To comprehend the genuine reading habits and preferences of diverse user cohorts and furnish tailored reading recommendations, this study introduces an English text reading recommendation model ...designed specifically for long-tail users. This model integrates collaborative filtering algorithms with the FastText classification method. Initially, the integrated collaborative filtering algorithm is explicated, followed by the calculation of the user's interest distribution across various types of English texts, achieved through an enhanced Ebbinghaus forgetting curve and analysis of user reading behaviors. Subsequently, an intelligent English text reading recommendation is generated by amalgamating collaborative filtering algorithms with association rule-based recommendation algorithms. Through optimization of the recommendation generation process, the model's recommendation accuracy is enhanced, thereby augmenting the performance and user satisfaction of the recommendation system. Finally, a comparative analysis is conducted with respect to the Top-N algorithm model, matrix factorization-based algorithm model, and FastText classification model, illustrating the superior recommendation accuracy and F-Measure value of the proposed model. The study findings indicate that when the recommendation list contains 10, 30, 50, and 70 texts, the recommendation accuracy of the proposed algorithm model is 0.75, 0.79, 0.8, and 0.74, respectively, outperforming other algorithms. Furthermore, as the number of texts increases, the F-Measure of all four models gradually improves, with the final F-Measure of the proposed model reaching 0.81. Notably, the F-Measure of the English text reading recommendation model proposed in this study significantly surpasses that of the other three recommendation methods. Demonstrating commendable performance in recall rate, root mean square error, normalized cumulative gain, precision, and accuracy, the model adeptly reflects user reading interests, thereby enhancing the accuracy of text recommendations and the overall system performance. The study findings offer crucial insights and guidance for enhancing the accuracy and overall efficacy of English text recommendation systems.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Electronic noses (e-noses) are instruments that can be used to measure gas samples conveniently. Based on the measured signal, the type and concentration of the gas can be predicted by pattern ...recognition algorithms. However, e-noses are often affected by influential factors, such as instrumental variation and time-varying drift. From the viewpoint of pattern recognition, the factors make the posterior distribution of the test data drift from that of the training data, thus will degrade the accuracy of the prediction models. In this paper, we propose drift correction autoencoder (DCAE) to address this problem. DCAE learns to model and correct the influential factors explicitly with the help of transfer samples. It generates drift-corrected and discriminative representation of the original data, which can then be applied to various prediction algorithms. We evaluate DCAE on data sets with instrumental variation and complex time-varying drift. Prediction models are trained on samples collected with one device or in the initial time period, then tested on other devices or time periods. Experimental results show that the DCAE outperforms typical drift correction algorithms and autoencoder-based transfer learning methods. It can improve the robustness of e-nose systems and greatly enhance their performance in real-world applications.
An improved nondominated sorting genetic algorithm-II (INSGA-II) has been proposed for optimal planning of multiple distributed generation (DG) units in this paper. First, multiobjective functions ...that take minimum line loss, minimum voltage deviation, and maximal voltage stability margin into consideration have been formed. Then, using the proposed INSGA-II algorithm to solve the multiobjective planning problem has been described in detail. The improved sorting strategy and the novel truncation strategy based on hierarchical agglomerative clustering are utilized to keep the diversity of population. In order to strengthen the global optimal searching capability, the mutation and recombination strategies in differential evolution are introduced to replace the original one. In addition, a tradeoff method based on fuzzy set theory is used to obtain the best compromise solution from the Pareto-optimal set. Finally, several experiments have been made on the IEEE 33-bus test case and multiple actual test cases with the consideration of multiple DG units. The feasibility and effectiveness of the proposed algorithm for optimal placement and sizing of DG in distribution systems have been proved.
