Search

Age-related macular degeneration (AMD) is a leading cause of vision loss in older people and is characterized by subtle retinal changes that make early identification difficult. Previous studies have demonstrated the efficacy of Vision Transformers (ViTs) in classifying medical images by successfully detecting retinal disorders such as AMD. This paper addresses multiple shortcomings in conventional AMD diagnostic techniques by exploring the detection and explanation of various AMD subtypes from numerical features extracted with a ViT model from fundus images through cascaded artificial intelligence (AI) models using transformers, convolutional neural networks (CNNs), and multilayer perceptrons (MLPs). The data were preprocessed to recognize intricate disease-related patterns. The best test results using the cascade method for each model type show that the MLP model achieved an accuracy of 91.86% (with a sensitivity of 92.22% and a specificity of 95.74%). The Transformer model achieved its highest accuracy of 83.72% (with a sensitivity of 83.86% and a specificity of 89.74%). The CNN model demonstrated the best performance, with an accuracy of 94.19% (with a sensitivity of 93.84% and a specificity of 96.00%). This work helps clinicians interpret AMD cases and supports decision-making revealing hidden features of AMD that are not visible to the human eye. Future research will focus on improving these systems by expanding the databases in aggregate and incorporating multimodal data.

Quantum computing (QC) stands apart from traditional computing systems by employing revolutionary techniques for processing information. It leverages the power of quantum bits (qubits) and harnesses the unique properties exhibited by subatomic particles, such as superposition, entanglement, and interference. These quantum phenomena enable quantum computers to operate on an entirely different level, exponentially surpassing the computational capabilities of classical computers. By manipulating qubits and capitalising on their quantum states, QC holds the promise of solving complex problems that are currently intractable in the case of traditional computers. The potential impact of QC extends beyond its computational power and reaches into various critical sectors, including healthcare. Scientists and engineers are working diligently to overcome various challenges and limitations associated with QC technology. These include issues related to qubit stability, error correction, scalability, and noise reduction. In such a scenario, our proposed work provides a concise summary of the most recent state of the art based on articles published between 2018 and 2023 in the healthcare domain. Additionally, the approach follows the necessary guidelines for conducting a systematic literature review. This includes utilising research questions and evaluating the quality of the articles using specific metrics. Initially, a total of 2,038 records were acquired from multiple databases, with 468 duplicate records and 1,053 records unrelated to healthcare subsequently excluded. A further 258, 68, and 39 records were eliminated based on title, abstract, and full-text criteria, respectively. Ultimately, the remaining 49 articles were subject to evaluation, thus providing a brief overview of the recent literature and contributing to existing knowledge and comprehension of Quantum Machine Learning (QML) algorithms and their applications in the healthcare sector. This analysis establishes a foundational framework for forthcoming research and development at the intersection of QC and machine learning, ultimately paving the way for innovative approaches to addressing complex challenges within the healthcare domain.

The Internet of Things (IoT) is evolving, driven by the increasing demand for bandwidth. A key focus is on minimizing communication delays. This paper introduces a new solution called Predictive Dynamic Bandwidth Allocation (PDBA), using adaptive predictive algorithms in the IoT context. The approach involves predicting resource needs and network conditions, allowing for efficient bandwidth allocation. The PDBA framework uses advanced predictive algorithms to foresee bandwidth requirements for IoT devices at specific intervals, contributing to low communication latency—crucial for responsive IoT applications.To handle dynamic changes in the IoT environment, like device connectivity fluctuations during sleep mode transitions, our framework incorporates a dynamic perceptual algorithm inspired by reinforcement learning principles. This real-time adaptation mitigates the impact of environmental fluctuations, ensuring consistently low latency. Simulations across various IoT scenarios demonstrate the PDBA framework’s effectiveness. The adaptive predictive algorithm significantly improves latency by nearly 10%, reduces packet loss to 6.8%, and increases throughput to 94.2% compared to traditional methods, with notably lower computing times of 0.69 seconds. These results underscore PDBA’s potential to enhance Quality of Service (QoS) in IoT networks. The article provides a comprehensive examination of the PDBA framework’s components, its seamless integration into the IoT environment, and its substantial role in optimizing communication performance within IoT networks.

