Precise anticipation of electrical demand holds crucial importance for the optimal operation of power systems and the effective management of energy markets within the domain of energy planning. This study builds on previous research focused on the application of artificial neural networks to achieve accurate electrical load forecasting. In this paper, an improved methodology is introduced, centering around bidirectional Long Short-Term Memory (LSTM) neural networks (NN). The primary aim of the proposed bidirectional LSTM network is to enhance predictive performance by capturing intricate temporal patterns and interdependencies within time series data. While conventional feed-forward neural networks are suitable for standalone data points, energy consumption data are characterized by sequential dependencies, necessitating the incorporation of memory-based concepts. The bidirectional LSTM model is designed to furnish the prediction framework with the capacity to assimilate and leverage information from both preceding and forthcoming time steps. This augmentation significantly bolsters predictive capabilities by encapsulating the contextual understanding of the data. Extensive testing of the bidirectional LSTM network is performed using multiple datasets, and the results demonstrate significant improvements in accuracy and predictive capabilities compared to the previous simpleRNN-based framework. The bidirectional LSTM successfully captures underlying patterns and dependencies in electrical load data, achieving superior performance as gauged by metrics such as root mean square error (RMSE) and mean absolute error (MAE). The proposed framework outperforms previous models, achieving a remarkable RMSE, attesting to its remarkable capacity to forecast impending load with precision. This extended study contributes to the field of electrical load prediction by leveraging bidirectional LSTM neural networks to enhance forecasting accuracy. Specifically, the BiLSTM’s MAE of 0.122 demonstrates remarkable accuracy, outperforming the RNN (0.163), LSTM (0.228), and GRU (0.165) by approximately 25%, 46%, and 26%, in the best variation of all networks, at the 24-h time step, while the BiLSTM’s RMSE of 0.022 is notably lower than that of the RNN (0.033), LSTM (0.055), and GRU (0.033), respectively. The findings highlight the significance of incorporating bidirectional memory and advanced neural network architectures for precise energy consumption prediction. The proposed bidirectional LSTM framework has the potential to facilitate more efficient energy planning and market management, supporting decision-making processes in power systems.

In the energy-planning sector, the precise prediction of electrical load is a critical matter for the functional operation of power systems and the efficient management of markets. Numerous forecasting platforms have been proposed in the literature to tackle this issue. This paper introduces an effective framework, coded in Python, that can forecast future electrical load based on hourly or daily load inputs. The framework utilizes a recurrent neural network model, consisting of two simpleRNN layers and a dense layer, and adopts the Adam optimizer and tanh loss function during the training process. Depending on the size of the input dataset, the proposed system can handle both short-term and medium-term load-forecasting categories. The network was extensively tested using multiple datasets, and the results were found to be highly promising. All variations of the network were able to capture the underlying patterns and achieved a small test error in terms of root mean square error and mean absolute error. Notably, the proposed framework outperformed more complex neural networks, with a root mean square error of 0.033, indicating a high degree of accuracy in predicting future load, due to its ability to capture data patterns and trends.

UAVs are widely used for multiple tasks, which in many cases require autonomous processing and decision making. This autonomous function often requires significant computational capabilities that cannot be integrated into the UAV due to weight or cost limitations, making the distribution of the workload and the combination of the results produced necessary. In this paper, a dual-stage processing architecture for object detection and tracking in Unmanned Aerial Vehicles (UAVs) is presented, focusing on efficient resource utilization and real-time performance. The proposed system delegates lightweight detection tasks to onboard hardware while offloading computationally intensive processes to a ground server. The UAV is equipped with a Raspberry Pi for onboard data processing, utilizing an Intel Neural Compute Stick 2 (NCS2) for accelerated object detection. Specifically, YOLOv5n is selected as the onboard model. The UAV transmits selected frames to the ground server, which handles advanced tracking, trajectory prediction, and target repositioning using state-of-the-art deep learning models. Communication between the UAV and the server is maintained through a high-speed Wi-Fi link, with a fallback to a 4G connection when needed. The ground server, equipped with an NVIDIA A40 GPU, employs YOLOv8x for object detection and DeepSORT for multi-object tracking. The proposed architecture ensures real-time tracking with minimal latency, making it suitable for mission-critical UAV applications such as surveillance and search and rescue. The results demonstrate the system’s robustness in various environments, highlighting its potential for effective object tracking under limited onboard computational resources. The system achieves recall and accuracy scores as high as 0.53 and 0.74, respectively, using the remote server, and is capable of re-identifying a significant portion of objects of interest lost by the onboard system, measured at approximately 70%.

