This paper presents a novel deep learning model for achieving millimeter accuracy for indoor localization. The model comprises a multi-head self-attention model and a convolutional neural network (CNN), allowing for robust feature extraction from the captured wireless signals. To further enhance the localization accuracy, we also introduced a data augmentation method to increase the size and diversity of the dataset by creating synthetic variants. The performance of the proposed model is tested on an open dataset containing measured channel state information (CSI) signals from a massive multiple-input multiple-output (MIMO) system. The validation accuracies for all three cases are more than seven times higher than the state of the art. The model has also been further evaluated in the COST INTERACT CA20120 Machine Learning Challenge. The performance of our model is competitive with the measured position and significantly outperforms other teams. The proposed model and the associated approaches contribute to the development of practical millimeter-level indoor localization systems using deep learning architectures.

Abstract It aims to explore the efficient and reliable wireless transmission and cooperative communication mechanism of Internet of Vehicles (IoV) based on edge intelligence technology. It first proposes an intelligent network architecture for IoV services by combining network slicing and deep learning (DL) technology, and then began to study the key technologies needed to achieve the architecture. It designs the cooperative control mechanism of unmanned vehicle network based on the full study of wireless resource allocation algorithm from the micro level. Second, in order to improve the safety of vehicle driving, deep reinforcement learning is used to configure the wireless resources of IoV network to meet the needs of various IoV services. The research results show that the accuracy rate of the improved AlexNet algorithm model can reach 99.64%, the accuracy rate is more than 80%, the data transmission delay is less than 0.02 ms, and the data transmission packet loss rate is less than 0.05. The algorithm model has practical application value for solving the data transmission related problems of vehicular internet communication, providing an important reference value for the intelligent development of unmanned vehicle internet.

OBJECTIVE: it aims to adopt deep transfer learning combined with Digital Twins (DTs) in Magnetic Resonance Imaging (MRI) medical image enhancement. METHODS: MRI image enhancement method based on metamaterial composite technology is proposed by analyzing the application status of DTs in medical direction and the principle of MRI imaging. On the basis of deep transfer learning, MRI super-resolution deep neural network structure is established. To address the problem that different medical imaging methods have advantages and disadvantages, a multi-mode medical image fusion algorithm based on adaptive decomposition is proposed and verified by experiments. RESULTS: the optimal Peak Signal to Noise Ratio (PSNR) of 34.11dB can be obtained by introducing modified linear element and loss function of deep transfer learning neural network structure. The Structural Similarity Coefficient (SSIM) is 85.24%. It indicates that the MRI truthfulness and sharpness obtained by adding composite metasurface are improved greatly. The proposed medical image fusion algorithm has the highest overall score in the subjective evaluation of the six groups of fusion image results. Group III had the highest score in Magnetic Resonance Imaging- Positron Emission Computed Tomography (MRI-PET) image fusion, with a score of 4.67, close to the full score of 5. As for the objective evaluation in group I of Magnetic Resonance Imaging- Single Photon Emission Computed Tomography (MRI-SPECT) images, the Root Mean Square Error (RMSE), Relative Average Spectral Error (RASE) and Spectral Angle Mapper (SAM) are the highest, which are 39.2075, 116.688, and 0.594, respectively. Mutual Information (MI) is 5.8822. CONCLUSION: the proposed algorithm has better performance than other algorithms in preserving spatial details of MRI images and color information direction of SPECT images, and the other five groups have achieved similar results.

With the continuous increase of the amount of information, people urgently need to identify the information in the image in more detail in order to obtain richer information from the image. This work explores the dynamic complex image segmentation of self-driving vehicle under Digital Twins (DTs) based on Memory-augmented Neural Networks (MANNs), so as to further improve the performance of self-driving in intelligent transportation. In view of the complexity of the environment and the dynamic changes of the scene in intelligent transportation, this work constructs a segmentation model for dynamic complex image of self-driving vehicle under DTs based on MANNs by optimizing the Deep Learning algorithm and further combining with the DTs technology, so as to recognize the information in the environment image during the self-driving. Finally, the performance of the constructed model is analyzed by experimenting with different image datasets (PASCALVOC 2012, NYUDv2, PASCAL CONTEXT, and real self-driving complex traffic image data). The results show that compared with other classical algorithms, the established MANN-based model has an accuracy of about 85.80%, the training time is shortened to 107.00 s, the test time is 0.70 s, and the speedup ratio is high. In addition, the average algorithm parameter of the given energy function α=0.06 reaches the maximum value. Therefore, it is found that the proposed model shows high accuracy and short training time, which can provide experimental reference for future image visual computing and intelligent information processing.

