Search

Brain machine interfaces (BMIs) can substantially improve the quality of life of elderly or disabled people. However, performing complex action sequences with a BMI system is onerous because it requires issuing commands sequentially. Fundamentally different from this, we have designed a BMI system that reads out mental planning activity and issues commands in a proactive manner. To demonstrate this, we recorded brain activity from freely-moving monkeys performing an instructed task and decoded it with an energy-efficient, small and mobile field-programmable gate array hardware decoder triggering real-time action execution on smart devices. Core of this is an adaptive decoding algorithm that can compensate for the day-by-day neuronal signal fluctuations with minimal re-calibration effort. We show that open-loop planning-ahead control is possible using signals from primary and pre-motor areas leading to significant time-gain in the execution of action sequences. This novel approach provides, thus, a stepping stone towards improved and more humane control of different smart environments with mobile brain machine interfaces. [ABSTRACT FROM AUTHOR]

An adaptively hybrid method was proposed to improve the performance of fractal coding methods. First, it is found that the range blocks with large variances (RBLVs) play a crucial role in degrading decoded images, and the effect of the remaining range blocks with small variances (RBSVs) can be ignored. Then, an adaptive method was proposed to divide the range blocks into the above two categories: RBLVs and RBSVs. Second, RBLVs were designed to be encoded in an extended domain block pool (EDBP). Then, better block‐matching effect can be obtained, which will result in better decoded image quality. Further, the no‐search fractal encoding method is adopted for RBSVs to achieve faster encoding speed and fewer bits per pixel (bpp). Finally, four fractal coding methods were adopted to assess the performance of the proposed method. Experimental results show that compared with the previous methods, the PSNR quality of decoded images in the proposed method can be improved by about 0.15–0.4 dB, about 20%–35% of the total computations in encoding process can be saved, and about 0.2 bpp can be saved. Moreover, under the same decoding time, the proposed method can achieve comparable or smaller deviations regarding the decoded image. [ABSTRACT FROM AUTHOR]

In this paper, we consider a downlink non-orthogonal multiple access (NOMA) system over Nakagami-m channels. The single-antenna base station serves two single-antenna NOMA users based on statistical channel state information (CSI). We derive the closed-form expression of the exact outage probability under a given decoding order, and we also deduce the asymptotic outage probability and diversity order in a high-SNR regime. Then, we analyze all the possible power allocation ranges and theoretically prove the optimal power allocation range under the corresponding decoding order. The demarcation points of the optimal power allocation ranges are affected by target data rates and total power, without an effect from the CSI. In particular, the values of the demarcation points are proportional to the total power. Furthermore, we formulate a joint decoding order and power allocation optimization problem to maximize the sum throughput, which is solved by efficiently searching in our obtained optimal power allocation ranges. Finally, Monte Carlo simulations are conducted to confirm the accuracy of our derived exact outage probability. Numerical results show the accuracy of our deduced demarcation points of the optimal power allocation ranges. And the optimal decoding order is not constant at different total transmit power levels. [ABSTRACT FROM AUTHOR]

Genetically engineered mouse models play a pivotal role in the modeling of diseases, exploration of gene functions, and the development of novel therapies. In recent years, clustered regularly interspaced short palindromic repeats (CRISPR)-CRISPR-associated protein 9 (Cas9)-mediated genome editing technology has revolutionized the process of developing such models by enabling precise genome modifications of the multiple interested genes simultaneously. Following genome editing, an efficient genotyping methodology is crucial for subsequent characterization. However, current genotyping methods are laborious, timeconsuming, and costly. Here, using targeting the mouse trypsinogen genes as an example, we introduced common applications of CRISPR-Cas9 editing and a streamlined cost-effective genotyping workflow for CRISPR-edited mouse models, in which Sanger sequencing is required only at the initial steps. In the F0 mice, we focused on identifying the presence of positive editing by PCR followed by Sanger sequencing without the need to know the exact sequences, simplifying the initial screening. In the F1 mice, Sanger sequencing and algorithms decoding were used to identify the precise editing. Once the edited sequence was established, a simple and effective genotyping strategy was established to distinguish homozygous and heterozygous status by PCR from tail DNA. The genotyping workflow applies to deletions as small as one nucleotide, multiple-gene knockout, and knockin studies. This simplified, efficient, and cost-effective genotyping shall be instructive to new investigators who are unfamiliar with characterizing CRISPR-Cas9-edited mouse strains. [ABSTRACT FROM AUTHOR]

