Search

Deep learning (DL) is increasingly recognized for its effectiveness in analyzing and forecasting complex economic systems, particularly in the context of Pakistan's evolving economy. This paper investigates DL's transformative role in managing and interpreting increasing volumes of intricate economic data, leading to more nuanced insights. DL models show a marked improvement in predictive accuracy and depth over traditional methods across various economic domains and policymaking scenarios. Applications include demand forecasting, risk evaluation, market trend analysis, and resource allocation optimization. These processes utilize extensive datasets and advanced algorithms to identify patterns those traditional methods cannot detect. Nonetheless, DL's broader application in economic research faces challenges like limited data availability, complexity of economic interactions, interpretability of model outputs, and significant computational power requirements. The paper outlines strategies to overcome these barriers, such as enhancing model interpretability, employing federated learning for better data privacy, and integrating behavioral and social economic theories. It concludes by stressing the importance of targeted research and ethical considerations in maximizing DL's impact on economic insights and innovation, particularly in Pakistan and globally. [ABSTRACT FROM AUTHOR]

Most deep-learning-based vision models are trained and tested on clear images, avoiding noisy, or hazy, images. However, these models may encounter degraded images. So, it is important to recover and enhance them using a dehazing process. Dehazing usually serves as a preprocessing step for low-, medium-, and high-level vision tasks. Therefore, this article empirically studies the impact of haze and dehazing on high-level vision tasks and considers the degree to which dehazing algorithms can improve a vision model's performance. For this purpose, we created two synthetic hazy datasets and trained several detection and classification models on both clear and hazy images. We found that haze and fog can easily affect a vision model's performance and observed that using dehazing directly as a preprocessing step for high-level vision tasks did not substantially improve vision model's performance but also renders performance unreliable and unpredictable. Therefore, when developing deep vision models, the research community should maintain aspects of bad weather conditions, such as haze, mist, fog, and rain, to avoid the failure of their proposed outdoor vision models. [ABSTRACT FROM AUTHOR]

With recent developments in communication technologies, vehicular networks have become a reality with various applications. However, the cybersecurity aspect of vehicular networks is still an open issue that needs to be addressed with novel defence mechanisms against attacks. This paper first presents the state-of-the-art communication technologies in vehicular networks (either inter-vehicle networking or in-vehicle networking) along with their applications. Then we explore novel technologies including machine learning and blockchain as cybersecurity defence mechanisms in vehicular networks. Based on the extensive survey, we highlight some insights for future research to secure vehicular networks. [ABSTRACT FROM AUTHOR]

With the rise of internet facilities, a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the bank physically for every transaction. However, the fraud cases have also increased causing the loss of money to the consumers. Hence, an effective fraud detection system is the need of the hour which can detect fraudulent transactions automatically in real-time. Generally, the genuine transactions are large in number than the fraudulent transactions which leads to the class imbalance problem. In this research work, an online transaction fraud detection system using deep learning has been proposed which can handle class imbalance problem by applying algorithm-level methods which modify the learning of the model to focus more on the minority class i.e., fraud transactions. A novel loss function named Weighted Hard-Reduced Focal Loss (WH-RFL) has been proposed which has achieved maximum fraud detection rate i.e., True PositiveRate (TPR) at the cost of misclassification of few genuine transactions as high TPR is preferred over a high True Negative Rate (TNR) in fraud detection system and same has been demonstrated using three publicly available imbalanced transactional datasets. Also, Thresholding has been applied to optimize the decision threshold using cross-validation to detect maximum number of frauds and it has been demonstrated by the experimental results that the selection of the right thresholding method with deep learning yields better results. [ABSTRACT FROM AUTHOR]