Obtaining valuable clues for noncoding RNA (ribonucleic acid) subsequences remains a significant challenge, acknowledging that most of the human genome transcribes into noncoding RNA parts related to unknown biological operations. Capturing these clues relies on accurate “base pairing” prediction, also known as “RNA secondary structure prediction”. As COVID-19 is considered a severe global threat, the single-stranded SARS-CoV-2 virus reveals the importance of establishing an efficient RNA analysis toolkit. This work aimed to contribute to that by introducing a novel system committed to predicting RNA secondary structure patterns (i.e., RNA’s pseudoknots) that leverage syntactic pattern-recognition strategies. Having focused on the pseudoknot predictions, we formalized the secondary structure prediction of the RNA to be primarily a parsing and, secondly, an optimization problem. The proposed methodology addresses the problem of predicting pseudoknots of the first order (H-type). We introduce a context-free grammar (CFG) that affords enough expression power to recognize potential pseudoknot pattern. In addition, an alternative methodology of detecting possible pseudoknots is also implemented as well, using a brute-force algorithm. Any input sequence may highlight multiple potential folding patterns requiring a strict methodology to determine the single biologically realistic one. We conscripted a novel heuristic over the widely accepted notion of free-energy minimization to tackle such ambiguity in a performant way by utilizing each pattern’s context to unveil the most prominent pseudoknot pattern. The overall process features polynomial-time complexity, while its parallel implementation enhances the end performance, as proportional to the deployed hardware. The proposed methodology does succeed in predicting the core stems of any RNA pseudoknot of the test dataset by performing a 76.4% recall ratio. The methodology achieved a F1-score equal to 0.774 and MCC equal 0.543 in discovering all the stems of an RNA sequence, outperforming the particular task. Measurements were taken using a dataset of 262 RNA sequences establishing a performance speed of 1.31, 3.45, and 7.76 compared to three well-known platforms. The implementation source code is publicly available under knotify github repo.

The accurate “base pairing” in RNA molecules, which leads to the prediction of RNA secondary structures, is crucial in order to explain unknown biological operations. Recently, COVID-19, a widespread disease, has caused many deaths, affecting humanity in an unprecedented way. SARS-CoV-2, a single-stranded RNA virus, has shown the significance of analyzing these molecules and their structures. This paper aims to create a pioneering framework in the direction of predicting specific RNA structures, leveraging syntactic pattern recognition. The proposed framework, Knotify+, addresses the problem of predicting H-type pseudoknots, including bulges and internal loops, by featuring the power of context-free grammar (CFG). We combine the grammar’s advantages with maximum base pairing and minimum free energy to tackle this ambiguous task in a performant way. Specifically, our proposed methodology, Knotify+, outperforms state-of-the-art frameworks with regards to its accuracy in core stems prediction. Additionally, it performs more accurately in small sequences and presents a comparable accuracy rate in larger ones, while it requires a smaller execution time compared to well-known platforms. The Knotify+ source code and implementation details are available as a public repository on GitHub.

The observation and analysis of RNA molecules have proved crucial for the understanding of various processes in nature. Scientists have mined knowledge and drawn conclusions using experimental methods for decades. Leveraging advanced computational methods in recent years has led to fast and more accurate results in all areas of interest. One highly challenging task, in terms of RNA analysis, is the prediction of its structure, which provides valuable information about how it transforms and operates numerous significant tasks in organisms. In this paper, we focus on the prediction of the 2-D or secondary structure of RNA, specifically, on a rare but yet complex type of pseudoknot, the L-type pseudoknot, extending our previous framework specialized for H-type pseudoknots. We propose a grammar-based framework that predicts all possible L-type pseudoknots of a sequence in a reasonable response time, leveraging also the advantages of core biological principles, such as maximum base pairs and minimum free energy. In order to evaluate the effectiveness of our methodology, we assessed four performance metrics: precision; recall; Matthews correlation coefficient (MCC); and F1-score, which is the harmonic mean of precision and recall. Our methodology outperformed the other three well known methods in terms of Precision, with a score of 0.844, while other methodologies scored 0.500, 0.333, and 0.308. Regarding the F1-score, our platform scored 0.671, while other methodologies scored 0.661, 0.449, and 0.449. The proposed methodology surpassed all methods in terms of the MCC metric, achieving a score of 0.521. The proposed method was added to our RNA toolset, which aims to enhance the capabilities of biologists in the prediction of RNA motifs, including pseudoknots, and holds the potential to be applied in a multitude of biological domains, including gene therapy, drug design, and comprehending RNA functionality. Furthermore, the suggested approach can be employed in conjunction with other methodologies to enhance the precision of RNA structure prediction.