This study integrates a hybrid approach to sentiment analysis in the area of medical texts (patient reviews) that merges lexical strategies with deep learning and machine learning models. Different methodologies are used, such as reviews annotated by SenticNet and Text Blob lexicons. and for extracting crucial features in which TF and TF-IDF are utilized. Lastly, classification tasks are performed using machine learning models and deep learning models, and models based on transformers such as Bio-BERT. Performance metrics are utilized to evaluate the effectiveness of this combined methodology. Experimental results demonstrate that hybridization of lexicon and a transformer-based medical learning model produces superior outcomes compared to using each method independently in sentiments finding. Text Blob exhibits impressive performance, achieving 97 percent accuracy with a hybrid of LSTM and CNN, and another medical transformer model is Bio-BERT, on a drug review dataset, with 95 percent accuracy in term frequency and the logistic regression model. TextBlob also attains 94 percent accuracy when paired with term frequency and the LSTM model, and 97 percent accuracy when combined with the Bio-BERT transformer-based model on a dataset sourced from tweets.
This work introduces a dynamic load-balancing algorithm called CHHO (Cuckoo Harris Hawks multiobjective optimization) applied to task scheduling in cloud environment. CHHO is a new hybrid method that combines Cuckoo Search Optimization (CSO) and Harris Hawks Optimization (HHO). This combination uses the strengths of both algorithms to address the complex issues of cloud task scheduling. Specifically, CHHO uses Cuckoo Search Optimization to widen the search area of Harris Hawks Optimization, aiming to improve factors such as cost, response time, and resource use. The CHHO algorithm improves system performance by increasing VM throughput, effectively distributing workloads across VMs and maintaining a balance among task priorities through dynamic adjustments in task waiting times. To test the performance of CHHO, the algorithm is implemented in the CloudSim environment. It is compared with existing load-balancing algorithms on various performance measures. Our simulation results clearly show that CHHO performs better than existing algorithms, providing a strong and efficient solution for load balancing in cloud computing. Introducing CHHO offers a significant advancement in the field, providing a dynamic and adaptable approach that improves cloud task scheduling and enhances the overall efficiency and effectiveness of cloud computing systems.
A knowledge graph is a structured representation of entities and their relationships, often used in biomedical domains to model complex interactions. Graph neural networks (GNNs), which utilize these graphs, are effective for predicting interactions missing in the knowledge graph. However, GNN lacks the ability to incorporate causal reasoning, which is crucial to biomedical applications. Additionally, they limit their ability to generalize to unseen data. In oncology, where treatment regimens are intricate and patient responses are highly variable, predicting adverse drug reactions (ADRs) is particularly difficult. Existing models fail to capture the indirect, high-granularity information needed for accurate ADR prediction. To address these challenges, we propose the Causality and Proximity-based Relational Multihead Attention Model (CPRMAM). This model leverages a knowledge graph of ADR-related cancer case studies and introduces a causal proximity vector to prioritize relevant relationships. By employing an inductive GNN approach, CPRMAM generalizes to unseen data, improving ADR prediction.
In natural language processing with text data, which forms the basis of the studies in the field of artificial intelligence, various studies such as semantics and natural language generation are carried out, especially the solution of classification problems. This study aims to analyze the effect of detected named entities on text classification performance to make the text preprocessing stage more effective. In order to reduce the analysis time and increase the performance, after the classical preprocessing stage, word filtering was performed with Named Entity Recognition according to the thresholds determined in the 5% and 10% ranges. Analysis was performed with various machine learning, deep-learning algorithms, Bidirectional Encoder Representations from Transformers (BERT), and the obtained results are discussed in the last part of the study. In the problem of classifying 50,000 news texts, 93% with a support vector machine (SVM) algorithm in statistical classification with machine learning, 87% with long short-term memory (LSTM), and 83% with BERT success was achieved. In the analyses performed with LSTM and BERT, although the model performances were numerically lower, it was observed that the semantic integrity was stronger in text classification and that the success increased in general after Named Entity Recognition (NER) filtering. Thus, it can be interpreted that the dataset that is passed through the NER filter according to the threshold values positively affects the model's success in terms of time and performance.
