Complexity Reduction Research Articles

Simultaneously resettable zero knowledge protocol in Public Key model

AbstractIn this paper, we construct a 6-round simultaneously resettable sound resettable $$(T, \epsilon )$$ ( T , ϵ ) -zero knowledge protocol for $$\mathsf {NP \cap coNP}$$ NP ∩ coNP in the Public Key model under standard assumptions, comparing with the 27-round simultaneously resettable zero knowledge protocol in the BPK model by Deng et al. in 2011, we have achieved a significant reduction in the round complexity. Our model assumes that both prover and verifier hold public keys, we call it the Public Key model. It is a variation of the traditional BPK model where only the verifier is assumed to hold public keys. In the original BPK model, under the sub-exponential hardness assumption of factoring, we construct a 2-round simultaneously resettable sound resettable $$(T,\epsilon )$$ ( T , ϵ ) -zero knowledge protocol for $$\textsf{NP}$$ NP .

Machine learning-based methods for piecewise digital predistortion in mmW 5G NR systems

AbstractPiecewise linearization techniques require dividing the signal into multiple pieces each linearized individually. Machine learning (ML) is one of the useful tools to perform the automatic division of these pieces. Complexity reduction in the classification of piecewise digital predistortion is possible through carefully constructing features from both the signal statistics and the power amplifier (PA) characteristics. Our paper introduces two low-complex classical ML-based methods that facilitate the classification of baseband input data into distinct segments. These methods effectively linearize PA behavior by employing tailored Volterra models corresponding to each segment. Moreover, we perform an in-depth analysis of the proposed schemes to further optimize their classification and regression complexities. The two proposed low-complexity approaches are validated by laboratory experiments and show up to 4 dB error vector magnitude (EVM) improvement over the conventional approach for a class A PA at 28 GHz. Similarly, the EVM improvement is up to 2 dB over the vector-switched general memory polynomial scheme. With only one indirect learning architecture iteration, the two proposed schemes obey the 5G new radio standard up to 6.5 dB and 7 dB output backoff, respectively.

Abstract 4123630: MRPL44 Plays an Important Role in Cardiac Hypertrophy and Function

Background: Mitochondrial ribosomal large subunit 44 (MRPL44) knockout mice were embryonic lethal, for which mutations are known to cause mitochondrial infantile cardiomyopathy and hypertrophic cardiomyopathy. However, it remains unknown how MRPL44 contributes to cardiac function and hypertrophy. Aims: Our aim is to investigate the effect of MRPL44 haploinsufficiency in mice. Methods: MRPL44 haploinsufficient (MRPL44 +/- ) mice were generated. Mineralocorticoid receptor-associated hypertension mice were induced in MRPL44 +/- and wild-type (WT, MRPL44 +/+ ) mice with subcutaneous infusion of aldosterone(Aldo) and 8% NaCl food for 4 weeks after uninephrectomy. Systolic blood pressure was measured by tail cuffs every week. WB, qPCR, cardiac echo, and histological examinations were performed. RNA sequencing analysis, electron microscopy examinations and mitochondrial activity assay were performed to find differences between MRPL44 +/- and MRPL44 +/+ mice. Results: MRPL44 haploinsufficient mice spontaneously developed left ventricular hypertrophy. Heart rate, blood pressure, and cardiac systolic function were normal in MRPL44 haploinsufficient mice. MRPL44 was decreased about to 70% in MRPL44 haploinsufficient mice and mitochondrial arrangement were impaired in electron microscopic analysis. After Aldo treatment, blood pressure elevation were similar, however, MRPL44 haploinsufficient mice developed left ventricular systolic dysfunction and dilation compared with MRPL44 +/+ mice. WB showed mitochondrial electron transport chain protein complex IV expression was significantly decreased. Furthermore, mitochondrial activity assay showed MRPL44 haploinsufficient mice had a significant reduction in complex IV activity, whereas complex I and II activity were similar to MRPL44 +/+ mice. RNA sequencing analysis showed the significant changes in the expression of ribosomal subunits coded by nucleus in addition to mitochondrial ribosomal subunits. These results indicate MRPL44 plays an important role in the cardiac function of mitochondrial electron transport chain protein complexes via the expression of ribosomal protein subunits coded by both nucleus and mitochondria. Conclusion: MRPL44 haploinsufficient mice spontaneously develop left ventricular hypertrophy and shows systolic dysfunction after aldosterone treatment accompanied with oxidative phosphorylation enzyme dysfunction.

