In the NFC application, the leakage of user privacy information is inevitable. A lightweight NFC authentication algorithm based on a modified hash function is proposed to ensure the security of user privacy informatio...
详细信息
Machine learning (ML), sensors networks, and Internet of Things (IoT) are the most important contributor in the newest revolution in the industry. It is going towards a fully automated industrial environment where all...
详细信息
Combining machine learning with multiple-input multiple-output (MIMO) antennas requires a careful approach that includes the latest advancements in wireless communication for 5G technology. This antenna is built using...
Combining machine learning with multiple-input multiple-output (MIMO) antennas requires a careful approach that includes the latest advancements in wireless communication for 5G technology. This antenna is built using Rogers 5880 material, known for its excellent high-frequency performance. It achieves a strong isolation level of 28 dB, which reduces interference between channels and improves signal clarity. The operative bandwidth ranges from 35.739 to 39.289 GHz, critical for high data rates in 5G while keeping a return loss of − 10 dB or better. The antenna has a maximum gain of 8.5 dB and an efficiency of 97.41%, meaning it effectively translates power into strong signals. Its small size of 21 mm × 21 mm makes it ideal for compact devices without sacrificing performance. This article explores methods for evaluating the antenna’s fitness for 5G, including advanced simulations and an RLC circuit model. We use the Advanced Design System (ADS) to create a detailed model and compare the results with CST Microwave Studio (CST MWS), directing on return loss metrics. After simulations, we apply regression machine learning techniques to improve predictive accuracy using a dataset from CST MWS. Among the tested methods, decision tree regression is particularly effective, providing accurate efficiency predictions. Overall, this antenna design is strong for modern 5G communication systems, ensuring reliable performance and advancing wireless connectivity.
Senior citizens consider the most significant part of aging to be the changes that occur to their bodies. For this reason, they avoid doing body exercises and therefore often prone to heart diseases, muscle disorders ...
详细信息
In the context of big data analytics, this study examines the use of algorithms based on deep learning for feature extraction. Traditional methods usually have trouble sifting through the complexity and volume of data...
In the context of big data analytics, this study examines the use of algorithms based on deep learning for feature extraction. Traditional methods usually have trouble sifting through the complexity and volume of data to find the important elements. We investigate the application of auto encoders, transformer-based models, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) to address this problem. Our comprehensive review of existing literature compares these deep learning techniques with traditional methods and highlights their adaptability to large-scale datasets. The efficacy and precision of these methodologies are demonstrated by empirical investigations conducted on authentic datasets across a range of disciplines, including but not limited to time-series analysis, picture identification, and natural language processing. Despite challenges like computational requirements and model interpretability, our findings indicate that deep learning-based feature extraction holds significant promise for enhancing big data analytics, leading to valuable insights and discoveries in various fields.
Hypertension is one of the most common diseases in Jordan. It is one of the main reasons of death among Jordanian adult citizens. Worldwide, nearly 13% of all deaths are due to Hypertension with nearly 8 million death...
详细信息
ISBN:
(数字)9798331540012
ISBN:
(纸本)9798331540029
Hypertension is one of the most common diseases in Jordan. It is one of the main reasons of death among Jordanian adult citizens. Worldwide, nearly 13% of all deaths are due to Hypertension with nearly 8 million deaths yearly. Hence, this research is interested in the early prediction of this disease among Jordanian people. To achieve this main objective, Machine Learning (ML) is utilized through a large number of classification models and considering five well-known evaluation metrics. These classification models have been trained on a primary dataset that has been collected for the purpose of the research. The results revealed that Random Forest, Random Committee, and MultilayerPerceptron are the best classification models to handle the task of the early prediction of Hypertension in Jordan.
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems are unable to achieve improved performance in cross-language settings. In this paper, we propose a Multimodal Dual Attention Tr...
详细信息
Energy optimization is critical in smart home systems and IoT networks, necessitating innovative models that reduce energy use. This research presents two Long Short-Term Memory (LSTM) network models for estimating ho...
详细信息
ISBN:
(数字)9798350379396
ISBN:
(纸本)9798350379402
Energy optimization is critical in smart home systems and IoT networks, necessitating innovative models that reduce energy use. This research presents two Long Short-Term Memory (LSTM) network models for estimating home power consumption using time-series data. The first model employs a standard LSTM technique with multivariate characteristics including global active power, voltage, and sub-metering variables. This technique strikes a balance between prediction accuracy and computing economy, making it ideal for resource-constrained applications. The second model provides an optimized version of the LSTM, which uses PyTorch and Ray Tune for hyperparameter optimization. The optimization focuses on tweaking learning rates, batch sizes, and LSTM layers to improve model accuracy and convergence speed. Using hyperparameter tuning, the Mean Squared Error (MSE) for global active power forecasts is decreased to 0.0018, proving its appropriateness for low-resource IoT systems. Both models are tested on a resampled real-world household electric power consumption dataset for effective training. The study emphasizes the advantages of multivariate time-series analysis and hyperparameter optimization, demonstrating that the optimized LSTM model can accurately predict energy consumption, enhance energy management in smart homes, and lower computing costs. Future work will look into combining more IoT data streams and real-world deployment for further improvement. The findings add to the expanding body of knowledge about energy optimization in IoT environments, addressing the crucial demand for effective, real-time energy management systems.
Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for...
详细信息
ISBN:
(数字)9798350373820
ISBN:
(纸本)9798350373837
Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians’ future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.
Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning oper...
Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.
暂无评论