery earlier in functional decline may be associated with a better outcome.

A new approach for heart disease detection using Motif transform-based CWT's time-frequency images with DenseNet deep transfer learning methods.

OBJECTIVES: Electrocardiogram (ECG) signals are extensively utilized in the identification and assessment of diverse cardiac conditions, including congestive heart failure (CHF) and cardiac arrhythmias (ARR), which present potential hazards to human health. With the aim of facilitating disease diagnosis and assessment, advanced computer-aided systems are being developed to analyze ECG signals. METHODS: This study proposes a state-of-the-art ECG data pattern recognition algorithm based on Continuous Wavelet Transform (CWT) as a novel signal preprocessing model. The Motif Transformation (MT) method was devised to diminish the drawbacks and limitations inherent in the CWT, such as the issue of boundary effects, limited localization in time and frequency, and overfitting conditions. This transformation technique facilitates the formation of diverse patterns (motifs) within the signals. The patterns (motifs) are constructed by comparing the amplitudes of each individual sample value in the ECG signals in terms of their largeness and smallness. In the subsequent stage, the obtained one-dimensional signals from the MT transformation were subjected to CWT to obtain scalogram images. In the last stage, the obtained scalogram images were subjected to classification using DenseNET deep transfer learning techniques. RESULTS AND CONCLUSIONS: The combined approach of MT + CWT + DenseNET yielded an impressive success rate of 99.31 %.

Comparative modeling and enzymatic affinity of novel haloacid dehalogenase from Bacillus megaterium strain BHS1 isolated from alkaline Blue Lake in Turkey.

This study presents the initial structural model of L-haloacid dehalogenase (DehLBHS1) from Bacillus megaterium BHS1, an alkalotolerant bacterium known for its ability to degrade halogenated environmental pollutants. The model provides insights into the structural features of DehLBHS1 and expands our understanding of the enzymatic mechanisms involved in the degradation of these hazardous pollutants. Key amino acid residues (Arg40, Phe59, Asn118, Asn176, and Trp178) in DehLBHS1 were identified to play critical roles in catalysis and molecular recognition of haloalkanoic acid, essential for efficient binding and transformation of haloalkanoic acid molecules. DehLBHS1 was modeled using I-TASSER, yielding a best TM-score of 0.986 and an RMSD of 0.53 Å. Validation of the model using PROCHECK revealed that 89.2% of the residues were located in the most favored region, providing confidence in its structural accuracy. Molecular docking simulations showed that the non-simulated DehLBHS1 preferred 2,2DCP over other substrates, forming one hydrogen bond with Arg40 and exhibiting a minimum energy of -2.5 kJ/mol. The simulated DehLBHS1 exhibited a minimum energy of -4.3 kJ/mol and formed four hydrogen bonds with Arg40, Asn176, Asp9, and Tyr11, further confirming the preference for 2,2DCP. Molecular dynamics simulations supported this preference, based on various metrics, including RMSD, RMSF, gyration, hydrogen bonding, and molecular distance. MM-PBSA calculations showed that the DehLBHS1-2,2-DCP complex had a markedly lower binding energy (-21.363 ± 1.26 kcal/mol) than the DehLBHS1-3CP complex (-14.327 ± 1.738 kcal/mol). This finding has important implications for the substrate specificity and catalytic function of DehLBHS1, particularly in the bioremediation of 2,2-DCP in contaminated alkaline environments. These results provide a detailed view of the molecular interactions between the enzyme and its substrate and may aid in the development of more efficient biocatalytic strategies for the degradation of halogenated compounds.Communicated by Ramaswamy H. Sarma.

Production of secondary metabolites using tissue culture-based biotechnological applications.

