Journal of Ambient Intelligence and Humanized Computing最新文献

The significance of facial recognition in the era of artificial intelligence lies in its utilization of facial features as a type of biometric characteristic possessing uniqueness and irreversibility. However, exposing these features to attacks, tampering, or unauthorized disclosure poses considerable threats to user privacy and security. A privacy and security solution based on deep learning and encryption algorithms is proposed to tackle this issue. This solution employs the FaceNet deep learning algorithm to extract facial features efficiently. The combination of biometric feature blurriness and cryptographic system precision is achieved, utilizing the CKKS fully homomorphic encryption algorithm for operations in the ciphertext domain of facial recognition. The SM4 algorithm is used to enhance the resilience of facial feature ciphertext against malicious attacks. By leveraging the properties of symmetric ciphers, a balance is achieved between security and computational efficiency. The management of the symmetric key used in the SM4 algorithm is conducted through the employment of the SM9 asymmetric encryption algorithm. Experimental results and analysis demonstrate that the proposed solution enhances the security of data transmission, storage, and comparison without compromising the accuracy and efficiency of facial recognition.

Free Space Optical (FSO) is a wireless communication technology that is distinguished from other communication systems by several advantages including license free of operating spectrum, high data rate, low installation cost, and fast deployment. FSO is employed in many applications including Internet and mobile services links. Nevertheless, FSO link quality is affected by weather conditions including fog, rain, and snow. The main challenge of the FSO channel is the dynamic fluctuating of these weather conditions which degrade the link quality and reduces the data rate. Therefore, the development of robust FSO link topology is a crucial issue to overcome the bad and severe weather conditions. Cluster-based Wireless Sensor Network (WSN) arranges the network into groups called clusters where one Cluster Head (CH) is selected to manage the communication activities inside the group. CHs localization is the main challenge in cluster-based WSN. The key objective of this research is to develop cluster-based WSN that employs the FSO links to interconnect the CHs to each other. Optimal Cluster Head Localization (OCHL) algorithm is developed to optimally determined the locations of CHs so that the network diversity and coverage area of CHs are improved. Genetic Algorithm (GA) technique is used to obtain a near-optimal solution for the proposed fitness function. Simulation results show that the proposed OCHL algorithm improves the network diversity and coverage area of cluster-based WSN. The weighting parameter of the proposed fitness function can be adjusted to control the effects of covered areas, and link diversity in the fitness function. Additionally, increasing the number of CHs leads to improve the covered area and link diversity. Furthermore, with growing of the number of GA iterations, a better solution for the proposed optimization problem is obtained. Moreover, the Bit Error Rate and Signal to Noise Ratio of FSO links are evaluated based on the rain rate, snow rate, fog, transmitted power, transmitter and receiver aperture diameters, FSO communication range, and weighting parameter. The results demonstrate that the normalized covered area in case of using the proposed OCHL algorithm outperforms as compared to NFCA and LEACH algorithms with 12.95 and 8.52% rise, respectively. In addition, the proposed OCHL algorithm enhances the normalized link diversity by 14.15 and 19.21%, compared with NFCA and LEACH algorithms, respectively.

In the competitive landscape of the telecom sector, a Communication Service Provider's success hinges on its ability to offer compelling mobile plans tailored to diverse customer needs. This not only boosts company profits but also enhances metrics like average revenue per user (ARPU), customer lifecycle value, and reduces customer churn. Striking a balance between these objectives presents a formidable task. To address this challenge, we propose a novel approach called Genetic Algorithm Mobile Plan Generation (GA-MPG). The proposed method stands out for its deterministic approach that equally focuses on minimizing customer churn. This is done by providing them with the best-suited plans without making them pay extra for features they would use. The efficient mobile plan generation using GA-MPG is accomplished by the combination of the AdaBoost classifier and the Fuzzy model. The AdaBoost is utilized for feasible mobile plan generation and predicting the optimal solution amongst the various plans. Additionally, a fuzzy model recommends personalized plans based on customers' typical service usage. This also maximizes company profits, contrasting with existing strategies employed by various telecom companies which focus on one of the two problems. The proposed GA-MPG algorithm demonstrated promising results on a prominent US-based telecom dataset encompassing around 7000 customers, with a substantial 44% reduction in customer churn. These findings are based on the simulation results. The algorithm also shows improvements of 13% and 18% in ARPU and company profit, respectively, over a defined period.