Abstract 4113951: Calcification Alters Luminal Surface Complexity in Cadaveric Left Anterior Descending Arteries

Background: Understanding the intricacies of luminal surface topographic changes in pathologic coronary arteries may yield insight not only on the efficacy of existing clinical interventions (e.g. impact of surface changes on stent anchoring), but also on the subsequent hemodynamic changes and pathophysiology of thrombus formation. In this study, we aim to detect and quantify luminal surface alterations induced by the presence of calcification in cadaveric left anterior descending arteries (LADs) using a novel approach–surface metrology. Methods: LADs (n=10) were harvested from cadaveric hearts using a systematic dissection approach, scanned using the Bruker Skyscan 1173 microCT scanner, and then underwent threshold-based image segmentation on Dragonfly by Object Research Systems to quantify the total calcium volume present throughout the vessel. Each specimen was then splayed open and up to 15 scans were performed at 20X magnification using the Sensofar S Neox optical profiler. Each scan subsequently underwent surface metrologic scale-sensitive fractal analyses in SensoMap 10. Results: Extent of calcification was standardized and expressed using the following ratio: total calcium volume by total vessel length (TC/VL). We considered a TC/VL ratio of 0-0.25 as low calcification and 0.26-0.5 as high calcification. Interestingly, our findings demonstrated statistically significant increases in smooth-rough crossover (SRC) and scale of maximum complexity (Smfc) with positive correlation, but reductions in fractal complexity (Lsfc) and fractal dimension (Dls) with negative correlation, in highly calcified compared to lowly calcified LADs. Conclusions: Our data suggests that the presence of calcium in the walls of LADs may translate to increased roughness in luminal surfaces generally, but smoothness over calcified plaques, locally. Our proposed mechanism is increased endothelial tension directly over areas of calcification, thus reducing surface complexity. Future studies will involve modeling blood flow using smooth particle hemodynamics (SPH) based on complete luminal and surface topographical geometries to evaluate the impact of these surface changes on hemodynamics.

Low hardware-complexity IQ skew tolerant finite field and time domain hybrid adaptive equalization for 400G/800G-ZR coherent transmission

In 400G/800G-ZR transmission systems afflicted by substantial inter-symbol interference (ISI) stemming from chromatic dispersion (CD), frequency-domain adaptive equalizers (FD-AEQs) are preferred to time-domain AEQs (TD-AEQs) as the former have relatively lower computation load. However, the reliance of FD-AEQs on computationally expensive fast Fourier transform (FFT)/inverse fast Fourier transform (IFFT) operations poses a major obstacle in the development of low-power 400G/800G-ZR digital coherent transceivers. Furthermore, to mitigate the significant performance degradation due to receiver in-phase and quadrature (IQ) skew, the employment of twice the number of filters becomes imperative to enable individual adjustments of the I and Q tributaries, nearly doubling the number of necessary FFT/IFFT operations and computation load. This prohibitively high computation load poses a formidable obstacle to the realization of low-power and cost-effective transceivers. To address this issue, we introduce a novel low hardware-complexity IQ skew tolerant finite field (FF) and TD hybrid AEQ for 400G/800G-ZR coherent transmission. By optimizing the AEQ design and the Fermat number transform (FNT) based linear convolution scheme, the proposed hybrid AEQ can achieve a remarkable reduction in hardware complexity by more than 70%, compared with the existing IQ skew tolerant FD-AEQ, while preserving the same receiver sensitivity. Both numerical simulations and experiments demonstrate that the performance of the low complexity hybrid AEQ is the same as the FD-AEQ with much higher complexity. The proposed comprehensive and hardware efficient hybrid AEQ scheme is very appealing for 400G/800G-ZR coherent receivers which need to compensate for large ISI and IQ skew under stringent power constraints.

