Correct Class Research Articles

Leaf-based Classification of Important Indigenous Tree Species by Different Feature Extraction Techniques and Selected Classification Algorithms

The machine learning algorithms, namely, k-Nearest Neighbor (KNN), Support Vector Machine (SVM), Back-Propagation (BP) networks, and Convolutional Neural Networks (CNN) are four of the mostly used classifiers. Different sets of features are required as input in different application domains. In this paper, a set of significant leaf features and classification model was determined with a high accuracy in classifying important indigenous tree species. Leaf images were acquired using a scanner to control the image quality. The image dataset was then duplicated into two sets. The first set was labeled with their correct classes, preprocessed, and segmented in preparation for feature extraction. The leaf features extracted were leaf shape, leaf color, and leaf texture. Then, training and classification was done by KNN, SVM, and BP networks. On the other hand, the second set was unlabeled for training and classification by CNN. A CNN model was built and chosen with the best training and validation accuracy and the least training and validation loss rate. The study concluded that using all three leaf features for classification by BP networks resulted in a 93.48% accuracy with training done by supervised learning. However, the CNN achieved a high accuracy rate of 98.5% making it the best approach for classification of tree species using digital leaf images in the context of this study.

Rethinking Sampling Strategies for Unsupervised Person Re-Identification.

Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design and loss function, this paper shows that sampling strategy plays an equally important role. We analyze the reasons for the performance differences between various sampling strategies under the same framework and loss function. We suggest that deteriorated over-fitting is an important factor causing poor performance, and enhancing statistical stability can rectify this problem. Inspired by that, a simple yet effective approach is proposed, termed group sampling, which gathers samples from the same class into groups. The model is thereby trained using normalized group samples, which helps alleviate the negative impact of individual samples. Group sampling updates the pipeline of pseudo-label generation by guaranteeing that samples are more efficiently classified into the correct classes. It regulates the representation learning process, enhancing statistical stability for feature representation in a progressive fashion. Extensive experiments on Market-1501, DukeMTMC-reID and MSMT17 show that group sampling achieves performance comparable to state-of-the-art methods and outperforms the current techniques under purely camera-agnostic settings. Code has been available at https://github.com/ucas-vg/GroupSampling.

Evaluation of Hard Tissue, Soft Tissue and Airway Changes Post Twin Block Therapy: An In-vitro Study

Introduction: Aesthetic improvement happens to be one of the main reasons for seeking orthodontic treatment in patients with Angle’s Class II malocclusion. Prognathic maxilla, retrognathic mandible or a combination of both are the main aetiological factors for this malocclusion. Growth modification treatment with different methods can be performed in order to correct skeletal class II malocclusion. Appliance therapy to correct similar malocclusions should immaculately be directed towards addressing the dentoskeletal discord, in order to gain a favourable facial aesthetic result. Aim: To assess the effects of twin block on mandibular length, soft tissue profile and Oropharyngeal Airway (OAW) dimensions in skeletal class II malocclusion patients. Materials and Methods: An in-vitro study was carried out in the Department of Paedodontics at Sardar Patel Postgraduate Institute of Dental and Medical Sciences, Lucknow from June 2018 to March 2021. Study was done on lateral cephalograms of 15 growing children with Angle’s Class II Division 1 malocclusion in the age group of 9-12 years, who had undergone functional appliance therapy with twin block appliance. Standardised lateral cephalograms were evaluated at pretreatment (0 month) and postactive phase of twin-block therapy (9-12 months). Selected hard tissue, soft tissue and airway landmarks were marked and traced to evaluate hard tissue, soft tissue and airway changes. The data was analysed using statistical package for social sciences (SPSS) version 21. Results: There was a statistically significant increase in effective mandibular length (Condyle-Gnathion) and mandibular base length Gonion-Pogonion (Go-Pog) values (p<0.001). Significant decrease in the facial convexity Glabella- Soft tissue Nasion (G-Sn) Soft tissue Nasion- Soft tissue Pogonion (Sn-Pog) was observed and airway dimensions showed significant increase after twin block therapy. Conclusion: Correction of Class II malocclusion by twin block appliance resulted in significant cephalometric changes in the hard tissue profile (increase in mandibular length), together with clinically favourable soft tissue changes and OAW dimensions.

