Voting Methodology Research Articles

DenseNet model incorporating hybrid attention mechanisms and clinical features for pancreatic cystic tumor classification.

The aim of this study is to develop a deep learning model capable of discriminating between pancreatic plasma cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN) by leveraging patient-specific clinical features and imaging outcomes. The intent is to offer valuable diagnostic support to clinicians in their clinical decision-making processes. The construction of the deep learning model involved utilizing a dataset comprising abdominal magnetic resonance T2-weighted images obtained from patients diagnosed with pancreatic cystic tumors at Changhai Hospital. The dataset comprised 207 patients with SCN and 93 patients with MCN, encompassing a total of 1761 images. The foundational architecture employed was DenseNet-161, augmented with a hybrid attention mechanism module. This integration aimed to enhance the network's attentiveness toward channel and spatial features, thereby amplifying its performance. Additionally, clinical features were incorporated prior to the fully connected layer of the network to actively contribute to subsequent decision-making processes, thereby significantly augmenting the model's classification accuracy. The final patient classification outcomes were derived using a joint voting methodology, and the model underwent comprehensive evaluation. Using the five-fold cross validation, the accuracy of the classification model in this paper was 92.44%, with an AUC value of 0.971, a precision rate of 0.956, a recall rate of 0.919, a specificity of 0.933, and an F1-score of 0.936. This study demonstrates that the DenseNet model, which incorporates hybrid attention mechanisms and clinical features, is effective for distinguishing between SCN and MCN, and has potential application for the diagnosis of pancreatic cystic tumors in clinical practice.

Anomaly Detection in 6G Networks Using Machine Learning Methods

While the cloudification of networks with a micro-services-oriented design is a well-known feature of 5G, the 6G era of networks is closely related to intelligent network orchestration and management. Consequently, artificial intelligence (AI), machine learning (ML), and deep learning (DL) have a big part to play in the 6G paradigm that is being imagined. Future end-to-end automation of networks requires proactive threat detection, the use of clever mitigation strategies, and confirmation that 6G networks will be self-sustaining. To strengthen and consolidate the role of AI in safeguarding 6G networks, this article explores how AI may be employed in 6G security. In order to achieve this, a novel anomaly detection system for 6G networks (AD6GNs) based on ensemble learning (EL) for communication networks was redeveloped in this study. The first stage in the EL-ADCN process is pre-processing. The second stage is the feature selection approach. It applies the reimplemented hybrid approach using a comparison of the ensemble learning and feature selection random forest algorithms (CFS-RF). NB2015, CIC_IDS2017, NSL KDD, and CICDDOS2019 are the three datasets, each given a reduced dimensionality, and the top subset characteristic for each is determined separately. Hybrid EL techniques are used in the third step to find intrusions. The average voting methodology is employed as an aggregation method, and two classifiers—support vector machines (SVM) and random forests (RF)—are modified to be used as EL algorithms for bagging and adaboosting, respectively. Testing the concept of the last step involves employing classification forms that are binary and multi-class. The best experimental results were obtained by applying 30, 35, 40, and 40 features of the reimplemented system to the three datasets: NSL_KDD, UNSW_NB2015, CIC_IDS2017, and CICDDOS2019. For the NSL_KDD dataset, the accuracy was 99.5% with a false alarm rate of 0.0038; the accuracy was 99.9% for the UNSW_NB2015 dataset with a false alarm rate of 0.0076; and the accuracy was 99.8% for the CIC_IDS2017 dataset with a false alarm rate of 0.0009. However, the accuracy was 99.95426% for the CICDDOS2019 dataset, with a false alarm rate of 0.00113.

Advanced Feature Extraction Methods from Images of Drillings in Melamine Faced Chipboard for Automatic Diagnosis of Drill Wear.