Labeled medical imaging data is scarce and expensive to generate. To achieve generalizable deep learning models large amounts of data are needed. Standard data augmentation is a method to increase ...generalizability and is routinely performed. Generative adversarial networks offer a novel method for data augmentation. We evaluate the use of CycleGAN for data augmentation in CT segmentation tasks. Using a large image database we trained a CycleGAN to transform contrast CT images into non-contrast images. We then used the trained CycleGAN to augment our training using these synthetic non-contrast images. We compared the segmentation performance of a U-Net trained on the original dataset compared to a U-Net trained on the combined dataset of original data and synthetic non-contrast images. We further evaluated the U-Net segmentation performance on two separate datasets: The original contrast CT dataset on which segmentations were created and a second dataset from a different hospital containing only non-contrast CTs. We refer to these 2 separate datasets as the in-distribution and out-of-distribution datasets, respectively. We show that in several CT segmentation tasks performance is improved significantly, especially in out-of-distribution (noncontrast CT) data. For example, when training the model with standard augmentation techniques, performance of segmentation of the kidneys on out-of-distribution non-contrast images was dramatically lower than for in-distribution data (Dice score of 0.09 vs. 0.94 for out-of-distribution vs. in-distribution data, respectively, p < 0.001). When the kidney model was trained with CycleGAN augmentation techniques, the out-of-distribution (non-contrast) performance increased dramatically (from a Dice score of 0.09 to 0.66, p < 0.001). Improvements for the liver and spleen were smaller, from 0.86 to 0.89 and 0.65 to 0.69, respectively. We believe this method will be valuable to medical imaging researchers to reduce manual segmentation effort and cost in CT imaging.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
•The work introduces a novel semi-supervised approach to detect and diagnose faults for AHUs.•80% accuracy rate is reached using a training set with 8000 normal samples and only around 30 samples for ...each fault type.•This work addresses the tradeoff between the initial number of faulty samples and the final classification accuracy.•This work addresses the tradeoff between the initial number of faulty samples and the computational cost.•This work addresses the tradeoff between the threshold of confidently levels and the final classification accuracy.
Modern data-driven fault detection and diagnosis (FDD) techniques show impressive high diagnostic accuracy in recognizing various air handling units (AHUs) faults. Most existing data-driven FDD approaches simply adopt supervised machine learning techniques that presume the availability of a sufficient number of faulty training data samples. However, in real-world AHU FDD scenarios, the number of faulty training samples is not enough to support supervised learning methods, since faults are usually fixed within short periods of time. In this study, a semi-supervised learning FDD framework is proposed to deal with the above problem. By using the proposed framework, the training pool can be enriched by iteratively inserting confidently labeled testing samples, which mimics the scenario of detecting faults the earliest possible. Furthermore, the proposed framework can be easily extended with various kinds of state-of-art classifiers. Three important tradeoffs are observed through a series of experiments. With a reasonably small number of faulty training data samples available, the performance of the proposed semi-supervised learning technique is comparable to the classic supervised FDD methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Domain adaptation algorithms are useful when the distributions of the training and the test data are different. In this paper, we focus on the problem of instrumental variation and time-varying drift ...in the field of sensors and measurement, which can be viewed as discrete and continuous distributional change in the feature space. We propose maximum independence domain adaptation (MIDA) and semi-supervised MIDA to address this problem. Domain features are first defined to describe the background information of a sample, such as the device label and acquisition time. Then, MIDA learns a subspace which has maximum independence with the domain features, so as to reduce the interdomain discrepancy in distributions. A feature augmentation strategy is also designed to project samples according to their backgrounds so as to improve the adaptation. The proposed algorithms are flexible and fast. Their effectiveness is verified by experiments on synthetic datasets and four real-world ones on sensors, measurement, and computer vision. They can greatly enhance the practicability of sensor systems, as well as extend the application scope of existing domain adaptation algorithms by uniformly handling different kinds of distributional change.
The regulation of glycometabolism homeostasis is vital to maintain health and development of animal and humans; however, the molecular mechanisms by which organisms regulate the glucose metabolism ...homeostasis from a feeding state switching to a non-feeding state are not fully understood. Using the holometabolous lepidopteran insect Helicoverpa armigera, cotton bollworm, as a model, we revealed that the steroid hormone 20-hydroxyecdysone (20E) upregulated the expression of transcription factor Krüppel-like factor (identified as Klf15) to promote macroautophagy/autophagy, apoptosis and gluconeogenesis during metamorphosis. 