Search Results (45)

Artificial intelligence (AI)-supported agricultural disease detection has become increasingly important for addressing global food security challenges. In this study, a hybrid meta-heuristic optimization-based feature selection approach is proposed for the detection of peacock eye disease (Venturia oleaginea) on olive leaves. The proposed method combines Artificial Rabbit Optimization (ARO) and Genetic Algorithm (GA) strategies to balance global exploration and local exploitation during feature selection. Comprehensive experiments conducted on a dataset of 954 olive leaf images demonstrate that the proposed approach achieves an F1-score of 99.7% while reducing the feature dimensionality by 95%, selecting only 100 features from ResNet101. Statistical analysis confirms that the method significantly outperforms standalone GA and ARO approaches ($p<0.05$, paired t-tests), demonstrating superior long-term convergence behavior and a 47–56% reduction in performance variance across repeated runs. Compared to existing approaches in the literature, the proposed method attains competitive or superior accuracy with substantially fewer features, indicating a marked reduction in computational complexity. These results suggest that the proposed hybrid feature selection framework has strong potential for deployment in resource-constrained agricultural monitoring scenarios, where efficient inference and reduced model complexity are critical. Full article

To enable mains-free wireless access in confined environments such as tunnels and mines, this paper proposes and experimentally demonstrates a converged power-over-fiber (PoF) and analog radio-over-fiber (A-RoF) system over a single standard single-mode fiber (SMF). Using wavelength-division multiplexing (WDM), the system employs 1310 nm/1330 nm channels for bidirectional RF transmission and a 1550 nm channel for optical power delivery, respectively, while an ultra-simplified remote unit (RU) with a steady-state power consumption of 0.37 W is designed to match the PoF power-delivery capability. Experimental results show that for back-to-back, 1 km and 2 km links, the A-RoF performance remains essentially unaffected, with error vector magnitude (EVM) remaining stable, as the delivered PoF optical power varies from 0 to 3 W. For the 2 km transmission case, an incident PoF optical power of 2 W at the photovoltaic power converter (PPC) is sufficient to sustain stable system operation for over 10 hours. Under these conditions, using an IEEE 802.11ax MCS-7 (64QAM ) waveform, the optimum operating point yields an EVM of approximately 0.7%, satisfying the MCS-7 modulation-quality requirement. Full article

This work presents the design and experimental validation of a 2 × 2 MIMO communication system assisted by a directly modulated analog radio-over-fiber (A-RoF) fronthaul, targeting low-complexity connectivity solutions for underserved/remote regions. The study details the complete end-to-end architecture, including a wireless access segment to complement the 20-km optical fronthaul link. The system is implemented on an software defined radio (SDR) platform using GNU Radio 3.7.11, running on Ubuntu 18.04 with kernel 4.15.0-213-generic. It also employs adaptive modulation driven by real-time signal-to-noise ratio (SNR) estimation to keep bit error rate (BER) close to zero while maximizing throughput. Performance is characterized over 20 km of single-mode fiber (SMF) using coarse wavelength division multiplexing (WDM) and assessed through root mean square error vector magnitude (${\mathrm{EVM}}_{\mathrm{RMS}}$), throughput, and spectral integrity. The results identify an optimum radio-frequency drive region around $-16$ dBm enabling high-order modulation (e.g., 256-QAM), whereas RF input powers above approximately $-10$ dBm increase ${\mathrm{EVM}}_{\mathrm{RMS}}$ due to nonlinearity in the RF front-end/low-noise amplifier (LNA) and direct modulation stage, forcing the adaptive scheme to reduce modulation order and throughput. Over the optical-power sweep, when the incident optical power exceeds approximately $-8$ dBm, the system reaches ∼130 Mbps (24-MHz channel) with ${\mathrm{EVM}}_{\mathrm{RMS}}$ approaching ∼1%, highlighting the need for careful joint tuning of RF drive, optical launch power, and wavelength allocation across transceivers. Finally, the integrated access link employs diplexers for transmitter/receiver separation in a 2 × 2 configuration with 2.8 m antenna separation and low channel correlation, demonstrating a 10 m proof-of-concept range and enabling end-to-end spectrum/EVM/throughput observations across the full communication chain. Full article

