Lung cancer has become one of the malignant tumors with the highest morbidity and mortality rate worldwide. The early images of lung cancer are pulmonary nodules, and early detection and diagnosis can help reduce the incidence of lung cancer. However, due to the large differences in shape, size and location of pulmonary nodules in medical imaging, the detection of small nodules is very challenging. This paper proposes a new model, based on improved YOLOv5s, called YOLOv5-CASP. The proposed YOLOv5s improvements include: (i) incorporating Convolutional Block Attention Modules (CBAM) to suppress the interference features of the medical images through a channel dimension and spatial dimension, and to improve the detection accuracy of the model; (ii) optimizing the Spatial Pyramid Pooling - Fast (SPPF) module of YOLOv5s to Atrous Spatial Pyramid Pooling (ASPP) as to increase the model’s receptive field of images of different sizes and extract multi-scale contextual information for improving the detection performance on small lung nodules; and (iii) introducing a Contextual Transformer (CoT) module to optimize part of the CSPDarknet53 module of YOLOv5s in order to enhance the characteristics of the model while removing redundant operations extraction capacity. Experimental results conducted on two public datasets confirm that the proposed YOLOv5-CASP model outperforms the original YOLOv5s model and other five state-of-the-art models (Faster R-CNN, SSD, YOLOv4-Tiny, DETR-R50, Deformable DETR-R50), in terms of the mean average precision ( mAP ) and F1 score , by achieving corresponding values of 72% and 0.740 on the LUNA16 dataset, and 79.44% and 0.766 on the X-Nodule dataset.

Deep neural networks (DNNs) have widely used in various Internet-of-Things (IoT) applications. Pursuing superior performance is always a hot spot in the field of DNN modeling. Recently, feature reuse provides an effective means of achieving favorable nonlinear approximation performance in deep learning. Existing implementations utilizes a multilayer perception (MLP) to act as a functional unit for feature reuse. However, determining connection weight and bias of MLP is a rather intractable problem, since the conventional back-propagation learning approach encounters the limitations of slow convergence and local optimum. To address this issue, this paper develops a novel DNN considering a well-behaved alternative called reservoir computing, i.e., reservoir in network (ResInNet). In this structure, the built-in reservoir has two notable functions. First, it behaves as a bridge between any two restricted Boltzmann machines in the feature learning part of ResInNet, performing a feature abstraction once again. Such reservoir-based feature translation provides excellent starting points for the following nonlinear regression. Second, it serves as a nonlinear approximation, trained by a simple linear regression using the most representative (learned) features. Experimental results over various benchmark datasets show that ResInNet can achieve the superior nonlinear approximation performance in comparison to the baseline models, and produce the excellent dynamic characteristics and memory capacity. Meanwhile, the merits of our approach is further demonstrated in the network traffic prediction related to real-world IoT application.

The existing end-to-end (E2E) wireless communication systems require fewer communication modules and have a simple processing signal flow, compared to conventional wireless communication systems. However, in the absence of a differentiable channel model, it is impossible to train transmitters, used in such systems, which makes impossible to get optimal system performance. To solve this problem, an E2E wireless communication system, learned with conditional generative adversarial networks (CGANs) for channel modeling, has been proposed recently. Unfortunately, the CGAN training is prone to instability, slow convergence, and inaccurate channel modeling, which affects the system performance. To this end, a learning-based E2E wireless communication system, utilizing a deep neural network (DNN) channel module to model an unknown channel, is proposed in this paper. Simulation results show that the proposed DNN channel modeling has faster convergence, simpler network structure, and can reflect the behavior of real channels more accurately. In addition, the proposed E2E wireless communication system performs better, in terms of bit error rate (BER) and block error rate (BLER), than the E2E wireless communication system, using CGAN as unknown channel, and a traditional communication system, designed based on the prior knowledge of the channel. Compared to these two systems, at high signal-to-noise ratio (SNR) values, the proposed system can achieve a SNR gain of at least 2 dB, in communication scenarios involving frequency-selective multi-path channels.

The accuracy of behavioral interactive features is a key factor for improving the performance of rating prediction. In order to deeply explore the potential rules of user behavior and enhance the accurate representation of interactive features, this paper proposes two rating prediction models, based on the spatial dimension and distance measurement (SDDM), under the premise of taking the mean value of the user behavior history as a user feature, and obtaining the interactive features of an item and a user by calculating the distance between them in each feature dimension. In the proposed SDDM-Var and SDDM-PCC models, the variance and the Pearson correlation coefficient (PCC) are respectively utilized to evaluate the user’s attention to each feature dimension as to further obtain the weight vector of the interactive features. Finally, in order to improve the generalization ability of the proposed models, the rating prediction is accomplished by means of a specially designed multi-layer full-connection neural network. The conducted experiments with two public MovieLens datasets demonstrate the superior rating prediction performance of the proposed models in comparison with the existing baseline models, in terms of the root mean square error (RMSE), by achieving values of 0.865 and 0.872 on MovieLens 100K, and 0.839 and 0.832 on MovieLens 1M, respectively for SDDM-Var and SDDM-PCC.

Authentication is the process of confirming the legal identity of communicating entities, and it is the first line of defense for security communication. Most of the existing tag-based physical layer security authentication (PLSA) requires distributing the shared keys in advance. In the large scale internet of things scenario, nodes frequently join and leave the wireless networks that cause the distribution and management of keys particularly difficult. This paper proposes a tag-based PLSA scheme, which utilizes channel characteristics instead of distributing keys to generate authentication tags. Specifically, based on watermarking mechanism, we design a fault-tolerant hash algorithm to couple the secret sequence and the message signal for authentication tags generation. The shared secret sequence is generated by legitimate nodes through channel probing. And the theories of information theory and composite hypothesis testing is employed to analyze the performance of system. The simulation results show that the agreement ratio of the generating shared secret sequence is as high as 96% in the case of high signal-to-noise ratio and low power tag embedding. In addition, performance analysis demonstrates the scheme can resist against multiple attacks, such as replay, jamming, tampering, and impersonation attack.

In order to optimize the performance of data transmission in multiple input multiple output (MIMO) wireless communication systems, a spread spectrum self-interference system based on channel inverse matrix modulation is proposed. First of all, we improved the spread spectrum method and proposed the DIMMSS(channel inverse matrix modulation spread spectrum) spread spectrum method based on the channel inverse matrix. And a simulation comparison experiment was carried out for the anti-interference ability and anti-eavesdropping ability of this method. Secondly, this paper also proposes two blind despreading methods based on Walsh-hadamard algorithm and cluzeau algorithm. We studied the anti-jamming performance of these two algorithms, and optimized the blind despreading process according to their different characteristics of computational complexity. Experimental results show that compared with ordinary direct sequence spread spectrum, the spread spectrum self-interference system can not only improve the confidentiality and security of the transmitted signal, but also greatly simplify the receiving equipment. It has certain application value in the military and civilian fields.