Search

Colorectal cancer (CRC) is a prevalent and life-threatening malignancy, demanding early diagnosis and effective treatment for improved patient outcomes. Accurate segmentation of colon cancer in medical images is a challenging task due to the complexity of its morphology and limited annotated data availability. This paper presents an efficient approach for colon cancer segmentation and image synthesis, combining an Attention U-Net and Pix2Pix Generative Adversarial Network (Pix2Pix-GAN) guided by Sine Cosine Algorithm (SCA) for hyperparameter tuning within the GAN framework. The utilization of SCA plays a pivotal role in optimizing the delicate balance between generator and discriminator dynamics, resulting in enhanced convergence and stability. Our method achieved state-of-the-art results with a mean Dice score of 0.9514, mean Intersection over Union of 0.9123, F beta score of 0.9636, and similarity index of 0.9430 outperforming existing methods. Moreover, the Mean Absolute Error reached a minimal value of 0.01583. This proposed approach shows promise in enhancing the accuracy and robustness of colon cancer diagnosis and treatment which could lead to better diagnosis and treatment of colon cancer.

The field of low-resource sentiment analysis has seen significant developments in recent years. This research review SLR evaluates the approaches and data sources utilized in low-resource sentiment analysis by deep learning. The primary aim is to discover suitable approaches for future sentiment analysis in low-resource. Our studies explore various languages, models, and data sources expressing a desire to create effective approaches. Our emphasis lies in the critical evaluation of the approaches and the datasets utilized, to identify areas where further research is needed. Our analysis study adds to the existing body of literature reviews, encompassing multilingual low-resource sentiment analysis research spanning from 2018 to 2023. The findings indicate that the transfer learning approach is the most frequently used, followed by word embedding learning and machine translation systems. Additionally, the study shows that social media is the most used platform for data collection, followed by product reviews, movies, and hotels. There has been a significant surge in the adoption of pre-trained transformers, indicating a growing interest in exploring the potential of these models for low-resource languages within the natural language processing (NLP) community. This trend is largely attributed to the novel nature of these models and their feature of being non-labour intensive. However, the scarcity of annotated datasets for such languages remains a major hurdle. finally, these research findings are relevant and informative for any researcher working in the field of low-resource multilingual sentiment analysis. The study introduces a conceptual framework for performing sentiment analysis in low-resource. The study provides a valuable resource for future researchers.

Energy is of paramount importance for the world, and it is a fundamental driver of economic growth and development. Industries, businesses, and households rely on energy for even a small task. Due to its high demand, a significant portion of the global population still lacks access to reliable and affordable energy sources. Many industries and sectors continue to waste significant amounts of energy through inefficiencies. While energy is essential, the production and consumption of energy can have significant environmental consequences. Predicting power usage can help to significantly improve energy efficiency, reduce costs, enhance grid reliability, and minimize the environmental impact of energy consumption. In this work, a novel model named, the Optimized Multi-level Multi-type Ensemble (OMME) Forecasting Model is presented to estimate the power consumption. The proposed model was applied to the data set of total power consumption recorded in Austria at each hour after the pre-processing. The model applied bootstrapping at level 1 and a hybrid ensemble at level 2. Both ensemble methods utilized different algorithms for time series forecasting including ARIMA, Exponential smoothing, LSTM, GRU, and MLP. The parameters were tuned using Bayesian and Tabu search optimization. Different experiments were conducted for day and night usage separately. The proposed model was able to estimate the power usage with an error of 22%. This work also learned the most suitable technique for power consumption time series. GRU performed very well in different experiments and gave the forecast with 12% error. Distribution graphs of the OMME prediction further validate the integrity of the results.

The novelty of Federated Learning (FL) has emerged as a promising alternative to centralized machine learning systems in the context of anomaly-based intrusion detection systems (AIDS) deployed on Internet of Things (IoT) devices. Unlike traditional centralized models, FL allows on-device model training and updates, reducing privacy concerns and issues such as single points of failure and high false alarm rates (FAR). This approach, termed ‘Fed-AIDS,’ offers a more secure and efficient solution. However, the development of Fed-AIDS models faces challenges related to limited training data and the diverse nature of IoT datasets. Additionally, FL’s decentralized nature introduces weight divergence issues arising from non-Independently and Identically Distributed (non-IID) clients. To address these challenges and optimize Fed-AIDS modeling, interdisciplinary research efforts are vital. The primary objective of this study is to conduct an up-to-date review by adopting a Systematic Literature Review (SLR) approach to analyze existing studies of Fed-AIDS modeling procedures for IoT devices. Data from the published studies were retrieved from Scopus database, which covered major publishers such as IEEE, Elsevier and others. Specifically, our review conducted from the following Fed-AIDS perspectives: workflow and tools, training dataset, complexities of non-IID data in Fed-AIDS models, classification tasks, aggregation tasks, and model validation metrics. Based on the research findings, the study highlights a series of challenges and proposes potential solutions to stand in future research in Fed-AIDS modeling, aiming to advance the field of IoT device security.

In the context of Enhanced Remote Area Communications (ERAC), Radio over Fiber (RoF) technology plays a crucial role in extending reliable connectivity to underserved and remote areas. This paper explores the significance of fifth-generation (5G) Digital Predistortion (DPD) role in mitigating non-linearities in Radio over Fiber (RoF) systems for enhancing communication capabilities in remote regions. The seamless integration of RoF and 5G technologies requires robust linearization techniques to ensure high-quality signal transmission. In this paper, we propose and exhibit the effectiveness of a machine learning (ML)-based DPD method for linearizing next-generation Analog Radio over Fiber (A-RoF) links within the 5G landscape. The study investigates the use of an optimized recurrent neural network (ORNN) based DPD experimentally on a multiband 5G new radio (NR) A-RoF system while maintaining low complexity. The ORNN model is evaluated using flexible-waveform signals at 2.14 GHz and 5G NR signals at 10 GHz transmitted over a 10 km fiber length. The proposed ORNN-based machine learning approach is optimized and is compared with conventional generalized memory polynomial (GMP) model and canonical piecewise linearization (CPWL) methods in terms of Adjacent Channel Power Ratio (ACPR), Error Vector Magnitude (EVM), and in terms of computation complexity including, storage, time and memory consumption. The findings demonstrate that the proposed ORNN model reduces EVM to below 2% as compared to 12% for non-compensated cases while ACPR is reduced by 18 dBc, meeting 3GPP limits.