Sensors最新文献

Ensuring the security of picture data on a network presents considerable difficulties because of the requirement for conventional embedding systems, which ultimately leads to subpar performance. It poses a risk of unauthorized data acquisition and misuse. Moreover, the previous image security-based techniques faced several challenges, including high execution times. As a result, a novel framework called Graph Convolutional-Based Twofish Security (GCbTS) was introduced to secure the images used in healthcare. The medical data are gathered from the Kaggle site and included in the proposed architecture. Preprocessing is performed on the data inserted to remove noise, and the hash 1 value is computed. Using the generated key, these separated images are put through the encryption process to encrypt what they contain. Additionally, to verify the user's identity, the encrypted data calculates the hash 2 values contrasted alongside the hash 1 value. Following completion of the verification procedure, the data are restored to their original condition and made accessible to authorized individuals by decrypting them with the collective key. Additionally, to determine the effectiveness, the calculated results of the suggested model are connected to the operational copy, which depends on picture privacy.

To enhance the classification accuracy of lower limb movements, a fusion recognition model integrating a surface electromyography (sEMG)-based convolutional neural network, transformer encoder, and long short-term memory network (CNN-Transformer-LSTM, CNN-TL) was proposed in this study. By combining these advanced techniques, significant improvements in movement classification were achieved. Firstly, sEMG data were collected from 20 subjects as they performed four distinct gait movements: walking upstairs, walking downstairs, walking on a level surface, and squatting. Subsequently, the gathered sEMG data underwent preprocessing, with features extracted from both the time domain and frequency domain. These features were then used as inputs for the machine learning recognition model. Finally, based on the preprocessed sEMG data, the CNN-TL lower limb action recognition model was constructed. The performance of CNN-TL was then compared with that of the CNN, LSTM, and SVM models. The results demonstrated that the accuracy of the CNN-TL model in lower limb action recognition was 3.76%, 5.92%, and 14.92% higher than that of the CNN-LSTM, CNN, and SVM models, respectively, thereby proving its superior classification performance. An effective scheme for improving lower limb motor function in rehabilitation and assistance devices was thus provided.

Traffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely on fixed road network structures, failing to account for the dynamic spatial correlations that vary over time. To address this, we propose a Transformer-Enhanced Adaptive Graph Convolutional Network (TEA-GCN) that alternately learns temporal and spatial correlations in traffic data layer-by-layer. Specifically, we design an adaptive graph convolutional module to dynamically capture implicit road dependencies at different time levels and a local-global temporal attention module to simultaneously capture long-term and short-term temporal dependencies. Experimental results on two public traffic datasets demonstrate the effectiveness of the proposed model compared to other state-of-the-art traffic flow prediction methods.

Compared with discrete emotion space, image emotion analysis based on dimensional emotion space can more accurately represent fine-grained emotion. Meanwhile, this high-precision representation of emotion requires dimensional emotion prediction methods to sense and capture emotional information in images as accurately and richly as possible. However, the existing methods mainly focus on emotion recognition by extracting the emotional regions where salient objects are located while ignoring the joint influence of objects and background on emotion. Furthermore, in the existing literature, when fusing multi-level features, no consideration has been given to the varying contributions of features from different levels to emotional analysis, which makes it difficult to distinguish valuable and useless features and cannot improve the utilization of effective features. This paper proposes an image emotion prediction network named ARMNet. In ARMNet, a unified affective region extraction method that integrates eye fixation detection and attention detection is proposed to enhance the combined influence of objects and backgrounds. Additionally, the multi-level features are fused with the consideration of their different contributions through an improved channel attention mechanism. In comparison to the existing methods, experiments conducted on the CGnA10766 dataset demonstrate that the performance of valence and arousal, as measured by Mean Squared Error (MSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²), has improved by 4.74%, 3.53%, 3.62%, 1.93%, 6.29%, and 7.23%, respectively. Furthermore, the interpretability of the network is enhanced through the visualization of attention weights corresponding to emotional regions within the images.

Technologies for rapid and high-throughput separation of rare cells from large populations of other types of cells have recently attracted much attention in the field of bioengineering. Among the various cell separation technologies proposed in the past, dielectrophoresis has shown particular promise because of its preciseness of manipulation and noninvasiveness to cells. However, one drawback of dielectrophoresis devices is that their application of high voltage generates Joule heat that exposes the cells within the device to high temperatures. To further explore this problem, this study investigated the temperature field in a previously developed cell separation device in detail. The temperature rise at the bottom of the microfluidic channel in the device was measured using a micro-LIF method. Moreover, the thermofluidic behavior of the cell separation device was numerically investigated by adopting a heat generation model that takes the electric-field-dependent heat generation term into account in the energy equation. Under the operating conditions of the previously developed cell separation device, the experimentally obtained temperature rise in the device was approximately 20 °C, and the numerical simulation results generally agreed well. Next, parametric calculations were performed with changes in the flow rate of the cell sample solution and the solution conductivity, and a temperature increase of more than 40 °C was predicted. The results demonstrated that an increase in temperature within the cell separation device may have a significant impact on the physiological functions of the cells, depending on the operating conditions of the device.

