The use of content features, particularly textual and linguistic for fake news detection is under-researched, despite empirical evidence showing the features could contribute to differentiating real and fake news. To this end, this study investigates a selection of content features such as word bigrams, part of speech distribution etc. to improve fake news detection. We performed a series of experiments on a new dataset gathered during the COVID-19 pandemic using Decision Tree, K-Nearest Neighbor, Logistic Regression, Support Vector Machine and Random Forest. Random Forest yielded the best results, followed closely by Support Vector Machine, across all setups. In general, both the textual and linguistic features were found to improve fake news detection when used separately, however, combining them into a single model did not improve the detection significantly. Differences were also noted between the use of bigrams and part of speech tags. The study shows that textual and linguistic features can be used successfully in detecting fake news using the traditional machine learning approach as opposed to deep learning.

Smart manufacturing has transformed the way decisions are made. By accelerating the delivery of data to the various decision points, more rapid decision-making processes can be realized. A generic Decision Support System (DSS) utilizes an efficient technique, which integrates the algorithm for inventive problem solving (ARIZ) and supervised machine learning into a model for supporting various automated decision making processes. The proposed model is to examine the theoretical framework of ARIZ by devising an ARIZ-based DSS model. It incorporates supervised ML algorithms to assist decision making processes. Three case studies from the manufacturing sector are evaluated. The results indicate the capability of the proposed DSS in achieving a high accuracy rate and, at the same time reducing the time and resources required for decision making. Our study has simplified the data processing and extraction processes through an automated ARIZ-based DSS model; therefore enabling a non-technical user the opportunity to harvest the vast knowledge from the collected data for efficient decision making.

A finger vein authentication system is proposed in this research. Biometrics is the science of determining a person's identity based on physiological or behavioral characteristics. Physical characteristics like fingerprints, a face or a retina, as well as personal characteristics like a signature, are included in these characteristics. Biometric features are significantly more difficult for attackers to replicate or fabricate than traditional methods, and they are extremely rare to lose. Biometric traits are used in the identification system, which increases security and dependability. The technology to verify vein patterns is still relatively new, compared with other human characteristics. The proposed work focuses on developing a contactless sensor to retrieve features from the hand's finger vein pattern using a Deep attribute Representation based Fractional Firefly method (DAR-FFF). Vein pattern identification scans the blood for hemoglobin using an infrared light source. After the participant's palm is placed over the sensing device, an infrared region beam from the device measures the orientation of the arteries. These ultraviolet wavelengths are absorbed by liquid hemoglobin in the vasculature, resulting in dark streaks on the map. The hand's finger has more intricate circulatory pathways and a variety of distinguishing characteristics. Image enhancement, skeletonization, and vein pattern chain code comparison are all processes in this procedure.

In this paper, Weight Decorrelated Stacked Autoencoder-Deep Neural Decision Trees (WDSAE-DNDT), a novel hybrid model is proposed for automating the assessment of children’s speech fluency disorders by discerning their disfluencies. In fluency disorder classification, it is imperative to know how each feature contributes to the disorder classification rather than the diagnosis itself and so the depth modified DNDT acts as the best discriminator since it is interpretable by its very nature. The WDSAE presents DNDT with a high-level latent representation of the disfluent speech. A fusion feature vector was built by combining the prosodic cues from disfluent speech segments combined with the WDSAE-based Bottleneck features. The proposed hybrid model was compared with the performance of the experimented baseline models. Further analysis was carried out to check the impact of tree cut points for each feature and epochs on the accuracy of prediction of the hybrid model. The proposed hybrid model when trained on the fusion feature set has shown appreciable improvement in the area under the Receiver Operating Characteristics (ROC) curve, classification accuracy, Kappa statistical value, and Jaccard similarity index. The WDSAE-DNDT demonstrates high precision than the baseline models in setting clinical benchmark to distinguish subjects with dysphemia from those with Specific Language Impairment.

