Search

Quantum machine learning (QML) is an emerging field that combines the power of quantum computing with machine learning (ML) techniques to solve complex problems. In recent years, QML algorithms have shown tremendous potential in various applications such as image recognition, natural language processing, health care, finance, and drug discovery. QML algorithms aim to reduce computation costs and solve complex problems beyond the scope of classical machine learning algorithms. In this article, we study the performance of two QML algorithms, that is, quantum support vector classifiers (QSVC) and variational quantum classifiers (VQC), for chronic heart disease prediction in Healthcare 4.0. The performance of the two classifiers is assessed using different evaluation metrics like accuracy, precision, recall, and F1 score. The authors concluded the superior performance of QSVC over VQC with an accuracy of 82%. [ABSTRACT FROM AUTHOR]

Image-denoising techniques are widely used to defend against Adversarial Examples (AEs). However, denoising alone cannot completely eliminate adversarial perturbations. The remaining perturbations tend to amplify as they propagate through deeper layers of the network, leading to misclassifications. Moreover, image denoising compromises the classification accuracy of original examples. To address these challenges in AE defense through image denoising, this paper proposes a novel AE detection technique. The proposed technique combines multiple traditional image-denoising algorithms and Convolutional Neural Network (CNN) network structures. The used detector model integrates the classification results of different models as the input to the detector and calculates the final output of the detector based on a machine-learning voting algorithm. By analyzing the discrepancy between predictions made by the model on original examples and denoised examples, AEs are detected effectively. This technique reduces computational overhead without modifying the model structure or parameters, effectively avoiding the error amplification caused by denoising. The proposed approach demonstrates excellent detection performance against mainstream AE attacks. Experimental results show outstanding detection performance in well-known AE attacks, including Fast Gradient Sign Method (FGSM), Basic Iteration Method (BIM), DeepFool, and Carlini &Wagner (C&W), achieving a 94% success rate in FGSM detection, while only reducing the accuracy of clean examples by 4%. [ABSTRACT FROM AUTHOR]

Vehicular communication is the backbone of future Intelligent Transportation Systems (ITS). It offers a network-based solution for vehicle safety, cooperative awareness, and traffic management applications. For safety applications, Basic Safety Messages (BSM) containing mobility information is shared by the vehicles in their neighborhood to continuously monitor other nearby vehicles and prepare a local traffic map. BSMs are shared using mode 4 of Cellular V2X (C-V2X) communications in which resources are allocated in an ad hoc manner. However, the strict packet transmission requirements of BSM and hidden node problem causes packet collisions in a vehicular network, thus reducing the reliability of safety applications. Moreover, as vehicles choose the transmission resources in a distributed manner in mode 4 of CV2X, the packet collision problem is further aggravated. This paper presents a novel solution in the form of a Space Division Multiple Access (SDMA) protocol that intelligently schedules BSM transmissions using vehicle position data to reduce concurrent transmissions from hidden node interferers. The proposed protocol works by dividing road segments into clusters and subclusters. Several sub-frames are allocated to a cluster and these sub-frames are reused after a certain distance. Within a cluster, sub-channels are allocated to sub-clusters. We implement the proposed SDMA protocol and evaluate its performance in a highway vehicular network. Simulation results show that the proposedSDMAprotocol outperforms standard Sensing-Based Semi Persistent Scheduling (SB-SPS) in terms of safety range and packet delay. [ABSTRACT FROM AUTHOR]

With the rapid development in business transactions, especially in recent years, it has become necessary to develop different mechanisms to trace business user records in web server log in an efficient way. Online business transactions have increased, especially when the user or customer cannot obtain the required service. For example, with the spread of the epidemic Coronavirus (COVID-19) throughout the world, there is a dire need to rely more on online business processes. In order to improve the efficiency and performance of E-business structure, a web server log must be well utilized to have the ability to trace and record infinite user transactions. This paper proposes an event stream mechanism based on formula patterns to enhance business processes and record all user activities in a structured log file. Each user activity is recorded with a set of tracing parameters that can predict the behavior of the user in business operations. The experimental results are conducted by applying clustering-based classification algorithms on two different datasets; namely, Online Shoppers Purchasing Intention and Instacart Market Basket Analysis. The clustering process is used to group related objects into the same cluster, then the classification process measures the predicted classes of clustered objects. The experimental results record provable accuracy in predicting user preferences on both datasets. [ABSTRACT FROM AUTHOR]