Search

The study presented in this paper evaluated gene expression profiles from The Cancer Genome Atlas (TCGA). To reduce complexity, we focused on genes in the cGAS–STING pathway, crucial for cytosolic DNA detection and immune response. The study analyzes three clinical variables: disease-specific survival (DSS), overall survival (OS), and tumor stage. To effectively utilize the high-dimensional gene expression data, we needed to find a way to project these data meaningfully. Since gene pathways can be represented as graphs, a novel method of presenting genomics data using graph data structure was employed, rather than the conventional tabular format. To leverage the gene expression data represented as graphs, we utilized a graph convolutional network (GCN) machine learning model in conjunction with the genetic algorithm optimization technique. This allowed for obtaining an optimal graph representation topology and capturing important activations within the pathway for each use case, enabling a more insightful analysis of the cGAS–STING pathway and its activations across different cancer types and clinical variables. To tackle the problem of unexplainable AI, graph visualization alongside the integrated gradients method was employed to explain the GCN model’s decision-making process, identifying key nodes (genes) in the cGAS–STING pathway. This approach revealed distinct molecular mechanisms, enhancing interpretability. This study demonstrates the potential of GCNs combined with explainable AI to analyze gene expression, providing insights into cancer progression. Further research with more data is needed to validate these findings.

The development and testing of a virtual assistant (VA) designed to enhance information retrieval and support in an academic environment are presented in this paper, with the Retrieval-Augmented Generation (RAG) approach being utilized alongside Google’s VERTEX AI Palm-2 model. A novel integration of RAG with contextual learning is introduced in this study, specifically for applications in university contact centers, where accuracy and relevance are considered paramount. The effectiveness of the VA was evaluated through user testing, focusing on two primary hypotheses: first, that the VA can achieve accurate interpretation and response to queries with context-based information, and second, that the VA minimizes potential harm from erroneous responses. In total, 187 participants were involved in the testing, and a diverse set of inquiries was utilized, resulting in 561 query–response interactions that were analyzed. It was shown that contextual data significantly reduced hallucinations and increased response accuracy, thereby underscoring the value of the RAG method in applications requiring high levels of specificity. Furthermore, the study provides empirical insights into the impact of AI-generated hallucinations and response inconsistencies, particularly about structured or procedural data. A framework for mitigating these challenges in future implementations is also offered. The scalability and adaptability of the RAG method in specialized academic contexts are demonstrated in this work, with broader implications for integrating AI-driven VAs across educational and professional domains being highlighted.

Smart cities rely on a network of sensors to gather real-time data on various environmental factors, including air quality. This paper addresses the challenges of improving the accuracy of low-cost particulate matter sensors (LCPMSs) which can be compromised by environmental conditions, such as high humidity, which is common in many urban areas. Such weather conditions often lead to the overestimation of particle counts due to hygroscopic particle growth, resulting in a potential public concern, although most of the detected particles consist of just water. The paper presents an innovative design for an indicative air-quality measuring station that integrates the particulate matter sensor with a preconditioning subsystem designed to mitigate the impact of humidity. The preconditioning subsystem works by heating the incoming air, effectively reducing the relative humidity and preventing the hygroscopic growth of particles before they reach the sensor. To validate the effectiveness of this approach, parallel measurements were conducted using both preconditioned and non-preconditioned sensors over a period of 19 weeks. The data were analyzed to compare the performance of the sensors in terms of accuracy for PM1, PM2.5, and PM10 particles. The results demonstrated a significant improvement in measurement accuracy for the preconditioned sensor, especially in environments with high relative humidity. When the conditions were too severe and both sensors started measuring incorrect values, the preconditioned sensor-measured values were closer to the actual values. Also, the period of measuring incorrect values was shorter with the preconditioned sensor. The results suggest that the implementation of air preconditioning subsystems in LCPMSs deployed in smart cities can provide a cost-effective solution to overcome humidity-related inaccuracies, thereby improving the overall quality of measured air pollution data.

Recent advancements in cognitive neuroscience, particularly in electroencephalogram (EEG) signal processing, image generation, and brain–computer interfaces (BCIs), have opened up new avenues for research. This study introduces a novel framework, Bridging Artificial Intelligence and Neurological Signals (BRAINS), which leverages the power of artificial intelligence (AI) to extract meaningful information from EEG signals and generate images. The BRAINS framework addresses the limitations of traditional EEG analysis techniques, which struggle with nonstationary signals, spectral estimation, and noise sensitivity. Instead, BRAINS employs Long Short-Term Memory (LSTM) networks and contrastive learning, which effectively handle time-series EEG data and recognize intrinsic connections and patterns. The study utilizes the MNIST dataset of handwritten digits as stimuli in EEG experiments, allowing for diverse yet controlled stimuli. The data collected are then processed through an LSTM-based network, employing contrastive learning and extracting complex features from EEG data. These features are fed into an image generator model, producing images as close to the original stimuli as possible. This study demonstrates the potential of integrating AI and EEG technology, offering promising implications for the future of brain–computer interfaces.

