Basem Assiri

The development of blockchain technology has facilitated its application in many areas of life due to its ability to enable decentralization in processing and storage. To support blockchain's application in various fields, its algorithms, and consensus protocols should be developed. Nowadays, there are many consensus protocols, each of which can be applied to the appropriate field, considering the cost of each protocol. Users should be motivated to use blockchain and participate in its processes. Considering the processing, communication, and storage costs, effective reward mechanisms are necessary to compensate users and encourage participation. Therefore, this study investigates and reviews a variety of blockchain consensus protocols and corresponding reward strategies. The study analyses twenty-two consensus protocols, explaining how they work, and their advantages and disadvantages. In addition, this paper discusses the types of reward strategies, their sources, limitations, and future. According to the nature of consensus protocols, they are classified into seven categories, which are computational-based, wealth-based, behavioral-based, fairness-based, fault-tolerance-based, leader-based, and transactional-based. The study aims to provide information on the future paths of blockchain consensus mechanisms, promoting a more profound understanding of their capabilities and constraints in many situations.

The accurate prediction of cryptocurrency prices is crucial due to the volatility and complexity of digital asset markets, which pose significant challenges to traders, investors, and researchers. This research addresses these challenges by leveraging machine learning and deep learning techniques to forecast closing prices for cryptocurrencies, focusing on Bitcoin, Ethereum, Binance Coin, and Litecoin cryptocurrency datasets. A Random Forest ensemble learning algorithm, a Gradient Boosting model, and a feedforward neural network were implemented to handle the complexities in cryptocurrency data. A Z-Score-based anomaly detection framework was integrated to classify closing prices as normal or abnormal, aiding in identifying significant market events. Evaluation metrics, such as the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²), demonstrate the superior precision and reliability of the Random Forest and Gradient Boosting models. The deep learning model indicates strong generalization capabilities, suggesting potential advantages on more complex datasets. These findings highlight the importance of combining advanced machine learning techniques and cryptocurrencies to develop a robust framework for cryptocurrency forecasting and anomaly detection.

Recently, distributed systems have become the backbone of technological development. It serves as the foundation for new trends technologies such as blockchain, the internet of things and others. A distributed system provides fault tolerance and decentralization, where a fault in any component does not result in a whole system failure. In addition, deep learning model enables processing data to find patterns, which helps in classification, regression, prediction, and clustering. This work employs deep learning to handle faults within distributed systems in three scenarios. Firstly, a faulty processor may not be able to produce the right output. Therefore, deep learning model uses the inputs and outputs of other processors to find patterns and produces the proper output of the faulty processor. Secondly, if a faulty possessor corrupts its inputs as well, then the deep learning model learns from the inputs and the outputs of successful processors and produces the proper output of the faulty processor, even with corrupted inputs. Thirdly, for unrelated data, in which the patterns of the input of the faulty processors differ from the patterns of the inputs of successful ones. In this case, the model is able to discover the new pattern and to be labeled as unknown. In the experiments, we use deep learning models like VGG16, VGG19, AlexNet LSTM and ResNet34, to investigate the performance of the deep learning in the three mentioned scenarios. For unstructured datasets, the accuracy of the models is affected by the size of the faulty data. The accuracy of all models lies between 60% when the size of the faulty data is 90%, and 96%, when the size of the faulty data is 90%. The structured datasets are not significantly affected by the portion of the faulty data and the accuracy reaches 99%.

The automatic detection of fires and the determination of their causes play a crucial role in mitigating the catastrophic consequences of such events. The literature reveals substantial research on automatic fire detection using machine learning models. However, once a fire is detected, there is a notable gap in the literature concerning the automatic classification of fire types like solid-material fires, flammable gas fires, and electric-based fires. This classification is essential for firefighters to quickly and effectively determine the most appropriate fire suppression method. This work introduces a benchmark dataset comprising over 1353 manually annotated images, classified into five categories, which is publicly released. It introduces a multiclass dataset based on the types of origins of fires. This work also presents a system incorporating eight deep-learning models evaluated for fire detection and fire-type classification. In fire-type classification, this work focuses on four fire types: solid material, chemical, electrical-based, and oil-based fires. Under the single-level, five-way classification setting, our system achieves its best performance with an accuracy score of 94.48%. Meanwhile, under the two-level classification setting, our system achieves its best performance with accuracy scores of 98.16% for fire detection and 97.55% for fire-type classification, using the DenseNet121 and EffecientNet-b0 models, respectively. The results also indicate that electrical and oil-based fires are the most challenging to detect.

