Deep learning innovations in diagnosing diabetic retinopathy: The potential of transfer learning and the DiaCNN model.

Diabetic retinopathy (DR) is a significant cause of vision impairment, emphasizing the critical need for early detection and timely intervention to avert visual deterioration. Diagnosing DR is inherently complex, as it necessitates the meticulous examination of intricate retinal images by experienced specialists. This makes the early diagnosis of DR essential for effective treatment and prevention of eventual blindness. Traditional diagnostic methods, relying on human interpretation of medical images, face challenges in terms of accuracy and efficiency. In the present research, we introduce a novel method that offers superior precision in DR diagnosis, compared to traditional methods, by employing advanced deep learning techniques. Central to this approach is the concept of transfer learning. This entails the utilization of pre-existing, well-established models, specifically InceptionResNetv2 and Inceptionv3, to extract features and fine-tune selected layers to cater to the unique requirements of this specific diagnostic task. Concurrently, we also present a newly devised model, DiaCNN, which is tailored for the classification of eye diseases. To prove the efficacy of the proposed methodology, we leveraged the Ocular Disease Intelligent Recognition (ODIR) dataset, which comprises eight different eye disease categories. The results are promising. The InceptionResNetv2 model, incorporating transfer learning, registered an impressive 97.5% accuracy in both the training and testing phases. Its counterpart, the Inceptionv3 model, achieved an even more commendable 99.7% accuracy during training, and 97.5% during testing. Remarkably, the DiaCNN model showcased unparalleled precision, achieving 100% accuracy in training and 98.3% in testing. These figures represent a significant leap in classification accuracy when juxtaposed with existing state-of-the-art diagnostic methods. Such advancements hold immense promise for the future, emphasizing the potential of our proposed technique to revolutionize the accuracy of DR and other eye disease diagnoses. By facilitating earlier detection and more timely interventions, this approach stands poised to significantly reduce the incidence of blindness associated with DR, thus heralding a new era of improved patient outcomes. Therefore, this work, through its novel approach and stellar results, not only pushes the boundaries of DR diagnostic accuracy but also promises a transformative impact in early detection and intervention, aiming to substantially diminish DR-induced blindness and champion enhanced patient care.

Energy Harvesting for TDS-OFDM in NOMA-Based Underwater Communication Systems.

Non-orthogonal multiple access (NOMA) is considered a promising multiple access technique for fifth generation (5G) mobile networks and tactical internet due to its high spectral efficiency. Thanks to the high spectral efficiency of NOMA, it can be a strong candidate suitable for the limited channel bandwidth of underwater acoustic communication. The NOMA transmitter is employing superposition coding (SC). The NOMA receiver is based on the successive interference cancellation (SIC) technique. The multicarrier NOMA adopts orthogonal frequency division multiplexing (OFDM) as a multicarrier modulation (MCM) technique; however, conventional cyclic prefix OFDM (CP-OFDM) and zero padding (ZP-OFDM) have inefficient spectral efficiency. Thanks to efficient synchronization and high energy-spectral efficiency of the time-division synchronization OFDM (TDS-OFDM), it is a significant attractive candidate for underwater multicarrier communication. However, wasting the power transmission of long guard intervals in the battery-based underwater communication is represented as one of the TDS-OFDM main drawbacks. Harvesting energy and improving the energy efficiency of acoustic-based TDS-OFDM-NOMA represent high achievement goal battery recharging challenges due to the ocean environment. This paper proposes time switching simultaneous wireless information and power transfer (TS-SWIPT) to harvest the energy of transmitted power over the guard interval in the TDS-OFDM-NOMA scheme. The proposed energy harvested scheme harvests the energy from the wasted power in the long guard interval and improves the energy efficiency of the TDS-OFDM multicarrier scheme. This study demonstrates the superiority of the proposed TDS-OFDM-NOMA over the underwater acoustic channel by revealing high energy efficiency, high spectral efficiency, better bit error rate performance, and high system data throughput.

Multi-Stage Feature Extraction and Classification for Ship-Radiated Noise.

