Search

In an era where social media platforms burgeon with diverse content, compelling moderation is imperative to filter harmful materials. Traditional methods often grapple with the dual challenges of accuracy and computational efficiency levels. These conventional approaches typically rely on text-based or image-based analysis, neglecting the complex interplay of multimodal content prevalent in social media scenarios. This limitation leads to suboptimal content filtering, often missing contextually nuanced or visually deceptive harmful content sets. Addressing these challenges, in response to the pressing need for effective social media content moderation, we introduce a pioneering approach that combines Convolutional Neural Networks (CNNs) and Transformers. We aim to enhance accuracy and computational efficiency in filtering harmful multimodal content prevalent on social media platforms. By integrating CNNs and Transformers, we achieve nuanced visual content extraction and contextual textual understanding, thus improving the identification of harmful content. Additionally, our model utilises a Bi-directional Attention Mechanism (BAM) and Genetic Algorithms (GAs) for efficient text-visual fusion and hyper-parameter optimisation, respectively. Empirical testing on datasets from Google, Facebook, and Kaggle demonstrates the superior performance of our model in terms of precision, accuracy, recall, AUC, specificity, and response delay in detecting harmful content. The proposed Multimodal Social Media Content Moderation Using Hybrid Graph Theory & Bio-inspired Optimization (MSCMGTB) model consistently achieves superior precision, accuracy, recall, AUC, and specificity with rates ranging from 86.78% to 98.82% across varying dataset sizes, highlighting its efficacy in content moderation as well as reduced the delay time to classify social media contents as compared to Social Graph Neural Network (SGNN), CrediBot, and Adaptive LDA (ALDA) techniques. The model also preempts potentially harmful content posters, offering enhanced pre-emption metrics.

The growth of irregular brain cells leads to a disease called brain tumor (BT). It is difficult to predict a patient’s chance of survival due to the low rate and wide range of tumor shapes. Even though it is possible to manually detect cancer, doing so is difficult and time-consuming and runs the risk of producing false-positive results. This can be done via MRI, which is necessary for locating cancer. It is very difficult to reliably identify different illnesses from MRI images for successful therapy via a computer-aided diagnostic system. In the experiment, three openly accessible benchmark datasets were utilized. To perform feature extraction in our proposed method, a CNN model was employed, followed by the application of five machine learning classifiers: Decision tree (DT), Naive Bayes (NB), Adaptive Boosting (AdaBoost), K-nearest neighbor (KNN), and support vector machine (SVM). The outcomes show that the proposed CNN architecture with the KNN classifier performs better than previous CNN models by outperforming other cutting-edge DL models under various classification metrics. Finally, the achieved F1-Score, precision, recall, and accuracy values for the classification and detection of the proposed model were 99.58%, 99.59%, 99.58%, and 99.58%, respectively. For the comparison study, additional Transfer Learning models are utilized. Experimental findings support the strength of the proposed architecture, which has rapidly accelerated and improved the classifications of BTs. The designed method outperforms the body of existing knowledge, demonstrating that it is a quick and precise method for classifying BTs.