DIDACTIC GAMES AS A MEANS OF DEVELOPING DESCRIPTIVE VOCABULARY OF YOUNGER SCHOOLCHILDREN WITH INTELLECTUAL DISABILITIES

The article provides an overview of the theoretical foundations on the problem of developing descriptive vocabulary through didactic games. Features of the formation of descriptive vocabulary of younger schoolchildren with intellectual disabilities are described. The characteristic features of speech of children of this category are considered, such as poor vocabulary, inaccurate use of words, difficulties in updating the dictionary, violations of the process of organizing semantic fields. It was found out that due to the peculiarities of cognitive activity of this category of children, one of the most effective means of their development is didactic games, since they contribute to the activation of speech and educational activities, a positive attitude to learning and speech development, which occurs in the game and therefore is invisible to the student himself. Types of didactic games that are aimed at developing students’ speech are considered. Games for developing descriptive vocabulary are offered. The directions of activity on the formation of descriptive vocabulary of younger schoolchildren with intellectual disabilities are described: expansion, actualization, clarification of passive and active vocabulary of nouns, verbs, adjectives, adverbs; formation of lexical consistency and semantic fields, development of antonymic, synonymous relations, unambiguous and polysemous words, homonyms, formation of generalizing concepts. The article summarizes the methodology and features of using didactic games for the development of descriptive vocabulary of younger schoolchildren. For successful education and upbringing of these children, it is necessary to awaken their interest in educational activities and activate their activities. Despite the fact that the game activity of children with developmental disabilities is very peculiar, speech therapists widely use various game technologies to correct the cognitive activity of this category of children. The proposed didactic games can be actively used for the development of descriptive vocabulary by speech therapists in correctional and developmental classes, teachersdefectologists – in primary classes of a special school, teachers – in inclusive classes, during lessons on speech development, Ukrainian language, natural science, social orientation and parents of children with intellectual disabilities at home.

Orthodontic Marvel: Correction of Class II Malocclusion with the Churro Jumper Appliance

Class II malocclusion is a common orthodontic issue characterised by an excessive overjet, where the upper front teeth are significantly ahead of the lower ones. It often leads to aesthetic concerns and functional problems. Orthodontic treatment is the preferred solution to correct Class II malocclusion, and among the diverse range of appliances available, the Churro Jumper Appliance has emerged as a groundbreaking innovation. The present case report is about a 15-year-old male patient with Class II division 1 malocclusion and a retrognathic mandible. The MBT 0.022" prescription was used for bonding. After levelling and aligning both the upper and lower arches, and closing the anterior spacing, the Churro Jumper was used as a fixed functional appliance for mandibular repositioning. The required results were achieved using the appliance, and the patient’s occlusion was brought to a Class I molar and canine relationship, while also improving the profile. The treatment was completed in 17 months. Although several fixed functional appliances are available in the market for Class II correction, the Churro Jumper appliance was used in the present case.

Fine-Grained Object Detection in Remote Sensing Images via Adaptive Label Assignment and Refined-Balanced Feature Pyramid Network

Object detection in high-resolution remote sensing images remains a challenging task due to the uniqueness of its viewing perspective, complex background, arbitrary orientation, etc. For fine-grained object detection in high-resolution remote sensing images, the high intra-class similarity is even more severe, which makes it difficult for the object detector to recognize the correct classes. In this article, we propose the refined and balanced feature pyramid network (RB-FPN) and center-scale aware (CSA) label assignment strategy to address the problems of fine-grained object detection in remote sensing images. RB-FPN fuses features from different layers and suppresses background information when focusing on regions that may contain objects, providing high-quality semantic information for fine-grained object detection. Intersection over Union (IoU) is usually applied to select the positive candidate samples for training. However, IoU is sensitive to the angle variation of oriented objects with large aspect ratios, and a fixed IoU threshold will cause the narrow oriented objects without enough positive samples to participate in the training. In order to solve the problem, we propose the CSA label assignment strategy that adaptively adjusts the IoU threshold according to statistical characteristics of oriented objects. Experiments on FAIR1M dataset demonstrate that the proposed approach is superior. Moreover, the proposed method was applied to the fine-grained object detection in high-resolution optical images of 2021 Gaofen challenge. Our team ranked sixth and was awarded as the winning team in the final.