S-ketamine alleviates depression-like behavior and hippocampal neuroplasticity in the offspring of mice that experience prenatal stress

Prenatal stress exerts long-term impact on neurodevelopment in the offspring, with consequences such as increasing the offspring’s risk of depression in adolescence and early adulthood. S-ketamine can produce rapid and robust antidepressant effects, but it is not clear yet whether and how S-ketamine alleviates depression in prenatally stressed offspring. The current study incestigated the preliminary anti-depression mechanism of S-ketamine in prenatally stressed offspring, particularly with regard to neuroplasticity. The pregnant females were given chronic unpredictable mild stress on the 7th-20th day of pregnancy and their male offspring were intraperitoneally injected with a single dose of S-ketamine (10 mg/kg) on postnatal day 42. Our findings showed that S-ketamine treatment counteracted the development of depression-like behaviors in prenatally stressed offspring. At the cellular level, S-ketamine markedly enhanced neuroplasticity in the CA1 hippocampus: Golgi-Cox staining showed that S-ketamine alleviated the reduction of neuronal complexity and dendritic spine density; Transmission electron microscopy indicated that S-ketamine reversed synaptic morphology alterations. At the molecular level, by western blot and RT-PCR we detected that S-ketamine significantly upregulated the expression of BDNF and PSD95 and activated AKT and mTOR in the hippocampus. In conclusion, prenatal stress induced by chronic unpredictable mild stress leads to depressive-like behaviors and hippocampal neuroplasticity impairments in male offspring. S-ketamine can produce antidepressant effects by enhancing hippocampal neuroplasticity via the BDNF/AKT/mTOR signaling pathway.

Rolling Bearing Fault Diagnosis Model Based on External Attention Integrated Convolutional Neural Network under Imbalanced Data Conditions

Abstract Rolling bearings are essential components in numerous mechanical systems, and their failure can result in considerable downtime and expensive repairs. Therefore, accurate and timely fault diagnosis is vital for effective predictive maintenance and overall reliability. Traditional diagnostic methods often struggle with complex and non-stationary signals, compounded by issues of data imbalance in 
 realworld scenarios. A method for diagnosing rolling bearing faults has been developed in this paper utilizing External Attention (EA), Convolutional Neural Networks (CNN), and Continuous Wavelet Transform (CWT), specifically addressing the challenge of imbalanced sample data. This approach offers significant advantages, including a reduction in complexity by eliminating the need for data augmentation and leveraging external attention for enhanced feature extraction from samples. Compared to other attention mechanisms, this method demonstrates outstanding performance on both training and testing sets with imbalanced samples, exhibiting minimal overfitting tendencies. The proposed CWT-EACNN method effectively addresses the challenge of imbalanced sample data in rolling bearing fault diagnosis, demonstrating exceptional performance and reduced complexity.

Spectral density modulation and universal Markovian closure of fermionic environments.

The combination of chain-mapping and tensor-network techniques provides a powerful tool for the numerically exact simulation of open quantum systems interacting with structured environments. However, these methods suffer from a quadratic scaling with the physical simulation time, and therefore, they become challenging in the presence of multiple environments. This is particularly true when fermionic environments, well-known to be highly correlated, are considered. In this work, we first illustrate how a thermo-chemical modulation of the spectral density allows replacing the original fermionic environments with equivalent, but simpler, ones. Moreover, we show how this procedure reduces the number of chains needed to model multiple environments. We then provide a derivation of the fermionic Markovian closure construction, consisting of a small collection of damped fermionic modes undergoing a Lindblad-type dynamics and mimicking a continuum of bath modes. We describe, in particular, how the use of the Markovian closure allows for a polynomial reduction of the time complexity of chain-mapping based algorithms when long-time dynamics are needed.

Numerical study of effective parameters on deformation and coalescence of ferrofluid droplets under uniform magnetic field

This research examines different numerical techniques for modeling ferrofluids in a non-magnetic liquid subjected to homogeneous and steady magnetic field. It particularly compares the conservative level set method with the Volume of Fluid (VOF) and Simple Coupled Level Set and Volume of Fluid (SCLSVOF) methods. By comparing these methods with experimental data, we established the superiority of the utilized method in this study. Several case studies were conducted to evaluate how a homogeneous magnetic actuation affects ferrofluid dynamics, considering parameters such as initial droplet size, surface tension coefficient, and magnetic susceptibility. Additionally, the study explored the coalescence of two falling ferrofluid droplets under the combined effects of an external magnetic field and gravity. The conservative level set method was shown to be extendable to three-dimensional environments, unlike the standard level set method. The novelty of this work lies in demonstrating that the conservative level set method is particularly effective for ferrofluids, accurately capturing their complex dynamics. The main novelty of this article lies in demonstrating the precision of Conservative Level Set Method while utilizing a reduced number of equations compared to other works. This reduction in complexity enhances the method's efficiency without compromising precision, making it especially suited for applications requiring both speed and accuracy, such as model-based control systems.

Enhancing inertial sensor-based sports activity recognition through reduction of the signals and deep learning

The increasing demand for sport training and health monitoring aligns with contemporary lifestyle trends. Developing a system to support sport training and verify exercise correctness can significantly enhance the acquisition of detailed, subject-specific data. This study aims to evaluate the accuracy of sport exercise recognition while minimizing the number of sensors required. The dataset includes 8,968 samples of exercises such as bar dips, squats, dips, lunges, pull-ups, sit-ups, and push-ups. Data were collected from 60 signals using mobile sensors positioned at the chest, right hand, and right foot of 21 subjects. The objective is to identify the most efficient method for recognizing these activities. Our methodology involved experiments with 21 participants in a custom-built setup and the application of deep learning techniques. Initially, a novel algorithm identified the optimal set of signals. We then tested two scenarios: training a Convolutional Neural Network (CNN) on raw signals and on pre-processed signals to reduce noise. The findings indicate that the magnetic field (MF) signal is crucial for recognizing exercises in both filtered and unfiltered data sets. The CNN’s accuracy was 2–3% higher with unfiltered data and remained robust at 93.7% for training and 90.0% for testing, despite a reduction in model complexity. This method’s practical implications are significant, enhancing sports training systems by reducing the number of sensors needed, thereby improving user comfort. Additionally, it contributes valuable insights to the field of Human Activity Recognition.

In Situ FT-IR Spectroelectrochemistry Reveals Mechanistic Insights into Nitric Oxide Release from Ruthenium(II) Nitrosyl Complexes.

Ruthenium(II) tetraamine nitrosyl complexes with N-heterocyclic ligands are known for their potential as nitric oxide (NO•) donors, capable of releasing NO• through either direct photodissociation or one-electron reduction of the Ru(II)NO+ center. This study delivers a novel insight into the one-electron reduction mechanism for the model complex trans-[RuII(NO)(NH3)4(py)]3+ (RuNOpy, py = pyridine) in phosphate buffer solution (pH 7.4). In situ FT-IR spectroelectrochemistry reveals that the pyridine ligand is readily released upon one-electron reduction of the nitrosyl complex, a finding supported by nuclear magnetic resonance spectroscopy (1H NMR) and electrochemistry coupled to mass spectrometry (EC-MS), which detect free pyridine in solution. However, direct evidence of NO• release from RuNOpy as the primary step following reduction was not observed. Interestingly, FT-IR results indicate that the isomers of the nitrosyl complex, cis-[Ru(NO)(NH3)4(OH)]+ and trans-[Ru(NO)(NH3)4(OH)]+, are formed following reduction and pyridine labilization, initiating an outer-sphere electron transfer process that triggers a chain electron transfer reaction. Finally, nitric oxide is liberated as an end product, arising from the reduction of the hydroxyl isomer complexes cis-[Ru(NO)(NH3)4(OH)]2+ and trans-[Ru(NO)(NH3)4(OH)]2+. This study provides new insights into the reduction mechanism and transformation pathways of ruthenium nitrosyl complexes, contributing to our understanding of their potential as NO• donors.

MRPL44 haploinsufficient mouse spontaneously develops hypertrophic cardiomyopathy and shows systolic dysfunction after aldosterone treatment

Abstract Introduction It has been recently reported there are big differences in pathophysiological and molecular phenotypes in mouse and human hypertrophic cardiomyopathy. These differences are observed all in terms of myocyte redox, mitochondrial number and respiration, mitochondrial reactive oxygen species generation and Ca2+ handling. Therefore we should search for molecules to be able to induce similar phenotype and molecular signaling both in mice and human. Mitochondrial ribosomal large subunit 44 (MRPL44) knockout mice were embryonic lethal, for which mutations are known to cause mitochondrial infantile cardiomyopathy and hypertrophic cardiomyopathy. Purpose Our purpose is to investigate the effect of MRPL44 haploinsufficiency in mice. Methods MRPL44 haploinsufficient (MRPL44+/-) mice were generated. Mineralocorticoid receptor-associated hypertension mice were induced in MRPL44+/- and wild-type (WT, MRPL44+/+) mice with subcutaneous infusion of aldosterone(Aldo) and 8% NaCl food for 4 weeks after uninephrectomy. Systolic blood pressure was measured by tail cuffs every week. WB, qPCR, cardiac echo, and histological examinations were performed. RNA sequencing analysis, electron microscopy examinations and mitochondrial activity assay were performed to find differences between MRPL44+/- and MRPL44+/+ mice. Results MRPL44 haploinsufficient mice spontaneously developed left ventricular hypertrophy in 6 weeks old. Heart rate, blood pressure, and cardiac systolic function were normal in MRPL44 haploinsufficient mice. MRPL44 was decreased about to 70% in MRPL44 haploinsufficient mice and mitochondrial arrangement were impaired in electron microscopic analysis. After Aldo treatment, blood pressure elevation were similar, however, MRPL44 haploinsufficient mice developed left ventricular systolic dysfunction and dilation compared with MRPL44+/+ mice. WB showed mitochondrial electron transport chain protein complex IV expression was significantly decreased. Furthermore, mitochondrial activity assay showed MRPL44 haploinsufficient mice had a significant reduction in complex IV activity, whereas complex I and II activity were similar to MRPL44+/+ mice. RNA sequencing analysis showed the significant changes in the expression of ribosomal subunits coded by nucleus in addition to mitochondrial ribosomal subunits. These results indicate MRPL44 plays an important role in the cardiac function of mitochondrial electron transport chain protein complexes via the expression of ribosomal protein subunits coded by both nucleus and mitochondria. Conclusions MRPL44 haploinsufficient mice spontaneously develop left ventricular hypertrophy and shows systolic dysfunction after aldosterone treatment accompanied with oxidative phosphorylation enzyme dysfunction.

A Low Computational Complexity Family of Spline NLMS Adaptive Filter Algorithm

This paper presents novel and low computational complexity spline adaptive filtering (SAF) algorithms based on partial coefficients selection and adaption. They are addressed partial update SAF normalized least mean squares (PU-SAF-NLMS) algorithms. The PU-SAF-NLMS equations are established via the steepest gradient descent constraint to the proposed cost function. In the proposed algorithms, the filter coefficients are updated based on periodic, sequential, and selective rules, leading to reduction in computational complexity. Furthermore, the convergence speed of PU-SAF-NLMS algorithms is close to the conventional SAF-NLMS. Moreover, the convergence analysis of algorithms is studied. Ultimately, the performance of the presented algorithms is appraised through several experimental results.

Time-Efficient RSA over Large-Scale Multi-Domain EON.

The poor timeliness of routing has always been an urgent problem in practical operator networks, especially in situations with large-scale networks and multiple network domains. In this article, a pruning idea of routing integrated with Dijkstra's shortest path searching is utilized to accelerate the process of routing in large-scale multi-domain elastic optical networks (EONs). The layered-graph approach is adopted in the spectrum allocation stage. To this end, an efficient heuristic algorithm is proposed, called "Branch-and-Bound based Routing and Layered Graph based Spectrum Allocation algorithm (BBR-LGSA)", which is an integrated RSA algorithm. Notably, the significant reduction in algorithm time complexity is not only reflected in the pruning method used in the routing stage but also in the construction of auxiliary graphs during the spectrum allocation stage utilizing the Branch-and-Bound method. Simulation results show that the proposed BBR-LGSA significantly reduces the average running time by nearly 78% with higher spectrum utilization in large-scale multi-domain EONs, compared with benchmark algorithms. In addition, the impact of key parameters on performance comparisons of different algorithms is evaluated.

EKV-VBQ: Ensuring Verifiable Boolean Queries in Encrypted Key-Value Stores.

To address the deficiencies in privacy-preserving expressive query and verification mechanisms in outsourced key-value stores, we propose EKV-VBQ, a scheme designed to ensure verifiable Boolean queries over encrypted key-value data. We have integrated blockchain and homomorphic Xor operations and pseudo-random functions to create a secure and verifiable datastore, while enabling efficient encrypted Boolean queries. Additionally, we have designed a lightweight verification protocol using bilinear map accumulators to guarantee the correctness of Boolean query results. Our security analysis demonstrates that EKV-VBQ is secure against adaptive chosen label attacks (IND-CLA) and guarantees Integrity and Unforgeability under the bilinear q-strong Diffie-Hellman assumption. Our performance evaluations showed reduced server-side storage overhead, efficient proof generation, and a significant reduction in user-side computational complexity by a factor of log n. Finally, GPU-accelerated optimizations significantly enhance EKV-VBQ's performance, reducing computational overhead by up to 50%, making EKV-VBQ highly efficient and suitable for deployment in environments with limited computational resources.

Hydrogel Containing Propolis: Physical Characterization and Evaluation of Biological Activities for Potential Use in the Treatment of Skin Lesions.

Skin injury affects the integrity of the skin structure and induces the wound healing process, which is defined by a well-coordinated series of cellular and molecular reactions that aim to recover or replace the injured tissue. Hydrogels are a group of promising biomaterials that are able to incorporate active ingredients for use as dressings. This study aimed to synthesize hydrogels with and without propolis extract and evaluate their physical characteristics and biological activities in vitro for potential use as active dressings in the treatment of skin lesions. The antifungal [Candida albicans (C. albicans) and Candida tropicalis (C. tropicalis)] and antibacterial [Staphylococcus aureus (S. aureus), Pseudomonas aeruginosas (P. aeruginosas) and Escherichia coli (E. coli)] activity was assessed by the microdilution method in plates and antioxidant potential by the reduction of the phosphomolybdate complex. The hydrogels showed good water absorption capacity, high solubility, and high gel fraction, as well as good porosity, water retention, and vapor transmission rates. They revealed a totally amorphous structure. The extract and the hydrogels containing the propolis extract (1.0% and 2.5%) did not inhibit fungal growth. However, they showed antibacterial activity against strains of S. aureus and P. aeruginosas. Regarding the E. coli strain, only the extract inhibited its growth. It showed good antioxidant activity by the evaluation method used. Therefore, the hydrogels containing propolis extract can be a promising alternative with antibacterial and antioxidant action for use as dressings for the treatment of skin lesions.

Exploring AES Encryption Implementation Through Quantum Computing Techniques

A coming great revolution in technology is quantum computing, which opens new attacks on most of the developed cryptographic algorithms, including AES. These emerging quantum capabilities risk weakening cryptographic techniques, which safeguard a vast amount of data across the globe. This research uses Grover's algorithm to explore the vulnerabilities of the Advanced Encryption Standard to quantum attacks. By implementing quantum cryptographic algorithms and Quantum Error Correction on simulators and quantum hardware, the study evaluates the effectiveness of these techniques in mitigating noise and improving the reliability of quantum computations. The study shows that while AES is theoretically at risk due to Grover’s algorithm, which demonstrates a theoretical reduction in AES key search complexity, current hardware limitations and noise levels encountered in today’s quantum computers reduce the immediate threat and limit practical exploitation. The research also examines NTRU encryption, a quantum-resistant alternative, highlighting its robustness in quantum environments. The findings emphasize the need for further development in QEC and quantum-resistant cryptography to secure digital communications against future quantum threats. Future work will focus on advancing QEC techniques and refining quantum algorithms, addressing both hardware and theoretical advancements, including the potential use of high-capacity processors like Jiuzhang 3.0. These improvements will ensure the scalability of quantum-resistant systems to practical key sizes and usage scenarios.