Plants are the sources of many bioactive secondary metabolites which are present in plant organs including leaves, stems, roots, and flowers. Although they provide advantages to the plants in many cases, they are not necessary for metabolisms related to growth, development, and reproduction. They are specific to plant species and are precursor substances, which can be modified for generations of various compounds in different plant species. Secondary metabolites are used in many industries, including dye, food processing and cosmetic industries, and in agricultural control as well as being used as pharmaceutical raw materials by humans. For this reason, the demand is high; therefore, they are needed to be obtained in large volumes and the large productions can be achieved using biotechnological methods in addition to production, being done with classical methods. For this, plant biotechnology can be put in action through using different methods. The most important of these methods include tissue culture and gene transfer. The genetically modified plants are agriculturally more productive and are commercially more effective and are valuable tools for industrial and medical purposes as well as being the sources of many secondary metabolites of therapeutic importance. With plant tissue culture applications, which are also the first step in obtaining transgenic plants with having desirable characteristics, it is possible to produce specific secondary metabolites in large-scale through using whole plants or using specific tissues of these plants in laboratory conditions. Currently, many studies are going on this subject, and some of them receiving attention are found to be taken place in plant biotechnology and having promising applications. In this work, particularly benefits of secondary metabolites, and their productions through tissue culture-based biotechnological applications are discussed using literature with presence of current studies.

The power of retrotransposons in high-throughput genotyping and sequencing.

The use of molecular markers has become an essential part of molecular genetics through their application in numerous fields, which includes identification of genes associated with targeted traits, operation of backcrossing programs, modern plant breeding, genetic characterization, and marker-assisted selection. Transposable elements are a core component of all eukaryotic genomes, making them suitable as molecular markers. Most of the large plant genomes consist primarily of transposable elements; variations in their abundance contribute to most of the variation in genome size. Retrotransposons are widely present throughout plant genomes, and replicative transposition enables them to insert into the genome without removing the original elements. Various applications of molecular markers have been developed that exploit the fact that these genetic elements are present everywhere and their ability to stably integrate into dispersed chromosomal localities that are polymorphic within a species. The ongoing development of molecular marker technologies is directly related to the deployment of high-throughput genotype sequencing platforms, and this research is of considerable significance. In this review, the practical application to molecular markers, which is a use of technology of interspersed repeats in the plant genome were examined using genomic sources from the past to the present. Prospects and possibilities are also presented.

Molecular interactions of trichoderma ß-1,4-glucosidase (ThBglT12) with mycelial cell wall components of phytopathogenic Macrophomina phaseolina.

Efficacy of a ß-1,4-glucosidase from Trichoderma harzianum T12 (ThBglT12) in disrupting the cell wall of the phytopathogenic fungus M. phaseolina (Macrophomina phaseolina) was studied, as the underlying molecular mechanisms of cell wall recognition remains elusive. In this study, the binding location identified by a consensus of residues predicted by COACH tool, blind docking, and multiple sequence alignment revealed that molecular recognition by ThBglT12 occurred through interactions between the α-1,3-glucan, ß-1,3-glucan, ß-1,3/1,4-glucan, and chitin components of M. phaseolina, with corresponding binding energies of -7.4, -7.6, -7.5 and -7.8 kcal/mol. The residue consensus verified the participation of Glu172, Tyr304, Trp345, Glu373, Glu430, and Trp431 in the active site pocket of ThBglT12 to bind the ligands, of which Trp345 was the common interacting residue. Root mean square deviation (RMSD), root mean square fluctuation (RMSF), total energy, and minimum distance calculation from molecular dynamics (MD) simulation further confirmed the stability and the closeness of the binding ligands into the ThBglT12 active site pocket. The h-bond occupancy by Glu373 and Trp431 instated the role of the nucleophile for substrate recognition and specificity, crucial for cleaving the ß-1,4 linkage. Further investigation showed that the proximity of Glu373 to the anomeric carbon of ß-1,3/1,4-glucan (3.5 Å) and chitin (5.5 Å) indicates the nucleophiles' readiness to form enzyme-substrate intermediates. Plus, the neighboring water molecule appeared to be correctly positioned and oriented towards the anomeric carbon to hydrolyze the ß-1,3/1,4-glucan and chitin, in less than 4.0 Å. In a nutshell, the study verified that the ThBglT12 is a good alternative fungicide to inhibit the growth of M. phaseolina.Communicated by Ramaswamy H. Sarma.

A new approach for physical human activity recognition based on co-occurrence matrices.