Multimodal representation learning is beneficial for many multimedia-oriented applications, such as social image recognition and visual question answering. The different modalities of the same instance (e.g., a social image and its corresponding description) are usually correlational and complementary. Most existing approaches for multimodal representation learning are not effective to model the deep correlation between different modalities. Moreover, it is difficult for these approaches to deal with the noise within social images. In this article, we propose a deep learning-based approach named evolutionary adversarial attention networks (EAANs), which combines the attention mechanism with adversarial networks through evolutionary training, for robust multimodal representation learning. Specifically, a two-branch visual-textual attention model is proposed to correlate visual and textual content for joint representation. Then adversarial networks are employed to impose regularization upon the representation by matching its posterior distribution to the given priors. Finally, the attention model and adversarial networks are integrated into an evolutionary training framework for robust multimodal representation learning. Extensive experiments have been conducted on four real-world datasets, including PASCAL, MIR, CLEF, and NUS-WIDE. Substantial performance improvements on the tasks of image classification and tag recommendation demonstrate the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

The Industrial Internet of Things (IIoT) is a physical information system developed based on traditional industrial control networks. As one of the most critical infrastructure systems, IIoT is also a preferred target for adversaries engaged in advanced persistent threats (APTs). To address this issue, we explore a deep-learning-based proactive APT detection scheme in IIoT. In this scheme, considering the characteristics of long attack sequences and long-term continuous APT attacks, our solution adopts a well-known deep learning model, bidirectional encoder representations from transformers (BERT), to detect APT attack sequences. The APT attack sequence is also optimized to ensure the model's long-term sequence judgment effectiveness. The experimental results not only show that the proposed deep learning method has feasibility and effectiveness for APT detection, but also certify that the BERT model has better accuracy and a lower false alarm rate when detecting APT attack sequences than other time series models. [ABSTRACT FROM AUTHOR]

Game player modeling is a paradigm of computational models to exploit players' behavior and experience using game and player analytics. Player modeling refers to descriptions of players based on frameworks of data derived from the interaction of a player's behavior within the game as well as the player's experience with the game. Player behavior focuses on dynamic and static information gathered at the time of gameplay. Player experience concerns the association of the human player during gameplay, which is based on cognitive and affective physiological measurements collected from sensors mounted on the player's body or in the player's surroundings. In this paper, player experience modeling is studied based on the board puzzle game "Candy Crush Saga" using cognitive data of players accessed by physiological and peripheral devices. Long Short-Term Memory-based Deep Neural Network (LSTM-DNN) is used to predict players' effective states in terms of valence, arousal, dominance, and liking by employing the concept of transfer learning. Transfer learning focuses on gaining knowledge while solving one problem and using the same knowledge to solve different but related problems. The homogeneous transfer learning approach has not been implemented in the game domain before, and this novel study opens a new research area for the game industry where the main challenge is predicting the significance of innovative games for entertainment and players' engagement. Relevant not only from a player's point of view, it is also a benchmark study for game developerswho have been facing problems of "cold start" for innovative games that strengthen the game industrial economy. [ABSTRACT FROM AUTHOR]

Drought is the least understood natural disaster due to the complex relationship of multiple contributory factors. Its beginning and end are hard to gauge, and they can last for months or even for years. India has faced many droughts in the last few decades. Predicting future droughts is vital for framing drought management plans to sustain natural resources. The data-driven modelling for forecasting the metrological time series prediction is becoming more powerful and flexible with computational intelligence techniques. Machine learning (ML) techniques have demonstrated success in the drought prediction process and are becoming popular to predict the weather, especially the minimumtemperature using backpropagation algorithms. The favouriteML techniques for weather forecasting include singular vector machines (SVM), support vector regression, random forest, decision tree, logistic regression, Naive Bayes, linear regression, gradient boosting tree, k-nearest neighbours (KNN), the adaptive neuro-fuzzy inference system, the feed-forward neural networks, Markovian chain, Bayesian network, hidden Markov models, and autoregressive moving averages, evolutionary algorithms, deep learning and many more. This paper presents a recent review of the literature using ML in drought prediction, the drought indices, dataset, and performance metrics. [ABSTRACT FROM AUTHOR]