ИЗУЧЕНИЕ ОСОБЕННОСТЕЙ ПРОФЕССИОНАЛЬНЫХ ПРЕДПОЧТЕНИЙ ПОДРОСТКОВ С ИНТЕЛЛЕКТУАЛЬНЫМИ НАРУШЕНИЯМИ ПРИ ОВЛАДЕНИИ ПРОФЕССИЕЙ ОПЕРАТОР ШВЕЙНОГО ОБОРУДОВАНИЯ

Introduction. The professional preferences of adolescents with intellectual disabilities re-quire special attention in the prospects of work on their socialization. Teachers develop and shape the skills and abilities that are available to the adolescent to assert themselves in their chosen profession. At the same time, when choosing each profession to be mastered by a student with intellectual disabilities, it is necessary to understand the peculiarities of their professional preferences. The relevance of issues in this area determined the content of our research. The purpose of the study is to identify the features of professional preferences of adolescents with intellectual disabilities when mastering the profession of sewing equipment operator and to develop recommendations designed to help in mastering the skills required in the profession. Materials and methods. The study involved 28 students enrolled in the vocational training program 16185 sewing equipment operator (OSHO) for people with intellectual disabilities aged 16 to 20 years, groups OSHO-21 and OSHO-22. All students enrolled in the college after graduating from a special correctional school or correctional classes of secondary schools. The following methods and techniques were used in the study: the method of theoretical analysis of scientific, special and psychological-pedagogical literature, the study and generalization of pedagogical experience, the analysis of research results; empirical methods: the method of expert assessment, pedagogical experiment, the method of qualitative and quantitative analysis. The results. The study revealed the peculiarities of professional preferences, which made it possible not only to determine and understand the correspondence of adolescents’ abilities and interests to the profession but also to identify their problems: in mastering hand sewing tools and in the process of laying out patterns. The groups of subjects were described. The prerequisites for mastering the profession of sewing equipment operator among the adolescents in the experimental group are identified. Conclusion. Based on the identified difficulties in mastering professional skills and abilities in adolescents with intellectual disabilities, the components of the professional sphere necessary for their further development in the learning process were determined. On this basis, differentiated recommendations were developed for the students to master professional skills and abilities in the following areas: theoretical, communicative and vocational.

Postoperative relapse after bilateral sagittal split osteotomy of the mandible for correction of dentofacial deformity: Is it common?

Aim To investigate the effect of the magnitude of mandibular movement during bilateral sagittal split osteotomy (BSSO) on the incidence of postoperative relapse. Patients and methods The present cohort study included patients presented to the Maxillofacial Unit, General Surgery Department, Assiut University Hospital, Egypt. All patients underwent BSSO to correct class II malocclusion. Patients were divided into two groups, the first group included patients with mandibular movement less than 7 mm and the second group included patients with mandibular movement more than 7 mm. Then, we investigated the incidence of postoperative relapse in both groups. Results The study included 32 patients (64 sides). The first group included 24 patients (48 sides) and the second group included eight patients (16 sides). The incidence of postoperative relapse is 12.5%. Conclusion magnitude of mandibular movement more than 7 mm during BSSO is considered to be a risk factor for postoperative relapse.

PROCESSES FORMATION IN CHILDREN OF SENIOR PRESCHOOL AGE

Theoretical and methodological analysis of the problem of motor and speech rhythms development in children of senior preschool age with stuttering confirmed the assumption about delayed rhythm development in children of this nosological group. The need for a comprehensive study of this issue was the driving force for carrying out the observational experiment, whose purpose was to study the peculiarities of the development of motor and speech rhythms in older preschool children with stuttering. In the process of analyzing the comparative characteristics of the levels of motor and verbal response in senior preschool children with stuttering, it was proved that these two processes develop simultaneously and are interdependent. The retardation of one process leads to the retardation of the other one, which affects the development of children's motor and verbal (speech) rhythm. Comparative characteristics of the formation levels of motor and verbal rhythms in senior preschool children with stuttering before and after correctional and developmental classes show that after performing correctional and developmental exercises there are no children with zero and low levels of reproduction, while medium and sufficient levels of motor reproduction and speech response prevail. This fact experimentally confirmed that the selected correctional and developmental work, conducting of speech therapy and logorhythmic classes aimed at the development of motor and verbal rhythms contributed to a significant improvement in the children’s results.

An optimized fuzzy deep learning model for data classification based on NSGA-II

As a powerful paradigm, deep learning (DL) models have been used in many applications for classification tasks in images, text, and audio. Through DL models, we can learn task-driven features from big data. However, DL models are fully deterministic and cannot handle uncertain and imprecise data. DL models are often sensitive to noise in data and do not operate well in areas where data are vague. Moreover, when there is a large feature set or high-dimensional data with irrelevant and redundant features, the DL models’ performance decreases in classification due to training with irrelevant features. To gain reliable results in such high-dimensional problems, DL models require a large amount of data which usually grows exponentially concerning the number of features. Data uncertainty problems and irrelevant features in DL models cause low performance in classification tasks. This paper proposes an optimized fuzzy deep learning (OFDL) model for data classification based on Non-Dominated Sorting Genetic Algorithm II (NSGA-II). OFDL utilizes optimization in the composition of DL and fuzzy learning via the NSGA-II in multi-modal learning. To achieve effective classification, OFDL first considers intelligent feature selection by finding the best trade-offs between two conflicting objective functions, minimizing the number of features, and maximizing the accuracy (maximizing weights of selected features). Next, to reach optimized backpropagation and fuzzy membership functions, OFDL utilizes Pareto optimal solutions for multi-objective optimization using NSGA-II based on their objective functions. Furthermore, the fusion layer in OFDL fused optimized views of DL and fuzzy learning that provides a high-level representation of inputs and optimum features for classification tasks where the data contain high uncertainties and noises. This functionality gives valuable attributes during classification since identifying and selecting appropriate features ensures prompt and correct class. Also, it provides deep insight into tackling the effect of ambiguous data and each feature’s uncertainty in the classification tasks. The examination of OFDL reveals good performance in terms of F-measure, accuracy, recall, precision, and True Positive Rate (TPR) compared to fuzzy classifiers. Furthermore, OFDL has higher accuracy in classification tasks than earlier fuzzy DNN models.

CHILD-VICTIM OF BULLYING AS AN OBJECT OF SOCIAL AND PEDAGOGICAL ASSISTANCE

The article considers the problem of social and pedagogical assistance to children who are victims of bullying. Its purpose is to analyze the content of social and pedagogical assistance to children who are victims of bullying in an educational institution. Different positions on the phenomenon of bullying and bullying structure are presented. Features and characteristics of bullying victims are analyzed. A portrait of a potential victim of bullying is presented through the definition of typical signs of a victim of bullying, emotional background and behavior of victims of bullying. The characteristics of the types of victims of bullying (passive, provocative, chronic), symptoms of bullying, signs of impact on the health of students, the consequences in future adult life. It is determined that assistance to children victims of bullying is an important area of social and pedagogical work, should be comprehensive and multilevel, not limited to work with a child who has become a victim of school bullying. The stages of social and pedagogical assistance are analyzed: diagnostic; individual assistance to students who are victims of bullying; group work, which is based on the system of interaction of students, class teacher, teachers and class, parents of bullies. It was found that social and pedagogical work with victims of bullying should be carried out using both traditional and innovative methods of work: conversations, individual consultations, correctional and developmental classes, group classes with elements of training, communication hours, etc. Because bullying is a deliberate, group, conscious, and organized process, it cannot be stopped without the intervention of professionals (educators, psychologists, social educators) and parents. This involves purposeful anti-bullying work, which requires the involvement of all available resources of the educational institution and the child’s environment.

Covid-19 Control: Face Mask Detection Using Deep Learning for Balanced and Unbalanced Dataset