To accurately and effectively analyze electroencephalogram (EEG) with high complexity, large amount of data, and strong uncertainty, brain–computer interface (BCI) cognitive computing and its signal analysis algorithms are studied based on the digital twins (DTs) cognitive computing platform. To avoid the influence of noise on EEG analysis results, it is necessary to use filtering and defalsification methods to process EEG. Four methods, including Butterworth filter, finite impulse response (FIR) filter, elliptic filter, and wavelet decomposition, are summarized. Based on the Riemann manifold theory, a feature extraction algorithm under transfer learning based on tangent space selection (TL-TSS) is proposed. In the process of decoding EEG, an EEG decoding method combining entropy measure and singular spectrum analysis (SSA) is proposed. An algorithm performance is tested on the motor imagery dataset of the two International BCI Competitions. It is found that when the training sample size accounts for 5%, the TL-TSS algorithm proposed in this work is superior to other algorithms in classification accuracy. In particular, compared with common spatial pattern (CSP) algorithm, it has great advantages. The classification accuracy of A2, A4, A8, and A9 users is the best, and especially for A8 users, the classification accuracy reaches 97.88%. In summary, in the EEG interface technology of DT cognitive computing platform, the combination of cognitive computing and deep learning can improve the recognition and analysis effect of EEG, which is of great value for further optimization of DT cognitive computing system.

To realize the great potential of the intelligent transportation infrastructure, the investment in the transportation infrastructure in the intelligent transportation system should be rationally planned. Firstly, the application status of cutting-edge Data Envelopment Analysis (DEA) model in transportation infrastructure efficiency evaluation is analyzed, and based on this, a DEA model of transportation infrastructure efficiency evaluation under Digital Twins technology is established. Secondly, with the transportation infrastructure of 12 prefecture-level cities in Jiangsu Province from 2005 to 2020 as the research object, the Digital Twins DEA model and the traditional Stochastic Frontier Approach (SFA) model are used to estimate the efficiency of transportation infrastructure in 12 cities. Finally, the traffic flow data of a certain road section in Zhenjiang City (J11 City) is simulated and predicted by using the Long Short-term Memory (LSTM) traffic flow prediction model. The results show that the average efficiency of the 12 cities estimated by the DEA model based on the Digital Twins is 0.7083, the average efficiency of the 12 cities estimated by the SFA model is 0.6445, and there are significant differences in the efficiency rankings of the cities. Compared with the actual efficiency, the established Digital Twins DEA model is more reasonable for the calculation of transportation infrastructure efficiency. The results of the LSTM traffic flow prediction model show that the Mean Absolute Error (MAE) of the LSTM model is 24.29, the Root Mean Square Error (RSME) is 0.1186, and the Mean Absolute Perce (MAPE) is 17.78, which are all lower than other models. Compared with other models, the proposed LSTM-based traffic flow prediction model is more accurate in traffic flow prediction. Hence, the research content provides a reference for the investment planning of intelligent transportation system infrastructure.

