Input Requirements Research Articles

Magnetite addition reduces nitrite requirement for efficient anaerobic ammonium oxidation by facilitating mutualism of ANAMMOX and FEAMMOX bacteria

Partial nitrification (PN) is crucial for anaerobic ammonium oxidation (ANAMMOX), but faces challenges such as high energy demands and process control. Recent research has highlighted additives like magnetite as potential alternatives to conventional electron acceptors (O₂ and NO₂−) for enhancing ammonium (NH4+) oxidation with lower energy consumption. This study investigated the effect of adding 50 mg/L of magnetite to ANAMMOX reactors, resulting in improved nitrogen (N) removal efficiency. The magnetite-added ANAMMOX (M-ANA) reactor yielded N removal efficiencies of 71 %, 66 %, and 57 % for NH4+:NO2− molar ratios of 1:1.3, 1:0.8, and 1:0.5, respectively. The M-ANA reactor operated under a 0.5 mol lower NO2− concentration achieved similar performance to the control ANAMMOX (C-ANA) reactor operated with a theoretical amount of NO2−. Moreover, the M-ANA reactor showed the potential to remove NH4+ by 56 % without any NO2− supplementation. Metagenomic analysis showed that the addition of magnetite significantly improved the relative abundance of microorganisms involved in the FEAMMOX reaction, such as Fimbriimonas ginsengisoli and Pseudomonas stutzeri. It also facilitated positive mutualism between ANAMMOX and FEAMMOX reactions. In addition, M-ANA granules exhibited a dense and compact structure compared with C-ANA, and the presence of magnetite facilitated the formation of resilient granules. Notably, the useful protein (Heme C) concentration and specific microbial activity in the M-ANA reactor were 1.3 and 2.2 times higher than those in the C-ANA reactor. Overall, the results demonstrate that an appropriate amount of magnetite can enhance the N removal efficiency while reducing the energy input requirements and associated carbon emissions. These findings can guide the future development of carbon- and energy-neutral N removal processes.

Validation and Implementation of a Somatic-Only Tumor Exome for Routine Clinical Application

Next-generation sequencing-based genomic testing is standard of care for tumor workflows. However, its application across different institutions continues to be challenging given the diversity of needs and resource availability among different institutions globally. Moreover, the use of a variety of different panels, including those from a few individual genes to those involving hundreds of genes, results in a relatively skewed distribution of care for patients. It is imperative to obtain a higher level of standardization without having to be restricted to specific kits or requiring repeated validations, which are generally expensive. We show the validation and clinical implementation of the DH-CancerSeq assay, a tumor-only whole-exome-based sequencing assay with integrated informatics, while providing similar input requirements, sensitivity, and specificity to a previously validated targeted gene panel and maintaining similar turnaround times for patient care.

Classifying methods to quantify crop nitrogen input requirements

In this short communication, we propose a framework that classifies methods for estimating crop nitrogen (N) input requirements along two dimensions: short-term versus long-term and current versus optimal crop management practices. The four resulting quadrants provide different perspectives on modelling methods, each distinctive in handling soil N supply, mineral versus organic N sources, management and yield levels. For each quadrant, study examples and data requirements are provided. We emphasise the importance of accurate and purpose-oriented selection of crop N requirement modelling methods and acknowledge the complexity and uncertainties inherent in N modelling, often due to a lack of data availability. The choice of methods to estimate N inputs strongly impacts model outcomes and conclusions, affecting agricultural practices, advisories, and policy strategies. Therefore, a decision tree is presented to support choices in assessing N input requirements so that models can help identify under and over-fertilisation hotspots, maintain soil fertility, and optimise crop yields, contributing to environmental protection and food security goals.

Augmenting Radiological Diagnostics with AI for Tuberculosis and COVID-19 Disease Detection: Deep Learning Detection of Chest Radiographs.