In this paper, a novel approach to evaluation of feature extraction methodologies is presented. In the case of machine learning algorithms, extracting and using the most efficient features is one of the key problems that can significantly influence overall performance. It is especially the case with parameter-heavy problems, such as tool condition monitoring. In the presented case, images of drilled holes are considered, where state of the edge and the overall size of imperfections have high influence on product quality. Finding and using a set of features that accurately describes the differences between the edge that is acceptable or too damaged is not always straightforward. The presented approach focuses on detailed evaluation of various feature extraction approaches. Each chosen method produced a set of features, which was then used to train a selected set of classifiers. Five initial feature sets were obtained, and additional ones were derived from them. Different voting methods were used for ensemble approaches. In total, 38 versions of the classifiers were created and evaluated. Best accuracy was obtained by the ensemble approach based on Weighted Voting methodology. A significant difference was shown between different feature extraction methods, with a total difference of 11.14% between the worst and best feature set, as well as a further 0.2% improvement achieved by using the best voting approach.

A novel sample and feature dependent ensemble approach for Parkinson’s disease detection

Parkinson’s disease (PD) is a neurological disease that has been reported to have affected most people worldwide. Recent research pointed out that about 90% of PD patients possess voice disorders. Motivated by this fact, many researchers proposed methods based on multiple types of speech data for PD prediction. However, these methods either face the problem of low rate of accuracy or lack generalization. To develop an approach that will be free of these issues, in this paper we propose a novel ensemble approach. These paper contributions are two folds. First, investigating feature selection integration with deep neural network (DNN) and validating its effectiveness by comparing its performance with conventional DNN and other similar integrated systems. Second, development of a novel ensemble model namely EOFSC (Ensemble model with Optimal Features and Sample Dependant Base Classifiers) that exploits the findings of recently published studies. Recent research pointed out that for different types of voice data, different optimal models are obtained which are sensitive to different types of samples and subsets of features. In this paper, we further consolidate the findings by utilizing the proposed integrated system and propose the development of EOFSC. For multiple types of vowel phonations, multiple base classifiers are obtained which are sensitive to different subsets of features. These features and sample-dependent base classifiers are integrated, and the proposed EOFSC model is constructed. To evaluate the final prediction of the EOFSC model, the majority voting methodology is adopted. Experimental results point out that feature selection integration with neural networks improves the performance of conventional neural networks. Additionally, feature selection integration with DNN outperforms feature selection integration with conventional machine learning models. Finally, the newly developed ensemble model is observed to improve PD detection accuracy by 6.5%.

Blockchain oriented hyperledger based performance driven framework for mass e-voting

Voting is a process for making collective decisions or to express a mass opinion on list of options available. It is a most commonly used instrument to elect a political representative. It is apparent that the methodology currently followed for voting in India can be improved at many levels to make it more robust and efficient. Currently, the voting methodology followed in Indian political elections has two major issues, one is high cost per voter, and low voter turnout. There are many attempts by other democratic setups to tackle this problem by offering online method of voting, but the most trustworthy and promising solution is considered to be voting platform/infrastructure backed by Blockchain. Most of the currently existing Blockchain based voting solutions are computationally expensive, doesn’t provide a verifiable secret ballot, slow, and Byzantine Fault Tolerant Proof of Work algorithms run on a public Blockchain network. The work presented in this paper aims at addressing these issues by proposing Blockchain based framework that leverages Hyperledger Fabric for Scalable Voting System. The proposed method uses Aadhar number for authentication of voters. The proposed method can efficiently cater the secure, trustworthy, and promising to Indian scale. The proposed method offers a various solution, offline and online voting with features such as cost-effective deployments, instantaneous vote counting, Cast as Intended Verifiability, and an observable and auditable architecture. The proposed method has been tested on real time setup and the experimental results are promising.