In order to explore the application value of deep learning denoising autoencoder (DAE) in Internet-of-Things (IoT) fusion security, in this study, a hierarchical intrusion security detection model stacked DAE supporting vector machine (SDAE-SVM) is constructed based on the three-layer neural network of self-encoder. The sample data after dimension reduction are obtained by layer by layer pretraining and fine-tuning. The traditional deep learning algorithms [stacked noise autoencoder (SNAE), stacked autoencoder (SAE), stacked contractive autoencoder (SCAE), stacked sparse autoencoder (SSAE), deep belief network (DBN)] are introduced to carry out the comparative simulation with the model in this study. The results show that when the encoder in the model is a 4-layer network structure, the accuracy rate (Ac) of the model is the highest (97.83%), the false-negative rate (Fn) (1.27%) and the false-positive rate (Fp) (3.21%) are the lowest. When the number of nodes in the first hidden layer is about 110, the model accuracy is about 98%. When comparing the model designed in this study with the common feature dimension reduction methods, the Ac, Fn, and Fp of this model are the best, which are 98.12%, 3.21%, and 1.27%, respectively. When compared with other deep learning algorithms of the same type, the recognition rate, Ac, error rate, and rejection rate show good results. In multiple data sets, the recognition rate, Ac, error rate, and rejection rate of the model in this study are always better than the traditional deep learning algorithms. In conclusion, when deep learning SDAE is applied to IoT convergence-based intrusion security detection, the detection load can be reduced, the detection effect can be improved, and the operation is more secure and stable.

The brain-computer interface (BCI) connects the brain and the external world through an information transmission channel by interpreting the physiological information of the brain during thinking activities. The effective classification of electroencephalogram (EEG) signals is the key to improving the performance of the system. To improve the classification accuracy of EEG signals in the BCI system, the transfer learning algorithm and the improved Common Spatial Pattern (CSP) algorithm are combined to construct a data classification model. Finally, the effectiveness of the proposed algorithm is verified. The results show that in actual and imagined movements, the accuracy of the left- and right-hand movements at different speeds is higher than when the speeds are the same. The proposed Adaptive Composite Common Spatial Pattern (ACCSP) and Self Adaptive Common Spatial Pattern (SACSP) algorithms have good classification effects on 5 subjects, with an average classification accuracy rate of 83.58 percent, which is an increase of 6.96 percent compared with traditional algorithms. When the training sample size is 10, the classification accuracy of the ACCSP algorithm is higher than that of the traditional CSP algorithm. The improved CSP algorithm combined with transfer learning embodies a good classification effect in both ACCSP and SACSP. Especially, the performance of SACSP mode is better. Combining the improved CSP algorithm proposed with the CSP-based transfer learning algorithm can improve the classification accuracy of the BCI classifier.

With the increasing size of data, massive amounts of data are being generated continuously. It is hoped to find a cognitive computing technology that can effectively learn and process large-scale data. The decision tree algorithm is optimized from the perspective of machine learning. A cognitive computing model based on context-aware data flow is constructed. Classification and regression tree (CART) algorithm is used in the data computing layer of the cognitive model. In addition, the clustering effectiveness index based on frequent patterns optimizes the K-means clustering method. The performance of the algorithm is analyzed through simulation experiments. The results show that the CART algorithm requires fewer training data sets while guaranteeing classification accuracy. Also, the algorithm has obvious advantages under large-scale data. In the application of actual data set, on Over, Over+Noise, and Bridge, only the clustering validity index based on frequent pattern (FPCVI) index proposed finds the correct number of clusters. The application of DPCK-K-means clustering algorithm can ensure the accuracy and stability of behavior classification, which is greatly significant for operators to analyze user behavior and develop personalized services.

To explore the electric vehicle networks in smart cities through big data analysis technology, this study utilizes K-means and fuzzy theory in big data analysis technology to construct an objective function-based fuzzy mean clustering algorithm theory (FCM). Then, the FCM algorithm is improved, and the electric vehicle network is simulated. The results show that in the analysis of network data transmission performance, when the probability of successful propagation is 100% and the λ value is between 0.01-0.05, it is closest to the actual result, and the data delay is the smallest. In the analysis of the route guidance effects, when facing congested road sections, the route guidance strategy of this study can restrain the spread of congestion effectively and achieve timely evacuation of traffic congestion. In the further analysis of the impact of different factors on traffic conditions, under route guidance, with the increase in market penetration rate (MPR) of devices, following rate (FR) of vehicles, and congestion level (CL), the improvement of the induction strategy becomes clearer, and greater economic benefits are achieved. This study has found that utilizing big data analysis technology to improve the electric vehicle transportation networks can reduce the network data transmission performance delay significantly and change the path to suppress the spread of congestion effectively, which has provided experimental references for the development of electric vehicle transportation networks.