In recent years, it has been observed that many researchers have been working on different areas of detection, recognition and monitoring of human activities. The automatic determination of human physical activities is often referred to as human activity recognition (HAR). One of the most important technology that detects and tracks the activity of the human body is sensor-based HAR technology. In recent days, sensor-based HAR attracts attention in the field of computers due to its wide use in daily life and is a rapidly growing field of research. Activity recognition (AR) application is carried out by evaluating the signals obtained from various sensors placed in the human body. In this study, a new approach is proposed to extract features from sensor signals using HAR. The proposed approach is inspired by the Gray Level Co-Occurrence Matrix (GLCM) method, which is widely used in image processing, but it is applied to one-dimensional signals, unlike GLCM. Two datasets were used to test the proposed approach. The datasets were created from the signals obtained from the accelerometer, gyro and magnetometer sensors. Heralick features were obtained from co-occurrence matrix created after 1D-GLCM (One (1) Dimensional-Gray Level Co-Occurrence Matrix) was applied to the signals. HAR operation has been carried out for different scenarios using these features. Success rates of 96.66 and 93.88% were obtained for two datasets, respectively. It has been observed that the new approach proposed within the scope of the study provides high success rates for HAR applications. It is thought that the proposed approach can be used in the classification of different signals.

Antibacterial activity of Calendula officinalis and Echinacea purpurea extracts against the causal agent of tomatoes' bacterial canker: Clavibacter michiganensis subsp. michiganensis / Actividad antibacteriana de los extractos de Calendula officinalis y Echinacea purpurea contra el agente causal del cancro bacteriano del tomate: Clavibacter michiganensis subsp. Michiganensis

We aimed to investigate the effects of Calendula officinalis and Echinacea purpurea extracts in terms of growth parameters, antibacterial activity and phenolic profile in tomato infected by Clavibacter michiganensis subsp. michiganensis (CmmT7). A significant difference was observed in E. purpuraextract, indicating the highest effects on plant height (27.25 cm), fresh plant weight (28.45 cm), root length (24.42 cm), and root weight (6.74 g) (p<0.05). Moreover, Calendula officinalis and Echinacea purpurea extracts showed significant inhibitory activity against CmmT7 (p<0.05). Among phenolic compounds, the only chlorogenic acid amounts were varied in the tomato seedlings leaves with C. officinalis extract (K3) + CmmT7, E. purpurea extract (E3) + CmmT7 and CmmT7 (p<0.01). Moreover, chlorogenic acid amount was approximately 9 times higher than in CmmT7-treated leaves when compared to control. The results showed that application of the extracts of these plants had a significant influence on bacterial canker and growth parameters.

Nuestro objetivo fue investigar los efectos de los extractos de Calendula officinalis y Echinacea purpurea en términos de parámetros de crecimiento, actividad antibacteriana y perfil fenólico en tomate infectado por Clavibacter michiganensis subsp. michiganensis (CmmT7). Se observó una diferencia significativa en el extracto de E. purpura, que indica los mayores efectos sobre la altura de la planta (27,25 cm), el peso de la planta fresca(28,45 cm), la longitud de la raíz (24,42 cm) y el peso de la raíz (6,74 g) (p<0,05). Además, los extractos de Calendula officinalis y Echinacea purpurea mostraron una actividad inhibidora significativa contra CmmT7 (p<0,05). Entre los compuestos fenólicos, las únicas cantidades de ácido clorogénico se variaron en las hojas de las plántulas de tomate con extracto de C. officinalis (K3) CmmT7, extracto de E. purpurea(E3) CmmT7 y CmmT7 (p<0.01). Además, la cantidad de ácido clorogénico fue aproximadamente 9 veces mayor que en las hojas tratadas con CmmT7 en comparación con el control. Los resultados mostraron que la aplicación de los extractos de estas plantas tuvo una influencia significativa sobre el cancro bacteriano y los parámetros de crecimiento.

Molecular docking and molecular dynamics simulations studies on ß-glucosidase and xylanase Trichoderma asperellum to predict degradation order of cellulosic components in oil palm leaves for nanocellulose preparation.

