Soft Margin Research Articles

Influence of marginal and segmental bony resection on the local control of oral Squamous cell carcinoma involving the mandible

Background and objective: Marginal or segmental resection of bone are often required for tumor removal in oral squamous cell carcinoma patients to secure adequate margin. The present study aims to evaluate the surgical outcome and post-operative complication of both group of patients and also assesses the local control of the disease in the oral cavity.
 Methods: In this prospective study, 32 patients who were treated with marginal or segmental jaw resection for oral squamous cell carcinoma of the lower part of oral cavity was undertaken within September 2008 to August 2013.There were 9 males and 23 females with a median age of 40.5 years. Twenty patients underwent marginal and 12 patients had segmental resection of the mandible. Distribution of the subject by age, sex, primary site of lesion, pathologic tumor stage, presence of mandibular invasion, pathologic cervical lymph node stage and feature of post- operative complications were analyzed prospectively.
 Results: According to this study, the mandible was involved in 83.3% of patient with segmental resection and 15% of patients with marginal resection. Buccal mucosa was mostly involved site in marginal group (60%) and retro molar trigon was highly involved site with segmental group (41.7%). In marginal group 30% cases was involved with stage1 and 70% was stage2; in segmental group 25% cases were stage2 and 67.7% were stage3. Statistically significant difference was exist in pathological cervical node stage(p<0.05). Mandibular invasion was significantly more in segmental group (p<0.05). Soft tissue surgical margins were positive in 4 patients (20%) in the marginal group and in 3 patients (25%) in the segmental group. Negative neck lymph node was found in 20 (63%) cases and positive neck node was found in 12 (37%) cases, of which four patients, including 2(15%) cases in the marginal group and 2(8.3%) cases in the segmental group was died. Trismus and mastication problems were found higher in segmental than marginal resection group.
 Conclusion: Marginal resection of mandible is effective for patient with oral squamous cell carcinoma in the early stage. Post-operative outcome and local control of disease in segmental group were slightly higher than marginal group. Positive surgical margin status and bone invasion was found as the most important predictor of local control of the diseases in patient with oral squamous cell carcinoma.
 Bangladesh Journal of Medical Science Vol.18(4) 2019 p.801-807

Safety of resection margins in CAD/CAM-guided primarily reconstructed oral squamous cell carcinoma-a retrospective case series.

After resection of malignancies of the jaws, CAD/CAM procedures have become standard for primary bony reconstruction. Even so, these techniques may limit surgical resection safety. Therefore, the aim of the study was to examine osseous as well as soft tissue resection margins after CAD/CAM-guided tumor resections and reconstructions. A retrospective analysis of patients treated with oral squamous cell carcinoma (OSCC) from 2014 to 2019 was performed. Inclusion criteria were CAD/CAM-guided osseous resection and primary reconstruction. Evaluation was performed for histological confirmed resection margins (hard and soft tissue) as well as recurrence of the disease related to the resection status. In 46 patients, bony resection margins were classified: tumor free (R0 41/46), microscopical invasion (R1 1/46), and close margin (R0 < 4mm 4/46) respectively for soft tissue 29/46 tumor free (R0), 7/46 close margin (R0 < 4mm), 5/46 R1, and 4/46 could not be further determined (Rx). Fourteen patients (14/46) showed recurrent disease (2/46 locoregional) without association with the bony resection margin status. Recurrence occurred predominantly (13/46) in high-staged tumor patients. R1/close margin/Rx resection of the soft tissue resulted in a significant earlier recurrence when compared with R0 resection. CAD/CAM procedure allows safe tumor resection with the profit of a guided and accurate reconstruction. In contrast to positive soft tissue margins, positive bony resection margins did not increase recurrence parameters.

Ten-Year Oncologic Outcomes Following Robot-Assisted Radical Cystectomy: Results from the International Robotic Cystectomy Consortium.