LFIR-YOLO: Lightweight Model for Infrared Vehicle and Pedestrian Detection

The complexity of urban road scenes at night and the inadequacy of visible light imaging in such conditions pose significant challenges. To address the issues of insufficient color information, texture detail, and low spatial resolution in infrared imagery, we propose an enhanced infrared detection model called LFIR-YOLO, which is built upon the YOLOv8 architecture. The primary goal is to improve the accuracy of infrared target detection in nighttime traffic scenarios while meeting practical deployment requirements. First, to address challenges such as limited contrast and occlusion noise in infrared images, the C2f module in the high-level backbone network is augmented with a Dilation-wise Residual (DWR) module, incorporating multi-scale infrared contextual information to enhance feature extraction capabilities. Secondly, at the neck of the network, a Content-guided Attention (CGA) mechanism is applied to fuse features and re-modulate both initial and advanced features, catering to the low signal-to-noise ratio and sparse detail features characteristic of infrared images. Third, a shared convolution strategy is employed in the detection head, replacing the decoupled head strategy and utilizing shared Detail Enhancement Convolution (DEConv) and Group Norm (GN) operations to achieve lightweight yet precise improvements. Finally, loss functions, PIoU v2 and Adaptive Threshold Focal Loss (ATFL), are integrated into the model to better decouple infrared targets from the background and to enhance convergence speed. The experimental results on the FLIR and multispectral datasets show that the proposed LFIR-YOLO model achieves an improvement in detection accuracy of 4.3% and 2.6%, respectively, compared to the YOLOv8 model. Furthermore, the model demonstrates a reduction in parameters and computational complexity by 15.5% and 34%, respectively, enhancing its suitability for real-time deployment on resource-constrained edge devices.

Lightweight Detection of Broccoli Heads in Complex Field Environments Based on LBDC-YOLO

Robotically selective broccoli harvesting requires precise lightweight detection models to efficiently detect broccoli heads. Therefore, this study introduces a lightweight and high-precision detection model named LBDC-YOLO (Lightweight Broccoli Detection in Complex Environment—You Look Only Once), based on the improved YOLOv8 (You Look Only Once, Version 8). The model incorporates the Slim-neck design paradigm based on GSConv to reduce computational complexity. Furthermore, Triplet Attention is integrated into the backbone network to capture cross-dimensional interactions between spatial and channel dimensions, enhancing the model’s feature extraction capability under multiple interfering factors. The original neck network structure is replaced with a BiFPN (Bidirectional Feature Pyramid Network), optimizing the cross-layer connection structure, and employing weighted fusion methods for better integration of multi-scale features. The model undergoes training and testing on a dataset constructed in real field conditions, featuring broccoli images under various influencing factors. Experimental results demonstrate that LBDC-YOLO achieves an average detection accuracy of 94.44% for broccoli. Compared to the original YOLOv8n, LBDC-YOLO achieves a 32.1% reduction in computational complexity, a 47.8% decrease in parameters, a 44.4% reduction in model size, and a 0.47 percentage point accuracy improvement. When compared to models such as YOLOv5n, YOLOv5s, and YOLOv7-tiny, LBDC-YOLO exhibits higher detection accuracy and lower computational complexity, presenting clear advantages for broccoli detection tasks in complex field environments. The results of this study provide an accurate and lightweight method for the detection of broccoli heads in complex field environments. This work aims to inspire further research in precision agriculture and to advance knowledge in model-assisted agricultural practices.

Should the multi-layer transportation network structure be reduced?

ABSTRACT The increasing diversity of transportation modes and the rapid expansion of transportation networks present significant challenges for modeling multi-layer comprehensive transportation networks. It is crucial to determine whether aggregating certain layers is a viable option for balancing complexity reduction and information preservation. This decision defines the layered structures and informs subsequent analyses of these networks. Two-dimensional factors, namely topological structures and transportation attributes, are considered to enhance understanding of the similarities among network layers. The relative entropy and the Gini index are employed as metrics to assess information gain or loss resulting from layer aggregation or segregation, guiding decisions on network reduction. Furthermore, an integrated similarity measure, based on the quantum Jensen-Shannon divergence and the Gower distance, is utilized to identify the optimal aggregation sequences. Two real-world transportation networks serve as case studies. Results demonstrate that these transportation networks are more effectively maintained with layer-separated structures, preserving maximum information.