Brain tumors occur due to the expansion of abnormal cell tissues and can be malignant (cancerous) or benign (not cancerous). Numerous factors such as the position, size, and progression rate are considered while detecting and diagnosing brain tumors. Detecting brain tumors in their initial phases is vital for diagnosis where MRI (magnetic resonance imaging) scans play an important role. Over the years, deep learning models have been extensively used for medical image processing. The current study primarily investigates the novel Fine-Tuned Vision Transformer models (FTVTs)—FTVT-b16, FTVT-b32, FTVT-l16, FTVT-l32—for brain tumor classification, while also comparing them with other established deep learning models such as ResNet50, MobileNet-V2, and EfficientNet - B0. A dataset with 7,023 images (MRI scans) categorized into four different classes, namely, glioma, meningioma, pituitary, and no tumor are used for classification. Further, the study presents a comparative analysis of these models including their accuracies and other evaluation metrics including recall, precision, and F1-score across each class. The deep learning models ResNet-50, EfficientNet-B0, and MobileNet-V2 obtained an accuracy of 96.5%, 95.1%, and 94.9%, respectively. Among all the FTVT models, FTVT-l16 model achieved a remarkable accuracy of 98.70% whereas other FTVT models FTVT-b16, FTVT-b32, and FTVT-132 achieved an accuracy of 98.09%, 96.87%, 98.62%, respectively, hence proving the efficacy and robustness of FTVT’s in medical image processing.

Hyperspectral imagery, capturing information beyond the visible spectrum, is essential for many remote sensing applications. This paper introduces a novel approach utilizing a 3D Convolutional Neural Network (CNN) enhanced with self-attention mechanism to address the limitations of traditional architectures in hyperspectral image classification. The main problem tackled is the effective extraction of both spatial and spectral features from complex hyperspectral datasets. Our proposed model simultaneously analyzes spatial and spectral dimensions with improved accuracy and adaptability through self-attention. We systematically evaluate the performance of 1D CNN, 2D CNN, and 3D CNN models, alongside Multi-Column Neural Network (MCNN) and Hybrid Spectral Network (Hybrid SN) models, comparing them to our proposed approach. The evaluation, conducted on the Indian Pines and Salinas datasets, highlights significant improvements in classification accuracy and adaptability. Specifically, the proposed 3D CNN with self-attention achieves accuracy values of 98.45% and 91.32% on the Indian Pines and Salinas datasets, respectively. This paper provides critical insights for data scientists and remote sensing experts, contributing to informed decision-making in selecting CNN models tailored to specific application requirements and advancing the field of hyperspectral image classification (HSIC). Furthermore, our approach shows improved handling of the complex spectral variability and spatial heterogeneity inherent in hyperspectral data.

Blockchain is a developing technology that promises advancements when it is applied to other fields. Applying blockchain to other systems requires a customized blockchain model to satisfy the requirements of different application fields. One important area is to integrate blockchain with smart spaces and the Internet of Things to process, manage, and store data. Actually, smart spaces and Internet of Things systems include various types of transactions in terms of sensitivity. The sensitivity can be considered as correctness sensitivity, time sensitivity, and specialization sensitivity. Correctness sensitivity means that the systems should accept precise or approximated data in some cases, whereas time sensitivity means that there are time bounds for each type of transaction, and specialization sensitivity applies when some transactions are processed only by specialized people. Therefore, this work introduces the smart partitioned blockchain model, where we use machine learning and deep learning models to classify transactions into different pools according to their sensitivity levels. Then, each pool is mapped to a specific part of the smart partitioned blockchain model. The parts can be permissioned or permissionless. The permissioned parts can have different sub-parts if needed. Consequently, the smart partitioned blockchain can be customized to meet application-field requirements. In the experimental results, we use bank and medical datasets with a predefined sensitivity threshold for classification accuracy in each system. The bank transactions are critical, whereas the classification of the medical dataset is speculative and less critical. The Random Forest model is used for bank-dataset classification, and its accuracy reaches 100%, whereas Sequential Deep Learning is used for the medical dataset, which reaches 91%. This means that all bank transactions are correctly mapped to the corresponding parts of the blockchain, whereas accuracy is lower for the medical dataset. However, acceptability is determined based on the predefined sensitivity threshold.