This paper comprehensively reviews advanced signal processing methods for partial discharge (PD) analysis, covering traditional time-frequency techniques, wavelet transform, Hilbert–Huang transform, and artificial intelligence-based methods. This paper critically examines the principles, advantages, limitations, and applicable scenarios of each method. A key contribution of this review is the systematic comparison of these methods, highlighting their evolution and complementary roles in processing non-stationary and noisy PD signals. However, a significant gap in current research remains the lack of standardized, explainable, and embeddable AI solutions for real-time, fine-grained PD classification. Future trends point to hybrid approaches and edge AI systems that combine physical insights with lightweight deep learning models to improve diagnostic accuracy and deployability. Full article

Irony and sarcasm are forms of expression that emphasize the inconsistency between what is said and what is meant. Correctly classifying such expressions is an important text mining problem, especially on user-centered platforms such as social media. Due to the increasing prevalence of implicit expressions, this topic has become a significant area of research in Natural Language Processing (NLP). However, the simultaneous detection of ironic and sarcastic expressions is highly challenging, as both types of implicit sentiments often convey closely related meanings. To address the detection of irony and sarcasm, this study compares the performance of transformer-based models and an ensemble learning method on Turkish texts, using five textual datasets—monogram, bigram, trigram, quadrigram, and omnigram—that share the same textual content but differ in context length. To improve classification performance, an ensemble learning approach based on the Artificial Rabbit Optimization (ARO) algorithm was implemented, combining the outputs of the models to produce final predictions. The experimental results indicate that as the context width of the datasets increases, the models achieve better predictions, leading to improvements across all performance metrics. The ensemble learning method outperformed individual models in all metrics, with performance increasing as the context expanded, achieving the highest success in the omnigram dataset with 76.71% accuracy, 74.64% precision, 73.29% sensitivity, and 73.96% F-Score. This study demonstrates that both model architecture and data structure are decisive factors in text classification performance, showing that community methods can make significant contributions to the effectiveness of deep learning solutions in low-resource languages. Full article

A common drawback of denoising methods of images is that all pixels are filtered regardless of the amount of noise affecting them individually. Since the essence of denoising is lowpass filtering, subjecting clean pixels to denoising results in blurring. In this paper, a filtering framework is introduced where a fitness function is incorporated in a Kalman filter (KF) to assess the suitability of accepting the value recommended by KF or retaining the existing value of a pixel. Furthermore, a limit on the number of iterations is imposed to avoid over filtering that leads to shrinkage of pixel value ranges of the channels and loss of spectral signatures. In post processing, the means of the filtered channels are shifted to their original values prior to filtering, to spread the pixel value ranges and regain important spectral signatures. The experiments involve the implementation of KF, extended Kalman filter (EKF), Kalman smoother (KS), extended Kalman smoother (EKS) and moving average filter (MAF) in filtering noisy channels of oil palm hyperspectral data under the same framework. Their performances are compared in terms of execution time, SNR gain, NIQE and SSIM metrics. In the second set of experiments, the performance of the improved KF with a fitness function and mean restoration is compared to those of KF and MAF. The results show that the improved KF outperforms the other two filters in the spectral signature characteristics and pixel value ranges of the denoised channels. Full article

Background/Objective: The rise of multidrug-resistant bacteria underscores the urgent need for alternative antimicrobial strategies. Metal-based compounds and bacteriophage (phage) therapy have emerged as promising candidates, but the evolutionary trade-offs associated with these selective pressures and their combination remain poorly understood. This study aimed to investigate how prior exposure to T4 phage influences Escherichia coli B’s subsequent adaptation to iron (III) stress and to assess the resulting phenotypic and genomic signatures of dual resistance. Method: In this study, we performed experimental evolution using Escherichia coli B to investigate adaptive responses under four conditions: control (LB broth), T4 phage-only, iron (III) sulfate-only, and sequential phage followed by iron (III) exposure. Each treatment consisted of ten independently evolved populations (biological replicates), all derived from a common ancestral strain and passaged daily for 35 days. Phage resistance evolved rapidly, with complete resistance observed within 24 h of exposure. Results: In contrast, iron-selected populations evolved tolerance to high iron concentrations (1000–1750 mg/L) over time at a cost to resistance in other metals (gallium and iron (II) and antibiotics (tetracycline). Notably, prior phage exposure altered these outcomes: phage/iron-selected populations retained phage resistance and iron tolerance but showed diminished resistance to iron (II) and distinct antibiotic sensitivity profiles. Whole-genome sequencing revealed stressor-specific adaptations: large deletions in phage receptor-related genes (waaA and waaG) under phage pressure, and selective sweeps in iron-adapted populations affecting regulatory and membrane-associated genes (qseB, basR, aroK, fieF, rseB, and cpxP). Conclusions: These results demonstrate that the sequence of environmental stressors significantly shapes phenotypic and genetic resistance outcomes. Our findings highlight the importance of fitness epistasis and historical contingency in microbial adaptation, with implications for the design of evolution-informed combination therapies. Full article