Literature has shown that oil palm leaves (OPL) can be transformed into nanocellulose (NC) by fungal lignocellulosic enzymes, particularly those produced by the Trichoderma species. However, mechanism of ß-glucosidase and xylanase selectivity to degrade lignin, hemicellulose and cellulose in OPL for NC production remains relatively vague. The study aimed to comprehend this aspect by an in silico approach of molecular docking, molecular dynamics (MD) simulation and Molecular-mechanics Poisson-Boltzmann surface area (MM-PBSA) analysis, to compare interactions between the ß-glucosidase- and xylanase from Trichoderma asperellum UC1 in complex with each substrate. Molecular docking of the enzyme-substrate complex showed residues Glu165-Asp226-Glu423 and Arg155-Glu210-Ser160 being the likely catalytic residues of ß-glucosidase and xylanase, respectively. The binding affinity of ß-glucosidase for the substrates are as follows: cellulose (-8.1 kcal mol-1) > lignin (-7.9 kcal mol-1) > hemicellulose (-7.8 kcal mol-1), whereas, xylanase showed a corresponding preference for; hemicellulose (-6.7 kcal mol-1) > cellulose (-5.8 kcal mol-1) > lignin (-5.7 kcal mol-1). Selectivity of both enzymes was reiterated by MD simulations where interactions between ß-glucosidase-cellulose and xylanase-hemicellulose were the strongest. Notably low free-binding energy (ΔGbind) of ß-glucosidase and xylanase in complex with cellulose (-207.23 +/- 47.13 kJ/mol) and hemicellulose (-131.48 +/- 24.57 kJ/mol) were observed, respectively. The findings thus successfully identified the cellulose component selectivity of the polymer-acting ß-glucosidase and xylanase of T. asperellum UC1.Communicated by Ramaswamy H. Sarma.

Brain tumor classification using modified local binary patterns (LBP) feature extraction methods.

Automatic classification of brain tumor types is very important for accelerating the treatment process, planning and increasing the patient's survival rate. Today, MR images are used to determine the type of brain tumor. Manual diagnosis of brain tumor type depends on the experience and sensitivity of radiologists. Therefore, researchers have developed many brain tumor classification models to minimize the human factor. In this study, two different feature extraction (nLBP and αLBP) approaches were used to classify the most common brain tumor types; Glioma, Meningioma, and Pituitary brain tumors. nLBP is formed based on the relationship for each pixel around the neighbors. The nLBP method has a d parameter that specifies the distance between consecutive neighbors for comparison. Different patterns are obtained for different d parameter values. The αLBP operator calculates the value of each pixel based on an angle value. The angle values used for calculation are 0, 45, 90 and 135. To test the proposed methods, it was applied to images obtained from the brain tumor database collected from Nanfang Hospital, Guangzhou, China, and Tianjin Medical University General Hospital between the years of 2005 and 2010. The classification process was performed by using K-Nearest Neighbor (Knn) and Artificial Neural Networks (ANN), Random Forest (RF), A1DE, Linear Discriminant Analysis (LDA) classification methods, with the feature matrices obtained with nLBP, αLBP and classical LBP from the images in the data set. The highest success rate in brain tumor classification was 95.56% with the nLBPd = 1 feature extraction method and Knn model.

Haloadaptation: insights from comparative modeling studies between halotolerant and non-halotolerant dehalogenases.

Halophiles are extremophilic microorganisms that grow optimally at high salt concentrations by producing a myriad of equally halotolerant enzymes. Structural haloadaptation of these enzymes adept to thriving under high-salt environments, though are not fully understood. Herein, the study attempts an in silico investigation to identify and comprehend the evolutionary structural adaptation of a halotolerant dehalogenase, DehHX (GenBank accession number: KR297065) of the halotolerant Pseudomonas halophila, over its non-halotolerant counterpart, DehMX1 (GenBank accession number KY129692) produced by Pseudomonas aeruginosa. GC content of the halotolerant DehHX DNA sequence was distinctively higher (58.9%) than the non-halotolerant dehalogenases (55% average GC). Its acidic residues, Asp and Glu were 8.27% and 12.06%, respectively, compared to an average 5.5% Asp and 7% Glu, in the latter; but lower contents of basic and hydrophobic residues in the DehHX. The secondary structure of DehHX interestingly revealed a lower incidence of α-helix forming regions (29%) and a higher percentage of coils (57%), compared to 49% and 29% in the non-halotolerant homologues, respectively. Simulation models showed the DehHX is stable under a highly saline environment (25% w/v) by adopting a highly negative-charged surface with a concomitant weakly interacting hydrophobic core. The study thus, established that a halotolerant dehalogenase undergoes notable evolutionary structural changes related to GC content over its non-halotolerant counterpart, in order to adapt and thrive under highly saline environments.Communicated by Ramaswamy H. Sarma.