In this research, we introduce a network that can identify pneumonia, COVID-19, and tuberculosis using X-ray images of patients' chests. The study emphasizes tuberculosis, COVID-19, and healthy lung conditions, discussing how advanced neural networks, like VGG16 and ResNet50, can improve the detection of lung issues from images. To prepare the images for the model's input requirements, we enhanced them through data augmentation techniques for training purposes. We evaluated the model's performance by analyzing the precision, recall, and F1 scores across training, validation, and testing datasets. The results show that the ResNet50 model outperformed VGG16 with accuracy and resilience. It displayed superior ROC AUC values in both validation and test scenarios. Particularly impressive were ResNet50's precision and recall rates, nearing 0.99 for all conditions in the test set. On the hand, VGG16 also performed well during testing-detecting tuberculosis with a precision of 0.99 and a recall of 0.93. Our study highlights the performance of our deep learning method by showcasing the effectiveness of ResNet50 over traditional approaches like VGG16. This progress utilizes methods to enhance classification accuracy by augmenting data and balancing them. This positions our approach as an advancement in using state-of-the-art deep learning applications in imaging. By enhancing the accuracy and reliability of diagnosing ailments such as COVID-19 and tuberculosis, our models have the potential to transform care and treatment strategies, highlighting their role in clinical diagnostics.

Pollination services in the North China Plain measured using buckwheat sentinel plants; is there a deficit?

The transition of food systems for healthy diets and sustainable food systems calls for greater production of fruit and nuts, i.e. pollinated crops. The North China Plain (NCP) is a cereal dominated area that needs to transition to a more sustainable food system with a nutritionally more diverse output. Buckwheat pairs high nutritional quality with low input requirement, but it is pollination dependent. There is little knowledge on the pollinator communities and pollination service in the NCP. We selected Quzhou county as a study region on the NCP, and used potted plants of buckwheat (Fagopyrum esculentum M.) to measure pollination in three treatments: insect exclusion, open pollination, and honeybee supplementation. Measurements were made at 24 sites across the county in 2021 and 2022. At each site, we directly observed the activity of flower-visiting insects and measured the pollination rate, seed set, seed abortion rate and yield-related indicators. Most flower visits were made by hoverflies (Syrphidae) and flies from the families Muscidae, Sarcophagidae, and Calliphoridae. Compared with open pollination, insect exclusion reduced buckwheat pollination rate and seed set by more than 90 %. Without honeybee supplementation, the pollination rate in different experimental sessions was reduced by 12–21 %, and the seed set was reduced by 22–33 %. Honeybee supplementation increased harvest index and seed weight per plant with factors of 1.6 and 2.0, respectively. Hence, a pollination deficit would exist if only natural pollinators were relied upon. Managed honeybees provide an efficient means for enhancing pollination of buckwheat in the North China Plain.

Self-Powered Acceleration Sensor for Distance Prediction via Triboelectrification.

Accurately predicting the distance an object will travel to its destination is very important in various sports. Acceleration sensors as a means of real-time monitoring are gaining increasing attention in sports. Due to the low energy output and power density of Triboelectric Nanogenerators (TENGs), recent efforts have focused on developing various acceleration sensors. However, these sensors suffer from significant drawbacks, including large size, high complexity, high power input requirements, and high cost. Here, we described a portable and cost-effective real-time refreshable strategy design comprising a series of individually addressable and controllable units based on TENGs embedded in a flexible substrate. This results in a highly sensitive, low-cost, and self-powered acceleration sensor. Putting, which accounts for nearly half of all strokes played, is obviously an important component of the golf game. The developed acceleration sensor has an accuracy controlled within 5%. The initial velocity and acceleration of the forward movement of a rolling golf ball after it is hit by a putter can be displayed, and the stopping distance is quickly calculated and predicted in about 7 s. This research demonstrates the application of the portable TENG-based acceleration sensor while paving the way for designing portable, cost-effective, scalable, and harmless ubiquitous self-powered acceleration sensors.

Multi-modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers.