DESIGN AND IMPLEMENTATION OF IMPROVED ENSEMBLE CLASSIFICATION ALGORITHM FOR HUMAN ACTIVITY RECOGNITION (HAR)

To recognize the human activity is considered very essential in human-to-human interaction and interpersonal relations due to its nature of providing information regarding the identity of a people, their personality and psychological state. The extraction of this information is very challenging. The main operation occurred before the systematic fields of computer vision as well as ML is the potential for recognizing the activities of different person. The human activity recognition technique is executed in various stages such as to pre-process the data, extract the features and classifying the data. This work proposes a improved ensemble model in the human activity recognition which is the combination of K-mean clustering, PCA and of multiple classifiers which are merged through voting methodology. Python is executed to get evaluated the presented framework and various metrics such as accuracy, precision and recall are considered to analyse the results. The major subject of study of the scientific and research areas of computer vision and ML is the potential of human for identifying the activities of particular person. A sequence of human body movements in which different body parts (head, hands, legs etc.) are engaged in concurrent manner is known as action.

A new ensemble based approach for intrusion detection system using voting

With the increase in the amount of data available today, the responsibility of keeping that data safe has also taken a more severe form. To prevent confidential data from getting in the hands of an attacker, some measures need to be taken. Here comes the need for an effective system, which can classify the traffic as an attack or normal. Intrusion Detection Systems can do this work with perfection. Many machine learning algorithms are used to develop efficient IDS. These IDS provide remarkable results. However, ensemble-based IDS using voting have been seen to outperform individual approaches (Support Vector Machine and ExtraTree). Since the Voting methodology is able to work around both, theoretically similar and different classifiers and produce a single classifier based on the majority characteristics, it proved to be better than the other ensemble based techniques. In this paper, an ensemble IDS implementation is presented based on the voting ensemble method, using the two algorithms, Support Vector Machine (SVC) and ExtraTree. The experiment is performed on the KDDCup99 Dataset. The evaluation of the performance of the proposed method is based on the comparison with an unoptimized implementation of the same. The results based on performing the experiment in Python fetched an accuracy of 99.90%.

Discovering the Unclassified Suicide Cases Among Undetermined Drug Overdose Deaths Using Machine Learning Techniques.

The Centers for Disease Control and Prevention (CDC) monitor accidental and intentional deaths to answer questions that are critical for the development of effective prevention and resource allocation. CDC's National Violent Death Reporting System (NVDRS) is a major innovation in surveillance linking individual-level data from multiple sources. However, suicide underreporting is common, particularly from drug overdose deaths. This study sought to assess machine learning (ML) techniques in quantifying drug overdose suicide underreporting rates. Clinical, sociodemographic, toxicological, and proximal stressor data on overdose decedents (n=2,665) were extracted from Utah's NVDRS from 2012 to 2015. The existing well-determined cases were used to train and test our ML models. We assessed and compared multiple machine learning methods including Logistic Regression, Random Forest Classifier, Support Vector Machines, and Artificial Neural Networks. We applied a majority voting methodology to classify undetermined drug overdose deaths. Overdose suicide rates were estimated to be underreported by 33% across all years, increasing yearly from 29% in 2012 to 37% in 2015. The overall test accuracies for all models ranged from 92.3% to 94.6%. This research identifies a cost-effective, replicable, and expandable ML-based methodology to estimate the true rates of suicide which may be partially masked during the opioid epidemic.

Using Ensemble Technique to Improve Multiclass Classification

Many real world applications inevitably contain datasets that have multiclass structure characterized by imbalance classes, redundant and irrelevant features that degrade performance of classifiers. Minority classes in the datasets are treated as outliers’ classes. The research aimed at establishing the role of ensemble technique in improving performance of multiclass classification. Multiclass datasets were transformed to binary and the datasets resampled using Synthetic minority oversampling technique (SMOTE) algorithm. Relevant features of the datasets were selected by use of an ensemble filter method developed using Correlation, Information Gain, Gain-Ratio and ReliefF filter selection methods. Adaboost and Random subspace learning algorithms were combined using Voting methodology utilizing random forest as the base classifier. The classifiers were evaluated using 10 fold stratified cross validation. The model showed better performance in terms of outlier detection and classification prediction for multiclass problem. The model outperformed other well-known existing classification and outlier detection algorithms such as Naive bayes, KNN, Bagging, JRipper, Decision trees, RandomTree and Random forest. The study findings established that ensemble technique, resampling datasets and decomposing multiclass results in an improved classification performance as well as enhanced detection of minority outlier (rare) classes. Keywords: Multiclass, Classification, Outliers, Ensemble, Learning Algorithm DOI : 10.7176/JIEA/9-5-04 Publication date : August 31 st 2019