Grid integration of Renewable Energy Systems (RES) involves various types of power electronics-based converters and inverters. The use of these electronic-based devices results in inducing both current and voltage harmonics to the grid. In order to reduce harmonics, especially for large-scale integration of RES, harmonics forecasting is one of many techniques used to design harmonics mitigation devices. The core objective of this work is to develop a novel forecasting model for accurate and reliable harmonics estimation for RES. To achieve this; two hybrid generator models are used. First model consists of wind turbine coupled with Doubly Fed Induction Generator (DFIG) combined with Solar Photo Voltaic (PV) based power generator which are connected to common grid. The second model uses Permanent Magnet Synchronous Generator (PMSG) with wind turbine in conjunction with Solar-PV generator. With real world meteorological data (wind speed and solar irradiation) as inputs, these generators simulate and produce output power with current and voltage waveforms. Harmonics are extracted from these waveforms to record, analyze, arrange and forecast future harmonics. Three parameters namely, Total Harmonics Distortion (THD) and the dominant individual harmonics contents, 11th harmonic (h11) and 13th harmonic (h13) are forecasted for both voltage and current waveforms. Artificial Neural Networks (ANN) and Adaptive Neuro Fuzzy Inference Systems (ANFIS) are the prominent methods used for forecasting. Three types of three-layered ANN structures namely Cascaded Neural Network with Recurrent Local feedback (3LCRNNL), Cascaded Neural Network with Recurrent Global feedback (3LCRNNG) and Cascaded Neural Network with Local and Global feedback (CRNNGL) have been proposed and utilized in this work with hyperbolic tangent as transfer function to adjust weights and scaled conjugate gradient method as optimizer to reduce training error. ANFIS is also employed with subtractive clustering method to improve adaptability and accuracy of forecasts. The results are compared and presented which shows that ANFIS recorded the best performance for THDV and h13 and 3LCRNNGL for h11 for the Wind DFIG-PV model voltage harmonics forecast. For forecasts of the current harmonics, 3LCRNNGL performed best for THDI and h11, whereas ANFIS performed best for h13. For Wind PMSG-PV generator model, ANFIS yields the best results in every scenario involving voltage and current harmonics.

The paper presents $AVQBits$ , a versatile, bitstream-based video quality model. It can be applied in several contexts such as video service monitoring, evaluation of video encoding quality, of gaming video QoE, and even of omnidirectional video quality. In the paper, it is shown that $AVQBits$ predictions closely match video quality ratings obained in various subjective tests with human viewers, for videos up to 4K-UHD resolution (Ultra-High Definition, 3840 x 2180 pixels) and framerates up 120 fps. With the different variants of $AVQBits$ presented in the paper, video quality can be monitored either at the client side, in the network or directly after encoding. The no-reference $AVQBits$ model was developed for different video services and types of input data, reflecting the increasing popularity of Video-on-Demand services and widespread use of HTTP-based adaptive streaming. At its core, $AVQBits$ encompasses the standardized ITU-T P.1204.3 model, with further model instances that can either have restricted or extended input information, depending on the application context. Four different instances of $AVQBits$ are presented, that is, a Mode 3 model with full access to the bitstream, a Mode 0 variant using only metadata such as codec type, framerate, resoution and bitrate as input, a Mode 1 model using Mode 0 information and frame-type and -size information, and a Hybrid Mode 0 model that is based on Mode 0 metadata and the decoded video pixel information. The models are trained on the authors’ own AVT-PNATS-UHD-1 dataset described in the paper. All models show a highly competitive performance by using AVT-VQDB-UHD-1 as validation dataset, e.g., with the Mode 0 variant yielding a value of 0.890 Pearson Correlation, the Mode 1 model of 0.901, the hybrid no-reference mode 0 model of 0.928 and the model with full bitstream access of 0.942. In addition, all four $AVQBits$ variants are evaluated when applying them out-of-the-box to different media formats such as 360° video, high framerate (HFR) content, or gaming videos. The analysis shows that the ITU-T P.1204.3 and Hybrid Mode 0 instances of $AVQBits$ for the considered use-cases either perform on par with or better than even state-of-the-art full reference, pixel-based models. Furthermore, it is shown that the proposed Mode 0 and Mode 1 variants outperform commonly used no-reference models for the different application scopes. Also, a long-term integration model based on the standardized ITU-T P.1203.3 is presented to estimate ratings of overall audiovisual streaming Quality of Experience (QoE) for sessions of 30 s up to 5 min duration. In the paper, the $AVQBits$ instances with their per-1-sec score output are evaluated as the video quality component of the proposed long-term integration model. All $AVQBits$ variants as well as the long-term integration module are made publicly available for the community for further research.