Head and neck (HN) gross tumor volume (GTV) auto-segmentation is challenging due to the morphological complexity and low image contrast of targets. Multi-modality images, including computed tomography (CT) and positron emission tomography (PET), are used in the routine clinic to assist radiation oncologists for accurate GTV delineation. However, the availability of PET imaging may not always be guaranteed. To develop a deep learning segmentation framework for automated GTV delineation of HN cancers using a combination of PET/CT images, while addressing the challenge of missing PET data. Two datasets were included for this study: Dataset I: 524 (training) and 359 (testing) oropharyngeal cancer patients from different institutions with their PET/CT pairs provided by the HECKTOR Challenge; Dataset II: 90 HN patients(testing) from a local institution with their planning CT, PET/CT pairs. To handle potentially missing PET images, a model training strategy named the "Blank Channel" method was implemented. To simulate the absence of a PET image, a blank array with the same dimensions as the CT image was generated to meet the dual-channel input requirement of the deep learning model. During the model training process, the model was randomly presented with either a real PET/CT pair or a blank/CT pair. This allowed the model to learn the relationship between the CT image and the corresponding GTV delineation based on available modalities. As a result, our model had the ability to handle flexible inputs during prediction, making it suitable for cases where PET images are missing. To evaluate the performance of our proposed model, we trained it using training patients from Dataset I and tested it with Dataset II. We compared our model (Model 1) with two other models which were trained for specific modality segmentations: Model 2 trained with only CT images, and Model 3 trained with real PET/CT pairs. The performance of the models was evaluated using quantitative metrics, including Dice similarity coefficient (DSC), mean surface distance (MSD), and 95% Hausdorff Distance (HD95). In addition, we evaluated our Model 1 and Model 3 using the 359 test cases in Dataset I. Our proposed model(Model 1) achieved promising results for GTV auto-segmentation using PET/CT images, with the flexibility of missing PET images. Specifically, when assessed with only CT images in Dataset II, Model 1 achieved DSC of 0.56±0.16, MSD of 3.4±2.1mm, and HD95 of 13.9±7.6mm. When the PET images were included, the performance of our model was improved to DSC of 0.62±0.14, MSD of 2.8±1.7mm, and HD95 of 10.5±6.5mm. These results are comparable to those achieved by Model 2 and Model 3, illustrating Model 1's effectiveness in utilizing flexible input modalities. Further analysis using the test dataset from Dataset I showed that Model 1 achieved an average DSC of 0.77, surpassing the overall average DSC of 0.72 among all participants in the HECKTOR Challenge. We successfully refined a multi-modal segmentation tool for accurate GTV delineation for HN cancer. Our method addressed the issue of missing PET images by allowing flexible data input, thereby providing a practical solution for clinical settings where access to PET imaging may be limited.

An Economic Analysis of Market Acceptance and Performance of Rice Varieties Grown in Northern Telangana Zone

This study aims to conduct an economic analysis of market acceptance and performance of rice varieties grown in the Northern Telangana Zone, where diverse rice cultivars face cultivation and marketing challenges. The objectives are to identify and document rice cultivars released by PJTSAU, study technological attributes preferred by stakeholders, and document constraints faced by stakeholders. A purposive sampling technique was used to select 90 farmers, 30 traders, and 30 consumers, totaling 150 participants. Data were collected using well-developed schedules and analyzed using tabular analysis, Rice Preference Index (RPI), Garrett ranking technique, and other suitable methods. The results showed that Telangana Sona (RNR 15048) is highly favored for its long grain size, high head rice recovery, and strong market demand, despite its susceptibility to stem borer and higher fertilizer requirements. Pranahitha (JGL 11727) is appreciated for its good rice quality but faces significant challenges, including high susceptibility to lodging, pests, and diseases, and lower germination rates. Kunaram Rice-1 (KNM 733) showed acceptable profitability but struggled with low market demand, poor grain quality, and higher water requirements. The study concludes that while Telangana Sona excels in market appeal and profitability, Pranahitha and Kunaram Rice-1 need targeted interventions to overcome their specific constraints. Enhancing pest resistance, improving grain quality, and reducing input requirements are essential for optimizing the potential of these varieties. Addressing these challenges through improved management practices and technology adoption can significantly benefit farmers and boost the marketability of these paddy varieties.

A novel multi-criteria group decision making algorithm for enhancing supply chain efficiency under high uncertainty during crisis based on q-rung orthopair fuzzy information

In recent years, q-rung orthopair fuzzy sets (q-ROFSs) have been becoming gradually more advantageous in handling information with high uncertainty. Several multi-criteria group decision-making (MCGDM) algorithms under q-ROFS information have been proposed in literature and used to solve various real-life problems. However, several shortcomings of some existing MCGDM algorithms under certain circumstances also emerged which limit their applicability. To overcome these challenges and deal with information under high uncertainty more accurately and reasonably, we propose a novel MCGDM algorithm under q-ROF information, i.e., (q-ROF-MCGDM), that retains the advantages of currently available methods, but extend its applicability by introducing a new q-rung orthopair fuzzy weighted averaging aggregation operator (q-ROFWAAO) along with a new entropy measure. The proposed q-ROF-MCGDM algorithm involves the steps: firstly, the input requirement in terms of alternatives, criteria and expert evaluations are required. Secondly, aggregating expert opinions using weights and normalizing decision matrices, and finally, calculating entropy weights and aggregating overall evaluations for final prioritization. Further, new operational laws have been developed and several necessary properties of the proposed q-ROFWAAO are also proved. Moreover, a sensitivity and comparative analysis has been carried out for validity and effectiveness of the proposed q-ROF-MCGDM algorithm. The proposed q-ROF-MCGDM algorithm has been implemented to enhance the efficiency of the United Arab Emirates (UAE) food industry under high uncertainty during the recent crisis. Finally, an evaluation of identifying and prioritizing the most severe food SC disruptions and appropriate mitigation strategies under crisis is provided to demonstrate applicability of the proposed q-ROF-MCGDM algorithm, and the obtained real case results confirm its usefulness. Findings of the study offer valuable insights to both food industry researchers and managers in developing effective recovery strategies, mitigating risks, and improving overall efficiency to ensure the survival of food businesses during the crisis.

Effects of Heat and Drought Stress on Sustainable Agriculture and Future Food Security in Türkiye

This review investigates the effects of heat and drought stress on future food security of Turkish agriculture. Temperature average is expected to rise to 3.2°C at the end of the current century while annual precipitation will decline more than 10% in the west and south and rise by 20% in the north of Türkiye, implying that climate change will affect ecosystem sustainability. It is therefore crucial to develop strategies to mitigate and adapt to climate change such as adjusting the planting schedule, reduced tillage, fertiliser microdosing, pre-sowing seed treatment, and the application of growth promoting bacteria to improve tolerance to stress by comprehending how plants respond physiologically and biochemically under these stress conditions. Long-term heat stress may hinder photosynthetic electron transport, decreasing the plant's ability to make use of energy for photosynthesis. The immediate response of plants under drought stress involves closing stomatal openings to reduce water loss through stomatal conductance. Combined heat and drought stress have a greater adverse effect on plant development and production than their effects in isolation. Plant phenotyping can play a major role in “climate-proofing” Turkish agriculture through the identification and development of crop varities with improved prouctivity, climate resilience and input requirements. Digital agriculture will also improve the efficiency of Turkish agricultural systems as the adapt to a hotter drier climate. To ensure future food security and the viability of the agro-economic system in Türkiye steps must be taken to make Turkish agriculture more robust in preparation for the impacts of climate change.

Tumor reactive T cells from the cerebrospinal fluid of patients with leptomeningeal disease from melanoma.