An Ensemble Model for Multiclass Classification and Outlier Detection Method in Data Mining

Real life world datasets exhibit a multiclass classification structure characterized by imbalance classes. Minority classes are treated as outliers’ classes. The study used cross-industry process for data mining methodology. A heterogeneous multiclass ensemble was developed by combining several strategies and ensemble techniques. The datasets used were drawn from UCI machine learning repository. Experiments for validating the model were conducted and represented in form of tables and figures. An ensemble filter selection method was developed and used for preprocessing datasets. Point-outliers were filtered using Inter quartile range filter algorithm. Datasets were resampled using Synthetic minority oversampling technique (SMOTE) algorithm. Multiclass datasets were transformed to binary classes using OnevsOne decomposing technique. An Ensemble model was developed using adaboost and random subspace algorithms utilizing random forest as the base classifier. The classifiers built were combined using voting methodology. The model was validated with classification and outlier metric performance measures such as Recall, Precision, F-measure and AUCROC values. The classifiers were evaluated using 10 fold stratified cross validation. The model showed better performance in terms of outlier detection and classification prediction for multiclass problem. The model outperformed other well-known existing classification and outlier detection algorithms such as Naïve bayes, KNN, Bagging, JRipper, Decision trees, RandomTree and Random forest. The study findings established ensemble techniques, resampling datasets and decomposing multiclass results in an improved detection of minority outlier (rare) classes. Keywords: Multiclass, Outlier, Ensemble, Model, Classification DOI : 10.7176/JIEA/9-2-04 Publication date : April 30 th 2019

A new DEA based Voting Method for Ranking and Evaluating the Influence of E-marketing on Bank Performance

Due to the importance of measuring banks' performance and because of the remarkable impact of recent growth of the internet on banking industry, this study evaluated the influence of e-marketing on bank performance by using a DEA-based voting methodology. In this way, usually more than one unit may be efficient in the DEA models and their scores are one. Therefore, how to rank DMUs and increase the power of discrimination among efficient DMUs become an important part of performance assessments. So, in order to provide a satisfactory ranking, this paper presents a voting methodology that uses the results of some ranking models. For this purpose, each DMU is considered as an alternative and each ranking method is considered as a decision maker. The proposed methodology is applied to evaluate the influence of e-marketing on Iranian's bank performance.

Academic Primer Series: Key Papers About Competency-Based Medical Education.

IntroductionCompetency-based medical education (CBME) presents a paradigm shift in medical training. This outcome-based education movement has triggered substantive changes across the globe. Since this transition is only beginning, many faculty members may not have experience with CBME nor a solid foundation in the grounding literature. We identify and summarize key papers to help faculty members learn more about CBME.MethodsBased on the online discussions of the 2016–2017 ALiEM Faculty Incubator program, a series of papers on the topic of CBME was developed. Augmenting this list with suggestions by a guest expert and by an open call on Twitter for other important papers, we were able to generate a list of 21 papers in total. Subsequently, we used a modified Delphi study methodology to narrow the list to key papers that describe the importance and significance for educators interested in learning about CBME. To determine the most impactful papers, the mixed junior and senior faculty authorship group used three-round voting methodology based upon the Delphi method.ResultsSummaries of the five most highly rated papers on the topic of CBME, as determined by this modified Delphi approach, are presented in this paper. Major themes include a definition of core CBME themes, CBME principles to consider in the design of curricula, a history of the development of the CBME movement, and a rationale for changes to accreditation with CBME. The application of the study findings to junior faculty and faculty developers is discussed.ConclusionWe present five key papers on CBME that junior faculty members and faculty experts identified as essential to faculty development. These papers are a mix of foundational and explanatory papers that may provide a basis from which junior faculty members may build upon as they help to implement CBME programs.