Facemask wearing is becoming a norm in our daily lives to curb the spread of Covid-19. Ensuring facemasks are worn correctly is a topic of concern worldwide. It could go beyond manual human control and enforcement, leading to the spread of this deadly virus and many cases globally. The main aim of wearing a facemask is to curtail the spread of the covid-19 virus, but the biggest concern of most deep learning research is about who is wearing the mask or not, and not who is incorrectly wearing the facemask while the main objective of mask wearing is to prevent the spread of the covid-19 virus. This paper compares three state-of-the- art object detection approaches: Haarcascade, Multi-task Cascaded Convolutional Networks (MTCNN), and You Only Look Once version 4 (YOLOv4) to classify who is wearing a mask, who is not wearing a mask, and most importantly, who is incorrectly wearing the mask in a real-time video stream using FPS as a benchmark to select the best model. Yolov4 got about 40 Frame Per Seconds (FPS), outperforming Haarcascade with 16 and MTCNN with 1.4. YOLOv4 was later used to compare the two datasets using Intersection over Union (IoU) and mean Average Precision (mAP) as a comparative measure; dataset2 (balanced dataset) performed better than dataset1 (unbalanced dataset). Yolov4 model on dataset2 mapped and detected images of masks worn incorrectly with one correct class label rather than giving them two label classes with uncertainty in dataset1, this work shows the advantage of having a balanced dataset for accuracy. This work would help decrease human interference in enforcing the COVID-19 face mask rules and create awareness for people who do not comply with the facemask policy of wearing it correctly. Hence, significantly reducing the spread of COVID-19.

Abstract PR013: Transcriptomic profiling of liquid biopsy in colorectal cancer

Abstract Objective: Consensus molecular subtype (CMS) is a predictive factor for treatment outcomes of chemotherapies for metastatic colorectal cancer (CRC). CMS classification is based on transcriptomic profiles of CRC specimens obtained by tumor biopsy. Tumor biopsy often provides limited information due to the heterogeneity within tumor and spatial heterogeneity between the primary tumor and distant metastases. In addition, repeated tissue biopsy to monitor the treatment response is not practical. Liquid biopsy is a minimally invasive method for the real-time monitoring of cancer-derived biomarkers. Among liquid biopsy biomarkers, extracellular vesicles (EVs) have a unique potential because they possess nucleic acids. We explored the use of CRC plasma EVs in predicting the molecular subtype of CRCs using RNA-seq. Methods: EVs were isolated from 10 different CMS-stratified colorectal cancer cell lines and a normal control. Whole transcriptome RNA-seq on cellular RNA (cRNA) and cell-derived evRNA was done to determine if EVs could be used to predict the CMS subtype of their cells of origin. We then sought to perform molecular subtyping of plasma EVs from patients with CRC. RNA-seq was performed on tumor tissues and matched plasma EVs from 46 patients with CRC and 59 healthy controls (age/gender matched). The bulk transcriptome from CRC plasma EVs was deconvoluted to predict the cancer percentage (CIBERSORTx) and to utilize cancer-specific transcriptome for CMS subtyping (DeMixT). Artificial neural network (ANN)-based CMS subtype classifier was used to classify molecular subtypes. Results: There was 100% concordance between CMS subtype of evRNA with that of the cRNA. We showed that, RNA mixtures containing as low as 1% cancer cell RNA could be accurately classified into the correct CMS class. Imputed proportions of cancer in plasma of CRC patients ranged from 0.89% to 2.08%. Receiver operating characteristic (ROC) curve showed area under the curve of 0.961 with specificity and sensitivity of 0.96 and 0.9, respectively. Plasma evRNA was classified into CMS classes and there was 67% (31/46) concordance between the predicted subtype of liquid biopsies and the tumor samples. In patients with tumor purity greater than 10%, the concordance was higher at 75% (27/36). Conclusions: EVs could be used to accurately predict CMS subtypes of their cells of origin. We created a pipeline using low-input RNA library preparation from plasma EV to estimate the cancer RNA portion present in the bulk transcriptome and predict the molecular subtypes of colorectal cancers. Molecular subtyping of evRNA may help to track CMS changes of the tumor in patients undergoing treatment. Citation Format: Vahid Bahrambeigi, Jaewon J. Lee, Kimal I. Rajapakshe, Bret M. Stephens, Jason T. Henry, Sarah Dhebat, Mark W. Hurd, Ryan Sun, Scott Kopetz, Anirban Maitra, Paola A. Guerrero. Transcriptomic profiling of liquid biopsy in colorectal cancer [abstract]. In: Proceedings of the AACR Special Conference on Colorectal Cancer; 2022 Oct 1-4; Portland, OR. Philadelphia (PA): AACR; Cancer Res 2022;82(23 Suppl_1):Abstract nr PR013.

