The sustainability of low-power mobile sensors is severely challenged by their limited battery capacity, and while simultaneous wireless information and power transfer (SWIPT) is a promising solution, its efficiency suffers dramatically under the uncertainty inherent to mobile three-dimensional (3D) aerial-to-ground environments. This work addresses the critical need for robust and efficient SWIPT under dynamic uncertainty by proposing a novel sensing-assisted SWIPT framework based on a unique hybrid learning algorithm. Our approach first formulates a two-layer optimization problem that rigorously couples a sensing layer, characterized by the Posterior Cram´er-Rao Bound (PCRB), with a SWIPT resource allocation layer. For the sensing layer, the core novelty is a learning-based Kalman Filtering (KF) estimator that merges the interpretative stability of model-based filtering with the adaptive power of neural networks to learn complex, nonlinear mobility patterns. We then prove that minimizing the estimator’s unsupervised loss is mathematically equivalent to minimizing the PCRB, ensuring convergence to optimal sensing without ground-truth supervision. This high-fidelity state information drives a decision-making learning model that adaptively optimizes beamforming, transmit power, and power splitting for the SWIPT resource allocation layer, forming a closed-loop hybrid learning system that continuously reinforces sensing and SWIPT performance. Extensive simulations demonstrate that our framework significantly outperforms benchmark methods in sensing accuracy, communication rate, and energy harvesting, validating its effectiveness in dynamic mobile environments.

Mobile edge computing (MEC) servers integrated with multi‐unmanned aerial vehicles (multi‐UAVs) present a new system the multi‐UAV‐assisted MEC system. This system relies on the mobility of the UAVs to reduce the transmission distance between the servers and mobile users, thereby enhancing service quality and minimizing the overall energy consumption. Achieving optimal UAV deployment and precise task scheduling is crucial for improved coverage and service quality in this system. This problem is framed as a nonconvex optimization problem known as joint task scheduling and deployment optimization. Recently, an optimization technique based on a dual‐layer framework: Upper layer optimization and lower layer optimization have been proposed to tackle this problem and achieved superior performance compared to the alternative methods. In this framework, the lower layer was responsible for task scheduling optimization, while the upper layer was designed to assist in optimizing UAV deployment and thus achieving improved coverage and enhanced task scheduling for mobile users, thereby minimizing the total energy consumption. However, further refinement of upper layer optimization is needed to improve the deployment process. In this study, the upper layer undergoes enhancement through key modifications: First, random selection of the solutions is replaced with sequential selection to maintain the unique characteristics of each individual throughout the optimization process, fostering both exploration and exploitation. Second, a selection of recently reported metaheuristic algorithms, such as spider wasp optimizer (SWO), generalized normal distribution optimization (GNDO), and gradient‐based optimizer (GBO), are adapted to optimize UAV deployments. Both improved upper layer and lower layer optimization led to the development of novel, more effective optimization approaches, including IToGBOTaS, IToGNDOTaS, and IToSWOTaS. These techniques are evaluated using nine instances with a variety of mobile tasks ranging from 100 to 900 to test their stability and then compared to different optimization techniques to measure their effectiveness. This comparison is based on several statistical information to determine the superiority and difference between their outcomes. The results reveal that IToGBOTaS and IToSWOTaS exhibit slightly superior performance compared to all other algorithms, showcasing their competitiveness and efficacy in addressing the optimization challenges of the multi‐UAV‐assisted MEC system.

Whilst a majority of affective computing research focuses on inferring emotions, examining mood or understanding the mood-emotion interplay has received significantly less attention. Building on prior work, we (a) deduce and incorporate emotion-change ($\Delta$) information for inferring mood, without resorting to annotated labels, and (b) attempt mood prediction for long duration video clips, in alignment with the characterisation of mood. We generate the emotion-change ($\Delta$) labels via metric learning from a pre-trained Siamese Network, and use these in addition to mood labels for mood classification. Experiments evaluating unimodal (training only using mood labels) vs muttimodat (training using mood plus $\Delta$ labels) models show that mood prediction benefits from the incorporation of emotion-change information, emphasising the importance of modelling the moodemotion interplay for effective mood inference.

