With the recent development of artificial intelligence (AI) and information and communication technology, manned vehicles operated by humans used on the ground, air, and sea are evolving into unmanned vehicles (UVs) that operate without human intervention. In particular, unmanned marine vehicles (UMVs), including unmanned underwater vehicles (UUVs) and unmanned surface vehicles (USVs), have the potential to complete maritime tasks that are unachievable for manned vehicles, lower the risk of man power, raise the power required to carry out military missions, and reap huge economic benefits. The aim of this review is to identify past and current trends in UMV development and present insights into future UMV development. The review discusses the potential benefits of UMVs, including completing maritime tasks that are unachievable for manned vehicles, lowering the risk of human intervention, and increasing power for military missions and economic benefits. However, the development of UMVs has been relatively tardy compared to that of UVs used on the ground and in the air due to adverse environments for UMV operation. This review highlights the challenges in developing UMVs, particularly in adverse environments, and the need for continued advancements in communication and networking technologies, navigation and sound exploration technologies, and multivehicle mission planning technologies to improve UMV cooperation and intelligence. Furthermore, the review identifies the importance of incorporating AI and machine learning technologies in UMVs to enhance their autonomy and ability to perform complex tasks. Overall, this review provides insights into the current state and future directions for UMV development.

A smart factory is a highly digitized and networked production facility based on smart manufacturing. A smart manufacturing plant is the result of intelligent systems deployed in the factory. Smart factories have higher production volumes and are prone to machine failures when operating in almost all applications on a daily basis. With the growing concept of smart manufacturing required for Industry 4.0, intelligent methods for detecting and classifying bearing faults have become a subject of scientific research and interest. In this paper, a deep learning-based 1-D convolutional neural network is proposed using the time-sequence bearing data from the Case Western Reserve University (CWRU) bearing database. Four different sets of data are used. The proposed method achieves state-of-the-art accuracy even with a small amount of training data. For the sensitivity analysis of the proposed method, metrics such as precision, recall, and f-measure are determined. Next, we compare the proposed method with a 2-D CNN that uses two-dimensional image illustrations of raw data as input. This method shows the effectiveness of using 1-D CNNs over 2-D CNNs for time-sequence data. The proposed method is computationally inexpensive and outperforms the most complex and computationally intensive algorithms used for bearing fault detection and diagnosis.

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things (IoT) and artificial intelligence (AI). Quality control is an important part of today’s smart manufacturing process, effectively reducing costs and enhancing operational efficiency. As technology in the industry becomes more advanced, identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing process. In this study, we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques, incorporating a global average pooling (GAP) layer and a machine learning-based SVM classifier, with the aim of enhancing accuracy. Initially, features are extracted by the VGG19 convolutional block. Then, after processing through the GAP layer, the extracted features are fed to the SVM classifier for classification. For this purpose, we collected images from publicly available datasets, including the Xsteel surface defect dataset (XSDD) and the NEU surface defect (NEU-CLS) datasets, and we employed offline data augmentation techniques to balance and increase the size of the datasets. The outcome of experiments shows that the proposed methodology achieves the highest metrics score, with 99.79% accuracy, 99.80% precision, 99.79% recall, and a 99.79% F1-score for the NEU-CLS dataset. Similarly, it achieves 99.64% accuracy, 99.65% precision, 99.63% recall, and a 99.64% F1-score for the XSDD dataset. A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

Sonobuoy is a disposable device that collects underwater acoustic information and is designed to transmit signals collected in a particular area to nearby aircraft or ships and sink to the seabed upon completion of its mission. In a conventional sonobuoy signal transmission and reception system, collected signals are modulated and transmitted using techniques such as frequency division modulation or Gaussian frequency shift keying. They are received and demodulated by an aircraft or a ship. However, this method has the disadvantage of a large amount of information being transmitted and low security due to relatively simple modulation and demodulation methods. Therefore, in this paper, we propose a method that uses an autoencoder to encode a transmission signal into a low-dimensional latent vector to transmit the latent vector to an aircraft or vessel. The method also uses an autoencoder to decode the received latent vector to improve signal security and to reduce the amount of transmission information by approximately a factor of a hundred compared to the conventional method. In addition, a denoising autoencoder, which reduces ambient noises in the reconstructed outputs while maintaining the merit of the proposed autoencoder, is also proposed. To evaluate the performance of the proposed autoencoders, we simulated a bistatic active and a passive sonobuoy environments. As a result of analyzing the sample spectrograms of the reconstructed outputs and mean square errors between original and reconstructed signals, we confirmed that the original signal could be restored from a low-dimensional latent vector by using the proposed autoencoder within approximately 4% errors. Furthermore, we verified that the proposed denoising autoencoder reduces ambient noise successfully by comparing spectrograms and by measuring the overall signal-to-noise ratio and the log-spectral distance of noisy input and reconstructed output signals.

For decades, the soft-kill strategy which detects high-speed underwater targets with passive sonar and attract the targets using decoys has been used. However, recently, the paradigm to respond to the high-speed underwater targets is shifting to a hard-kill method that directly intercepts the targets. Therefore, an active sonar detection and tracking technique is required to estimate the exact location of the target. Existing detection and tracking techniques using active sonar divide pulses either temporally or along the frequency axis, transmitting pulses in various directions within a pulse repetition interval. This division, however, leads to a reduction in the time-bandwidth product, consequently diminishing detection performance. Therefore, this paper proposes a generalized sinusoidal frequency modulation (GSFM)-based pulsed active sonar (PAS). The proposed PAS-GSFM employs short pulses for a quick update of target estimates, but the orthogonality between pulses of GSFM allows pulses to maximize bandwidth, thus high detection performance can be expected. Two types of simulations were performed to verify the performance of the proposed PAS-GSFM. First, the performance comparison with PAS-linear frequency modulation (LFM), and second, the comparison between the proposed method and continuous active sonar (CAS)-GSFM. Through the evaluation, the superiority of the proposed method over PAS-LFM and competitiveness compared to CAS-GSFM were proved.

In this paper, a unified framework for using speech interfaces with intelligent televisions (TVs) is proposed. The proposed framework is primarily based on suppressing the stereophonic acoustic echo of the TV audio sounds and adaptive tracking of the time varying acoustic transfer function of the echo sounds. In order to effectively suppress the acoustic echoes from the TV speakers, an optimal filter with a multichannel subspace approach is imposed on noisy inputs and the second order statistics of the stereophonic echoes are adaptively estimated by tracking the time varying acoustic transfer function using the normalized least mean square method. Through assessing the proposed method with a database collected in real TV watching environments, noticeable improvements were achieved in the SNR gain, Itakura-Saito distance, and speech recognition rates.