Due to the complexity and unique features of the hydroacoustic channel, ship-radiated noise (SRN) detected using a passive sonar tends mostly to distort. SRN feature extraction has been proposed to improve the detected passive sonar signal. Unfortunately, the current methods used in SRN feature extraction have many shortcomings. Considering this, in this paper we propose a new multi-stage feature extraction approach to enhance the current SRN feature extractions based on enhanced variational mode decomposition (EVMD), weighted permutation entropy (WPE), local tangent space alignment (LTSA), and particle swarm optimization-based support vector machine (PSO-SVM). In the proposed method, first, we enhance the decomposition operation of the conventional VMD by decomposing the SRN signal into a finite group of intrinsic mode functions (IMFs) and then calculate the WPE of each IMF. Then, the high-dimensional features obtained are reduced to two-dimensional ones by using the LTSA method. Finally, the feature vectors are fed into the PSO-SVM multi-class classifier to realize the classification of different types of SRN sample. The simulation and experimental results demonstrate that the recognition rate of the proposed method overcomes the conventional SRN feature extraction methods, and it has a recognition rate of up to 96.6667%.

Feature Extraction of Ship-Radiated Noise Based on Enhanced Variational Mode Decomposition, Normalized Correlation Coefficient and Permutation Entropy.

Due to the complexity and variability of underwater acoustic channels, ship-radiated noise (SRN) detected using the passive sonar is prone to be distorted. The entropy-based feature extraction method can improve this situation, to some extent. However, it is impractical to directly extract the entropy feature for the detected SRN signals. In addition, the existing conventional methods have a lack of suitable de-noising processing under the presence of marine environmental noise. To this end, this paper proposes a novel feature extraction method based on enhanced variational mode decomposition (EVMD), normalized correlation coefficient (norCC), permutation entropy (PE), and the particle swarm optimization-based support vector machine (PSO-SVM). Firstly, EVMD is utilized to obtain a group of intrinsic mode functions (IMFs) from the SRN signals. The noise-dominant IMFs are then eliminated by a de-noising processing prior to PE calculation. Next, the correlation coefficient between each signal-dominant IMF and the raw signal and PE of each signal-dominant IMF are calculated, respectively. After this, the norCC is used to weigh the corresponding PE and the sum of these weighted PE is considered as the final feature parameter. Finally, the feature vectors are fed into the PSO-SVM multi-class classifier to classify the SRN samples. The experimental results demonstrate that the recognition rate of the proposed methodology is up to 100%, which is much higher than the currently existing methods. Hence, the method proposed in this paper is more suitable for the feature extraction of SRN signals.

Deep Learning-Based Spread-Spectrum FGSM for Underwater Communication.

The limitation of the available channel bandwidth and availability of a sustainable energy source for battery feed sensor nodes are the main challenges in the underwater acoustic communication. Unlike terrestrial's communication, using multi-input multi-output (MIMO) technologies to overcome the bandwidth limitation problem is highly restricted in underwater acoustic communication by high inter-channel interference (ICI) and the channel multipath effect. Recently, the spatial modulation techniques (SMTs) have been presented as an alternative solution to overcome these issues by transmitting more data bits using the spatial index of antennas transmission. This paper proposes a new scheme of SMT called spread-spectrum fully generalized spatial modulation (SS-FGSM) carrying the information bits not only using the constellated data symbols and index of active antennas as in conventional SMTs, but also transmitting the information bits by using the index of predefined spreading codes. Consequently, most of the information bits are transmitted in the index of the transmitter antenna, and the index of spreading codes. In the proposed scheme, only a few information bits are transmitted physically. By this way, consumed power transmission can be reduced, and we can save the energy of underwater nodes, as well as enhancing the channel utilization. To relax the receiver computational complexity, a low complexity deep learning (DL) detector is proposed for the SS-FGSM scheme as the first attempt in the underwater SMTs-based communication. The simulation results show that the proposed deep learning detector-based SS-FGSM (DLSS-FGSM), compared to the conventional SMTs, can significantly improve the system data rate, average bit error rate, energy efficiency, and receiver's computational complexity.