A common model for classifying images is the convolutional neural network (CNN), which has the benefit of effectively using data correlation information. Despite their remarkable success, classical CNNs may face challenges in achieving further improvements in accuracy, computational efficiency, explainability, and generalization. However, if the specified data dimension or model grows too large, CNN becomes difficult to train effectively with a slowdown processing. In order to address a problem using CNN utilizing quantum computing, Quantum Convolutional Neural Network (QCNN) proposes a novel quantum solution or enhances the functionality of an existing learning model in terms of processing time during training. This paper presents a comparative analysis between classical Convolutional Neural Networks (CNNs) and a novel quantum circuit architecture tailored for image-based tasks, emphasizing the adaptability and versatility of quantum circuits in enhancing feature extraction capabilities and then final accuracy and processing time. A MNIST and covidx-cxr3 datasets was used to train quantum-CNN models, and the results of these comparisons were made with traditional CNN performance. The results demonstrate that the suggested QCNN beat the traditional CNN in terms of recognition accuracy and processing speed (process time) when combined with cutting-edge feature extraction techniques. This superiority is particularly evident when trained on the covidx-cxr3 dataset, highlighting the potential for quantum computing to revolutionize image classification tasks.

Emotion processing has been a very intense domain of investigation in data analysis and NLP during the previous few years. Currently, the algorithms of the deep neural networks have been applied for opinion mining tasks with good results. Among various neuronal models applied for opinion mining a deep belief network (DBN) model has gained more attention. In this proposal, we have developed a combined classifier based on fuzzy Vader lexicon and a parallel deep belief network for emotion analysis. We have implemented multiple pretreatment techniques to improve the quality and soundness of the data and eliminate disturbing data. Afterward, we have performed a semi-automatic dataset labeling using a combination of two different methods: Mamdani’s fuzzy system and Vader lexicon. As well, we have applied four feature extractors, which are: GloVe, TFIDF (Trigram), TFIDF (Bigram), TFIDF (Unigram) with the aim of transforming each incoming tweet into a digital value vector. In addition, we have integrated three feature selectors, namely: The ANOVA method, the chi-square approach and the mutual information technique with the objective of selecting the most relevant features. Further, we have implemented the DBN as classifier for classifying each inputted tweet into three categories: neutral, positive or negative. At the end, we have deployed our proposed approach in parallel way employing both Hadoop and Spark framework with the purpose of overcoming the problem of long runtime of massive data. Furthermore, we have carried out a comparison between our newly suggested hybrid approach and alternative hybrid models available in the literature. From the experimental findings, it was found that our suggested vague parallel approach is more powerful than the baseline patterns in terms of false negative rate (1.33%), recall (99.75%), runtime (32.95s), convergence, stability, F1 score (99.53%), accuracy (98.96%), error rate (1.04%), kappa-Static (99.1%), complexity, false positive rate (0.25%), precision rate (97.59%) and specificity rate (98.67%). As a conclusion, our vague parallel approach outperforms baseline and deep learning models, as well as certain other approaches chosen from the literature.

Quantum technologies have become powerful tools for a wide range of application disciplines, which tend to range from chemistry to agriculture, natural language processing, and healthcare due to exponentially growing computational power and advancement in machine learning algorithms. Furthermore, the processing of classical data and machine learning algorithms in the quantum domain has given rise to an emerging field like quantum machine learning. Recently, quantum machine learning has become quite a challenging field in the case of healthcare applications. As a result, quantum machine learning has become a common and effective technique for data processing and classification across a wide range of domains. Consequently, quantum machine learning is the most commonly used application of quantum computing. The main objective of this work is to present a brief overview of current state-of-the-art published articles between 2013 and 2021 to identify, analyze, and classify the different QML algorithms and applications in the biomedical field. Furthermore, the approach adheres to the requirements for conducting systematic literature review techniques such as research questions and quality metrics of the articles. Initially, we discovered 3149 articles, excluded the 2847 papers, and read the 121 full papers. Therefore, this research compiled 30 articles that comply with the quantum machine learning models and quantum circuits using biomedical data. Eventually, this article provides a broad overview of quantum machine learning limitations and future prospects.

