Data in Brief最新文献

With the development of smart buildings, the risks of cyber-attacks against them have also increased. One of the popular and evolving protocols used for communication between devices in smart buildings, especially HVAC systems, is the BACnet protocol. Machine learning algorithms and neural networks require datasets of normal traffic and real attacks to develop intrusion detection (IDS) and prevention (IPS) systems that can detect anomalies and prevent attacks. Real traffic datasets for these networks are often unavailable due to confidentiality reasons. To address this, we propose a framework that uses existing real datasets and converts them into BACnet protocol network traffic with detailed network behaviour. In this method, a virtual machine is prepared for each controller based on real scenarios, and by creating a simulator for the controller on the virtual machine, real data previously collected under real conditions from existing datasets is injected into the network with the same date and time during the simulation. We performed three types of attacks, including Falsifying, Modifying, and covert channel attacks on the network. For covert channel attacks, the message was modelled in three forms: Plain text, hashed using SHA3-256, and encrypted using AES-256. Network traffic was recorded using Wireshark software in pcap format. The advantage of the generated dataset is that since we used real data, the data behaviour aligns with real conditions.

Effective data representation in machine learning and deep learning is paramount. For an algorithm or neural network to capture patterns in data and be able to make reliable predictions, the data must appropriately describe the problem domain. Although there exists much literature on data preprocessing for machine learning and data science applications, novel data representation methods for enhancing machine learning model performance remain highly absent within the literature. This dataset is a compilation of convolutional neural network model performance trained and tested on a wide range of numerical base representations of the MNIST and MNIST-C datasets. This performance data can be further analysed by the research community to uncover trends in model performance against the numerical base of its data. This dataset can be used to produce more research of the same nature, testing cross-base data encoding on machine learning training and testing data for a wide range of real-world applications.

Species of the Boehmeria genus have the potential to be natural medicines and have industrial fibre production uses. Many species of this genus are morphologically similar and are difficult to distinguish, especially when their morphology is distorted. This dataset includes sequence information of several DNA regions isolated from the genome of Boehmeria holosericea, namely ITS (from the nuclear genome), matK, trnL-trnF, trnH-psbA, and rpoC1 (from the chloroplast genome) and phylogenetic analysis results based on the isolated sequences. On the phylogenetic tree based on the matK gene sequence, B. holosericea is grouped with B. umbrosa, B. clidemioides, B. spicata, and B. macrophylla with a bootstrap coefficient of 100%. In the phylogenetic tree based on the trnH-psbA spacer region sequences, B. holosericea was grouped with B. clidemioides (a bootstrap coefficient of 96%). In the phylogenetic tree based on the rpoC1 gene sequences, B. holosericea was grouped with B. spicata (a bootstrap coefficient of 100%). In the phylogenetic tree based on the ITS region sequences, B. holosericea was grouped with B. macrophylla (a bootstrap coefficient of 73%), and based on the trnL-trnF spacer region, B. holosericea was grouped with B. pilociuscula (a bootstrap coefficient of 16%). Two genes, matK and rpoC1 and the trnH-psbA region from the chloroplast genome, are potential DNA barcode candidates that could aid in the species identification of B. holosericea. This dataset the first report on the ITS, matK, trnL-trnF, trnH-psbA, and rpoC1 sequences and the phylogeny of B. holosericea.

Accurate system health state prediction through deep learning requires extensive and varied data. However, real-world data scarcity poses a challenge for developing robust fault diagnosis models. This study introduces two extensive datasets, Aalto Shim Dataset and Aalto Gear Fault Dataset, collected under controlled laboratory conditions, aimed at advancing deep learning-based fault diagnosis. The datasets encompass a wide range of gear faults, including synthetic and realistic failure modes, replicated on a downsized azimuth thruster testbench equipped with multiple sensors. The data features various fault types and severities under different operating conditions. The comprehensive data collected, along with the methodologies for creating synthetic faults and replicating common gear failures, provide valuable resources for developing and testing intelligent fault diagnosis models, enhancing their generalization and robustness across diverse scenarios.

Solar energy has become the fastest growing renewable and alternative source of energy. However, there is little or no open-source datasets to advance research knowledge in photovoltaic related systems. The work presented in this article is a step towards deriving Photo-Voltaic Module Dataset (PVMD) of thermal images and ensuring they are publicly available. The work provides a PVMD dataset comprising a total of 1000 self-acquired and augmented images. The dataset includes both permanent and temporal anomalies, namely Hotspots, Cracks, and Shadings. The dataset was collected on September 5, 2024 at the Soshanguve South Campus, Tshwane University of Technology, South Africa using DJI Mavic 3 Thermal's high-resolution thermal and visual imaging capabilities. DJI Mavic 3 Thermal coupled with its advanced flight features makes it an excellent tool for precise and efficient inspections of PV systems. The laboratory experiment performed on the dataset lasted one week. The work aims to provide supervised dataset good enough to support research method in providing a comprehensive and efficient approach to monitoring and maintaining large PV systems. Extensive analysis of the thermal data reveals the anomalies as indicative of faults in the solar cells of PV module, thereby opening up advancement in solar energy research. Because the data comes from a single-day collection and one week laboratory experiment, it makes the data more suitable for testing algorithms designed for fault detection. The dataset is publicly and freely available to the scientific community at 10.17632/5ssmfpgrpc.1.

Anthropogenic activities (e.g., logging, gold-mining, agriculture, and uncontrolled urban expansion) threaten the forests in the southeast of the Peruvian Amazon, one of the most diverse ecosystems worldwide. However, gold-mining generates the most severe impacts on ecosystems and limits its resilience. The natural regeneration of degraded areas in the southeastern Peruvian Amazon have not been studied deeply. The dataset contains floristic inventories of previously uncharacterized or poorly studied secondary forests degraded and abandoned by goldmining activities and an intact forest in the Tres Islas indigenous community, Madre de Dios region, in southeastern Peru. The data presented was obtained from 12 plots (20 m × 60 m) established in three successional forests abandoned by gold mining and an intact forest (without mining impacts), where all trees with a stem diameter at breast height greater than 1 cm were inventoried. To the best of our knowledge, this is the only dataset in the southwest of the Peruvian Amazon that compares the natural colonization after gold-mining and intact forests. This dataset can be useful for long-term study and monitoring of structure and tree diversity in relatively understudied yet important secondary forests after gold-mining abandonment. Also, this dataset could be used to analyze the successional trajectory process of vegetation and the recovery of aboveground biomass. Furthermore, the data could be used to investigate the effects of functional traits and types of mining on vegetation recovery. Hence, understanding the successional processes will help to improve restoration, reforestation, or reclamation strategies for the recovery of degraded lands in the Amazon.