Radical cystectomy is the gold standard for nonmetastatic muscle invasive bladder cancer and for refractory nonmuscle invasive disease. Compared to open radical cystectomy, robot-assisted radical cystectomy has been shown to provide comparable early oncologic outcomes and improved perioperative outcomes. However, there is a paucity of data on long-term oncologic outcomes and concerns about a higher incidence of local recurrence after robot-assisted radical cystectomy. We report 10-year oncologic outcomes following robot-assisted radical cystectomy using a multinational database. We retrospectively reviewed the prospective International Robotic Cystectomy Consortium database. Consecutive patients who underwent robot-assisted radical cystectomy 10 years ago or earlier were included in analysis. Data were reviewed for demographics, and perioperative, pathological and oncologic outcomes. Kaplan-Meier curves were used to depict recurrence-free, disease specific and overall survival. Multivariate stepwise Cox regression models were applied to identify variables associated with recurrence-free, disease specific and overall survival. We identified 446 patients with a median age of 67 years (IQR 59-76). Of the patients 10% received neoadjuvant chemotherapy, 51% experienced any complication, 23% had high grade complications and 4% died within 3 months of robot-assisted radical cystectomy. Disease was pT3 or greater in 43% of patients and pN+ in 24% while a positive soft tissue surgical margin was observed in 7%. At a median followup of 5 years (IQR 2-10, maximum 14) local and distant recurrence had developed in 15% and 29% of patients, respectively. Ten-year recurrence-free, disease specific and overall survival rates were 59%, 65% and 35%, respectively. Patients with pT3 or greater and pN+ disease showed worse recurrence-free, disease specific and overall survival. Long-term oncologic outcomes, and recurrence rates and patterns after robot-assisted radical cystectomy seem comparable to those in open series. Advanced disease stage and positive surgical margins remain the main determinants of survival after radical cystectomy.

Three-Dimensional Nanoscale Nuclear Architecture Mapping of Rectal Biopsies Detects Colorectal Neoplasia in Patients with Inflammatory Bowel Disease.

Patients with inflammatory bowel disease (IBD) colitis are at an increased risk of developing colorectal cancer and are currently recommended to undergo extensive annual or biennial colonoscopy, a costly and invasive procedure. Most surveillance colonoscopies are negative with no existing objective measures for assessing their risk of developing cancer. We have recently developed a less invasive, cost-effective and objective method to assess cancer risk by detecting the presence of colonic neoplasia via 3-dimensional (3D) nanoscale nuclear architecture mapping (nanoNAM) of normal-appearing rectal biopsies. To establish its translational relevance, we prospectively recruited 103 patients with IBD colitis undergoing surveillance colonoscopy and measured submicroscopic alterations in aberrant intrinsic nuclear architecture of epithelial cells from normal-appearing rectal biopsies with nanoNAM. The results were correlated with the histologic diagnoses from all random biopsies obtained during initial and follow-up colonoscopy within 3 years. Using nanoNAM-based structural characterization as input features into a soft margin-based ν-SVM risk classifier, we show that nanoNAM detects colonic neoplasia with AUC of 0.87 ± 0.04, sensitivity of 0.81 ± 0.09, and specificity of 0.82 ± 0.07 in the independent validation set. In addition, projecting nanoNAM features onto a 2-sphere reveals patients with low-risk and high-risk IBD colitis existing on separate hemispheres. Finally, we show that this ability to assess cancer risk translates to clinically-relevant estimation of individual-patient likelihood of being truly at risk. We demonstrate the potential of nanoNAM to identify patients with IBD at higher risk of developing cancer from normal-appearing rectum tissue, which may aid clinicians in patients with personalized IBD colitis surveillance.

A Support Vector Machine-Firefly Algorithm for Movie Opinion Data Classification

The sentiment analysis used in this study is the process of classifying text into two classes, namely negative and positive classes. The classification method used is Support Vector Machine (SVM). The successful classification of the SVM method depends on the soft margin coefficient C, as well as the σ parameter of the kernel function. Therefore we need a combination of SVM parameters that are appropriate for classifying film opinion data using the SVM method. This study uses the Firefly method as an SVM parameter optimization method. The dataset used in this study is public opinion data on several films. The results of this study indicate that the Firefly Algorithm (FA) can be used to find optimal parameters in the SVM classifier. This is evidenced by the results of SVM system testing using 2179 data with nine SVM parameter combinations resulting in 85% highest accuracy, while the FA-SVM system with nine population and generation combinations produces the highest accuracy of 88%. The second test results using 1200 data using the same combination as the one test, the SVM method produces the highest accuracy of 87%, while the FA-SVM method produces the highest accuracy of 89%.