Nowadays, quantum-enhanced methods have been widely studied to solve machine learning related problems. This article presents the application of a Variational Quantum Classifier (VQC) for binary classification. We utilized three datasets: a synthetic dataset with randomly generated values between 0 and 1, the publicly available University of California Intelligence Machine learning (UCI) sonar dataset consisting of mining data, and a proprietary diabetes dataset related to diabetes with acute diseases and diabetes without acute disease. To deal with the limitation of noisy intermediate-scale quantum systems (NISQ), we used a pre-processing method to enhance the prediction rate when applying the VQC method. The process includes feature selection and state preparation. Quantum state preparation is critical for obtaining a functioning pipeline in a quantum machine learning (QML) model. Amplitude encoding is a state preparation approach that enhances the performance of data encoding and the learning of quantum models. As a result, our proposed methods achieved accuracies of 75%, 71.4%, and 68.73% by using VQC model and in contrast, the amplitude encoding-based VQC achieved 98.40%, 67.3%, and 74.50% accuracies on the synthetic, sonar, and diabetes dataset, respectively.

The prevalence of heart diseases is rising quickly throughout the world, which has an impact on both the world economy and public health. According to the recent statistical survey reports, the increasing mortality rate is due to high blood pressure, high cholesterol, the use of tobacco, obesity, and an inconsistent pulse rate. It is difficult and time-consuming to investigate the various variations of these factors and their impact on Coronary Artery Disease (CAD). Therefore, it is necessary to use modern approaches to diagnose the disease early and minimize the mortality rate. The fields of machine learning and data mining have a wide research dimension and various novel techniques that could help in the prediction of CAD in its early stages and identify their patterns and behaviors in a huge amount of data. The results of such predictions will aid the clinical staff in decision making and early diagnosis. In such a scenario, we proposed a quantum version of the Fully Convolutional Neural Network (FCQ-CNN) for Ischemic Heart Disease (IHD) classification. The proposed model evaluates the quantum circuit-based technique that was inspired by convolutional neural networks, a very successful machine learning model. This method provides $O(log (n))$ depth for $n$ qubits, reducing the number of parameters and allowing for effective training and testing of real quantum devices. The model has been evaluated by considering the IHD dataset after the data has been cleaned and filtered through the Maximally Relevant Minimally Redundancy (MRMR) filter. For dimension reduction, a Support Vector Machine along with Recursive Feature Elimination (SVM-RFE) has been considered. Initially, the model is tested with 20% of the whole dataset and gets the promising results of a testing accuracy of 84.6% with a testing loss of 0.28. By taking into account the same optimal parameters, the proposed model outcomes are compared to those of the classical Optimized Convolution Neural Network (Optimized-CNN) and Fully Connected Neural Network (FCNN) models. Comparing the model’s competency to that of earlier published quantum models yields improvements in accuracy of 8.6%, 12.6%, 3.5%, and 1.8% respectively.

This study presents a computationally efficient deep learning model for binary sentiment classification, which aims to decide the sentiment polarity of people's opinions, attitudes, and emotions expressed in written text. To achieve this, we exploited three widely practiced datasets based on public opinions about movies. We utilized merely one bidirectional long short-term memory (BiLSTM) layer along with a global pooling mechanism and achieved an accuracy of 80.500%, 85.780%, and 90.585% on MR, SST2 and IMDb datasets, respectively. We concluded that the performance metrics of our proposed approach are competitive with the recently published models, having comparatively complex architectures. Also, it is inferred that the proposed single-layered BiLSTM based architecture is computationally efficient and can be recommended for real-time applications in the field of sentiment analysis.