There are several base types of deep learning models, such as radial basis function networks (RBFN), recurrent neural networks (RNN), generative-adversarial-networks (GANs), long-short-term memory networks (LSTMs), convolutional neural networks (CNNs), self-organizing maps (SOM), restricted Boltzmann machines (RBM), autoencoders, and multilayer-perceptron (MLP). Deep learning models and data-driven intelligent analytics are widely used components of artificial intelligence. [Extracted from the article]

Wireless sensing networks (WSNs) have been applied on various research applications such as monitoring health of humans, targets tracking, natural resources investigation, air quality prediction, water pollution prediction and radiation pollution. The challenge on predicting these applications still exists. Suitable monitoring systems are necessary, to maintain the healthy society with sustainable growth. With the advancement of Internet of Things and modern sensors, the environmental monitoring systems have become smart monitoring system. These wireless sensors are scattered around the environmental locations and places. The localization of sensor placement at the correct place will reduce the redundancy of the sensing environment and cost of the equipment. More nodes are placed at the area that has more pollutant. Accurate node sensor placing on the needed area will reduce the cost of sensors and increase the prediction accuracy. This helps to keep our health safe by selecting less polluted environment. Hence, this article focuses on introducing the deep learning algorithm called Graph Long Short-Term Memory (GLSTM) neural network to predict the air quality characteristics. Next, the evolutionary algorithm called Dragon fly optimizer has been used to localize the node based on the prediction. Deep evolutionary based algorithms will improve the air pollutant prediction and node localization sensor cost. • Application in the domain of smart wireless health care system. • Proposed graph Long Short-Term Memory (GLSTM) neural network to predict the air quality characteristics. • Applied Dragonfly optimizer for node localization based on prediction. • Hybrid approach between machine learning and metaheuristics. [ABSTRACT FROM AUTHOR]

Livestock health and welfare monitoring is a tedious and labour-intensive task previously performed manually by humans. However, with recent technological advancements, the livestock industry has adopted the latest AI and computer vision-based techniques empowered by deep learning (DL) models that, at the core, act as decision-making tools. These models have previously been used to address several issues, including individual animal identification, tracking animal movement, body part recognition, and species classification. However, over the past decade, there has been a growing interest in using these models to examine the relationship between livestock behaviour and associated health problems. Several DL-based methodologies have been developed for livestock behaviour recognition, necessitating surveying and synthesising state-of-the-art. Previously, review studies were conducted in a very generic manner and did not focus on a specific problem, such as behaviour recognition. To the best of our knowledge, there is currently no review study that focuses on the use of DL specifically for livestock behaviour recognition. As a result, this systematic literature review (SLR) is being carried out. The review was performed by initially searching several popular electronic databases, resulting in 1101 publications. Further assessed through the defined selection criteria, 126 publications were shortlisted. These publications were filtered using quality criteria that resulted in the selection of 44 high-quality primary studies, which were analysed to extract the data to answer the defined research questions. According to the results, DL solved 13 behaviour recognition problems involving 44 different behaviour classes. 23 DL models and 24 networks were employed, with CNN, Faster R-CNN, YOLOv5, and YOLOv4 being the most common models, and VGG16, CSPDarknet53, GoogLeNet, ResNet101, and ResNet50 being the most popular networks. Ten different matrices were utilised for performance evaluation, with precision and accuracy being the most commonly used. Occlusion and adhesion, data imbalance, and the complex livestock environment were the most prominent challenges reported by the primary studies. Finally, potential solutions and research directions were discussed in this SLR study to aid in developing autonomous livestock behaviour recognition systems. • SLR on the application of deep learning for livestock behaviour recognition. • Systematically evaluated 1101 publications for their significance to the field. • 44 studies were selected for deep learning for livestock behaviour recognition. • Results show that CNN and Faster R-CNN were the most used models for this purpose. • Summarised data collection process and challenges. [ABSTRACT FROM AUTHOR]

