Explore the vast range of titles available.

Crop monitoring focuses on detecting and identifying numerous crops within a limited region. A major challenge arises from the fact that the target crops are typically smaller in size compared to the image resolution, as seen in the case of rice plants. For instance, a rice plant may only span a few dozen pixels in an aerial image that comprises thousands to millions of pixels. This size discrepancy hinders the performance of standard detection methods. To overcome this challenge, our proposed solution includes a testing time grid cropping method to reduce the scale gap between rice plants and aerial images, a multi-scale prediction method for improved detection using cropped images based on varying scales, and a mean-NMS to prevent the potential exclusion of promising detected objects during the NMS stage. Furthermore, we introduce an efficient object detector, the Enhanced CSL-YOLO, to expedite the detection process. In a comparative analysis with two advanced models based on the public test set of the AI CUP 2021, our method demonstrated superior performance, achieving notable 4.6% and 2.2% increases in F1 score, showcasing impressive results.

This computational research seeks to classify unsolicited versus legitimate emails. A modified version of an existing genetic programming (GP) classifier—i.e., modified genetic programming (MGP)—is implemented to build an ensemble of classifiers to identify unsolicited emails.The proposed classifier is assessed using informative features extracted from two corpora (Enron and SpamAssassin) with the help of the greedy stepwise feature search method. Further, a comparative study is performed with other popular classifiers, such as Bayesian network, naïve Bayes, decision tree, random forest (RF), support vector machine (SVM), and GP. Further the results are validated with 20-fold cross-validation and paired T test. The results prove that the proposed classifier performs better in terms of accuracy and false-positive detection in comparison with the other machine learning classifiers tested in this study. Using different training and testing a set of email files from the Enron corpus, ensemble-based classifiers, such as boosted SVM, boosted Bayesian, boosted naïve Bayesian, RF, and the proposed MGP classifier, are tested and compared on all metrics, including training and testing time. The findings suggest that the MGP classifier with the greedy stepwise feature search method offers an improvement over alternative methods in detecting unsolicited emails.

Purpose The purpose of this paper is to present a novel method to estimate the optimal software testing time which minimizes the relevant expected software cost via a refined neural network approach with the grouped data, where the multi-stage look ahead prediction is carried out with a simple three-layer perceptron neural network with multiple outputs. Design/methodology/approach To analyze the software fault count data which follows a Poisson process with unknown mean value function, the authors transform the underlying Poisson count data to the Gaussian data by means of one of three data transformation methods, and predict the cost-optimal software testing time via a neural network. Findings In numerical examples with two actual software fault count data, the authors compare the neural network approach with the common non-homogeneous Poisson process-based software reliability growth models. It is shown that the proposed method could provide a more accurate and more flexible decision making than the common stochastic modeling approach. Originality/value It is shown that the neural network approach can be used to predict the optimal software testing time more accurately.

Many applications of machine-learning methods involve an iterative protocol in which data are collected, a model is trained, and then outputs of that model are used to choose what data to consider next. For example, a data-driven approach for designing proteins is to train a regression model to predict the fitness of protein sequences and then use it to propose new sequences believed to exhibit greater fitness than observed in the training data. Since validating designed sequences in the wet laboratory is typically costly, it is important to quantify the uncertainty in the model’s predictions. This is challenging because of a characteristic type of distribution shift between the training and test data that arises in the design setting—one in which the training and test data are statistically dependent, as the latter is chosen based on the former. Consequently, the model’s error on the test data—that is, the designed sequences—has an unknown and possibly complex relationship with its error on the training data. We introduce a method to construct confidence sets for predictions in such settings, which account for the dependence between the training and test data. The confidence sets we construct have finite-sample guarantees that hold for any regression model, even when it is used to choose the test-time input distribution. As a motivating use case, we use real datasets to demonstrate how our method quantifies uncertainty for the predicted fitness of designed proteins and can therefore be used to select design algorithms that achieve acceptable tradeoffs between high predicted fitness and low predictive uncertainty.

To further improve the accuracy of the power grid prediction, the paper proposes an improved binary tree classification algorithm with the SVM and predicts the real time power grid. Based on the basic principles of SVM, the common multi-classifier classification algorithm and its characteristics are summarized. Incorporating the advantages of existing classification algorithms, an improved binary tree classification algorithm was used, addressing the limitations of conventional methods. From the simulation results, it can be seen that the improved binary tree algorithm can shorten the test time from the original 0.285 seconds to 0.267 seconds, and the measured category can also be increased from the original 94.42 to 95.27. This shows that the improved binary tree can not only improve the practicability of the support vector machine algorithm, but also better improve the ability of real-time prediction of power grid.