With the rapid advancement of technologies and proliferation of intelligent devices, connecting to the internet challenges have grown manifold, such as ensuring communication security and keeping user credentials secret. Data integrity and user privacy have become crucial concerns in any ecosystem of advanced and interconnected communications. Cryptographic hash functions have been extensively employed to ensure data integrity in insecure environments. Hash functions are also combined with digital signatures to offer identity verification mechanisms and non-repudiation services. The federal organization National Institute of Standards and Technology (NIST) established the SHA to provide security and optimal performance over some time. The most well-known hashing standards are SHA-1, SHA-2, and SHA-3. This paper discusses the background of hashing, followed by elaborating on the evolution of the SHA family. The main goal is to present a comparative analysis of these hashing standards and focus on their security strength, performance and limitations against common attacks. The complete assessment was carried out using statistical analysis, performance analysis and extensive fault analysis over a defined test environment. The study outcome showcases the issues of SHA-1 besides exploring the security benefits of all the dominant variants of SHA-2 and SHA-3. The study also concludes that SHA-3 is the best option to mitigate novice intruders while allowing better performance cost-effectively.

Machine learning (ML) techniques are part of artificial intelligence. ML involves imitating human behavior in solving different problems, such as object detection, text handwriting recognition, and image classification. Several techniques can be used in machine learning, such as Neural Networks (NN). The expansion in information technology enables researchers to collect large amounts of various data types. The challenging issue is to uncover neural network parameters suitable for object detection problems. Therefore, this paper presents a literature review of the latest proposed and developed components in neural network techniques to cope with different sizes and data types. A brief discussion is also introduced to demonstrate the different types of neural network parameters, such as activation functions, loss functions, and regularization methods. Moreover, this paper also uncovers parameter optimization methods and hyperparameters of the model, such as weight, the learning rate, and the number of iterations. From the literature, it is notable that choosing the activation function, loss function, number of neural network layers, and data size is the major factor affecting NN performance. Additionally, utilizing deep learning NN resulted in a significant improvement in model performance for a variety of issues, which became the researcher's attention.

Face recognition is one of the most approachable and accessible authentication methods. It is also accepted by users, as it is non-invasive. However, aging results in changes in the texture and shape of a face. Hence, age is one of the factors that decreases the accuracy of face recognition. Face aging, or age progression, is thus a significant challenge in face recognition methods. This paper presents the use of artificial neural network with model-agnostic meta-learning (ANN-MAML) for face-aging recognition. Model-agnostic meta-learning (MAML) is a meta-learning method used to train a model using parameters obtained from identical tasks with certain updates. This study aims to design and model a framework to recognize face aging based on artificial neural network. In addition, the face-aging recognition framework is evaluated against previous frameworks. Furthermore, the performance and the accuracy of ANN-MAML was evaluated using the CALFW (Cross-Age LFW) dataset. A comparison with other methods showed superior performance by ANN-MAML.

Extracting information using an automated system from unstructured medical documents related to patients discharge summaries in the health care centers is considered a big challenge. Sentiment analysis of medical records has gained significant attention worldwide to understand the behaviors of both clinicians and patients. However, Sentiment analysis of discharge summary still does not provide a clear picture of the information available in these summaries. This study proposes a machine learning-based novel sentiment analysis unsupervised techniques to classify discharge summaries using TF-IDF, Word2Vec, GloVe, FastText, and BERT as deep learning approaches with statistical methods, and clustering. Our proposed model is an unsupervised sentiment framework that provides good understanding and insights of the clinical features that are not captured in the electronic health data records. Moreover, it’s a hybrid sentiment model consisting of clustering technique and vector space models for selecting the distinctive terms. The main intensity of measured sentiment is captured using the polarity of positive and negative terms in the discharge summary. The combination of SentiWordNet platform and our approach is used to build a lexicon sentiment dataset (assignment polarity). Experiments shows that our suggested method achieves 93% accuracy and significantly outperforms other state of the art approaches based on the inspiration of sentiment analysis technique to examine the treatment quality for discharge summaries.