Machine translation has revolutionized the field of language translation in the last decade. Initially dominated by statistical models, the rise of deep learning techniques has led to neural networks, particularly Transformer models, taking the lead. These models have demonstrated exceptional performance in natural language processing tasks, surpassing traditional sequence-to-sequence models like RNN, GRU, and LSTM. With advantages like better handling of long-range dependencies and requiring less training time, the NLP community has shifted towards using Transformers for sequence-to-sequence tasks. In this work, we leverage the sequence-to-sequence transformer model to translate Urdu (a low resourced language) to English. Our model is based on a variant of transformer with some changes as activation dropout, attention dropout and final layer normalization. We have used four different datasets (UMC005, Tanzil, The Wire, and PIB) from two categories (religious and news) to train our model. The achieved results demonstrated that the model’s performance and quality of translation varied depending on the dataset used for fine-tuning. Our designed model has out performed the baseline models with 23.9 BLEU, 0.46 chrf, 0.44 METEOR and 60.75 TER scores. The enhanced performance attributes to meticulous parameter tuning, encompassing modifications in architecture and optimization techniques. Comprehensive parametric details regarding model configurations and optimizations are provided to elucidate the distinctiveness of our approach and how it surpasses prior works. We provide source code via GitHub for future studies.

The keyboard, a major mean of interaction between human and internet devices, should beset right for good performance during authentication task. To guarantee that one legitimate user can interleave or simultaneously interact with two or more devices with protecting user privacy, it is essential to build device adaptation free-text keystroke dynamics authentication (free-KDA) model based on multi-teacher knowledge distillation methods. Some multi-teacher knowledge distillation methods have shown effective in C-way classification task. However, it is unreasonable for free-KDA model, since free-KDA model is one-class classification task. Instead of using soft-label to capture useful knowledge of source for target device, we propose a device adaptation free-KDA model. When one user builds the authentication model for target device with limited training samples, we propose a novel optimization objective by decreasing the distance discrepancy in Euclidean distance and cosine similarity between source and target device. And then, we adopt an adaptive confidence gate strategy to solve different correlation for each user between different source devices and target device. It is verified on two keystroke datasets with different types of keyboards, and compared its performance with the existing dominant multi-teacher knowledge distillation methods. Extensive experimental results demonstrate that AUC of target device reaches up to 95.17%, which is 15.28% superior to state-of-the-art multi-teacher knowledge distillation methods.

Covid-19 infection influenced the screening test rate of breast cancer worldwide due to the quarantine measures, routine procedures reduction, and delay of early diagnosis, causing high mortality risk and severity of the disease. X-ray mammography is the gold standard for diagnosing early signs of breast cancer, and Artificial Intelligence enables the detection of suspicious lesions and classifying them in terms of malignancy. This paper aimed to investigate mass detection and classification in a large-scale OPTIMAM dataset with 6000 cases and extracted 3524 images with masses in the mammograms of the Hologic manufacturer. The methodology of the detection step is to train the RetinaNet architecture of ResNet50, ResNet101, and ResNet152 backbones with three types of initializations by ImageNet and COCO weights and from scratch. The dataset was pre-processed to generate two types of input with entire mammograms and patches, which are stated as the first and the second approaches. The results show that in the first approach, RetinaNet of ResNet50 backbone with ImageNet and COCO weights and ResNet152 with the same weights performed 0.91 True Positive Rate at 0.78 False Positive Per Image, respectively. In contrast, in the second approach, ResNet152 with ImageNet weights reached 0.88 TPR at 0.78 FPPI. In the classification step, the Transfer Learning approach was applied with fine-tuning by adding L2-regularization and class weights to balance class distribution in the datasets.