Continuous human affect estimation from video data entails modelling the dynamic emotional state from a sequence of facial images. Though multiple affective video databases exist, they are limited in terms of data and dy-namic annotations, as assigning continuous affective labels to video data is subjective, onerous and tedious. While studies have established the existence of signature facial expressions corresponding to the basic categorical emotions, individual differences in emoting facial expressions nevertheless exist; factoring out these idiosyncrasies is critical for effective emotion inference. This work explores continuous human affect recognition using AFEW-VA, an ‘in-the-wild’ video dataset with limited data, employing subject-independent (SI) and subject-dependent (SD) settings. The SI setting involves the use of training and test sets with mutually exclusive subjects, while training and test samples corresponding to the same subject can occur in the SD setting. A novel, dynamically-weighted loss function is employed with a Convolutional Neural Network (CNN)-Long Short- Term Memory (LSTM) architecture to optimise dynamic affect prediction. Superior prediction is achieved in the SD setting, as compared to the SI counterpart.

Whilst deep learning techniques have achieved excellent emotion prediction, they still require large amounts of labelled training data, which are (a) onerous and tedious to compile, and (b) prone to errors and biases. We propose Multi-Task Contrastive Learning for Affect Representation (MT-CLAR) for few-shot affect inference. MT-CLAR combines multi-task learning with a Siamese network trained via contrastive learning to infer from a pair of expressive facial images (a) the (dis)similarity between the facial expressions, and (b) the difference in valence and arousal levels of the two faces. We further extend the image-based MT-CLAR framework for automated video labelling where, given one or a few labelled video frames (termed support-set), MT-CLAR labels the remainder of the video for valence and arousal. Experiments are performed on the AFEW-VA dataset with multiple support-set configurations; moreover, supervised learning on representations learnt via MT-CLAR are used for valence, arousal and categorical emotion prediction on the AffectNet and AFEW-VA datasets. The results show that valence and arousal predictions via MT-CLAR are very comparable to the state-of-the-art (SOTA), and we significantly outperform SOTA with a support-set ≈6% the size of the video dataset.

The lack of a gold standard synergy quantification method for chemotherapeutic drug combinations warrants the consideration of different synergy metrics to develop efficient predictive models. Furthermore, neglecting combination sensitivity may lead to biased synergistic combinations, which are ineffective in cancer treatment. In this paper, we propose a deep learning-based model, SynPredict, which effectively predicts synergy in five synergy metrics together with the combination sensitivity score. SynPredict assesses the impact of multimodal fusion architectures of the input data, including the gene expression data of cancer cells, along with the representative chemical features of drugs in pairwise combinations. Both ONEIL and ALMANAC anticancer combination datasets are employed comparatively. The impact of the training datasets was more significant and consistent across most synergy models than input data fusion architectures. Synpredict outperforms the state-of-the-art predictive models, including DeepSynergy, AuDNN synergy, TranSynergy and DrugComb, with up to 74% decline in the mean square error. We highlight the pivotal need to consider a multiplex of synergy metrics and the combined sensitivity in the predictive models.

In this paper, a bi-directional long-short term memory (LSTM) based approach is proposed for the estimation of missing body parts in a human pose estimation context. Accurate human pose estimation is often a key component for accurate human action and activity recognition. The key idea of our algorithm is to learn the temporal consistencies of the human body poses between previous and subsequent frames. This helps in estimating missing body parts and improves the general smoothness of the pose detection results. The approach acts as a post-processing step after the application of any off-the-shelf body part detector and has been evaluated on the PoseTrack dataset for both validation and testing sequences. The results show consistent improvement in the detection across all body parts.

Current anomaly detection systems (ADSs) apply statistical and machine learning algorithms to discover zero-day attacks, but such algorithms are vulnerable to advanced persistent threat actors. In this paper, we propose an adversarial statistical learning mechanism for anomaly detection, outlier Dirichlet mixture-based ADS (ODM-ADS), which has three new capabilities. First, it can self-adapt against data poisoning attacks that inject malicious instances in the training phase for disrupting the learning process. Second, it establishes a statistical legitimate profile and considers variations from the baseline of the profile as anomalies using a proposed outlier function. Third, to deal with dynamic and large-scale networks such as Internet of Things and cloud and fog computing, we suggest a framework for deploying the mechanism as Software as a Service in the fog nodes. The fog enables the proposed mechanism to concurrently process streaming data at the edge of the network. The ODM-ADS mechanism is evaluated using both NSL-KDD and UNSW-NB15 datasets, whose findings indicate that ODM-ADS outperforms seven other peer algorithms in terms of accuracy, detection rates, false positive rates, and computational time.