2027 Background: Leptomeningeal disease (LMD) is a devastating complication from cancer, with a median survival of 6-8 weeks. The incidence of LMD is highest in melanoma (5-25%) carrying the worst prognosis. Adoptive cell therapy (ACT) using tumor-infiltrating lymphocytes (TILs) showed complete and durable responses in patients with advanced metastatic melanoma. CSF-derived T cell populations in LMD shift to more exhausted phenotypes compared to extracranial and brain metastases. Ex vivo large T cell expansion can overcome this shortfall, with adoptive T cell transfer representing a novel therapeutic approach to treat melanoma LMD (M-LMD). The goal of this study is to optimize rapid CSF-derived tumor reactive T cell expansion in M-LMD, and evaluate the immune microenvironment in CSF compared to peripheral immunity and anti-tumoral response. Methods: CSF was collected from M-LMD patients (n=6) via lumbar puncture or Ommaya. Cells were plated following established TIL culture protocols to determine optimal expansion conditions i.e.: 1) 6000 IU/mL IL-2, 2) IL-2+OKT3, 3) IL-2+anti-4-1BB agonistic antibody, 4) IL-2+IL-7+IL-15+IL-21, 5) IL-2+anti-CD3/CD28 human dynabeads, & 6) IL-2+anti-CD3/CD28/CD137 human dynabeads. After 4 weeks, T cells were propagated via rapid expansion protocol (REP) and phenotyped for CD4+ and CD8+ T cells with flow cytometry. T cells were co-cultured for 18-24 hours with HLA-matched melanoma cell lines to assess functionality, and IFN-y levels evaluated in supernatant. Ongoing studies are evaluating other biomarkers i.e., chemokines via Luminex. To examine the expanded TCR clonotypes, TCR beta seq was done in CSF-derived T cells at different times point of expansion and peripheral T cells. Results: Collected CSF yielded an average 8.12e4 viable cells for expansion (range 5e2-2.43e6). After initial culture in IL-2, 61.9% of samples showed increased cell yield with an average 101.68-fold expansion (range 2.35-1054). PreREP T cells were predominantly CD4+ (45.7%). REP was completed with a 100% success rate (mean 187.47-fold expansion). Post-REP flow cytometry analysis revealed similar results with further expansion of T cells. Additional culture supplements (Methods #2-6) produced similar expansion with a reduced T cell input requirement and demonstrated the potential to enrich for CD8+ T cells. M-LMD T cells were highly functional, producing substantial levels of IFN-y in response to HLA-matched melanoma cell lines. Anti-CD3/CD28 produced a larger expansion of T cells with higher levels of IFN-y. Preliminary TCR beta sequencing data revealed a distinct clonal distribution between peripheral and CSF-derived T cells. Conclusions: Therapies for LMD patients are desperately needed. Results demonstrate successful expansion of T cells ex vivo from CSF in M-LMD. Results raise potential to use autologous CSF-derived T cells as therapeutic strategy for patients with LMD.

WEBSITE KELURAHAN SOLOK SIPIN

The smallest government agency at village level is the sub-district office, which is an agency that handles population data processing, especially in the process of making family cards, birth certificates, death certificates, immigrant certificates and moving certificates. In terms of data processing, Kelurahan Solok Sipin still experiences several obstacles, resulting in a long time in making reports. To overcome this, a web-based application is needed to speed up or simplify work and data and provide information more quickly and accurately. This application aims to make it easier for sub-district officials to improve population data collection and reports. The input requirements are admin data, population data, family card data, transfer mutation data, migrant mutation data, and birth event data. For process requirements, namely population data processing, family card data processing, transfer and immigrant mutation data processing, and processing data on birth and death events. The output requirements are population data reports, family card data reports, migration transfer data reports, migrant mutation data reports, and birth event data reports. So the expected results in this research are wide accessibility, no installation required, and updates can be automatic.

Farmers’ Awareness of Millets in the Marathwada region

Historically, millets have been integral to diets, offering not only a plethora of health benefits but also contributing to environmental conservation through low water and input requirements. The International Year of Millets, declared by the United Nations for 2023 at the initiative of the Government of India, aims to raise awareness, increase production, and promote consumption of millets. This research explores the awareness and consumption of millets among the farmers of the Marathwada region. The study revealed that Great Millet and Pearl Millet garnered high awareness, while Little Millet, Proso Millet, and Kodo Millet exhibited lower awareness among the respondents. The data also showcased varying awareness of millet nutritional content, with 44.12 per cent having a medium overall awareness. Consumption behaviours unveiled diverse frequency patterns for different millets, with 40.91 per cent at a medium overall consumption level. Consumption patterns of the respondents depicted preferences for staple millet-based items. Reasons for consumption/non-consumption highlighted taste and health as major motivators. Respondents suggested measures like training programs, online resources, and awareness campaigns to boost millet usage. These findings provide a comprehensive understanding of the complex interplay between awareness, consumption patterns, and influencing factors, offering valuable insights for stakeholders aiming to promote millet adoption within communities.