Driver’s mental stress is known as a prime factor in road crashes. The devastation of these crashes often results in losses of humans, vehicles, and infrastructure. Likewise, persistent mental stress could develop mental, cardiovascular, and abdominal disorders. Preceding research in this domain mostly focuses on feature engineering and conventional machine learning (ML) approaches. These approaches recognize different stress levels based on handcrafted features extracted from various modalities including physiological, physical, and contextual data. Acquiring the good quality features from these modalities using feature engineering is often a difficult job. The recent developments in the form of deep learning (DL) algorithms have relieved feature engineering by automatically extracting and learning resilient features. Conventional DL models, however, frequently over-fit due to large number of parameters. Thus, large networks face gradient vanishing issues causing an increase in learning failure and generalization errors. Furthermore, it is often hard to acquire a large dataset for training a deep learning model from scratch. To overcome these problems for driver’s stress recognition domain, this paper proposes fast and computationally efficient deep transfer learning models based on Xception pre-trained neural networks. These models classify the driver’s Low, Medium, and High stress levels through electrocardiogram (ECG), heart rate (HR), galvanic skin response (GSR), electromyogram (EMG), and respiration (RESP) signals. Continuous Wavelet Transform (CWT) acquires the scalograms for ECG, HR, GSR, EMG, and RESP signals separately. Then unimodal Xception models are trained based on these scalograms to classify the three stress levels. The proposed Xception models have achieved 97.2%, 86.4%, 82.7%, 71.9%, and 68.9% average validation accuracies based on ECG, RESP, HR, GSR, and EMG signals, respectively. The fuzzy EDAS (evaluation based on distance from average solution) approach also evaluates the performance of proposed models based on accuracy, recall, precision, F-score, and specificity. For the driver’s three stress levels, fuzzy EDAS performance estimation shows that the proposed ECG, RESP, and HR based Xception models achieved 1st, 2nd, and 3rd positions, respectively.

The Mixed Radial Basis Function Neural Network (MRBFNN) is an artificial neural network that employs Radial Basis Functions (RBFs) as activation functions in its hidden layer. The number of neurons in the hidden layer and the choice of RBF functions used in these neurons significantly affect the convergence of MRBFNN learning algorithms and impact the overall performance of neural networks. This article presents a nonlinear optimization model and an algorithm to select an appropriate architecture and learning strategy for MRBFNN. To approximate the solution of our model, we utilized an algorithm based on Particle Swarm Optimization (PSO) techniques. We will apply our approach in Medical Diseases Diagnosis (MDD). The numerical results obtained demonstrate the effectiveness of the proposed theoretical approach and underscore the advantages of the new modeling methodology.

At present, there are some problems in strength quality training methods, such as the sports training effect can not reach the expected goal, the feasibility is not good, and the lack of pertinence leads to the unsatisfactory training effect of some athletes. In order to improve the quality training effect of competitive Taekwondo special strength, this paper studies the quality training method of competitive Taekwondo special strength based on multi-scale Retinex algorithm under the background of “Internet+”. In this method, the strength quality training video image acquisition module is used to collect the strength quality training video image and transmit it to the strength quality training video image processing module, and the multi-scale Retinex algorithm is used to enhance the strength quality training video image and correct the measurement error of special strength quality training; Analyze the data related to the special strength quality training of competitive Taekwondo athletes in the intelligent evaluation module of strength quality training results, construct an evaluation index system, and evaluate the strength quality training results of competitive Taekwondo athletes; According to the evaluation results of the evaluation module, provide targeted special strength quality training programs for competitive taekwondo athletes; All sports training data are stored in the database management module. The experimental results show that this method can significantly improve the special strength quality training effect of competitive Taekwondo athletes, and can better grasp the training content and movement control accuracy.