Dehydroshikimate (DHS) dehydratase (DSD) catalyzes the conversion of DHS into 3,4-dihydroxybenzoic acid (3,4-DHBA), a compound with promising applications across various industries. The DSD from Podospora anserina (DSD_Pa) was characterized and its catalytic properties were compared with those of previously investigated enzymes, AsbF (Bacillus thuringiensis), Qa-4 (Neurospora crassa), and QsuB (Corynebacterium glutamicum), both in vitro and in vivo using tube fermentation. Escherichia coli and C. glutamicum were used as platforms to construct model 3,4-DHBA producers. To increase DHS availability in both hosts, shikimate dehydrogenase AroE was inactivated, and the plasmid pVS7-aroG4, encoding 3-deoxy-D-arabinoheptulosonate 7-phosphate synthase (E. coli), was introduced. In E. coli, heterologous 3,4-DHBA synthesis was achieved through chromosomal integration of dsd genes. The fungal genes were codon-optimized for this bacterium. The same genes were cloned into the pVK9 vector and introduced into C. glutamicum, where 3,4-DHBA degradation was disrupted (ΔpcaHG). AsbF (k_cat ~ 1 s⁻¹) showed poor 3,4-DHBA accumulation in both hosts (1–1.5 g/L). The enzymes with better catalytic characteristics, QsuB (k_cat ~ 60 s⁻¹), DSD_Pa (k_cat ~ 125 s⁻¹), and Qa-4 (k_cat ~ 220 s⁻¹), provided 5 g/L 3,4-DHBA in E. coli and 3 g/L 3,4-DHBA in C. glutamicum, except for Qa-4. The low production (~1.5 g/L) observed for Qa-4 in C. glutamicum might be attributed to a non-optimal nucleotide sequence rich in codons rare for C. glutamicum. Full article

This article presents the decision feedback equalizer (DFE), the maximum likelihood detection (MLD), and the radius-directed equalization (RDE) algorithms designed in MATLAB-R2018a to equalize the received signal in a dispersive optical link up to 120 km. DFE is essential for improving signal quality in several communication systems, including WiFi networks, cable modems, and long-term evolution (LTE) systems. Its capacity to mitigate inter-symbol interference (ISI) and rapidly adjust to channel variations renders it a flexible option for high-speed data transfer and wireless communications. Conversely, MLD is utilized in applications that require great precision and dependability, including multi-input–multi-output (MIMO) systems, satellite communications, and radar technology. The ability of MLD to optimize the probability of accurate symbol detection in complex, high-dimensional environments renders it crucial for systems where signal integrity and precision are critical. Lastly, RDE is implemented as an alternative algorithm to the CMA-based equalizer, utilizing the idea of adjusting the amplitude of the received distorted symbol so that its modulus is closer to the ideal value for that symbol. The algorithms are tested using a converged 5G mm-wave analog radio-over-fiber (A-RoF) system at 60 GHz. Their performance is measured regarding error vector magnitude (EVM) values before and after equalization for different optical fiber lengths and modulation formats (QPSK, 16-QAM, 64-QAM, and 128-QAM) and shows a clear performance improvement of the output signal. Moreover, the performance of the proposed algorithms is compared to three commonly used algorithms: the simple least mean square (LMS) algorithm, the constant modulus algorithm (CMA), and the adaptive median filtering (AMF), demonstrating superior results in both QPSK and 16-QAM and extending the transmission distance up to 120 km. DFE has a significant advantage over LMS and AMF in reducing the inter-symbol interference (ISI) in a dispersive channel by using previous decision feedback, resulting in quicker convergence and more precise equalization. MLD, on the other hand, is highly effective in improving detection accuracy by taking into account the probability of various symbol sequences achieving lower error rates and enhancing performance in advanced modulation schemes. RDE performs best for QPSK and 16-QAM constellations among all the other algorithms. Furthermore, DFE and MLD are particularly suitable for higher-order modulation formats like 64-QAM and 128-QAM, where accurate equalization and error detection are of utmost importance. The enhanced functionalities of DFE, RDE, and MLD in managing greater modulation orders and expanding transmission range highlight their efficacy in improving the performance and dependability of our system. Full article

Background: Neisseria meningitidis (N. meningitidis) is a leading cause of acute meningitis and is classified into 13 serogroups, six of which are predominantly associated with invasive meningococcal disease. This study aimed to investigate the genotype, subgenotype, and antigenic profiles of N. meningitidis serogroup B strains isolated in Vietnam. Methods: Genotyping was performed on 106 N. meningitidis strains isolated from clinical samples from Vietnamese patients and nasopharyngeal swabs of healthy adolescents between 2019 and 2024. The genetic profiles, including the porA, porB, fetA, fHbp, abcZ, adk, aroE, fumC, gdh, pdhC, and pgm genes, were analyzed using Sanger sequencing and bioinformatic methods. Results: We found that 84.9% of the strains carried VR3 families 36 or 35-1, with VR1, VR2, and VR3 families 22-25, 14, and 36 being the most prevalent. Among the 106 serogroup B isolates, 20 variants of the porB allele 3 were identified, with porB 3-1212 being the most frequent (30.2%). Dominant PorB variable loops included L1.6, L4.5, L5.7, L6.6, and L7.13. fHbp variant group 2 was predominant (104/106 strains), and 12 FetA allele variants were identified, with F1-7 being the most common (47.2%). Three clonal complexes were identified, and clonal complex ST-32 was the most predominant. Fifty-five strains (51.9%) belonged to sequence types that have not yet been assigned to any clonal complexes, and 15 strains (14.1%) with allelic profiles were not assigned to STs. The 3-253 and 3-1212 alleles of porB, the F1-7 variant of FetA, the ST-44 and ST-1576 sequence types, and the ST-41/44 complex were observed more frequently in patients compared to asymptomatic carriers, suggesting their association with more virulence. Conclusions: This study showed a high genetic and antigenic diversity of N. meningitidis serogroup B isolates in Vietnam, with VR3 family 36 most common and porB 3-1212 as the predominant allele. fHbp variant group 2 and FetA allele F1-7 were most frequent. ST-32 was the dominant clonal complex, though many strains remained unassigned, highlighting the need for ongoing molecular surveillance. Full article

Significant advances have been made in emotional speech synthesis technology; however, existing models still face challenges in achieving fine-grained emotion style control and simple yet precise emotion intensity regulation. To address these issues, we propose Easy-Control Emotion Text-to-Speech (ECE-TTS), a zero-shot TTS model built upon the F5-TTS architecture, simplifying emotion modeling while maintaining accurate control. ECE-TTS leverages pretrained emotion recognizers to extract Valence, Arousal, and Dominance (VAD) values, transforming them into Emotion-Adaptive Spherical Vectors (EASV) for precise emotion style representation. Emotion intensity modulation is efficiently realized via simple arithmetic operations on emotion vectors without introducing additional complex modules or training extra regression networks. Emotion style control experiments demonstrate that ECE-TTS achieves a Word Error Rate (WER) of 13.91%, an Aro-Val-Domin SIM of 0.679, and an Emo SIM of 0.594, surpassing GenerSpeech (WER = 16.34%, Aro-Val-Domin SIM = 0.627, Emo SIM = 0.563) and EmoSphere++ (WER = 15.08%, Aro-Val-Domin SIM = 0.656, Emo SIM = 0.578). Subjective Mean Opinion Score (MOS) evaluations (1–5 scale) further confirm improvements in speaker similarity (3.93), naturalness (3.98), and emotional expressiveness (3.94). Additionally, emotion intensity control experiments demonstrate smooth and precise modulation across varying emotional strengths. These results validate ECE-TTS as a highly effective and practical solution for high-quality, emotion-controllable speech synthesis. Full article