Objective: To realize the full coverage, full spectrum, and full application, of 6G networks, the channel measurement, channel characteristics, and channel research of the 6G-oriented full-spectrum full-scene wireless network are explored. Methods: At present, constructing an information network covering three dimensions of sea, land and air is one of the research directions of 6G technology development. Meanwhile, the full coverage of three dimensions of communication requires multiple channels including multiple frequency bands and multiple scenarios, mainly including terahertz, light band, satellite, unmanned aerial vehicle, ocean, high-speed rail, and vehicle-to-vehicle. For different channels, different parameters are analyzed and targeted discussed according to channel characteristics. Also, there are many other problems of wireless communication channel that need to be solved. Here, only the above problems are analyzed in detail. Because of the current development of the Internet of Vehicles, the interconnection of connected vehicles is analyzed, and this scenario is also the most widely common scenario in daily life. Results: For the above-mentioned communication channels, the relevant measurement and modeling results of the 6G channel are shown; besides, the characteristics, time, and space correlation functions are obtained for each channel. Conclusion: The existing research results of 6G-oriented wireless channel measurement and modeling are analyzed; the research methods are summarized; new ideas are proposed to provide researchers with important references.

Smart cities fully utilize the new generation of Internet of Things (IoT) technology in the process of urban informatization to optimize the urban management and service. However, in the IoT system, while information exchange and communication, wireless sensor network devices may not be able to resist all forms of attacks, which may lead to security issues such as user data disclosure. Aiming at the information security risks in smart city, the typical technologies in IoT is analyzed from the perspective of IoT perception layer and provides corresponding security solutions for the existing security threats. Regarding the communication security, the emerging wireless technology, long range (LoRa), is discussed, and the performance of wireless communication protocol is analyzed through simulation experiments, to verify that the IoT technology based on LoRa communication technology can improve the security of the system in the construction of smart city. The results show that REBEB, a new backoff algorithm, is similar to the binary exponential backoff algorithm in terms of throughput performance. REBEB focuses more on fairness, which is up to 0.985, and to a certain extent, its security is significantly improved. The fairness of REBEB algorithm is more than 0.4 in different nodes and competing windows, and the fairness of the system is better when the number of nodes is small. To sum up, the IoT system based on LoRa communication can effectively improve the security performance of the system in the construction of smart city and avoid the security threats in the IoT signal transmission.

As deep learning, virtual reality, and other technologies become mature, real-time data processing applications running on intelligent terminals are emerging endlessly; meanwhile, edge computing has developed rapidly and has become a popular research direction in the field of distributed computing. Edge computing network is a network computing environment composed of multi-edge computing nodes and data centers. First, the edge computing framework and key technologies are analyzed to improve the performance of real-time data processing applications. In the system scenario where the collaborative deployment tasks of multi-edge nodes and data centers are considered, the stream processing task deployment process is formally described, and an efficient multi-edge node-computing center collaborative task deployment algorithm is proposed, which solves the problem of copy-free task deployment in the task deployment problem. Furthermore, a heterogeneous edge collaborative storage mechanism with tight coupling of computing and data is proposed, which solves the contradiction between the limited computing and storage capabilities of data and intelligent terminals, thereby improving the performance of data processing applications. Here, a Feasible Solution (FS) algorithm is designed to solve the problem of placing copy-free data processing tasks in the system. The FS algorithm has excellent results once considering the overall coordination. Under light load, the V value is reduced by 73% compared to the Only Data Center-available (ODC) algorithm and 41% compared to the Hash algorithm. Under heavy load, the V value is reduced by 66% compared to the ODC algorithm and 35% compared to the Hash algorithm. The algorithm has achieved good results after considering the overall coordination and cooperation and can more effectively use the bandwidth of edge nodes to transmit and process data stream, so that more tasks can be deployed in edge computing nodes, thereby saving time for data transmission to the data centers. The end-to-end collaborative real-time data processing task scheduling mechanism proposed here can effectively avoid the disadvantages of long waiting times and unable to obtain the required data, which significantly improves the success rate of the task and thus ensures the performance of real-time data processing.