20E via its nuclear receptor EcR upregulated Klf15 transcription in the fat body during metamorphosis. Knockdown of Klf15 using RNA interference delayed pupation and repressed autophagy and apoptosis of larval fat body during metamorphosis. KLF15 promoted autophagic flux and transiting to apoptosis. KLF15 bound to the KLF binding site (KLF bs) in the promoter of Atg8 (autophagy-related gene 8/LC3) to upregulate Atg8 expression. Knockdown Atg8 reduced free fatty acids (FFAs), glycerol, free amino acids (FAAs) and glucose levels. However, knockdown of Klf15 accumulated FFAs, glycerol, and FAAs. Glycolysis was switched to gluconeogenesis, trehalose and glycogen synthesis were changed to degradation during metamorphosis, which were accompanied by the variation of the related genes expression. KLF15 upregulated phosphoenolpyruvate carboxykinase (Pepck) expression by binding to KLF bs in the Pepck promoter for gluconeogenesis, which utilised FFAs, glycerol, and FAAs directly or indirectly to increase glucose in the hemolymph. Taken together, 20E via KLF15 integrated autophagy and gluconeogenesis by promoting autophagy-related and gluconeogenesis-related genes expression.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Multiplexing, one of the main trends in biosensors, aims to detect several analytes simultaneously by integrating miniature sensors on a chip. However, precisely depositing electrode materials and ...selective enzymes on distinct microelectrode arrays remains an obstacle to massively produced multiplexed sensors. Here, we report on a “drop-on-demand” inkjet printing process to fabricate multiplexed biosensors based on nanostructured conductive hydrogels in which the electrode material and several kinds of enzymes were printed on the electrode arrays one by one by employing a multinozzle inkjet system. The whole inkjet printing process can be finished within three rounds of printing and only one round of alignment. For a page of sensor arrays containing 96 working electrodes, the printing process took merely ∼5 min. The multiplexed assays can detect glucose, lactate, and triglycerides in real time with good selectivity and high sensitivity, and the results in phosphate buffer solutions and calibration serum samples are comparable. The inkjet printing process exhibited advantages of high efficiency and accuracy, which opens substantial possibilities for massive fabrication of integrated multiplexed biosensors for human health monitoring.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
Flexible and wearable electronic devices are emerging as the novel platform for portable
health monitoring, human–machine interaction, and some other electronic/optic
applications. Future development ...of human-friendly smart electronics relies on efficient
manufacturing and processing of advanced functional materials on flexible/stretchable
substrates with effective device integration. Inkjet printing, known as a highly efficient
solution-based printing and patterning technology with low-cost, high-quality, and
high-throughput advantages, suits large-scale fabrication of flexible and wearable
electronics. Over the years, researchers focused on high pattern resolution and uniformity
on flexible substrates for advanced electrical/optical performances by various inkjet
printing techniques. Different ink materials that can realize multiple functions have been
fully investigated for achieving favorable printability and desired interactions with the
substrates. Here, the most recently reported inkjet printing strategies, functional ink
materials, and diverse inkjet-printed wearable electronic devices for practical
applications (e.g., sensors, displays, transistors, and energy storage devices) are
summarized. An outlook on future challenges as well as opportunities of inkjet-printed
flexible and wearable electronics for research development and industrial
commercialization is also presented.
Altitudinal diversity of terrestrial plants has been widely studied, whereas little is known for the patterns of aquatic plants. Here, we used a standardised field dataset to quantify the altitudinal ...patterns in the diversity and structure of aquatic plant assemblages, as well as the relationships between diversity indices and environmental variables.
Large‐scale field investigations were carried out in 128 sites ranging from 2,280 to 5,020 m above sea level across the southern part of Qinghai‐Tibet Plateau, China. In total, 102 species of aquatic plants were recorded, belonging to 67 genera, 31 families. Five taxonomic, phylogenetic, and functional indices were calculated for each collection site. We firstly examined altitudinal patterns of these diversity indices, then quantified the variations of indices across water areas, water flow, and soil matrix, respectively. We also explored the relationships between diversity indices and environmental variables using redundancy and variance partitioning analysis, to detect the ecological variables that drove the diversity.
The results showed that taxonomic, phylogenetic, and functional diversity of aquatic plants decreased with increasing altitude. Net relatedness index of aquatic plants showed a hump pattern along the altitude gradient, with a peak around 3,800 m above sea level. There was no obvious trend in the net functional relatedness index of aquatic plants with altitude. Annual mean temperature was the most important variable associated with the taxonomic, phylogenetic, and functional diversity. Water area and water flow were significantly associated with functional structure, but not phylogenetic structure. Soil matrix also correlated with aquatic plant diversity.
A large‐scale altitudinal gradient can influence aquatic plant diversity. Environmental filtering and niche convergence might have played dominant roles in the increasing and decreasing stages of phylogenetic structure of aquatic plant assemblages, respectively, along the altitudinal gradient. Phylogenetic and functional structure of aquatic plant assemblages showed different patterns along the altitudinal gradient, and the environmental variables better explained the change of functional structure than did the phylogenetic variables.
This is the first comprehensive study on the species, phylogeny, and function of aquatic plant assemblages along a large‐scale altitudinal gradient. We found an altitudinal decline in the diversity of aquatic plants and different patterns in the phylogenetic and functional structures of aquatic plant assemblages. These findings indicate that functional traits have high phenotypic plasticity and are more affected by environments than phylogenetic relationships which are mainly shaped by evolutionary processes.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK