Explore the vast range of titles available.

Artificial Intelligence (Al) models are being produced and used to solve a variety of current and future business and technical problems. Therefore, AI model engineering processes, platforms, and products are acquiring special significance across industry verticals. For achieving deeper automation, the number of data features being used while generating highly promising and productive AI models is numerous, and hence the resulting AI models are bulky. Such heavyweight models consume a lot of computation, storage, networking, and energy resources. On the other side, increasingly, AI models are being deployed in IoT devices to ensure real-time knowledge discovery and dissemination. Real-time insights are of paramount importance in producing and releasing real-time and intelligent services and applications. Thus, edge intelligence through on-device data processing has laid down a stimulating foundation for real-time intelligent enterprises and environments. With these emerging requirements, the focus turned towards unearthing competent and cognitive techniques for maximally compressing huge AI models without sacrificing AI model performance. Therefore, AI researchers have come up with a number of powerful optimization techniques and tools to optimize AI models. This paper is to dig deep and describe all kinds of model optimization at different levels and layers. Having learned the optimization methods, this work has highlighted the importance of having an enabling AI model optimization framework.

Adaptive designs for clinical trials permit alterations to a study in response to accumulating data in order to make trials more flexible, ethical, and efficient. These benefits are achieved while preserving the integrity and validity of the trial, through the pre-specification and proper adjustment for the possible alterations during the course of the trial. Despite much research in the statistical literature highlighting the potential advantages of adaptive designs over traditional fixed designs, the uptake of such methods in clinical research has been slow. One major reason for this is that different adaptations to trial designs, as well as their advantages and limitations, remain unfamiliar to large parts of the clinical community. The aim of this paper is to clarify where adaptive designs can be used to address specific questions of scientific interest; we introduce the main features of adaptive designs and commonly used terminology, highlighting their utility and pitfalls, and illustrate their use through case studies of adaptive trials ranging from early-phase dose escalation to confirmatory phase III studies.

In this manuscript, we present a new class of highly efficient two-parameter optimal iterative methods for solving nonlinear systems that generalizes Ostrowski’s method, King’s Family, Chun’s method, and KLAM Family in multidimensional context. This class is an extension to systems of the Ermakov’s Hyperfamily. The fourth order of convergence of the members of the class is demonstrated, thus obtaining optimal schemes for solving nonlinear systems. The high efficiency of the elements of the class is studied, compared with other known methods of the same order or even higher, and some numerical proofs are presented. We also analyze its robustness.

Proximal gradient method has a major role in solving nonsmooth composite optimization problems. However, in some machine learning problems related to black-box optimization models, the proximal gradient method could not be leveraged as the derivation of explicit gradients are difficult or entirely infeasible. Several variants of zeroth-order (ZO) stochastic variance reduced such as ZO-SVRG and ZO-SPIDER algorithms have recently been studied for nonconvex optimization problems. However, almost all the existing ZO-type algorithms suffer from a slowdown and increase in function query complexities up to a small-degree polynomial of the problem size. In order to fill this void, we propose a new analysis for the stochastic gradient algorithm for optimizing nonconvex, nonsmooth finite-sum problems, called ZO-PSVRG+ and ZO-PSPIDER+. The main goal of this work is to present an analysis that brings the convergence analysis for ZO-PSVRG+ and ZO-PSPIDER+ into uniformity, recovering several existing convergence results for arbitrary minibatch sizes while improving the complexity of their ZO oracle and proximal oracle calls. We prove that the studied ZO algorithms under Polyak-Łojasiewicz condition in contrast to the existent ZO-type methods obtain a global linear convergence for a wide range of minibatch sizes when the iterate enters into a local PL region without restart and algorithmic modification. The current analysis in the literature is mainly limited to large minibatch sizes, rendering the existing methods unpractical for real-world problems due to limited computational capacity. In the empirical experiments for black-box models, we show that the new analysis provides superior performance and faster convergence to a solution of nonconvex nonsmooth problems compared to the existing ZO-type methods as they suffer from small-level stepsizes. As a byproduct, the proposed analysis is generic and can be exploited to the other variants of gradient-free variance reduction methods aiming to make them more efficient.

GeneXpert-based testing with Xpert MTB/RIF or Ultra assays is essential for tuberculosis diagnosis. However, testing may be affected by cartridge and staff shortages. More efficient testing strategies could help, especially during the coronavirus disease pandemic. We searched the literature to systematically review whether GeneXpert-based testing of pooled sputum samples achieves sensitivity and specificity similar to testing individual samples; this method could potentially save time and preserve the limited supply of cartridges. From 6 publications, we found 2-sample pools using Xpert MTB/RIF had 87.5% and 96.0% sensitivity (average sensitivity 94%; 95% CI 89.0%-98.0%) (2 studies). Four-sample pools averaged 91% sensitivity with Xpert MTB/RIF (2 studies) and 98% with Ultra (2 studies); combining >4 samples resulted in lower sensitivity. Two studies reported that pooling achieved 99%-100% specificity and 27%-31% in cartridge savings. Our results show that pooling may improve efficiency of GeneXpert-based testing.

By using the two distinct methods known as the exp ( - ϕ ( η ) ) and the E x p a -function methods, various forms of soliton solutions of the modified equal width wave equation (MEWE) with beta time derivative (BTD) are produced in this study. This model is used as a model in partial differential equations for the simulation of one-dimensional wave transmission in nonlinear media with dispersion processes. The obtained solutions are in the form of rational, trigonometry and hyperbolic trigonometry functions. Using Mathematica software, the resulting solitons are validated. Graphs are also used at the conclusion to explain the findings. These soliton solutions imply that these two methods are more dependable, simple and efficient than other methods. The findings can be used to explain how studious structures and other comparable non-linear physical structures are substantially understood. The obtained results are very helpful in the fields of optics, kinetics solid-state physics and hydro-magnetic waves in cold plasma.

Recently, significant advancements have been made in the field of efficient single-image super-resolution, primarily driven by the innovative concept of information distillation. This method adeptly leverages multi-level features to facilitate high-resolution image reconstruction, allowing for enhanced detail and clarity. However, many existing approaches predominantly emphasize the enhancement of distilled features, often overlooking the critical aspect of improving the feature extraction capabilities of the distillation module itself. In this paper, we address this limitation by introducing an asymmetric large-kernel convolution design. By increasing the size of the convolution kernel, we expand the receptive field, which enables the model to more effectively capture long-range dependencies among image pixels. This enhancement significantly improves the model's perceptual ability, leading to more accurate reconstructions. To maintain a manageable level of model complexity, we adopt a lightweight architecture that employs asymmetric convolution techniques. Building on this foundation, we propose the Lightweight Asymmetric Large Kernel Distillation Network (ALKDNet). Comprehensive experiments conducted on five widely recognized benchmark datasets-Set5, Set14, BSD100, Urban100, and Manga109-indicate that ALKDNet not only preserves efficiency but also demonstrates performance enhancements relative to existing super-resolution methods. The average PSNR and SSIM values show improvements of 0.10 dB and 0.0013, respectively, thereby achieving state-of-the art performance.

An important aspect of medical rehabilitation using exoskeletons is objective monitoring of the effectiveness of the exercise program. This control is most often manual and relies on the attention of a rehabilitation physician, but advanced rehabilitation systems also use computer vision technology. Topological skeletons generalize large areas of digital images, representing a virtual internal framework of the analyzed object. The patient and the exoskeleton are described either as a set of spatially disparate (but not explicitly related to either the patient or the exoskeleton) topological skeletons, or as branches of a single topological skeleton which does not allow for objective monitoring of joint displacements. A method to solve this problem for medical rehabilitation using an upper-limb exoskeleton is proposed. It includes the following stages: (I) identifying the exoskeleton, as well as upper and lower parts of the patient’s body; (II) independent construction of three topological skeletons (separately for the exoskeleton and for the upper and lower parts of the patient’s body); (III) their integration. This approach allows for accurate, real-time analysis of movements in the upper-limb joints and prompt notification to the rehabilitation physician of any significant deviations in the technique of performing prescribed exercises.

Human activity recognition (HAR), which is important in context awareness services, needs to occur continuously in daily life, owing to which an energy-efficient method is needed. However, because human activities have a longer cycle than HAR methods, which have analysis cycles of a few seconds, continuous classification of human activities using these methods is computationally and energy inefficient. Therefore, we propose segment-level change detection to identify activity change with very low computational complexity. Additionally, a fully convolutional network (FCN) with a high recognition rate is used to classify the activity only when activity change occurs. We compared the accuracy and energy consumption of the proposed method with that of a method based on a convolutional neural network (CNN) by using a public dataset on different embedded platforms. The experimental results showed that, although the recognition rate of the proposed FCN model is similar to that of the CNN model, the former requires only 10% of the network parameters of the CNN model. In addition, our experiments to measure the energy consumption on the embedded platforms showed that the proposed method uses as much as 6.5 times less energy than the CNN-based method when only HAR energy consumption is compared.

The development of an energy-efficient wireless sensor network is a difficult problem since batteries are used to energize the sensor nodes. In certain circumstances, charging a battery is extremely difficult or even impossible. If the heterogeneity of sensor nodes is not correctly used, it can result in unequal energy consumption and lowering network performance. By combining power control and data aggregation, clustering has the ability to reduce energy consumption and extend network life. Many routing methods have been suggested for network optimization, with a major focus on energy efficiency, network longevity, and clustering processes. We proposed the Adaptive Active Sleep Energy Efficient Method (AASEEM) for Wireless Sensor Networks (WSNs), which takes into account network heterogeneity. We examine and improve some difficulties including network stability and cluster head selection procedure. The principle of providing a detailed pairing among sensor nodes is used to maximize energy usage. The results of the simulations show that the suggested method improves network performance significantly and it might be a beneficial technique for WSNs.