Emotional cognitive ability is a key technical indicator to measure the friendliness of interaction. Therefore, this research aims to explore robots with human emotion cognitively. By discussing the prospects of 5G technology and cognitive robots, the main direction of the study is cognitive robots. For the emotional cognitive robots, the analysis logic similar to humans is difficult to imitate; the information processing levels of robots are divided into three levels in this study: cognitive algorithm, feature extraction, and information collection by comparing human information processing levels. In addition, a multi-scale rectangular direction gradient histogram is used for facial expression recognition, and robust principal component analysis algorithm is used for facial expression recognition. In the pictures where humans intuitively feel smiles in sad emotions, the proportion of emotions obtained by the method in this study are as follows: calmness accounted for 0%, sadness accounted for 15.78%, fear accounted for 0%, happiness accounted for 76.53%, disgust accounted for 7.69%, anger accounted for 0%, and astonishment accounted for 0%. In the recognition of micro-expressions, humans intuitively feel negative emotions such as surprise and fear, and the proportion of emotions obtained by the method adopted in this study are as follows: calmness accounted for 32.34%, sadness accounted for 34.07%, fear accounted for 6.79%, happiness accounted for 0%, disgust accounted for 0%, anger accounted for 13.91%, and astonishment accounted for 15.89%. Therefore, the algorithm explored in this study can realize accuracy in cognition of emotions. From the preceding research results, it can be seen that the research method in this study can intuitively reflect the proportion of human expressions, and the recognition methods based on facial expressions and micro-expressions have good recognition effects, which is in line with human intuitive experience.

With increasing amounts of information, the image information received by people also increases exponentially. To perform fine-grained categorization and recognition of images and visual calculations, this study combines the Visual Geometry Group Network 16 model of convolutional neural networks and the vision attention mechanism to build a multi-level fine-grained image feature categorization model. Finally, the TensorFlow platform is utilized to simulate the fine-grained image classification model based on the visual attention mechanism. The results show that in terms of accuracy and required training time, the fine-grained image categorization effect of the multi-level feature categorization model constructed by this study is optimal, with an accuracy rate of 85.3% and a minimum training time of 108 s. In the similarity effect analysis, it is found that the chi-square distance between Log Gabor features and the degree of image distortion show a strong positive correlation; in addition, the validity of this measure is verified. Therefore, through the research in this study, it is found that the constructed fine-grained image categorization model has higher accuracy in image recognition categorization, shorter training time, and significantly better performance in similar feature effects, which provides an experimental reference for the visual computing of fine-grained images in the future.

To study the security performance of the Internet of multimedia things on the privacy protection of user identity, behavior trajectory, and preference under the new information technology industry wave, in this study, aiming at the problems of the sharing of Internet of things perception data and the exposure of users’ privacy information, the Anonymous Batch Authentication Scheme (ABAH) for privacy protection is designed. Hash-based Message Authentication Code is used to cancel the list-checking process and analyze its security performance. Compared with the methods of elliptic curve digital signature algorithm, Bayes least-square method, identity-based bulk verification, anonymous batch authentication and key protocol, conditional privacy authentication scheme, and expert message authentication protocol, the transmission delay, packet loss rate, and computation cost are studied without considering the undo list and during the undo check. The results show that with the increase of information size, the transmission delay and packet loss rate also increase, and the transmission delay of ABAH increases by about 15%, while the correlation between speed and transmission delay is small. In the case of the same amount of validation information, ABAH has the highest validation efficiency, and it still has an efficient validation effect in the case of invalid information. The message packet loss rate for ABAH is always 0 when the undo check validation overhead is considered. It can be found that ABAH can avoid the communication overhead and privacy leakage caused by the revocation list, ensure the integrity of batch verification information, meet the security performance of the vehicular ad hoc network under the Internet of Things, and protect the privacy of users from being disclosed.