The effectiveness of the method of correctional and developmental orientation for preschoolers 3-5 years old with cerebral palsy

Relevance. The content of this article deals with the organization and conduct of classes in adaptive physical education for preschoolers 3-5 years old with children's cerebral pathology. The developed experimental technique based on the complex application of means of adaptive physical culture and physical rehabilitation is substantiated. The means, methods and forms of organizing and conducting correctional and developmental classes with children of this nosological and age group are described. The obtained experimental data are presented, proving the effectiveness of the developed methodology in relation to improving the indicators of physical fitness and mental processes of preschool children with cerebral palsy. Research methods and organization: The developed methodology was based on the results of the analysis of data from scientific and methodological literature, medical records of preschool children, as well as the experience of instructors of methodologists on AFC of preschool correctional institutions and the scientific and practical center "Without Borders" of the Federal State Budgetary Educational Institution of Higher Education "VGAPC", carrying out correctional work -tu with children 3-5 years old suffering from cerebral palsy.

A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery

Knowledge discovery in biomedical data using supervised methods assumes that the data contain structure relevant to the class structure if a classifier can be trained to assign a case to the correct class better than by guessing. In this setting, acceptance or rejection of a scientific hypothesis may depend critically on the ability to classify cases better than randomly, without high classification performance being the primary goal. Random forests are often chosen for knowledge-discovery tasks because they are considered a powerful classifier that does not require sophisticated data transformation or hyperparameter tuning and can be regarded as a reference classifier for tabular numerical data. Here, we report a case where the failure of random forests using the default hyperparameter settings in the standard implementations of R and Python would have led to the rejection of the hypothesis that the data contained structure relevant to the class structure. After tuning the hyperparameters, classification performance increased from 56% to 65% balanced accuracy in R, and from 55% to 67% balanced accuracy in Python. More importantly, the 95% confidence intervals in the tuned versions were to the right of the value of 50% that characterizes guessing-level classification. Thus, tuning provided the desired evidence that the data structure supported the class structure of the data set. In this case, the tuning made more than a quantitative difference in the form of slightly better classification accuracy, but significantly changed the interpretation of the data set. This is especially true when classification performance is low and a small improvement increases the balanced accuracy to over 50% when guessing.

Age dependent treatment response to the Carriere ® Motion 3D ™ appliance for the correction of Class II malocclusion

Introduction and Purpose
 Class II malocclusion is a common anomaly. Both adults and adolescents with Class II malocclusion can be treated. One of the methods for correction is Carriere ® Motion 3D ™ appliance (CMA).
 The aim was to evaluate and compare the rate of tooth movement depending on age during treatment with Carriere ® Motion 3D ™ appliance (CMA).
 Material and method
 The retrospective study investigated medical records of 28 adult and 27 adolescent subjects who were treated with the Carriere ® Motion 3D ™ distalizer to correct Class II malocclusion. Time (in days) needed to achieve 1 mm correction was calculated for each patient, based on the quotient of days needed for Class II correction and the distance required to achieve Class I canine relationship. The difference between groups was analyzed using the Mann-Whitney-U test.
 Results
 Phase I treatment with CMA lasted on average 5,67 ± 2,01 months for adults and 4,67 ± 1,48 months for teenagers. The mean time to achieve 1 mm correction was 36,77 ± 11,01 days in the adult group and 36,59 ± 26,17 days in the adolescent group. The results showed no statistically significant difference between the two groups.
 Conclusions
 CMA can be applied to efficiently treat Class II malocclusion in adolescent as well as adult patients. No difference in age related tooth movement using the CMA was found.

Rehabilitation of patients with post-stroke aphasia using transcranial direct current electrical stimulation (tDCS)

BACKGROUND: Rehabilitation of patients with post-stroke aphasia is an important medical and social goal. The use of traditional methods of rehabilitation is often not effective enough, which forces us to look for new methods aimed at restoring lost functions.
 AIM: The aim of this study is to determine the effectiveness of non-invasive brain stimulation using transcranial direct electric current stimulation (tDCS) in patients with post-stroke aphasia.
 MATERIALS AND METHODS: 28 patients with motor post-stroke aphasia were examined according to the method of L.S. Tsvetkova with co-authors. All patients received a traditional rehabilitation complex: psychological and correctional classes with a speech therapist-aphasiologist; neurometabolic therapy. 14 patients (Group I) additionally had transcranial direct electric current stimulation; 14 patients had placebo transcranial direct electric current stimulation.
 RESULTS: All patients with post-stroke aphasia showed an improvement in expressive and impressive speech, however, in patients who had true transcranial direct electric current stimulation, the improvement in expressive and impressive speech was higher than in patients who had placebo transcranial direct electric current stimulation. There were no complications from the use of transcranial direct electric current stimulation.
 CONCLUSION: Based on the results of the study, it can be concluded that it is expedient to include the non-invasive transcranial direct electric current stimulation method in the rehabilitation of patients with post-stroke aphasia.