Radical cystectomy pentafecta: a proposal for standardisation of outcomes reporting following robot-assisted radical cystectomy.

To propose a standardisable composite method for reporting outcomes of radical cystectomy (RC) that incorporates both perioperative morbidity and oncological adequacy. From July 2010 to December 2017, 277 consecutive patients who underwent robot-assisted RC with intracorporeal urinary diversion (UD) for bladder cancer at our Institution were prospectively analysed. Patients who simultaneously demonstrated negative soft tissue surgical margins (STSMs), ≥16 lymph node (LN) yield, absence of major (grade III-IV) complications at 90days, absence of UD-related long-term sequelae and absence of clinical recurrence at ≤12months, were considered as having achieved the RC-pentafecta. A multivariable logistic regression model was assessed to measure predictors for achieving RC-pentafecta. Since 2010, 270 of 277 patients that had completed at least 12months of follow-up were included. Over a mean follow-up of 22.3months, ≥16 LN yield, negative STSMs, absence of major complications at 90days, and absence of UD-related surgical sequelae and clinical recurrence at ≤12months were observed in 93.0%, 98.9%, 76.7%, 81.5% and 92.2%, patients, respectively, resulting in a RC-pentafecta rate of 53.3%. Multivariable logistic regression analysis revealed age (odds ratio [OR] 0.95; P=0.002), type of UD (OR 2.19; P=0.01) and pN stage (OR 0.48; P=0.03) as independent predictors for achieving RC-pentafecta. We present a RC-pentafecta as a standardisable composite endpoint that incorporates perioperative morbidity and oncological adequacy as a potential tool to assess quality of RC. This tool may be useful for assessing the learning curve and calculating cost-effectiveness amongst others but needs to be externally validated in future studies.

Adjuvant radiotherapy for sebaceous carcinoma of the eyelid after orbital exenteration

Surgical excision is an optimal treatment option for sebaceous carcinoma of the orbital region. As tumor recurrence in this region might compromise the survival and locoregional control of patients as well as the cosmetic results, adjuvant radiotherapy is suggested to patients with adverse pathological findings. Here we report a case of sebaceous carcinoma of the eyelid that was treated using orbital exenteration and adjuvant radiotherapy. In 2011, a 54-year-old male was diagnosed with sebaceous carcinoma of the left eyelid, for which he underwent surgical excision of the lesion. After 4 years, recurrence was observed with pathological evidence. Severe deterioration of the left eye function made organ preservation of little significance to the patient himself; instead, minimizing the chances of future recurrences became his priority. The patient underwent orbital exenteration as a radical treatment approach. Postoperatively, the patient was administered adjuvant radiotherapy owing to a less than 1mm deep soft tissue margin and advanced T stage. For 3 months after radiotherapy, the patient was followed up at a radiation oncology clinic, and magnetic resonance imaging (MRI) of the orbit revealed no recurrence. The last follow-up at 15 months posttreatment revealed the stable condition of the treated area and no evidence of locoregional recurrence. This patient has been followed up for 8 years since the diagnosis in 2011. This successful treatment response indicates that surgical intervention and adjuvant radiotherapy with appropriate doses could be considered in patients with sebaceous carcinoma of the eyelid.

