Federated Adversarial Learning (FAL) maintains the decentralization of adversarial training for data-driven innovations while allowing the collaborative training of a common model to protect privacy facilities. Before...
详细信息
This study proposes a hybrid optimization-based mobility management strategy employing Kinetic Gas Molecular Optimization (KGMO) and Ant Lion Optimization (ALO). Initially, KGMO calculates particle properties, such as...
详细信息
In recent years, the demand for efficient evaluation systems in educational settings has surged, highlighting the need for automation in grading processes. This research presents a Grader pro (Automatic Answer Sheet E...
详细信息
Singular value decomposition (SVD) based image authentication has widespread applications for digital media protection including forensic and medical domains due to the high stability and robustness of singular values...
详细信息
Autism spectrum disorder (ASD) affects 1 in 100 children globally. Early detection and intervention can enhance life quality for individuals diagnosed with ASD. This research utilizes the support vector machine-recurs...
详细信息
Autism spectrum disorder (ASD) affects 1 in 100 children globally. Early detection and intervention can enhance life quality for individuals diagnosed with ASD. This research utilizes the support vector machine-recursive feature elimination (SVM-RFE) method in its approach for ASD classification using the phenotypic and Automated Anatomical Labeling (AAL) Brain Atlas datasets of the Autism Brain Imaging data Exchange preprocessed dataset. The functional connectivity matrix (FCM) is computed for the AAL data, generating 6670 features representing pair-wise brain region activity. The SVM-RFE feature selection method was applied five times to the FCM data, thus determining the optimal number of features to be 750 for the best performing support vector machine (SVM) model, corresponding to a dimensionality reduction of 88.76%. Pertinent phenotypic data features were manually selected and processed. Subsequently, five experiments were conducted, each representing a different combination of the features used for training and testing the linear SVM, deep neural networks, one-dimensional convolutional neural networks, and random forest machine learning models. These models are fine-tuned using grid search cross-validation (CV). The models are evaluated on various metrics using 5-fold CV. The most relevant brain regions from the optimal feature set are identified by ranking the SVM-RFE feature weights. The SVM-RFE approach achieved a state-of-the-art accuracy of 90.33% on the linear SVM model using the data Processing Assistant for Resting-State Functional Magnetic Resonance Imaging pipeline. The SVM model’s ability to rank the features used based on their importance provides clarity into the factors contributing to the diagnosis. The thalamus right, rectus right, and temporal middle left AAL brain regions, among others, were identified as having the highest number of connections to other brain regions. These results highlight the importance of using traditional ML models fo
This paper explores the concept of isomorphism in cellular automata (CAs), focusing on identifying and understanding isomorphic relationships between distinct CAs. A cellular automaton (CA) is said to be isomorphic to...
详细信息
Offensive messages on social media,have recently been frequently used to harass and criticize *** recent studies,many promising algorithms have been developed to identify offensive *** algorithms analyze text in a uni...
详细信息
Offensive messages on social media,have recently been frequently used to harass and criticize *** recent studies,many promising algorithms have been developed to identify offensive *** algorithms analyze text in a unidirectional manner,where a bidirectional method can maximize performance results and capture semantic and contextual information in *** addition,there are many separate models for identifying offensive texts based on monolin-gual and multilingual,but there are a few models that can detect both monolingual and multilingual-based offensive *** this study,a detection system has been developed for both monolingual and multilingual offensive texts by combining deep convolutional neural network and bidirectional encoder representations from transformers(Deep-BERT)to identify offensive posts on social media that are used to harass *** paper explores a variety of ways to deal with multilin-gualism,including collaborative multilingual and translation-based ***,the Deep-BERT is tested on the Bengali and English datasets,including the different bidirectional encoder representations from transformers(BERT)pre-trained word-embedding techniques,and found that the proposed Deep-BERT’s efficacy outperformed all existing offensive text classification algorithms reaching an accuracy of 91.83%.The proposed model is a state-of-the-art model that can classify both monolingual-based and multilingual-based offensive texts.
In the burgeoning field of anomaly detection within attributed networks, traditional methodologies often encounter the intricacies of network complexity, particularly in capturing nonlinearity and sparsity. This study...
详细信息
Freezing of gait (FoG) refers to sudden, relatively brief episodes of gait arrest in Parkinson’s disease, known to manifest in the advanced stages of the condition. Events of freezing are associated with tumbles, tra...
详细信息
Human authentication via ear biometrics is an appealing research prospect because of the growing demand for security, surveillance, and access control. The human ear has unique biometric traits that offer various adva...
详细信息
暂无评论