Software reliability growth is observed by investing not only the testing-time but also the testing-effort in the testing-phase of software development process. If the testing-time (testing-effort) is reduced to some extent, it is possible to observe the software reliability growth by investing the amount of testing-effort (testing-time) which can compensate the insufficiency of the testing-time (testing-effort). However, most of the existing software reliability growth models (SRGMs) are constructed as univariate models and the substitutability between the testing-time and testing-effort is not considered. Additionally, it is necessary to remove many faults efficiently within the budget. In this paper, we develop bivariate Weibull type SRGMs under budget constraint based on the Cobb-Douglas type and CES (constant elasticity of substitution) type testing-time functions. Simultaneously, we evaluate the substitutability between the testing-time and testing-effort factors which are software reliability growth factors. Finally, we conduct the sensitivity analysis and show numerical examples by using actual data sets.

Online test-time adaptation (OTTA) is a more general method for accomplishing domain adaptation in real-world scenarios because it just needs a pre-trained source model to adapt the mini-batch target online. One popular approach is to adapt the model with empirical risk minimization using generated pseudo-labels. However, it can fail to learn optimal feature space due to the noisy pseudo-labels under domain shift. To address this restriction, we propose a novel online test-time adaptation technique called Confidence-guided Semantic-Enhanced Alignment (CSEA) that separates the mini-batch target into distinct subsets based on the pseudo-labels confidence and applies tailored constraints to each subset for reliable target structure mining. We first divide the mini-batch target data into confident and non-confident based on an online updated memory bank for each class. Then, we customize the alignment strategy to fit each subset best. Specifically, we propose a Re-weighted Local Clustering for the confident subset to learn the local semantic structure information of unlabeled target. Further, we propose a Semantic-enhanced Alignment that applied to the non-confident subset to guide the model to learn additional discriminative semantic knowledge. Extensive experiments on three OTTA benchmarks indicate effectiveness of the proposed CSEA.

In this paper, the total duration of different environmental stresses such as temperature, relative humidity, temperature change, and vibration under rated conditions are calculated according to the rated environmental load spectrum as the reference input condition for designing the accelerated test. The controller single-board reliability accelerated stress model is constructed by using the basic layer information of controller single-board components and the physical failure acceleration model of each sensitive environmental stress. The test conditions, such as equivalent total duration at high temperature and relative humidity, number of temperature cycles, test time per cycle, and acceleration factor, are determined. The board-level accelerated reliability test is designed with a mission profile and carried out to provide a technical solution for rapid evaluation of board-level reliability.

Open-domain Question Answering models that directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared with conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models fall short of the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate improved QA-pair models, we introduce (PAQ), a very large resource of 65M automatically generated QA-pairs. We introduce a new QA-pair retriever, RePAQ, to complement PAQ. We find that PAQ and test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. Using PAQ, we train CBQA models which outperform comparable baselines by 5%, but trail RePAQ by over 15%, indicating the effectiveness of explicit retrieval. RePAQ can be configured for size (under 500MB) or speed (over 1K questions per second) while retaining high accuracy. Lastly, we demonstrate RePAQ’s strength at , abstaining from answering when it is likely to be incorrect. This enables RePAQ to “back-off” to a more expensive state-of-the-art model, leading to a combined system which is both more accurate and 2x faster than the state-of-the-art model alone.

Deep learning (DL) has shown great success in many human-related tasks, which has led to its adoption in many computer vision based applications, such as security surveillance systems, autonomous vehicles and healthcare. Such safety-critical applications have to draw their path to success deployment once they have the capability to overcome safety-critical challenges. Among these challenges are the defense against or/and the detection of the adversarial examples (AEs). Adversaries can carefully craft small, often imperceptible, noise called perturbations to be added to the clean image to generate the AE. The aim of AE is to fool the DL model which makes it a potential risk for DL applications. Many test-time evasion attacks and countermeasures, i.e., defense or detection methods, are proposed in the literature. Moreover, few reviews and surveys were published and theoretically showed the taxonomy of the threats and the countermeasure methods with little focus in AE detection methods. In this paper, we focus on image classification task and attempt to provide a survey for detection methods of test-time evasion attacks on neural network classifiers. A detailed discussion for such methods is provided with experimental results for eight state-of-the-art detectors under different scenarios on four datasets. We also provide potential challenges and future perspectives for this research direction.