Assessing biodiversity is an important step in the study of microbial ecology associated with a given environment. Multiple indices have been used to quantify species diversity, which is a key biodiversity measure. Measuring species diversity of viruses in different environments remains a challenge relative to measuring the diversity of other microbial communities. Metagenomics has played an important role in elucidating viral diversity by conducting metavirome studies; however, metavirome data are of high complexity requiring robust data preprocessing and analysis methods. In this review, existing bioinformatics methods for measuring species diversity using metavirome data are categorised broadly as either sequence similarity-dependent methods or sequence similarity-independent methods. The former includes a comparison of DNA fragments or assemblies generated in the experiment against reference databases for quantifying species diversity, whereas estimates from the latter are independent of the knowledge of existing sequence data. Current methods and tools are discussed in detail, including their applications and limitations. Drawbacks of the state-of-the-art method are demonstrated through results from a simulation. In addition, alternative approaches are proposed to overcome the challenges in estimating species diversity measures using metavirome data.

In metagenomics, the separation of nucleotide sequences belonging to an individual or closely matched populations is termed binning. Binning helps the evaluation of underlying microbial population structure as well as the recovery of individual genomes from a sample of uncultivable microbial organisms. Both supervised and unsupervised learning methods have been employed in binning; however, characterizing a metagenomic sample containing multiple strains remains a significant challenge. In this study, we designed and implemented a new workflow, Coverage and composition based binning of Metagenomes (CoMet), for binning contigs in a single metagenomic sample. CoMet utilizes coverage values and the compositional features of metagenomic contigs. The binning strategy in CoMet includes the initial grouping of contigs in guanine-cytosine (GC) content-coverage space and refinement of bins in tetranucleotide frequencies space in a purely unsupervised manner. With CoMet, the clustering algorithm DBSCAN is employed for binning contigs. The performances of CoMet were compared against four existing approaches for binning a single metagenomic sample, including MaxBin, Metawatt, MyCC (default) and MyCC (coverage) using multiple datasets including a sample comprised of multiple strains. Binning methods based on both compositional features and coverages of contigs had higher performances than the method which is based only on compositional features of contigs. CoMet yielded higher or comparable precision in comparison to the existing binning methods on benchmark datasets of varying complexities. MyCC (coverage) had the highest ranking score in F1-score. However, the performances of CoMet were higher than MyCC (coverage) on the dataset containing multiple strains. Furthermore, CoMet recovered contigs of more species and was 18 - 39% higher in precision than the compared existing methods in discriminating species from the sample of multiple strains. CoMet resulted in higher precision than MyCC (default) and MyCC (coverage) on a real metagenome. The approach proposed with CoMet for binning contigs, improves the precision of binning while characterizing more species in a single metagenomic sample and in a sample containing multiple strains. The F1-scores obtained from different binning strategies vary with different datasets; however, CoMet yields the highest F1-score with a sample comprised of multiple strains.

Huge amount of data in the form of strings are being handled in bio-computing applications and searching algorithms are quite frequently used in them. Many methods utilizing on both software and hardware are being proposed to accelerate processing of such data. The typical hardware-based acceleration techniques either require special hardware such as generalpurpose graphics processing units (GPGPUs) or need building a new hardware such as an FPGA based design. On the other hard, software-based acceleration techniques are easier since they only require some changes in the software code or the software architecture. Typical software-based techniques make use of computers connected over a network, also known as a network grid to accelerate the processing. In this paper, we test the hypothesis that multi-core architectures should provide better performance in this kind of computation, but still it would depend on the algorithm selected as well as the programming model being utilized. We present the acceleration of a string-searching algorithm on a multi-core CPU via a POSIX thread based implementation. Our implementation on an 8-core processor (that supports 16-threads) resulted in 9x throughput improvement compared to a single thread implementation.

Microgrids, comprised of interconnected loads and distributed energy resources, function as single controllable entities with respect to the main grid. However, the inherent variability of distributed wind and solar generation within microgrids presents operational stability challenges concerning voltage regulation and frequency stability. Accurate forecasting of renewable generation is crucial for mitigating these challenges. This work proposes a one-dimensional Convolutional Neural Network (1-D CNN) based approach to forecast photovoltaic (PV) generation and wind energy, using data from the University of California, San Diego microgrid and San Diego Airport weather records. The proposed method is evaluated against various forecasting methods using key metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared value. Results show that the 1-D CNN model achieves an improvement of up to 229.8 times in MSE and a 24.47 fold improvement in MAE compared to baseline models that use traditional statistical methods in forecasting. This demonstrates the potential of machine learning for enhancing microgrid management, particularly in short-term forecasting of renewable generation.

Food sustainability is crucial aspect in achieving several United Nations (UN) Sustainable Development Goals (SDGs). By integrating advanced technologies for reliable and accurate decision-making, we can advance food sustainability and, consequently, make significant advances toward achieving the UN SDGs. Rice, a staple crop in many Asian and some African nations, is crucial to Sri Lanka as well. Serving as the primary food for most Sri Lankans, it plays a vital role in sustaining the livelihoods of over 1.8 million farmers. In Sri Lanka, rice is grown during two distinct seasons of the year (Yala and Maha). This study focuses on ML with feature engineering for rice yield prediction using weather data: Rainfall, Maximum temperature, Minimum temperature, and Radiation. The data from two districts in Yala and Maha seasons collected from 1982 to 2019 were used for evaluating two sets of models respectively. Data were pre-processed to handle the outliers and missing values and scaled using normalization. The machine learning models considered are Linear Regression (LR), Support Vector Machine (SVM), k-Nearest Neighbour (KNN), and Random Forest (RF). The performance of these models was evaluated using metrics: Root Mean Squared Error (RMSE), Relative Root Mean Squared Error (RRMSE), and Mean Absolute Error (MAE). The results demonstrate that Random Forest Regression with less number of features can yield comparable results compared to the original set of features.

Inspections and condition monitoring of the stormwater pipe networks have become increasingly crucial due to their vast geographical span and complex structure. Unmanaged pipelines present significant risks, such as water leakage and flooding, posing threats to urban infrastructure. However, only a small percentage of pipelines undergo annual inspections. The current practice of CCTV inspections is labor-intensive, time-consuming, and lacks consistency in judgment. Therefore, this study aims to propose a cost-effective and efficient semi-automated approach that integrates computer vision technology with Deep Learning (DL) algorithms. A DL model is developed using YOLOv8 with instance segmentation to identify six types of defects as described in Water Services Association (WSA) Code of Australia. CCTV footage from Banyule City Council was incorporated into the model, achieving a mean average precision (mAP@0.5) of 0.92 for bounding boxes and 0.90 for masks. A cost–benefit analysis is conducted to assess the economic viability of the proposed approach. Despite the high initial development costs, it was observed that the ongoing annual costs decreased by 50%. This model allowed for faster, more accurate, and consistent results, enabling the inspection of additional pipelines each year. This model serves as a tool for every local council to conduct condition monitoring assessments for stormwater pipeline work in Australia, ultimately enhancing resilient and safe infrastructure asset management.