Combination of discrete wavelet packet transform with detrended fluctuation analysis using customized mother wavelet with the aim of an imagery-motor control interface for an exoskeleton

One critical issue in brain computer interface (BCI) studies is to extract imaginary movement patterns from electroencephalograph (EEG). In this study, two different techniques —detrended fluctuation analysis (DFA) and discrete wavelet packet transform— are combined (DWPT-DFA) for feature extraction. Both approaches are known as self-similarity quantifier techniques. In wavelet technique, mother wavelets play an important role. Herein, A customized mother wavelet utilizing event related desynchronization (ERD) potential patterns are extracted and updated automatically for individual subjects. Also, three predefined mother wavelets are used, and the results are compared with the customized mother wavelet. The predefined mother wavelets are db4, db8 and coiflet 4. The soft margin support vector machine with the generalized radial basis function (SSVM-GRBF) is employed to classify the DWPT-DFA features. For the efficiency of the method, nine subjects have participated to record EEG based on the imaginary hand movements. The ERDs and features are extracted from FC1 and CP6 channels. Results show that the combination of the DWPT and DFA with the personalize ERD mother wavelet gives the best accuracy of 85.33% with p < 0.001. Based on the results, we conclude that the DWPT-DFA method using the ERD mother wavelets improves significantly the efficiency of the SSVM-GRBF classifier.

Soft extreme learning machine for fault detection of aircraft engine

When extreme learning machine (ELM) is used to cope with classification problems, the ±1 is commonly used to construct the label vector. Since ELM adopts the square loss function, this means that it tends to force the margins of all the training samples exactly equaling one from the perspective of margin learning theory, which is unreasonable to some extent. To overcome this hard margin flaw, in this paper a soft extreme learning machine (SELM) is proposed, which flexibly sets a soft target margin for each training sample. Through solving a series of regularized ELMs (RELMs), SELM can be computed efficiently. Based on SELM, an improved SELM (ISELM) is proposed to deal with imbalanced classification problems, which can keep the same computational efficiency as SELM via solving a series of weighted RELMs. From the experimental results on benchmark data sets, the effectiveness and feasibility of SELM and ISELM are confirmed. More importantly, when they are applied to fault detection of aircraft engine, they are promising to be developed as the candidate techniques for it, and ISELM is especially in favor.

A novel robust kernel for classifying high-dimensional data using Support Vector Machines

This paper presents a new semantic kernel for classification of high-dimensional data in the framework of Support Vector Machines (SVM). SVMs have gained widespread application due to their relatively higher accuracy. The efficacy of SVMs, however, depends upon the separation of the data itself as well as the kernel function. Text data, for instance, is difficult to classify due to synonymy and polysemy in its contents, having multi-topical instances that can result in mislabeling, and being highly sparse in the bag-of-words representation. While the soft margin parameter and kernel tricks are used in SVM to deal with outliers and non-linearly separable data, using data statistics and correlation has not been fully explored in the literature. This paper explore the use co-similarity (i.e., soft co-clustering) to find latent relationships between documents motivated by the success of co-clustering and subspace clustering methods. It has been shown that the use of weighted higher-order paths between instances in the data can be a good measure of similarity values which can then be used for both classification and to correct mislabeled (or outlier) data in the training set. The proposed kernel is generic in nature and suitable for sparse, dyadic data where direct co-occurrences are not necessary common as in the case of textual data, link-analysis in social media networks, co-authorship, etc. It also studies the impact of noise in the training data and provides a technique to re-label such instances. It is also observed that re-labelling of selected training data reduces the adverse effect of outliers or label noise and can greatly improve the classification of the test data. To the best of our knowledge, we are the first to introduce a supervised co-similarity based kernel function and also provide mathematical formulation to show that it is a valid Mercer's kernel. Our experiments show that the proposed framework outperforms current and state-of-the-art methods in terms of classification accuracy and is more resilient to label noise.

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor.

Automatic detection of left ventricle myocardium is essential to subsequent cardiac image registration and tissue segmentation. However, it is considered challenging mainly because of the complex and varying shape of the myocardium and surrounding tissues across slices and phases. In this study, a hybrid model is proposed to detect myocardium in cardiac magnetic resonance (MR) images combining region proposal and deep feature classification and regression. The model firstly generates candidate regions using new structural similarity-enhanced supervoxel over-segmentation plus hierarchical clustering. Then it adopts a deep stacked sparse autoencoder (SSAE) network to learn the discriminative deep feature to represent the regions. Finally, the features are fed to train a novel nonlinear within-class neighborhood preserved soft margin support vector (C-SVC) classifier and multiple-output support vector (-SVR) regressor for refining the location of myocardium. To improve the stability and generalization, the model also takes hard negative sample mining strategy to fine-tune the SSAE and the classifier. The proposed model with impacts of different components were extensively evaluated and compared to related methods on public cardiac data set. Experimental results verified the effectiveness of proposed integrated components, and demonstrated that it was robust in myocardium localization and outperformed the state-of-the-art methods in terms of typical metrics. This study would be beneficial in some cardiac image processing such as region-of-interest cropping and left ventricle volume measurement.