Federated learning offers a solution to privacy-related dilemmas of data centralization by maintaining a decentralized architecture, thereby enabling local devices to preserve their data while concurrently exchanging model parameters. Despite its promise, federated learning encounters substantial obstacles concerning data quality, which may arise from inherent biases, the presence of outliers, and the utilization of compromized devices. To mitigate these challenges, we advocate for the implementation of a server-side filtering methodology within federated learning, specifically tailored for regression-related problems. Based on this architecture, local devices train the model on their own data sets and then send the learned parameters to a central server. The server is then tasked with the filtration of erroneous contributions, thereby enhancing the overall accuracy of the model. This methodology is substantiated through the application of the mean squared error (MSE) metric, a widely recognized standard within regression analysis, thereby augmenting both the efficiency and dependability of the learning process while safeguarding user privacy, an essential component of federated learning.
Air pollution remains one of the most critical environmental challenges of the 21st century, with severe implications for public health and urban sustainability. To address the need for accurate and timely air quality forecasting, this study introduces DeepBiGRULSTM, a hybrid deep-learning framework that memory (LSTM) networks. The model leverages both real-time Nowcast and raw concentration values to enhance the reliability of short-term predictions. Using a comprehensive historical dataset from the U.S. Dhaka consulate, incorporating pollutant and meteorological variables, we benchmarked the proposed model against established architectures. such as GRU, LSTM, and Temporal BiGRULSTM consistently outperforms the baselines, achieving the lowest errors with an RMSE of 0.4976 on the training set and 0.7548 on the test set. A key contribution of this work is its integration into a mobile application, providing real-time air quality updates and early warnings across Bangladesh. Beyond forecasting, the system supports health advisory services and can inform public policy on environmental management. Overall, this research delivers a practical and high-precision framework for air quality monitoring, with direct relevance to sustainable urban development and public health protection.
Conventional machine-learning models face limitations in performing time-toevent analyses due to censoring issues. This study introduces a Deep Additive Weibull (DAW) model that utilizes deep learning techniques for the survival analysis of right-censored COVID-19 patient data. Also, we explore Shapley additive explanations (SHAP) as a method for "opening the black box" of the neural networks for survival analysis, specifically to estimate survival probabilities for each patient using an autoencoder-based network. The DAW model achieved a concordance index of 0.9699 for training and 0.89015 for testing. Our findings show that the DAW model effectively captures nonlinearities and complex interactions. We also assessed the impact of specific features on the model's prediction, providing valuable insights. Based on SHAP, the important features are pneumonia, diabetes, age, and immunosuppression. Moreover, we demonstrated that explainable machine learning (ML) can elucidate how models make predictions, which is crucial to increase trust and adopt innovative ML techniques in healthcare.
This is a preface for the special issue including extended versions of the selected papers submitted to 2ND INTERNATIONAL WORKSHOP ON MACHINE LEARNING AND QUANTUM COMPUTING APPLICATIONSIN MEDICINE AND PHYSICS.
The amount of information shared amongst different devices and the variety of novel methods of network crimes have exponentially increased in recent years because of the widespread use of the internet. Quick identification of all types of attacks would not be possible with conventional methods including firewalls, which focused on data filtering. Dealing with the timely recognition of these types of assaults is very successful for intrusion detection systems (IDS) grounded on ML algorithms. They can efficiently manage the enormous amount of data in order to identify any harmful behaviour. Every network activity is searched for any possibly dangerous activity using IDS based on machine learning. The main objective of the planned effort is to provide analytical analyses of such current intrusion detection systems. Furthermore, examined in this work are the useful data sets and several techniques already in use to develop an effective IDS using single, hybrid, and ensemble machine learning algorithms. The approaches in the literature have then been investigated under several criteria in line to provide a clear road and direction for the next projects that will be successful. Nowadays, companies of all kinds include an intrusion detection system (IDS), which inhibits cybercrime to protect the network, resources, and private data. Many strategies have been suggested and implemented up till now to prevent uncivil behaviour. Since machine learning (ML) approaches are successful, the proposed approach applied several ML models for the intrusion detection system. The CIC IOT 2023 Dataset is the one applied in this paper. Tested were several techniques including random forest, XG Boost, logistic regression, MLP model, and RNN. Following fine-tuning, the federated learning model using neural networks had the best accuracy—99.84%.