Substrate docking and molecular dynamic simulation for prediction of fungal enzymes from Trichoderma species-assisted extraction of nanocellulose from oil palm leaves.

Fungi of the Trichoderma species are valued industrial enzymes in support of the 'zero-waste' technology to convert agro-industrial biomass into valuable products, i.e. nanocellulose (NC). In this study, an in silico approach using substrate docking and molecular dynamic (MD) simulation was used to predict the order of which the multilayers of cellulosic polymers, i.e. lignin, hemicellulose and cellulose in oil palm leaves (OPL) are degraded by fungal enzymes, endocellulase and exocellulase. The study aimed to establish the catalytic tendencies of the enzymes to optimally degrade the cellulosic components of OPL for high yield production of NC. Energy minimized endocellulase and exocellulase models revealed satisfactory scores of PROCHECK (90.0% and 91.2%), Verify3D (97.23% and 98.85%) and ERRAT (95.24% and 91.00%) assessments. Active site prediction by blind docking, COACH meta-server and multiple sequence alignment indicated the catalytic triads for endocellulase and exocellulase were Ser116-His205-Glu249 and Ser382-Arg124-Asp385, respectively. Binding energy of endocellulase docked with hemicellulose (-6.0 kcal mol-1) was the most favourable followed by lignin (-5.6 kcal mol-1) and cellulose (-4.4 kcal mol-1). Exocellulase, contrarily, bonded favorably with lignin (-8.7 kcal mol-1), closely followed by cellulose (-8.5 kcal mol-1) and hemicellulose (-8.4 kcal mol-1). MDs simulations showed that interactions of complexes, endocellulase-hemicellulose and the exocellulase-cellulose being the most stable. Thus, the findings of the study successfully identified the specific actions of sugar-acting enzymes for NC production. Communicated by Ramaswamy H. Sarma.

A novel feature extraction method for bearing fault classification with one dimensional ternary patterns.

Bearing is one of the most critical parts used in rotary machines. Bearing faults break down the mechanism where it is located. Moreover, the faults may cause to malfunction by spreading to the entire system. Thus this may result in catastrophic failure eventually. Precise and decisive feature extraction from the raw vibration signal maintains to be one of the current topics explored for fault diagnosis in bearings. In this study, vibration signals are obtained from bearings which are formed with artificial faults of specific dimensions from a bearing test setup. Instead of employing traditional feature extraction methods found in the literature, a novel feature extraction method for bearing faults called one-dimensional ternary pattern (1D-TP) is applied. The proposed approach is a statistical method that uses patterns obtained from comparisons between neighbors of each value on vibration signals. The study aims to identify the size (mm) of the fault by determining the bearing part (inner ring, outer ring, ball) from which the faults in the bearings are caused. Several classification techniques were performed by using ternary patterns with RF (Random Forest), k-NN (k-nearest neighbor), SVM (Support Vector Machine), BayesNet, ANN (Artificial Neural Networks) models. As a result of analyzing the signals obtained from the experimental setup with the proposed model, 91.25% for dataset_1 (different speed), 100% for dataset_2 (fault type - inner ring, outer ring, ball) and 100% for dataset_3 (fault size (mm)) success rates are determined.

A stable feature extraction method in classification epileptic EEG signals.

Epilepsy is one of the most common neurological disorders. Electroencephalogram (EEG) signals are generally employed in diagnosing epilepsy. Therefore, extracting relevant features from EEG signals is one of the major tasks in an accurate diagnosis. In this study, the local ternary patterns, which is an image processing method, was improved in order to extract robust features from epileptic EEG signals. The EEG signals that were recorded by the Department of Etymology in the Bonn University were employed in the evaluation and validation of the proposed approach. Low and up features, which were extracted by the proposed one-dimensional ternary patterns, were classified by some machine learning methods such that support vector machine, functional trees, random forest (RF), Bayes networks (BayesNet), and artificial neural network, while the highest accuracies were obtained by RF. Achieved accuracies were found successful according to the current literature.

Proximal tibiofibular joint pain versus peroneal nerve dysfunction: clinical results of closed-wedge high tibial osteotomy performed with proximal tibiofibular joint disruption.