Evaluation of soft tissue prediction accuracy for orthognathic surgery with skeletal class III malocclusion using maxillofacial regional aesthetic units.

This study aimed to evaluate the soft tissue prediction accuracy of patients undergoing orthognathic surgery to correct skeletal class III malocclusion using maxillofacial regional aesthetic units. Pre- and postoperative cone-beam computed tomography (CBCT) and 3D facial scans were taken for 58 patients who had undergone orthognathic surgery. The preoperative 3D facial scan was integrated with the preoperative CBCT using ProPlan CMF software. The software simulated the surgery and generated postoperative soft tissue prediction. The simulated 3D facial scan was then compared with the actual 3D facial scan obtained at least 6months after the surgery by the maxillofacial regional aesthetic units and the facial soft tissue landmark points. The anatomical regions of the upper lip, lower lip, chin, right external buccal and left external buccal prediction were above 2.0mm. As for the soft tissue landmarks, at chl, chr, ls, stm and li, the position of predicted scan was higher than that of the actual postoperative scan. The accuracy of 3D soft tissue predictions using ProPlan CMF software in Skeletal III patients was clinically satisfactory according to maxillofacial regional aesthetic units combined with facial soft tissue landmark points. However, the accuracy of prediction still needed improvement in some areas. The accuracy of soft tissue prediction can be analyzed more clearly through maxillofacial regional aesthetic units so that clinicians have a deeper understanding of the use of the software to predict soft tissue change after orthognathic surgery.

Trigonometric words ranking model for spam message classification

AbstractThe significant increase in the volume of fake (spam) messages has led to an urgent need to develop and implement a robust anti‐spam method. Several of the current anti‐spam systems depend mainly on the word order of the message in determining the spam message, which results in the system's inability to predict the correct type of message when the word order changes. In this paper, a new framework is proposed for anti‐spam filtering that does not depend on the word's position in the message, called the Trigonometric Words Ranking Model (TWRM). The proposed TWRM is based on restricting spammers over the network by measuring a theta angle, which is a relationship between message weight and spam. TWRM classifies messages by calculating the rank of each word that places the corresponding message in the correct class. The rank of words is derived from their frequency in the entire data category. The proposed method is applied to three datasets of spam messages: UCI spam email, Enron spam, and TREC spam data. The proposed model is proven as more efficient than the Minhash and vector space models. Moreover, the TWRM performance provided better retrieval time and defence, which is reflected in the accuracy of (99.64%), which is higher than that of Minhash (88.79%) and vector space (92.59%).

NoFED-Net: Nonlinear Fuzzy Ensemble of Deep Neural Networks for Human Activity Recognition

In the era of the Internet of Things (IoT), the need for human activity recognition (HAR) is growing, especially in smart-healthcare applications using on-body smart sensor devices. These devices amass data and employ various classification models to analyze and discern user activities. However, existing techniques that are susceptible to the data type, user inputs, and ensemble-based models lack the ability to correct a wrong classification made by a base classifier. Addressing the shortcomings, we propose a novel fuzzy ensemble of three deep neural networks, using three nonlinear functions to generate fuzzy scores. The proposed model works on sensor data and can adaptively penalize the activity classes when the classification is assumed to be incorrect. Besides, a novel rewarding technique is proposed that aids the ensemble to extract the correct class in adverse situations. The proposed model reports state-of-the-art accuracy when evaluated on four publicly available wearable sensor data sets. In addition, activities corresponding to real-time sensor data collected using a smartphone are predicted correctly by the proposed model, thereby establishing itself as a reliable smart-HAR model. We also discuss a possible future scope of implementing the model over the cloud for smart activity recognition.