Tandem repeats (TRs) are important components of eukaryotic genomes; they have both structural and functional roles: (i) they form essential chromosome structures such as centromeres and telomeres; (ii) they modify chromatin structure and affect transcription, resulting in altered gene expression and protein abundance. There are established links between variations in TRs and incompatibilities between species, evolutionary development, chromosome mis-segregation, aging, cancer outcomes and different diseases. Given the importance of TRs, it seemed essential to develop an efficient, sensitive and automated application for the identification of all kinds of TRs in various genomic sequences. Here, we present our new GRM application for identifying TRs, which is designed to overcome all the limitations of the currently existing algorithms. Our GRM algorithm provides a straightforward identification of TRs using the frequency domain but avoiding the mapping of the symbolic DNA sequence into numerical sequence, and using key string matching, but avoiding the statistical methods of locally optimizing individual key strings. Using the GRM application, we analyzed human, chimpanzee and mouse chromosome 19 genome sequences (RefSeqs), and showed that our application was very fast, efficient and simple, with a powerful graphical user interface. It can identify all types of TRs, from the smallest (2 bp) to the very large, as large as tens of kilobasepairs. It does not require any prior knowledge of sequence structure and does not require any user-defined parameters or thresholds. In this way, it ensures that a full spectrum of TRs can be detected in just one step. Furthermore, it is robust to all types of mutations in repeat copies and can identify TRs with various complexities in the sequence pattern. From this perspective, we can conclude that the GRM application is an efficient, sensitive and automated method for the identification of all kinds of TRs.

Decision makers (DMs) are often viewed as autonomous in the majority of multicriteria group decision making (MCGDM) situations, and their psychological behaviors are seldom taken into account. Once more, we are unable to prevent both positive and negative flows of varying alternative preferences due to the nature of attributes or criteria in complicated decision-making problems. However, DMs’ perspectives are likely to affect one another in complicated MCGDM issues, and they frequently use subjective limited rationality while making decisions. The multicriteria quantum decision theory-based group decision making integrating the TODIM-PROMETHEE II strategy under linguistic Z-numbers (LZNs) is designed to overcome the aforementioned problems. In our established technique, the PROMETHEE II controls the positive and negative flows of distinct alternative preferences, the TODIM method manages the experts’ personal regrets over a criterion, and the quantum probability theory (QPT) addresses human cognition and behavior. Because LZNs can convey linguistic judgment and trustworthiness, we provide expert LZNs for their viewpoints in this work. We determine the criterion weights for each expert after first obtaining their respective expert weights. Second, to represent the limited rational behaviors of the DMs, the TODIM-PROMETHEE II approach is introduced. It is employed to determine each alternative’s dominance in both positive and negative flows. Third, a framework for quantum possibilistic aggregation is developed to investigate the effects of interference between the views of DMs. The views of DMs are seen in this procedure as synchronously occurring wave functions that affect the overall outcome by interfering with one another. The model’s efficacy is then assessed by a selection of renewable energy case studies, sensitive analysis, comparative analysis, and debate.

Fog computing is a promising and challenging paradigm that enhances cloud computing by enabling efficient data processing and storage closer to data sources and users. This paper introduces a game-theoretic approach called GTRADPMFC (Game-Theoretic Resource Allocation and Dynamic Pricing Mechanism in Fog Computing) to address resource allocation and dynamic pricing challenges in fog computing environments with limited resources. The proposed model features non-cooperative competition among fog nodes for resources and dynamic pricing mechanisms to encourage efficient resource utilization. Theoretical analysis and simulations demonstrate that GTRADPMFC improves resource efficiency and overall fog computing system performance. Additionally, the paper discusses how to handle situations with insufficient samples and provide flexibility for users unable to meet completion time requirements. GTRADPMFC effectively manages resource allocation by establishing pricing in fog computing, considering potential delays in completion time. This is achieved through research, simulations, convergence analysis, complexity evaluation, and optimization guarantees.

In real-world scenarios, identifying the optimal number of clusters in a dataset is a difficult task due to insufficient knowledge. Therefore, the indispensability of sophisticated automatic clustering algorithms for this purpose has been contemplated by some researchers. Several automatic clustering algorithms assisted by quantum-inspired metaheuristics have been developed in recent years. However, the literature lacks definitive documentation of the state-of-the-art quantum-inspired metaheuristic algorithms for automatically clustering datasets. This article presents a brief overview of the automatic clustering process to establish the importance of making the clustering process automatic. The fundamental concepts of the quantum computing paradigm are also presented to highlight the utility of quantum-inspired algorithms. This article thoroughly analyses some algorithms employed to address the automatic clustering of various datasets. The reviewed algorithms were classified according to their main sources of inspiration. In addition, some representative works of each classification were chosen from the existing works. Thirty-six such prominent algorithms were further critically analysed based on their aims, used mechanisms, data specifications, merits and demerits. Comparative results based on the performance and optimal computational time are also presented to critically analyse the reviewed algorithms. As such, this article promises to provide a detailed analysis of the state-of-the-art quantum-inspired metaheuristic algorithms, while highlighting their merits and demerits.