Medical imaging plays a pivotal role in diagnostic medicine with technologies like Magnetic Resonance Imagining (MRI), Computed Tomography (CT), Positron Emission Tomography (PET), and ultrasound scans being widely used to assist radiologists and medical experts in reaching concrete diagnosis. Given the recent massive uplift in the storage and processing capabilities of computers, and the publicly available big data, Artificial Intelligence (AI) has also started contributing to improving diagnostic radiology. Edge computing devices and handheld gadgets can serve as useful tools to process medical data in remote areas with limited network and computational resources. In this research, the capabilities of multiple platforms are evaluated for the real-time deployment of diagnostic tools. MRI classification and segmentation applications developed in previous studies are used for testing the performance using different hardware and software configurations. Cost-benefit analysis is carried out using a workstation with a NVIDIA Graphics Processing Unit (GPU), Jetson Xavier NX, Raspberry Pi 4B, and Android phone, using MATLAB, Python, and Android Studio. The mean computational times for the classification app on the PC, Jetson Xavier NX, and Raspberry Pi are 1.2074, 3.7627, and 3.4747 s, respectively. On the low-cost Android phone, this time is observed to be 0.1068 s using the Dynamic Range Quantized TFLite version of the baseline model, with slight degradation in accuracy. For the segmentation app, the times are 1.8241, 5.2641, 6.2162, and 3.2023 s, respectively, when using JPEG inputs. The Jetson Xavier NX and Android phone stand out as the best platforms due to their compact size, fast inference times, and affordability.

Recent advancements in exoskeleton technology, both passive and active, are driven by the need to enhance human capabilities across various industries as well as the need to provide increased safety for the human worker. This review paper examines the sensors, actuators, mechanisms, design, and applications of passive and active exoskeletons, providing an in-depth analysis of various exoskeleton technologies. The main scope of this paper is to examine the recent developments in the exoskeleton developments and their applications in different fields and identify research opportunities in this field. The paper examines the exoskeletons used in various industries as well as research-level prototypes of both active and passive types. Further, it examines the commonly used sensors and actuators with their advantages and disadvantages applicable to different types of exoskeletons. Communication protocols used in different exoskeletons are also discussed with the challenges faced.

Using low-altitude platform stations (LAPSs) in the agricultural Internet of Things (IoT) enables the efficient and precise monitoring of vast and hard-to-reach areas, thereby enhancing crop management. By integrating edge computing servers into LAPSs, data can be processed directly at the edge in real time, significantly reducing latency and dependency on remote cloud servers. Motivated by these advancements, this paper explores the application of LAPSs and edge computing in the agricultural IoT. First, we introduce an LAPS-aided edge computing architecture for the agricultural IoT, in which each task is segmented into several interdependent subtasks for processing. Next, we formulate a total task processing delay minimization problem, taking into account constraints related to task dependency and priority, as well as equipment energy consumption. Then, by treating the task dependencies as directed acyclic graphs, a heuristic task processing algorithm with priority selection is developed to solve the formulated problem. Finally, the numerical results show that the proposed edge computing scheme outperforms state-of-the-art works and the local computing scheme in terms of the total task processing delay.

Large language models have demonstrated impressive capabilities in many domains. But they sometimes generate irrelevant or nonsensical text, or produce outputs that deviate from the provided input, an occurrence commonly referred to as hallucination. To mitigate this issue, we introduce a novel decoding method that incorporates both factual and hallucination prompts (DFHP). It applies contrastive decoding to highlight the disparity in output probabilities between factual prompts and hallucination prompts. Experiments on both multiple-choice and text generation tasks show that our approach significantly improves factual accuracy of large language models without additional training. On the TruthfulQA dataset, the DFHP method significantly improves factual accuracy of the LLaMA model, with an average improvement of 6.4% for the 7B, 13B, 30B, and 65B versions. Its high accuracy in factuality makes it an ideal choice for high reliability tasks like medical diagnosis and legal cases.

The weight of live pigs is directly related to their health, nutrition management, disease prevention and control, and the overall economic benefits to livestock enterprises. Direct weighing can induce stress responses in pigs, leading to decreased productivity. Therefore, modern livestock industries are increasingly turning to non-contact techniques for estimating pig weight, such as automated monitoring systems based on computer vision. These technologies provide continuous, real-time weight-monitoring data without disrupting the pigs' normal activities or causing stress, thereby enhancing breeding efficiency and management levels. Two methods of pig weight estimation based on image and point cloud data are comprehensively analyzed in this paper. We first analyze the advantages and disadvantages of the two methods and then discuss the main problems and challenges in the field of pig weight estimation technology. Finally, we predict the key research areas and development directions in the future.