Effects of Grain Sprout Fertilizer Application Rate on Yield and Its Composition of Hybrid Middle Rice–Ratoon Rice System

Enhancing yield and achieving environmental goals represent challenges for the future of agriculture. Rational nitrogen (N) management is one of the most promising ways to meet this challenge. However, complicated nitrogen management strategies and considerable input requirements still exist in rice–ratoon rice production. To address this issue, field experiments were conducted with two main high-yield rice crop genotypes and five fertilization treatments at six sites in Southwest China from 2018 to 2020. The results showed the following: (1) the yield of the main rice crop was extremely significantly affected by the year, location, and fertilization, but not by genotype; (2) the yield of the ratoon rice was extremely significantly affected by year, genotype, location, and fertilization; and (3) the total plant N content (TPN) and leaf SPAD value at the full heading stage of the main crop were significantly positively correlated with the total soil N content (TSN) and soil available N (SAN) content of the basic soil. The highly efficient N application rate of grain- and bud-promoting fertilizer for ratoon rice was 60–120 kg ha−1. The TSN, SAN, TPN, and SPAD values higher than 0.247 kg N kg−1, 298 mg N kg−1, 2.159 kg N kg−1, and 49.94 were, respectively, considered the reference values when not applying grain- and bud-promoting fertilizer. A regression equation was established to predict the amount of high-efficiency grain- and bud-promoting fertilizer based on the TSN and SPAD. Overall, the yield of rice–ratoon rice was significantly affected by year, genotype, location, fertilization, and their interactions. The use of the predicted grain- and bud-promoting fertilizer regression equation can achieve high yields under simplified and reduced N input practices in the rice–ratoon rice systems.

New methodology for the characterization of 3D model reconstructions to meet conditions of input data and requirements of downstream application

AbstractIn the field of 3D model reconstruction, manifold methods have been developed that derive CAD models from 3D scan data. Opposed to classical CAD modelling, where surface and solid modelling exist, a further diversification of modelling techniques is observed, caused by different methods to build up the geometry. This research introduces a new classification, the so-called Level of Complexities. It can be applied to the complete Reverse Engineering process chain and lays the foundation for further research on how to match requirements arising from all process steps and downstream applications.

Nanopore and Illumina sequencing reveal different viral populations from human gut samples.

The advent of viral metagenomics, or viromics, has improved our knowledge and understanding of global viral diversity. High-throughput sequencing technologies enable explorations of the ecological roles, contributions to host metabolism, and the influence of viruses in various environments, including the human intestinal microbiome. However, bacterial metagenomic studies frequently have the advantage. The adoption of advanced technologies like long-read sequencing has the potential to be transformative in refining viromics and metagenomics. Here, we examined the effectiveness of long-read and hybrid sequencing by comparing Illumina short-read and Oxford Nanopore Technology (ONT) long-read sequencing technologies and different assembly strategies on recovering viral genomes from human faecal samples. Our findings showed that if a single sequencing technology is to be chosen for virome analysis, Illumina is preferable due to its superior ability to recover fully resolved viral genomes and minimise erroneous genomes. While ONT assemblies were effective in recovering viral diversity, the challenges related to input requirements and the necessity for amplification made it less ideal as a standalone solution. However, using a combined, hybrid approach enabled a more authentic representation of viral diversity to be obtained within samples.

Design and Evaluation of a Robust CRISPR Kinetic Assay for Hot-Spot Genotyping.

Next-generation sequencing offers highly multiplexed and accurate detection of nucleic acid sequences but at the expense of complex workflows and high input requirements. The ease of use of CRISPR-Cas12 assays is attractive and may enable highly accurate detection of sequences implicated in, for example, cancer pathogenic variants. CRISPR assays often employ end-point measurements of Cas12 trans-cleavage activity after Cas12 activation by the target; however, end point-based methods can be limited in accuracy and robustness by arbitrary experimental choices. To overcome such limitations, we develop and demonstrate here an accurate assay targeting a mutation of the epidermal growth factor gene implicated in lung cancer (exon 19 deletion). The assay is based on characterizing the kinetics of Cas12 trans-cleavage to discriminate the mutant from wild-type targets. We performed extensive experiments (780 reactions) to calibrate key assay design parameters, including the guide RNA sequence, reporter sequence, reporter concentration, enzyme concentration, and DNA target type. Interestingly, we observed a competitive reaction between the target and reporter molecules that has important consequences for the design of CRISPR assays, which use preamplification to improve sensitivity. Finally, we demonstrate the assay on 18 tumor-extracted amplicons and 100 training iterations with 99% accuracy and discuss discrimination parameters and models to improve wild type versus mutant classification.