Nowadays, two technological trends, Federated Learning (FL) and Edge Computing (EC), are becoming more and more important and influential. FL is a distributed machine learning strategy that allows learning on distributed data. It primarily allows performing learning operations close to the user, where we can gather data. This approach lies in the EC domain, where the main goal is to move computation closer to the end user (e.g., from the centralized cloud). In our work, we apply the FL and EC in the context of network flow classification. We achieved an accuracy of 0.957 with the FL model, compared to 0.924 for the best local model. We achieved these results thanks to the federated averaging performed on neural network layers. To verify our approach, we executed all our experiments on a virtualized environment that emulates existing mid-scale EC network infrastructure, including limitations related to resource constraints on edge nodes.
Machine learning applications to high-throughput data in medicine-one of the biggest resources for understanding complex diseases-have been limited thus far. Here, we present a computational approach for assessing the intrinsic variability in the most prominent data type, transcriptomics data for disease cohorts. Our study looks at situations where multiple data sets for the same disease are available. We leverage concepts of network medicine to assess how the match between a biological network and a set of differentially expressed genes varies across different networks and experiments. Our results showed that different biological networks yielded markedly different results; also, the clustering of diseases depended strongly on the choice of the parameters that were contained in the data analysis and network processing.
In this article, we propose an enhancement to the computer forensics technique of using Machine-Learning tools to analyze the contents of RAM in order to extract information that is potentially useful during an investigation. In the specific case presented, the use of the extracted information to generate more-optimal dictionaries for dictionary cryptanalysis is considered. Increasing user awareness is making cryptanalysis of passwords increasingly difficult for law enforcement. Long and complex passwords are impossible to crack-even when high-performance computing platforms are available. A sensible method of optimization is to look for hints to use a dictionary that contains text phrases more likely to be used in the specific case under attack. Such a hint could be an analysis of RAM taken from a suspect computer. Machine-learning methods can significantly facilitate this task. In this article, we also explore the effectiveness of such an approach and its usefulness in practical applications. We also consider applications of the proposed approach for other purposes, such as OSINT.
The increased use of IoT devices in various domains generates abundant data traffic. Securing this data during its transfer and storage is essential. Blockchain is now a trending technology to provide security to the data; however, it is observed that blockchain performs poorly while managing large volume data. To mitigate this issue, an advanced Optchain method to reduce the data size before submitting it to the blockchain network is discussed in this paper. This Optchain method optimizes IoT-generated data using data-classification and compression techniques. The classification of data as relevant or irrelevant is based on predefined thresholds of critical healthcare parameters. Subsequently, the Optchain method employs the Z-standard algorithm for compressing only the relevant data, ensuring efficient storage and faster blockchain transactions. Simulation results using the iFogSim simulator and Ethereum blockchain demonstrated improved storage costs and computational times compared to traditional methods.
One of the major challenges of document images that can hinder readability and the analysis of information is low resolution; this is typically caused by low-pixel density scanning or excessive compression to save storage space. This results in a loss of fine detail in images, making it difficult to detect critical information. To solve these problems, super-resolution techniques are used. These techniques improve image quality by increasing the resolution while maintaining the fine detail. PSO-WESRGAN is an innovative method that combines wavelet processing, deep-transfer learning, and particle swarm optimization (PSO). Wavelet processing analyzes image detail at diverse scales and orientations, while transfer-based deep-learning advantages pre-trained models on vast image data sets. By integrating PSO, the efficiency of the method is enhanced through the optimal exploration of the solution space to identify the best parameters for the super-resolution model. The experimental results show the effectiveness of this method and open up prospects for future improvements in the super-resolution of document images.
Software engineering (SE) research often involves creating software-either as a primary research output (e.g., in design science research) or as a supporting tool for the traditional research process. Ensuring software quality is essential, as it influences both the research process and the credibility of findings. Integrating software-testing methods into SE research can streamline efforts by addressing the goals of both research and development processes simultaneously. This paper highlights the advantages of incorporating software testing in SE research-particularly for research evaluation. Through qualitative analysis of software artifacts and insights from two PhD projects, we present ten lessons learned. These experiences demonstrate that, when effectively integrated, software testing offers significant benefits for both the research process and its results.
This paper contributes to solving the low auto correlation binary sequence (LABS) problem that remains an open hard-optimization problem with many applications. The current direction of research is focused on developing algorithms dedicated to parallel architectures such as GPGPU or multi-core CPUs. The paper follows this direction and proposes new heuristics developed from the steepest-descent local search algorithm that extends the notion of a neighborhood of a given sequence. The introduced algorithms utilize the parallel nature of multicore CPUs and provide an effective method for solving the LABS problem. The efficiency levels of SDSL and the new algorithm are presented; to ensure an effective comparison, they were both implemented in the same manner. The comparison shows that exploring the larger neighborhood improves the efficiency of the search method.
In this article, we build a model for tsunami simulation based on physics-informed neural networks and the finite difference method. We then check how the numerical results obtained using these two methods differ from each other. Assuming that the finite difference method gives accurate results, we estimate the error resulting from the use of physics-informed neural networks. We compare this estimate with surveys conducted among computer science students in order to assess the level of public trust among specialists in the numerical results obtained using artificial intelligence tools. In particular, we assess how reliable tsunami predictions obtained using physics-informed neural networks are and what the public perception of the reliability of such predictions is.
Nowadays, two technological trends, Federated Learning (FL) and Edge Computing (EC), are increasingly important and influential. FL is a decentralized machine learning strategy that allows learning on distributed data. It primarily allows performing learning operations close to the user, where the data is gathered. This approach belongs to the EC domain, where the main goal is to move computation closer to the end user (e.g., from the centralized cloud). In our work, we apply the FL and EC in the context of network flow classification. We achieved an accuracy of 0.957 with the FL model, compared to 0.924 for the best local model. We achieved these results thanks to the federated averaging performed on neural network layers. To verify our approach, we executed all our experiments on a virtualized environment that emulates existing mid-scale EC network infrastructure, including limitations related to resource constraints on edge nodes.
Using the structures of large language models (LLMs) in creating knowledge graphs to understand more about the relationship between the entities of cognitive and biological sciences has become a hot research topic. Due to the great knowledge behind the curtain and the deep connections of this research, it is not possible to use the traditional approaches of machine learning and deep learning. In this study,the main goal is to create a comprehensive and integrated knowledge graph(KG) from the combination of three knowledge sources: Gene Ontology (GO), Disease Ontology (DO), and PharmKG. Large Language Models (LLMs) have been used to create this knowledge base. The main purpose of this KG is to understand the relationships between genes, diseases, and drugs. The proposed approach, GDPKG-LLM, has several key steps, including entity matching, similarity analysis, graph alignment, and using GPT-4. GDPKG-LLM was able to extract more than 16,800 nodes and 838,000 edges from these three knowledge bases and provide a rich KG. This graph provides meaningful relationships, making it a valuable resource for future research in personalized medicine and neuroscience. The reviewed evaluation criteria show the superiority of GDPKG-LLM, which strengthens the validity of this model.
Although several models for automatic text summarization exist, there are still limitations-like the anaphora problem that occurs during summarizations. To overcome such limitations, this paper proposes the Added dropout-Deleted Layer norm-Bidirectional Encoder Representations from Transformers (Ad-DL-BERT)-based extractive text summarization (ETS). Primarily, the input document's sentences are prepared for accurate summarization by pre-processing; then, the unwanted sentences are removed. With the Auto encoding using the Topic Description and Several priors (ATDS) approach, any sentences under the same topic are clustered afterwards. Moreover, keywords for summarization are extracted with an AnaphoraPOS (An-POS) extractor. For removing the redundant sentences, the rankings with Exponential Linear Unit-Generative Adversarial Network (ELU-GAN) and saliency score assignment processes are performed thereafter. Also, assignments for sentences are performed to enhance the coherency, sorting, and cosine-similarity score. Lastly, the Ad-DL-BERT-generated summary and the proposed technique's performance are evaluated on the document understanding conference (DUC2002) data set. Regarding the clustering time, execution time, recall-oriented understudy for the gisting evaluation (ROUGE-1) scores of recall, F-measure, and precision, the experimental outcomes exhibited the proposed technique's dominance over the conventional approaches.
