Mobile communication systems are not only the core of the Information and Communication Technology (ICT) infrastructure but also that of our social infrastructure. The 5th generation mobile communication system (5G) has already started and is in use. 5G is expected for various use cases in industry and society. Thus, many companies and research institutes are now trying to improve the performance of 5G, that is, 5G Enhancement and the next generation of mobile communication systems (Beyond 5G (6G)). 6G is expected to meet various highly demanding requirements even compared with 5G, such as extremely high data rate, extremely large coverage, extremely low latency, extremely low energy, extremely high reliability, extreme massive connectivity, and so on. Artificial intelligence (AI) and machine learning (ML), AI/ML, will have more important roles than ever in 6G wireless communications with the above extreme high requirements for a diversity of applications, including new combinations of the requirements for new use cases. We can say that AI/ML will be essential for 6G wireless communications. This paper introduces some ML techniques and applications in 6G wireless communications, mainly focusing on the physical layer.

We propose a new design approach to improve the computational efficiency of an optimal design of optical waveguide devices utilizing coupled mode theory (CMT) and a neural network (NN). Recently, the NN has begun to be used for efficient optimal design of optical devices. In this paper, the eigenmode analysis required in the CMT is skipped by using the NN, and optimization with an evolutionary algorithm can be efficiently carried out. To verify usefulness of our approach, optimal design examples of a wavelength insensitive 3dB coupler, a 1 : 2 power splitter, and a wavelength demultiplexer are shown and their transmission properties obtained by the CMT with the NN (NN-CMT) are verified by comparing with those calculated by a finite element beam propagation method (FE-BPM).

Due to the increase of outsourcing by IC vendors, we face a serious risk that malicious third-party vendors insert hardware Trojans very easily into their IC products. However, detecting hardware Trojans is very difficult because today's ICs are huge and complex. In this paper, we propose a hardware-Trojan classification method for gate-level netlists to identify hardware-Trojan infected nets (or Trojan nets) using a support vector machine (SVM) or a neural network (NN). At first, we extract the five hardware-Trojan features from each net in a netlist. These feature values are complicated so that we cannot give the simple and fixed threshold values to them. Hence we secondly represent them to be a five-dimensional vector and learn them by using SVM or NN. Finally, we can successfully classify all the nets in an unknown netlist into Trojan ones and normal ones based on the learned classifiers. We have applied our machine-learning-based hardware-Trojan classification method to Trust-HUB benchmarks. The results demonstrate that our method increases the true positive rate compared to the existing state-of-the-art results in most of the cases. In some cases, our method can achieve the true positive rate of 100%, which shows that all the Trojan nets in an unknown netlist are completely detected by our method.

An unsupervised adaptive signal processing method of principal components analysis (PCA) neural networks (NN) based on signal eigen-analysis is proposed to permit the eigenstructure analysis of lower signal to noise ratios (SNR) direct sequence spread spectrum (DS) signals. The objective of eigenstructure analysis is to estimate the pseudo noise (PN) of DS signals blindly. The received signal is firstly sampled and divided into non-overlapping signal vectors according to a temporal window, which duration is two periods of PN sequence. Then an autocorrelation matrix is computed and accumulated by these signal vectors one by one. Lastly, the PN sequence can be estimated by the principal eigenvector of autocorrelation matrix. Since the duration of temporal window is two periods of PN sequence, the PN sequence can be reconstructed by the first principal eigenvector only. Additionally, the eigen-analysis method becomes inefficient when the estimated PN sequence is long. We can use an unsupervised adaptive method of PCA NN to realize the PN sequence estimation from lower SNR input DS-SS signals effectively.

In this study, a hybrid genetic algorithm/neural network with fuzzy logic controller (NN-flcGA) is proposed to find the global optimum of reliability assignment/redundant allocation problems which should be simultaneously determined two different types of decision variables. Several researchers have obtained acceptable and satisfactory results using genetic algorithms for optimal reliability assignment/redundant allocation problems during the past decade. For large-size problems, however, genetic algorithms have to enumerate numerous feasible solutions due to the broad continuous search space. Recently, a hybridized GA combined with a neural network technique (NN-hGA) has been proposed to overcome this kind of difficulty. Unfortunately, it requires a high computational cost though NN-hGA leads to a robuster and steadier global optimum irrespective of the various initial conditions of the problems. The efficacy and efficiency of the NN-flcGA is demonstrated by comparing its results with those of other traditional methods in numerical experiments. The essential features of NN-flcGA namely, 1) its combination with a neural network (NN) technique to devise initial values for the GA, 2) its application of the concept of a fuzzy logic controller when tuning strategy GA parameters dynamically, and 3) its incorporation of the revised simplex search method, make it possible not only to improve the quality of solutions but also to reduce computational cost.

In the future asynchronous transfer mode (ATM) networks, an efficient virtual path (VP) control strategy must be applied to guarantee the network has high throughput with tolerable node processing load. The multistage VP control may be the best candidate since the tasks in this method are shared by the central node and local nodes, and it allows us to track the traffic changes while maintain a good state of the VP topology by reconfiguring it at regular or need based intervals. In this paper, we focus on the VP topology optimization problem in the multistage VP control. We first present the problem formulation in which the tradeoff between the network throughput and processing costs is considered, and then employ an algorithm based on a route-neuron Hopfield neural network (HNN) model to solve this problem. The numerical results demonstrate the HNN can converge to optimal solutions with high probability and stability while in other cases to near optimal solutions if the values of the system parameters in the route-neuron model are chosen according to some empirical formulas provided in this paper.