PURPOSE: Closed-wedge high tibial osteotomy (CW-HTO) requires shortening of the fibula or the fibular head or disruption of the proximal tibiofibular joint (PTFJ). However, no study has evaluated the proximal tibiofibular joint after the osteotomy. The aim of this study was to investigate the fate of the PTFJ after CW-HTO applied with using PTFJ disruption method. METHODS: This prospective study included 22 knees of 20 patients who underwent CW-HTO. The mean age of the patients was 50 ± 4 years, and the mean follow-up period was 27.5 ± 14.3 months (12-46 months). The grade of gonarthrosis (Ahlbäck's classification), tibiofemoral alignment and tibial slope angles were measured on radiographs pre- and post-operatively. During the surgery, the PTFJ capsule was released meticulously so as not to injure the peroneal nerve. Tenderness over the PTFJ was recorded preoperatively and at the last follow-up. RESULTS: No patient had tenderness or pain over PTFJ preoperatively. On the follow-up examinations, tenderness with compression was detected in nine knees with dorsiflexion, in ten with plantar flexion and in nine with neutral position of the ankle, respectively. None of the patients had peroneal nerve injury (including hypesthesia and mild weakness) post-operatively. However, while 11 knees were pain free in all positions of the ankle, seven knees had tenderness over PTFJ both in dorsiflexion and in plantar flexion. CONCLUSION: CW-HTO using PTFJ disruption provides good clinical results in terms of medial knee pain and corrects the alignment sufficiently while avoiding peroneal nerve injury. However, the results of this study indicated that this technique might result in painful PTFJs. Thus, the surgeon should consider a possibly painful PTFJ, which can be a cause of chronic lateral knee pain when performing this technique. LEVEL OF EVIDENCE: III.

A novel approach for SEMG signal classification with adaptive local binary patterns.

Feature extraction plays a major role in the pattern recognition process, and this paper presents a novel feature extraction approach, adaptive local binary pattern (aLBP). aLBP is built on the local binary pattern (LBP), which is an image processing method, and one-dimensional local binary pattern (1D-LBP). In LBP, each pixel is compared with its neighbors. Similarly, in 1D-LBP, each data in the raw is judged against its neighbors. 1D-LBP extracts feature based on local changes in the signal. Therefore, it has high a potential to be employed in medical purposes. Since, each action or abnormality, which is recorded in SEMG signals, has its own pattern, and via the 1D-LBP these (hidden) patterns may be detected. But, the positions of the neighbors in 1D-LBP are constant depending on the position of the data in the raw. Also, both LBP and 1D-LBP are very sensitive to noise. Therefore, its capacity in detecting hidden patterns is limited. To overcome these drawbacks, aLBP was proposed. In aLBP, the positions of the neighbors and their values can be assigned adaptively via the down-sampling and the smoothing coefficients. Therefore, the potential to detect (hidden) patterns, which may express an illness or an action, is really increased. To validate the proposed feature extraction approach, two different datasets were employed. Achieved accuracies by the proposed approach were higher than obtained results by employed popular feature extraction approaches and the reported results in the literature. Obtained accuracy results were brought out that the proposed method can be employed to investigate SEMG signals. In summary, this work attempts to develop an adaptive feature extraction scheme that can be utilized for extracting features from local changes in different categories of time-varying signals.

Hidden pattern discovery on epileptic EEG with 1-D local binary patterns and epileptic seizures detection by grey relational analysis.

This paper proposes a novel approach to detect epilepsy seizures by using Electroencephalography (EEG), which is one of the most common methods for the diagnosis of epilepsy, based on 1-Dimension Local Binary Pattern (1D-LBP) and grey relational analysis (GRA) methods. The main aim of this paper is to evaluate and validate a novel approach, which is a computer-based quantitative EEG analyzing method and based on grey systems, aimed to help decision-maker. In this study, 1D-LBP, which utilizes all data points, was employed for extracting features in raw EEG signals, Fisher score (FS) was employed to select the representative features, which can also be determined as hidden patterns. Additionally, GRA is performed to classify EEG signals through these Fisher scored features. The experimental results of the proposed approach, which was employed in a public dataset for validation, showed that it has a high accuracy in identifying epileptic EEG signals. For various combinations of epileptic EEG, such as A-E, B-E, C-E, D-E, and A-D clusters, 100, 96, 100, 99.00 and 100% were achieved, respectively. Also, this work presents an attempt to develop a new general-purpose hidden pattern determination scheme, which can be utilized for different categories of time-varying signals.