Underwater TDOA Acoustical Location Based on Majorization-Minimization Optimization.

Underwater acoustic localization is a useful technique applied to any military and civilian applications. Among the range-based underwater acoustic localization methods, the time difference of arrival (TDOA) has received much attention because it is easy to implement and relatively less affected by the underwater environment. This paper proposes a TDOA-based localization algorithm for an underwater acoustic sensor network using the maximum-likelihood (ML) ratio criterion. To relax the complexity of the proposed localization complexity, we construct an auxiliary function, and use the majorization-minimization (MM) algorithm to solve it. The proposed localization algorithm proposed in this paper is called a T-MM algorithm. T-MM is applying the MM algorithm to the TDOA acoustic-localization technique. As the MM algorithm iterations are sensitive to the initial points, a gradient-based initial point algorithm is used to set the initial points of the T-MM scheme. The proposed T-MM localization scheme is evaluated based on squared position error bound (SPEB), and through calculation, we get the SPEB expression by the equivalent Fisher information matrix (EFIM). The simulation results show how the proposed T-MM algorithm has better performance and outperforms the state-of-the-art localization algorithms in terms of accuracy and computation complexity even under a high presence of underwater noise.

Underwater Image Transmission Using Spatial Modulation Unequal Error Protection for Internet of Underwater Things.

A spatial modulation (SM) scheme has been developed as a hopeful candidate for spectral and energy-efficient wireless communication systems, as it provides a great judgment for the system performance, data transmission rate, receiver complexity, and energy/spectrum efficiency. In SM, the data is conveyed by both habitual M-ary signal constellations and the transmit antennas indices. Therefore, the system data rate improvement due to the side information bits transmitted, encapsulated in indices of the transmit antennas, improves the SM transmission efficiency compared to the different MIMO players. The information bits transmitted over the antenna index and data symbol constellation using M-ary signal performance have different levels of bit error rate (BER) performance. This paper proposes unequal error protection (UEP) scheme for image transmission over the Internet of Underwater Things (IoUTs) using SM. The Set Partitioning in Hierarchical Trees (SPIHT) coders encode the underwater image and classify the encoded bits in two categories: critical and uncritical bits. The critical bits are transmitted over the SM index bits and have a low BER while the uncritical bits are transmitted over high order M-ary signal constellation to resolve the underwater acoustic channel bandwidth limitation problem. The proposed SM-UEP technique has been developed carefully with enough justification and evaluation over the measured underwater acoustic channel and the simulated channel. The simulation results show that the proposed SM-UEP can increase the average peak signal-to-noise ratio (PSNR) of the reconstructed received image considerably, and significantly.

Enhanced Fully Generalized Spatial Modulation for the Internet of Underwater Things.

A full design of the Internet of Underwater Things (IoUT) with a high data rate is one of the greatest underwater communication difficulties due to the unavailability of a sustainable power source for the battery supplies of sensor nodes, electromagnetic spread weakness, and limited acoustic waves channel bandwidth. This paper presents a new energy-efficient communication scheme named Enhanced Fully Generalized Spatial Modulation (EFGSM) for the underwater acoustic channel, where the different number of active antennas used in Fully Generalized Spatial Modulation (FGSM) is combined with multiple signal constellations. The proposed EFGSM enhances energy efficiency over conventional schemes such as spatial modulation, generalized spatial modulation, and FGSM. In order to increase energy and spectral performance, the proposed technique conveys data bits not just by the number of active antenna's index as in the existing traditional FGSM, but also using the type of signal constellation to increase the data bit rate and improve power saving without increasing the receiver's complexity. The proposed EFGSM uses primary and secondary constellations as indexes to carry information, they are derived from others by geometric interpolation signal space. The performance of the suggested EFGSM is estimated and demonstrated through Monte Carlo simulation over an underwater acoustic channel. The simulation results confirm the advantage of the suggested EFGSM scheme not just regarding energy and spectral efficiency but also concerning the average bit error rate (ABER).