MP32-12 RADICAL CYSTECTOMY PENTAFECTA: A PROPOSAL FOR STANDARDIZATION OF OUTCOMES REPORTING FOLLOWING ROBOT ASSISTED RADICAL CYSTECTOMY

INTRODUCTION AND OBJECTIVES:To propose a standardisable composite method for reporting outcomes of radical cystectomy (RC) that incorporates both peri-operative morbidity and oncologic adequacy.METHODS:From July 2010 through December 2017, 277 consecutive patients who underwent robotic radical cystectomy (RRC) for bladder cancer at our institution were prospectively analysed. IRB approval was obtained (HS-01B014). Patients who simultaneously demonstrated negative soft tissue surgical margins, =/> 16 lymph node yield, absence of major (Clavien-Dindo grade III-IV) complications at 90 days, absence of urinary diversion (UD) related long-term sequelae and absence of clinical recurrence at =/< 12 mo. were considered as having achieved the RC-pentafecta. We created a multivariable logistic regression model using age, ASA score, type of UD, NACH, pT and pN stage as covariates to measure independent factors for achieving RC-pentafecta. The internal validity of the prediction model was assessed by 1,000 bootstrap ...

The impact of completeness of last transurethral resection of bladder tumors on the outcomes of radical cystectomy.

To evaluate the role of a complete transurethral resection of bladder tumors (c-TURBT) on oncological outcomes after radical cystectomy (RC) and its relationship with adverse pathological features. We retrospectively analyzed data of 727 patients treated with RC and bilateral pelvic lymph node dissection at three tertiary referral centers. Possible c-TURBT was reported by the treating surgeon. Multivariable Cox regression analyses were used to assess the relationship of c-TURBT and survival outcomes after surgery in 1:1 propensity score-matched cohort adjusted for age and gender. Moreover, multivariable logistic regression (MVA) was built to predict the relationship between c-TURBT and pT3-T4 stages at RC, lymph node invasion (LNI) and positive soft tissue surgical margin (STSM). A total of 433 (60%) patients received a c-TURBT. 3.0% of patients with a c-TURBT achieved a pT0-pTa-pTis status vs. 2.0% of patients with incomplete TURBT. At multivariable Cox regression analyses, c-TURBT was not associated with survival outcomes. At MVA, incompleteness of TURBT was significantly associated with a pT3-T4 stage [odds ratio (OR) 8.04, 95% confidence interval (CI) 2.33-27.67, p = 0.001]. No significant association was found between c-TURBT, LNI and STSM. We found a low rate of achievement of pT0 stage at RC. An incomplete TURBT before RC represented a predictor of pT3-T4 stages, but no effect of a c-TURBT was shown on survival outcomes. Given the current inadequacy of clinical staging strategies with more than 50% of extravesical disease being under-staged, our results could improve patients selection for NAC, driving the decision-making in doubtful cases.

Histologic variants associated with biological aggressiveness and poor prognosis in patients treated with radical cystectomy.