Phaeodactylum tricornutum is rich in bioactive substances, rendering it valuable in nutrition and medicine. Epigenetic editing mediated by human RNA demethylase FTO can significantly increase the yields of rice and potato and offers significant potential for the genetic breeding of microalgae. This study aimed to enhance the production of certain metabolites in P. tricornutum via FTO-mediated epigenetic editing. Phenotypic analysis revealed that transgenic P. tricornutum exhibits significantly reduced RNA m⁶A modification levels and faster growth, producing markedly higher levels of lipids, proteins, and carotenoids than the wild type. Transcriptome analysis revealed 1009 upregulated genes and 378 downregulated genes. KEGG analysis demonstrated the upregulated expression of multiple key enzymes involved in long-chain fatty acid synthesis (e.g., ACSL, fabF, and fabG), carotenoid synthesis (e.g., crtQ, PDS, and PSY1), and amino acid synthesis (e.g., dapF, glyA, and aroK) in transgenic P. tricornutum, consistent with our phenotypic results. These results indicate that FTO can promote growth and increase the bioactive compound content in P. tricornutum by regulating the m⁶A modification of RNA, and further suggest that FTO has the potential to serve as a new tool for the epigenetic editing of microalgae. Full article

This research presents a novel approach to 28 $\mathrm{GHz}$ impulse radio ultra-wideband (IR-UWB) transmission using pulse position modulation (PPM) over an analog radio-over-fiber (ARoF) link, investigating the impact of fiber-based fronthaul on the overall performance of the communication system. In this setup, an arbitrary waveform generator (AWG) is employed for PPM signal generation, while demodulation is performed with a commercial time-to-digital converter (TDC) based on an event timer. To enhance the reliability of transmitted reference PPM (TR-PPM) signals, the transmission system integrates Gray coding and Consultative Committee for Space Data Systems (CCSDS)-standard-compliant Reed-Solomon (RS) error correcting code (ECC). System performance was evaluated by transmitting pseudorandom binary sequences (PRBSs) and measuring the bit error ratio (BER) across a 5-m wireless link between two 20 $\mathrm{d}\mathrm{B}\mathrm{i}$ gain horn (Ka-band) antennas, with and without a 20 $\mathrm{k}\mathrm{m}$ single-mode optical fiber (SMF) link in transmitter side and ECC at the receiver side. The system achieved a BER of less than 8.17 × 10⁻⁷, using a time bin duration of 200 $\mathrm{p}\mathrm{s}$ and a pulse duration of 100 $\mathrm{p}\mathrm{s}$, demonstrating robust performance and significant potential for space-to-ground telecommunication applications. Full article

Metabolic engineering of the shikimate pathway offers a promising strategy for enhancing the production of aromatic compounds in microbial hosts. However, feedback inhibition of key enzymes, such as the 3-deoxy-D-arabino-heptulosonate 7-phosphate synthase (DAHP synthase), often limits the yield of target products. In this study, we focused on the DAHP synthase (AroF-I) from Pseudomonas putida. Through computational modeling and experimental validation, we identified specific amino-acid residues responsible for tyrosine-mediated feedback inhibition. By targeted mutagenesis, we engineered DAHP synthase variants that exhibit reduced sensitivity to feedback inhibition. The introduction of these engineered enzymes into a metabolically engineered Pseudomonas putida strain resulted in significantly increased production of p-coumaric acid. Our findings provide valuable insights into the regulation of the shikimate pathway and demonstrate the potential of protein engineering to improve microbial production of aromatic compounds. Full article

Usually, hyperspectral data captured from an airborne UAV or satellite contain some noise that can be severe in some channels. Often, channels that are badly affected by the noise are discarded. This is because the corrupted channels cannot be reclaimed by common filtering techniques, making important information in the affected channels different from those of field spectroscopy of similar wavelengths. In this study, a fast-denoising method is implemented on some channels of oil palm hyperspectral data that are badly affected by noise. The amount of noise is unknown, and it varies across the noisy channels from bad to severe. This is different from the data normally used by many studies, which are essentially clean data spiked with mild noise of known variance. The process starts by identifying which noisy channels to filter based on the level of the estimated noise in them. Then, filtering is conducted within each channel and across channels. Once the noise is removed, the improvement in signal-to-noise ratio (SNR) is calculated for each channel. The performance of Kalman, Wiener, Savitzky–Golay, wavelet, and cosine filters is tested in the same framework and the results are compared in terms of execution time, signal-to-noise ratio, and visual quality. The results show that the Kalman filter slightly outperformed the other filters. The proposed scheme was implemented using MATLAB R2023b running on an Intel i7 processor, and the average execution time was less than 1 second for each channel. To the best of our knowledge, this is the first attempt to filter real oil palm hyperspectral data containing speckle noise using a Kalman filter. This technique can be a useful tool to those working in the oil palm industry. Full article