Academic Primer Series: Eight Key Papers about Education Theory

IntroductionMany teachers adopt instructional methods based on assumptions of best practices without attention to or knowledge of supporting education theory. Familiarity with a variety of theories informs education that is efficient, strategic, and evidence-based. As part of the Academic Life in Emergency Medicine Faculty Incubator Program, a list of key education theories for junior faculty was developed.MethodsA list of key papers on theories relevant to medical education was generated using an expert panel, a virtual community of practice synthetic discussion, and a social media call for resources. A three-round, Delphi-informed voting methodology including novice and expert educators produced a rank order of the top papers.ResultsThese educators identified 34 unique papers. Eleven papers described the general use of education theory, while 23 papers focused on a specific theory. The top three papers on general education theories and top five papers on specific education theory were selected and summarized. The relevance of each paper for junior faculty and faculty developers is also presented.ConclusionThis paper presents a reading list of key papers for junior faculty in medical education roles. Three papers about general education theories and five papers about specific educational theories are identified and annotated. These papers may help provide foundational knowledge in education theory to inform junior faculty teaching practice.

Academic Primer Series: Five Key Papers for Consulting Clinician Educators.

IntroductionClinician educators are often asked to perform consultations for colleagues. Invitations to consult and advise others on local problems can help foster great collaborations between centers, and allows for an exchange of ideas between programs. In this article, the authors identify and summarize several key papers to assist emerging clinician educators with the consultation process.MethodsA consensus-building process was used to generate a list of key papers that describe the importance and significance of educational consulting, informed by social media sources. A three-round voting methodology, akin to a Delphi study, determined the most impactful papers from the larger list.ResultsSummaries of the five most highly rated papers on education consultation are presented in this paper. These papers were determined by a mixed group of junior and senior faculty members, who have summarized these papers with respect to their relevance for their peer groups.ConclusionFive key papers on the educational consultation process are presented in this paper. These papers offer background and perspective to help junior faculty gain a grasp of consultation processes.

Academic Primer Series: Five Key Papers about Team Collaboration Relevant to Emergency Medicine.

IntroductionTeam collaboration is an essential for success both within academics and the clinical environment. Often, team collaboration is not explicitly taught during medical school or even residency, and must be learned during one’s early career. In this article, we aim to summarize five key papers about team collaboration for early career clinician educators.MethodsWe conducted a consensus-building process among the writing team to generate a list of key papers that describe the importance or significance of team collaboration, seeking input from social media sources. The authors then used a three-round voting methodology akin to a Delphi study to determine the most important papers from the initially generated list.ResultsThe five most important papers on the topic of team collaboration, as determined by this mixed group of junior faculty members and faculty developers, are presented in this paper. For each included publication, a summary was provided along with its relevance to junior faculty members and faculty developers.ConclusionFive key papers about team collaboration are presented in this publication. These papers provide a foundational background to help junior faculty members with collaborating in teams both clinically and academically. This list may also inform senior faculty and faculty developers about the needs of junior faculty members.

Academic Primer Series: Five Key Papers Fostering Educational Scholarship in Junior Academic Faculty.

IntroductionScholarship is an essential part of academic success. Junior faculty members are often unfamiliar with the grounding literature that defines educational scholarship. In this article, the authors aim to summarize five key papers which outline education scholarship in the setting of academic contributions for emerging clinician educators.MethodsThe authors conducted a consensus-building process to generate a list of key papers that describe the importance and significance of academic scholarship, informed by social media sources. They then used a three-round voting methodology, akin to a Delphi study, to determine the most useful papers.ResultsA summary of the five most important papers on the topic of academic scholarship, as determined by this mixed group of junior faculty members and faculty developers, is presented in this paper. These authors subsequently wrote a summary of these five papers and discussed their relevance to both junior faculty members and faculty developers.ConclusionFive papers on education scholarship, deemed essential by the authors’ consensus process, are presented in this paper. These papers may help provide the foundational background to help junior faculty members gain a grasp of the academic scholarly environment. This list may also inform senior faculty and faculty developers on the needs of junior educators in the nascent stages of their careers.