Imagining things without mixed emotions is next to impossible in today's scenario. Whether it is news or any online movement started on social media applications. One of the social media applications i.e Twitter started a movement known as #BlackLivesMatter. The people from all over the world participated showing mixed reactions, sentiments, and emotions such as trusting the movement, gave negative feedback, felt disgusting, showing anger, etc. In this study, a deep learning classifier Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) is used to detect the sentiments and emotions of the people based on the tweets of the two provinces of the USA (Minnesota and Washington D.C.). The proposed hybrid model is validated over Random Forest, Convolutional Neural Network, Long Short Term Memory, and Bidirectional Long Short Term Memory. It is really surprising to see the results as in both the provinces people showing interest as they are trusting the movement with 48% in Minnesota and 54% in Washington D.C. Our proposed model CNN-LSTM is 94% accurate in detecting the various sentiments based on the hyper-parameters such as epoch, filter size, pooling, activation function, dropout, stride, padding, and number of filters. • CNN-LSTM is applied for the sentiment analysis for #BlackLivesMatter. • The results of two provinces of USA: Minnesota and Washington D.C are displayed. • Comparison with existing deep learning classifiers validated the proposed model. [ABSTRACT FROM AUTHOR]

Intelligent Transportation Systems (ITS) have revolutionized transportation by incorporating advanced technologies for efficient and safe mobility. However, these systems face challenges ensuring security and resilience against adversarial attacks. This research addresses these challenges and introduces a novel Dampster–Shafer data fusion-based Adversarial Deep Learning (DS-ADL) Model for ITS in fog cloud environments. Our proposed model focuses on three levels of adversarial attacks: original image level, feature level, and decision level. Adversarial examples are generated at each level to evaluate the system's vulnerability comprehensively. To enhance the system's capabilities, we leverage the power of several vital components. Firstly, we employ Dempster–Shafer-based Multimodal Sensor Fusion, enabling the fusion of information from multiple sensors for improved scene understanding. This fusion approach enhances the system's perception and decision-making abilities. For feature extraction and classification, we utilize ResNet 101, a deep learning architecture known for its effectiveness in computer vision tasks. We introduced a novel Monomodal Multidimensional Gaussian Model (MMGM-DD) based Adversarial Detection approach to detect adversarial examples. This detection mechanism enhances the system's ability to identify and mitigate adversarial attacks in real-time. Additionally, we incorporate the Defensive Distillation method for adversarial training, which trains the model to be robust against attacks by exposing it to adversarial examples during the training process. To evaluate the performance of our proposed model, we utilize two datasets: Google Speech Command version 0.01 and the German Traffic Sign Recognition Benchmark (GTSRB). Evaluation metrics include latency delay and computation time (fog–cloud), accuracy, MSE, loss, and F-score for attack detection and defense. The results and discussions demonstrate the effectiveness of our Dampster–Shafer data fusion-based Adversarial Deep Learning Model in enhancing the robustness and security of ITS in fog–cloud environments. The model's ability to detect and defend against adversarial attacks while maintaining low-latency fog–cloud operations highlights its potential for real-world deployment in ITS. • Proposed DS-ADL model for ITS to enhance the resilience and security against different adversarial attacks. • Dempster–Shafer-based Multimodal Sensor Fusion used for data fusion. • Analysis is based on Fog-Cloud Environment. • Applied defensive distillation method for adversarial training. • Performance of the model is obtained using GTSRB and GSC datasets. [ABSTRACT FROM AUTHOR]

All witnessed the terrible effects of the COVID-19 pandemic on the health and work lives of the population across the world. It is hard to diagnose all infected people in real time since the conventional medical diagnosis of COVID-19 patients takes a couple of days for accurate diagnosis results. In this paper, a novel learning framework is proposed for the early diagnosis of COVID-19 patients using hybrid deep fusion learning models. The proposed framework performs early classification of patients based on collected samples of chest X-ray images and Coswara cough (sound) samples of possibly infected people. The captured cough samples are pre-processed using speech signal processing techniques and Mel frequency cepstral coefficient features are extracted using deep convolutional neural networks. Finally, the proposed system fuses extracted features to provide 98.70% and 82.7% based on Chest-X ray images and cough (audio) samples for early diagnosis using the weighted sum-rule fusion method. [ABSTRACT FROM AUTHOR]