Postural sway is a reflection of brain signals that are generated to control a person’s balance. During the process of ageing, the postural sway changes, which increases the likelihood of a fall. Thus far, expensive specialist equipment is required, such as a force plate, in order to detect such changes over time, which makes the process costly and impractical. Our long-term goal is to investigate the use of inexpensive, everyday video technology as an alternative. This paper describes a study that establishes a 3-way correlation between the clinical gold standard (force plate), a highly accurate multi-camera 3D video tracking system (Vicon) and a standard RGB video camera. To this end, a dataset of 18 subjects performing the BESS balance test on the force plate was recorded, while simultaneously recording the 3D Vicon data, and the RGB video camera data. Then, using Gaussian process regression and a recurrent neural network, models were built to predict the lateral postural sway in the force plate data from the RGB video data. The predicted results show high correlation with the actual force plate signals, which supports the hypothesis that lateral postural sway can be accurately predicted from video data alone. Detecting changes to a person’s postural sway can be used to improve elderly people’s life by monitoring the likelihood of a fall and detecting its increase well before a fall occurs, so that countermeasures (e.g. exercises) can be put in place to prevent falls occurring.

Several techniques have been proposed for human action recognition from videos. It has been observed that incorporating mid-level viz. human body and/or high-level information viz. pose estimation in the computation of low-level features viz. trajectories yields the best performance in action recognition where full body is presumed. However, in datasets with a large number of classes, where the full body may not be visible at all times, incorporating such mid- and high-level information is unexplored. Moreover, changes and developments in any stage will require a recompute of all low-level features. We decouple mid-level and low-level feature computation and study on benchmark action recognition datasets such as UCF50, UCF101 and HMDB51, containing the largest number of action classes to date. Further, we employ a part-based model for human body part detection in frames statically, thus also investigating classes where the full body is not present. We also track dense regions around the detected human body parts by Hungarian particle linking, thus minimising most of the wrongly detected body parts and enriching the mid-level information.

In this paper, an automatic approach for 3D pose reconstruction from a single image is proposed. The presence of human body articulation, hallucinated parts and cluttered background leads to ambiguity during the pose inference, which makes the problem non-trivial. Researchers have explored various methods based on motion and shading in order to reduce the ambiguity and reconstruct the 3D pose. The key idea of our algorithm is to impose both kinematic and orientation constraints. The former is imposed by projecting a 3D model onto the input image and pruning the parts, which are incompatible with the anthropomorphism. The latter is applied by creating synthetic views via regressing the input view to multiple oriented views. After applying the constraints, the 3D model is projected onto the initial and synthetic views, which further reduces the ambiguity. Finally, we borrow the direction of the unambiguous parts from the synthetic views to the initial one, which results in the 3D pose. Quantitative experiments are performed on the Human Eva-I dataset and qualitatively on unconstrained images from the Image Parse dataset. The results show the robustness of the proposed approach to accurately reconstruct the 3D pose form a single image.

Human pose estimation is a classic problem in computer vision. Statistical models based on part-based modelling and the pictorial structure framework have been widely used recently for articulated human pose estimation. However, the performance of these models has been limited due to the presence of self-occlusion. This paper presents a learning-based framework to automatically detect and recover self-occluded body parts. We learn two different models: one for detecting occluded parts in the upper body and another one for the lower body. To solve the key problem of knowing which parts are occluded, we construct Gaussian Process Regression (GPR) models to learn the parameters of the occluded body parts from their corresponding ground truth parameters. Using these models, the pictorial structure of the occluded parts in unseen images is automatically rectified. The proposed framework outperforms a state-of-the-art pictorial structure approach for human pose estimation on 3 different datasets.