The Comitology Reform in the EU: Potential Effects on Trade Defence Instruments

The reform of the EU comitology system, enacted with Regulation 182/11, had the effect of extending the general principles regulating the Commission’s exercise of implementing powers to the trade defence instruments’ (TDIs) procedures, which, before the reform, were regulated by an autonomous discipline. This article offers an overview of the modifications brought about to TDI’s comitology by Reg. 182/11 and identifies the possible consequences of the new discipline. The analysis benefited from the results of an empirical simulation, consisting in the application of the new voting methodology to past procedures of TDIs. The authors conclude, among the others, that the new system will likely reduce the usual political interferences in the Commission activities regarding TDIs, and it will settle a number of shortcomings of the old system.

A robust spatio-temporal scheme for dynamic 3D facial expression retrieval

The problem of facial expression recognition in dynamic sequences of 3D face scans has received a significant amount of attention in the recent past whereas the problem of retrieval in this type of data has not. A novel retrieval scheme for such data is introduced in this paper. It is the first spatio-temporal retrieval scheme ever used for retrieval in dynamic sequences of 3D face scans. The proposed scheme automatically detects specific facial landmarks and uses them to create a spatio-temporal descriptor. At first, geometric as well as topological information of the 3D face scans is captured by using the detected landmarks. In the sequel, the aforementioned spatial information is filtered by using wavelet transformation, resulting to our final spatio-temporal descriptor. Our descriptor is invariant to the number of the 3D face scans of a facial expression sequence. The proposed retrieval scheme exploits the Square of Euclidean distance in order to compare descriptors corresponding to different 3D facial sequences. A detailed evaluation of the introduced retrieval scheme is presented showing that it outperforms previous state-of-the-art retrieval schemes. Experiments have been conducted using the six prototypical expressions of the standard data set $$\textit{BU}-4\textit{DFE}$$BU-4DFE. Finally, a majority voting methodology based on the retrieval results is used to achieve unsupervised dynamic 3D facial expression recognition. The achieved classification accuracy outperforms the state-of-the-art supervised dynamic 3D facial expression recognition techniques.

A Novel Self-Evolving Intelligent Multiagent Framework for Power System Control and Protection

In this paper, we propose a multiagent methodology (MAM) for power system monitoring and protection. The uniqueness of the proposed architecture is the ability of MAM to evolve in the wake of an attack of malicious intent by mutation, thus always monitoring power system buses remotely. The architecture interacts with the mutated agents using a voting methodology, thus alleviating the effect of agent malfunction in the presence of an attack. In addition, this proposed architecture enables inter-agent communication, thus developing a collaborative framework and increasing the degree of fault tolerance. This method is tested on a two-area five-machine eight-bus power network for abnormal condition detection and generator bus isolation, as well as for restoring power to the area that is affected by the bus isolation. Simulation studies indicate that the proposed methodology is not only capable of detecting the power grid attack but also capable of continuously monitoring and isolating the generator bus even in the presence of sustained attack as the agents are regenerated.

Research on Applied Technology in Experiments with Three Boosting Algorithms

Boosting algorithms are a means of building a strong ensemble classifier by aggregating a sequence of weak hypotheses. An ensemble consists of a set of independently trained classifiers whose predictions are combined when classifying novel instances. Previous research has shown that an ensemble as a whole is often more accurate than any of the single classifiers in the ensemble. In this paper we use applied technology to built an ensemble using a voting methodology of Boosting-BAN and Boosting-MultiTAN ensembles with 10 sub-classifiers in each one. We performed a comparison with Boosting-BAN and Boosting-MultiTAN ensembles with 25 sub-classifiers on standard benchmark datasets and the proposed technique was the most accurate. These results argue that boosting algorithms deserve more attention in machine learning and data mining communities.