Water quality prediction (WQP) plays an essential role in water quality management for aquaculture to make aquaculture production profitable and sustainable. In this work, we propose hybrid deep learning (DL) models, convolutional neural network (CNN) with the long short-term memory (LSTM) and gated recurrent unit (GRU) for aquaculture WQP. CNN can effectively fetch the aquaculture water quality characteristics, whereas GRU and LSTM can learn long-term dependencies in the time series data. We conduct experiments using the two different water quality datasets and present an extensive study on the impact of hyperparameters on the performance of the proposed hybrid DL models. Furthermore, the performance of hybrid CNN-LSTM and CNN-GRU models are compared with different baseline LSTM, GRU and CNN DL models and also with attention-based LSTM and attention-based GRU DL models. The results show that the hybrid CNN-LSTM outperformed all other models in terms of prediction accuracy and computation time.

The dramatic increase in Android-based smart devices has brought technological revolution to improve the overall quality of life and thus making it worth a billion-dollar market. Despite the huge hype surrounding Android market, the prevalent and potentially sophisticated malicious mobile malware has become a serious threat to the popular Android platform and an ideal target for varied cyber adversaries. Conversely, multivector malware efficient and timely detection is extremely challenging because it usually hides itself under legitimate third party software’s and having the capability to be easily crafted on any executable file extension. To better streamline this complex issue of paramount concern, the authors propose a highly proficient hybrid deep learning (DL)-enabled intelligent multi-vector malware detection mechanism. The devised approach leverages Convolutional Neural Networks and Bidirectional Long Short-Term Memory (BiLSTM) to efficiently identify persistent malware. The proposed technique has been thoroughly evaluated with publicly available datasets, standard performance metrics, and state-of-the-art hybrid DL-driven architectures and benchmark DL algorithms. Besides, the proposed framework has been cross-validated and shows out performance both in terms of time efficiency and detection accuracy.

A multitude of cyber-physical system (CPS) applications, including design, control, diagnosis, prognostics, and a host of other problems, are predicated on the assumption of model availability. There are mainly two approaches to modeling: Physics/Equation based modeling (Model-Based, MB) and Machine Learning (ML). Recently, there is a growing consensus that ML methodologies relying on data need to be coupled with prior scientific knowledge (or physics, MB) for modeling CPS. We refer to the paradigm that combines MB approaches with ML as hybrid learning methods. Hybrid modeling (HB) methods is a growing field within both the ML and scientific communities, and are recognized as an important emerging but nascent area of research. Recently, several works have attempted to merge MB and ML models for the complete exploitation of their combined potential. However, the research literature is scattered and unorganized. So, we make a meticulous and systematic attempt at organizing and standardizing the methods of combining ML and MB models. In addition to that, we outline five metrics for the comprehensive evaluation of hybrid models. Finally, we conclude by shedding some light on the challenges of hybrid models, which we, as a research community, should focus on for harnessing the full potential of hybrid models. An additional feature of this survey is that the hybrid modeling work has been discussed with a focus on modeling cyber-physical systems.

The era of artificial neural network (ANN) began with a simplified application in many fields and remarkable success in pattern recognition (PR) even in manufacturing industries. Although significant progress achieved and surveyed in addressing ANN application to PR challenges, nevertheless, some problems are yet to be resolved like whimsical orientation (the unknown path that cannot be accurately calculated due to its directional position). Other problem includes; object classification, location, scaling, neurons behavior analysis in hidden layers, rule, and template matching. Also, the lack of extant literature on the issues associated with ANN application to PR seems to slow down research focus and progress in the field. Hence, there is a need for state-of-the-art in neural networks application to PR to urgently address the above-highlights problems for more successes. The study furnishes readers with a clearer understanding of the current, and new trend in ANN models that effectively addresses PR challenges to enable research focus and topics. Similarly, the comprehensive review reveals the diverse areas of the success of ANN models and their application to PR. In evaluating the performance of ANN models, some statistical indicators for measuring the performance of the ANN model in many studies were adopted. Such as the use of mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and variance of absolute percentage error (VAPE). The result shows that the current ANN models such as GAN, SAE, DBN, RBM, RNN, RBFN, PNN, CNN, SLP, MLP, MLNN, Reservoir computing, and Transformer models are performing excellently in their application to PR tasks. Therefore, the study recommends the research focus on current models and the development of new models concurrently for more successes in the field.