The prognostic value of histologic variants (HV) after radical cystectomy (RC) remains controversial. We evaluated the clinicopathological features and prognosis in patients with pure urothelial carcinoma (UC) and HV following RC. From 1990 to 2015, 286 patients with bladder cancer were treated with RC at six Kitasato University-affiliated hospitals. All patients were divided into two groups: pure UC and HV, which contained pure variants and mixed-type UC with variant pattern. A comparison of patient characteristics between the two groups was made to assess the clinicopathological features, and statistical analyses were performed to investigate prognosis in the two groups. Of the 286 patients, 226 (79%) had pure UC, while 60 (21%) had HV. Of all HV, pure variants accounted for 45% (n = 27). The prevalence of lymph node involvement, locally advanced stage (≥ pT3), positive soft tissue surgical margin and lymphovascular invasion were significantly higher in patients with HV than in those with pure UC. Patients with HV showed worse disease-free survival and cancer-specific survival than those with pure UC (P = 0.009 and 0.003, respectively). In multivariate analysis, HV and lymph node involvement were independent predictors of worse disease-free survival (P = 0.017 and 0.001, respectively). HV, locally advanced stage, lymph node involvement, and positive soft tissue surgical margin were also confirmed as independent predictors of worse cancer-specific survival (P = 0.011, 0.012, 0.003 and 0.010, respectively.). HV was associated with greater biological aggressiveness and worse prognosis than pure UC.

A novel reconstructed training-set SVM with roulette cooperative coevolution for financial time series classification

In real applications, noises are often present in the obtained data, which would considerably affect the performance of machine learning models. Although support vector machine (SVM) is a classic and efficient learning model, however, it is sensitive to noises in the training data. In this paper, a novel support vector machine named as reconstructed training-set SVM (RTS-SVM) is proposed to implement classification for high-noise data, where the roulette cooperative coevolution algorithm (R-CC) is used to optimize the parameters of RTS-SVM. The proposed SVM model is applicable to make the classification of high-noise data by tackling with the sensitive effect of the ``soft margin'' of SVM on the original training set. By means of the hierarchical relations existing in feature sets, hierarchical grouping (HG) algorithm is applied to construct feature subsets, based on which R-CC coordinates the parameters of RTS-SVM to achieve the optimization of the whole model. The application of the proposed scheme in the classification of financial time series is mainly discussed. Besides, the proposed model is also verified by using synthetic data with high noises and daily life data sets. Examples are provided to illustrate the effectiveness and practicability of the proposed algorithm.

The use of retraction paste to simplify impression and cementation of ceramic veneers and crowns: 3-year follow-up report.

Proper gingival displacement is an important prerequisite to obtain good quality impressions. Retraction pastes could eliminate the need for retraction cords, as they have advantages such as comfort reported by patients, faster technique, ease of use, no need for anesthesia, and reduced tissue trauma. The objective of this paper was to present a clinical case of ceramic veneers and crowns in which a retraction paste was used for gingival displacement during both the impression and cementation stages, with 3 years of follow-up. Treatment planning consisted of the replacement of preexisting crowns and ceramic veneers on the anterior teeth. After finishing the preparations, gingival displacement with Astringent Retraction Paste was performed without anesthesia or the use of cords and the impression was taken. Before cementation of the crowns and veneers, the Astringent Retraction Paste was applied. Avoiding the use of cords during cementation prevented trauma. The soft tissue margins remained stable and healthy after a period of 3 years. It can be concluded that retraction pastes could be indicated for displacement of soft tissue when preparation margins are at the gingival level or slightly intrasulcular prior to impressions, restoration cementations, direct restorations, and before relining provisional restorations. Clinical significance: The impression appointment can be traumatic to some patients. The use of cords for gingival displacement usually requires local anesthesia and is time consuming. Retraction astringent pastes instead of cords seems to be a good option for some cases in gingival tissue displacement.

Ameloblastic carcinoma arising from a preexistent ameloblastoma

ABSTRACT Ameloblastic carcinoma (AC) is a rare odontogenic tumor that represents the malignant counterpart of an ameloblastoma. There are few cases of AC in the English-language literature, with only 16 cases arising from preexisting ameloblastomas reported in the last 10 years. Multiple local recurrences of ameloblastomas precede this transformation. In the current report, we describe a case of AC at the posterior maxilla in a 42-year-old female submitted to surgical resection, with three recurrences of ameloblastoma in a period of four years. Imaging exams showed a radiodense mass with cortical bone disruption and maxillary sinus invasion. Histologic analysis demonstrated features of islands and nests of malignant epithelium transformation, atypia, pleomorphic cells, nuclear hyperchromatism, necrosis and desmoplasia. AC represents a rare and challenging histologic diagnosis. Surgical access with adequate hard and soft tissue margins is essential for influencing survival. The description of new cases may reveal, through of treatment and clinical follow-up, characteristics that allow us better understanding of AC behavior.