Wind Power Forecasting Based on CNN and LSTM Models

Nowadays more and more sustainable and environmentally friendly energy sources are demanded and wind power is playing an increasingly significant role in the energy market. For example, according to the Chinese Academy of Sciences, China plans to generate more than ten times the current scale of wind power in the next decade. Accurate prediction of wind generation is essential for the scheduling, operation, and energy trading of power systems. In this study, a method combining long and short-term memory network (LSTM) and convolutional neural network (CNN) is proposed for wind power generation prediction. In this study, a wind power generation data set from Longyuan Power Group is used to adapt to the input requirements of the model. The data are entered into the LSTM model to capture long-term trends in the data. Next, this paper uses the CNN to process the local spatial features to improve the prediction accuracy. Combining the outputs of these two models, this paper obtains an efficient wind power generation prediction method. In order to evaluate the performance of the proposed method, root mean square error is used to analyze the prediction data. The results show that the combined method of LSTM and CNN is better than individual methods in prediction accuracy and stability. In conclusion, this study proposes a wind power forecasting method combining LSTM and CNN. This method helps to improve the dispatching and operation efficiency of the power system and provides strong support for the promotion of wind power in the energy market.

Optimizing variable selection and neighbourhood size in the K-nearest neighbour algorithm

The K-nearest neighbour (KNN) algorithm is one of the well-known classifiers applied in various research areas. The input requirement includes a set of variables, the choice of the neighbourhood size (K) and the distance metric which are typically selected on experimenting with the data. The first two are usually decided sequentially in previous studies. This paper proposes a mixed integer linear program for simultaneous variable selection and determination of neighbourhood size which has not been expored in past research. When ties occur in the variable selection and/or the choice of K, an optimization approach helps search for the best combination of decisions for a given objective. Two distance metrics, Euclidean and Hassanat, are incorporated into the model for comparison. The proposed model adopts accuracy and recall as separate objective functions to determine the best combination of the two decisions in binary classification problems. Computational experiments are designed with ten publicly available datasets. Results from the proposed models are compared with the ensemble approach KNN using Hassanat distance. Three larger problems are also tested with the optimal K generated by the model. An effective set of variables and neighbourhood size decided by optimization can facilitate solving classification problems. Model limitations are also discussed.

Microsatellite Instability Detection in Cancer: A Multiplex qPCR Approach that Obviates the Need for Matching Normal Samples.

Microsatellite instability (MSI) indicates DNA mismatch repair deficiency in certain types of cancer, such as colorectal cancer. The current gold standard technique, PCR-capillary electrophoresis (CE), requires matching normal samples and specialized instrumentation. We developed VarTrace, a rapid and low-cost quantitative PCR (qPCR) assay, to evaluate MSI using solely the tumor sample DNA, obviating the requirement for matching normal samples. One hundred and one formalin-fixed paraffin-embedded (FFPE) tumor samples were tested using VarTrace and compared with the Promega OncoMate assay utilizing PCR-CE. Tumor percentage limit of detection was evaluated on contrived samples derived from clinical high MSI (MSI-H) samples. Analytical sensitivity, specificity, limit of detection, and input requirements were assessed using synthetic commercial reference standards. VarTrace successfully analyzed all 101 clinical FFPE samples, demonstrating 100% sensitivity and 98% specificity compared to OncoMate. It detected MSI-H with 97% accuracy down to 10% tumor. Analytical studies using synthetic samples showed a limit of detection of 5% variant allele frequency and a limit of input of 0.5 ng. This study validates VarTrace as a swift, accurate, and economical assay for MSI detection in samples with low tumor percentages without the need for matching normal DNA. VarTrace's capacity for highly sensitive MSI analysis holds potential for enhancing the efficiency of clinical work flows and broadening the availability of this test.