Blockchain enhances the development of other technologies and systems by providing more transparency, sharing, decentralization, security, and privacy. Blockchain has many applications that enable integration and application in many areas, such as the field of ambient assisted living (AAL). However, blockchain includes many processes for data proposing, validating, and approving, which result in high latency. Such latency negatively influences AAL systems, which require real-time responses in many cases. In addition, blockchain processes are processed based on consensus. This challenges specialized decisions that should be taken only by specialized members within the blockchain network. Therefore, this work introduces an organized leader election consensus protocol with a blockchain model that is applicable for AAL. The proposed protocol and model are able to solve the issue of latency as well as consider specialized decisions. Solving the issue of latency enables AAL to perform real-time processes in the needed cases. While considering the matter of specialization gives more credibility to the blockchain’s decisions, which is necessary for AAL. Indeed, it classifies the blocks into special-sensitive, time-sensitive, and non-sensitive classes, where each class has a suitable procedure. In addition, to manage the organized leader election consensus protocol, we manage the blockchain feature and rewarding strategy. This enhances the miners’ participation in a way that supports blockchain and AAL simultaneously. The experimental results show that our model reduces the execution time by about 51% in comparison to the original blockchain model.

Blockchain technology is a decentralized and secure paradigm for data processing, sharing, and storing. It relies on consensus protocol for all decisions, which focuses on computational and resource capability. For example, proof of work (PoW) and proof of stake (PoS) are the most famous consensus protocols that are currently used. However, these current consensus protocols are required to recruit a node with a high computational or a large amount of cryptocurrency to act as a miner node and to generate a new block. Unfortunately, these PoW and PoS protocols could be impractical for adoption in today’s technological fields, such as the Internet of Things and healthcare. In addition, these protocols are susceptible to flexibility, security, and fairness issues, as they are discussed in detail in this work. Therefore, this paper introduces a proof of fairness (PoF) as a dynamic and secure consensus protocol for enhancing the mining selection process. The selection of the miner node is influenced by numerous factors, including the time required to generate a block based on the transaction’s sensitivity. Firstly, a reverse auction mechanism is designed as an incentive mechanism to encourage all nodes to participate in the miner selection process. In a reverse auction, each node will draw its strategy based on its computational capability and claimed cost. Secondly, an expressive language is developed to categorize transaction types based on their sensitivity to processing time, ensuring compatibility with our miner selection process. Thirdly, a homomorphic concept is designed as a security and privacy scheme to protect the bidder’s data confidentiality. Finally, an extensive evaluation involving numerical analysis was carried out to assess the efficiency of the suggested PoF protocol, which confirms that the proposed PoF is dynamic and more efficient than current PoW and PoS consensus protocols.

The progress of technology has played a crucial role in enhancing various fields such as education. Universities in Saudi Arabia offer free education to students and follow specific admission policies. These policies usually focus on features and scores such as the high school grade point average, general aptitude test, and achievement test. The main issue with current admission policies is that they do not fit with all majors, which results in high rates of failure, dropouts, and transfer. Another issue is that all mentioned features and scores are cumulatively calculated, which obscures some details. Therefore, this study aims to explore admission criteria used in Saudi Arabian universities and the factors that influence students’ choice of major. First, using data mining techniques, the research analyzes the relationships and similarities between the university’s grade point average and the other student admission features. The study proposes a new Jaccard model that includes modified Jaccard and approximated modified Jaccard techniques to match the specifications of students’ data records. It also uses data distribution analysis and correlation coefficient analysis to understand the relationships between admission features and student performance. The investigation shows that relationships vary from one major to another. Such variations emphasize the weakness of the generalization of the current procedures since they are not applicable to all majors. Additionally, the analysis highlights the importance of hidden details such as high school course grades. Second, this study employs machine learning models to incorporate additional features, such as high school course grades, to find suitable majors for students. The K-nearest neighbor, decision tree, and support vector machine algorithms were used to classify students into appropriate majors. This process significantly improves the enrolment of students in majors that align with their skills and interests. The results of the experimental simulation indicate that the K-nearest neighbor algorithm achieves the highest accuracy rate of 100%, while the decision tree algorithm’s accuracy rate is 81% and the support vector machine algorithm’s accuracy rate is 75%. This encourages the idea of using machine learning models to find a suitable major for applicants.