Evaluating Factors for Predicting the Life Dissatisfaction of South Korean Elderly using Soft Margin Support Vector Machine based on Communication Frequency, Social Network Health Behavior and Depression

Since health and the quality of life are caused not by a single factor but by the interaction of multiple factors, it is necessary to develop a model that can predict the quality of life using multiple risk factors rather than to identify individual risk factors. This study aimed to develop a model predicting the quality of life based on C-SVM using big data and provide baseline data for a successful old age. This study selected 2,420 elderly (1,110 men, 1,310 women) who were 65 years or older and completed the Seoul Statistics Survey. The quality of life satisfaction, a binary outcome variable (satisfied or dissatisfied), was evaluated based on a self-report questionnaire. This study performed a Gauss function among the SVM algorithms. To verify the predictive power of the developed model, this study compared the Gauss function with the linear algorithm, polynomial algorithm, and sigmoid algorithm. Additionally, C-SVM and Nu-SVM were applied to four kernel algorithm types to create eight types, and prediction accuracies of the eight SVM types were estimated and compared. Among 2,420 subjects, 483 elderly (19.9%) were not satisfied with their current lives. The final prediction accuracy of this SVM using 625 support vectors was 92.63%. The results showed that the difference between C-SVM and Nu-SVM was negligible in the models for predicting the satisfaction of life in old age while the Gaussian kernel had the highest accuracy and the sigmoid kernel had the lowest accuracy. Based on the prediction model of this study, it is required to manage local communities systematically to enhance the quality of life in old age.

LINEX Support Vector Machine for Large-Scale Classification

Traditional soft margin support vector machine usually uses hinge loss to build a classifier with the “maximum-margin”principle. However, C-SVM depends on support vectors causing the loss of data information. Then, least square support vector machine is proposed with square loss (l 2 -loss). It establishes equality constraints instead of inequalities and considering all the instances. However, the square loss is still not the perfect one, since it gives equivalent punishment to the instances at both sides of the center plane. It does not match the reality considering the instances between two center planes deserve heavier penalty than the others. To this end, we propose a novel SVM method with the adoption of the asymmetry LINEX (linear-exponential) loss, which we called it LINEX-SVM. The LINEX loss gives different treatments to instances based on the importance of each point. It gives a heavier penalty to the points between two center planes while drawing light penalty to the points outside of the corresponding center planes. The comprehensive experiments have been implemented to validate the effectiveness of the LINEX-SVM.

EEG Control of a Bionic Hand With Imagination Based on Chaotic Approximation of Largest Lyapunov Exponent: A Single Trial BCI Application Study

This paper investigates a method for imaginary hand fisting pattern recognition based on the electroencephalography (EEG). The proposed method estimate the largest Lyapunov exponent (LLE) chaotic feature that is based on approximation of mutual information (MI) and false nearest neighbor (FNN) methods for reconstructing a phase space. The selected method for MI and FNN approximation approaches is a new version of Tug of War optimization algorithm. The new algorithm utilizes chaotic maps to update candidate solutions. The chaotic approximation of the LLE (CALLE) is the utilized method for extracting the chaotic features and then categorizing features by means of soft margin support vector machine with a generalized radial basis function kernel classifier. Accuracy and paired t-test values are obtained and compared with the traditional LLE method; 18 candidates were participated to record the EEG for imaginary right-hand fisting task. The results show improvements for the CALLE algorithm in comparison with the traditional LLE by achieving a higher accuracy of 68.25%. Feature changes between two imaginary statuses were significant for 17 subjects, and the paired t-test values were (p <; 0.05). From the results, it is concluded that the Tug of War optimization method finds different values to reach a higher accuracy than the traditional LLE method, and the traditional methods for the LLE are not optimum.