The rapid serial visual presentation-based brain–computer interface (RSVP-BCI) system achieves the recognition of target images by extracting event-related potential (ERP) features from electroencephalogram (EEG) signals and then building target classification models. Currently, how to reduce the training and calibration time for classification models across different subjects is a crucial issue in the practical application of RSVP. To address this issue, a zero-calibration (ZC) method termed Attention-ProNet, which involves meta-learning with a prototype network integrating multiple attention mechanisms, was proposed in this study. In particular, multiscale attention mechanisms were used for efficient EEG feature extraction. Furthermore, a hybrid attention mechanism was introduced to enhance model generalization, and attempts were made to incorporate suitable data augmentation and channel selection methods to develop an innovative and high-performance ZC RSVP-BCI decoding model algorithm. The experimental results demonstrated that our method achieved a balance accuracy (BA) of 86.33% in the decoding task for new subjects. Moreover, appropriate channel selection and data augmentation methods further enhanced the performance of the network by affording an additional 2.3% increase in BA. The model generated by the meta-learning prototype network Attention-ProNet, which incorporates multiple attention mechanisms, allows for the efficient and accurate decoding of new subjects without the need for recalibration or retraining. [ABSTRACT FROM AUTHOR]

A lossless data compression code based on a binary-coded ternary number representation is investigated. The code is complete, universal, synchronizable, and supports a direct search in a compressed file. A simple monotonous encoding and very fast decoding algorithms are constructed owing to code properties. Experiments show that in natural language text compression, the new code outperforms byte-aligned codes SCDC and RPBC either in compression ratio or in decoding speed. [ABSTRACT FROM AUTHOR]

The prediction of molecular interactions is vital for drug discovery. Existing methods often focus on individual prediction tasks and overlook the relationships between them. Additionally, certain tasks encounter limitations due to insufficient data availability, resulting in limited performance. To overcome these limitations, we propose KGE-UNIT, a unified framework that combines knowledge graph embedding (KGE) and multi-task learning, for simultaneous prediction of drug–target interactions (DTIs) and drug–drug interactions (DDIs) and enhancing the performance of each task, even when data availability is limited. Via KGE, we extract heterogeneous features from the drug knowledge graph to enhance the structural features of drug and protein nodes, thereby improving the quality of features. Additionally, employing multi-task learning, we introduce an innovative predictor that comprises the task-aware Convolutional Neural Network-based (CNN-based) encoder and the task-aware attention decoder which can fuse better multimodal features, capture the contextual interactions of molecular tasks and enhance task awareness, leading to improved performance. Experiments on two imbalanced datasets for DTIs and DDIs demonstrate the superiority of KGE-UNIT, achieving high area under the receiver operating characteristics curves (AUROCs) (0.942, 0.987) and area under the precision-recall curve (AUPRs) (0.930, 0.980) for DTIs and high AUROCs (0.975, 0.989) and AUPRs (0.966, 0.988) for DDIs. Notably, on the LUO dataset where the data were more limited, KGE-UNIT exhibited a more pronounced improvement, with increases of 4.32 |$\%$| in AUROC and 3.56 |$\%$| in AUPR for DTIs and 6.56 |$\%$| in AUROC and 8.17 |$\%$| in AUPR for DDIs. The scalability of KGE-UNIT is demonstrated through its extension to protein–protein interactions prediction, ablation studies and case studies further validate its effectiveness. [ABSTRACT FROM AUTHOR]

Among numerous dynamic scheduling strategies for low‐density parity‐check codes, many of them are of high complexity due to repetitive computation and ordering of belief residuals. To address these challenges, two novel approaches are proposed: the derived informed variable‐to‐check residual belief propagation and the derived variable‐node and variable‐to‐check‐edge residual belief propagation for low‐density parity‐check codes. Simulation results show that the derived dynamic scheduling exhibits a substantial gain of approximately 0.15 dB in signal‐to‐noise ratio over the non‐derived one with considerably lower decoding complexity when targeting a bit‐error rate of 10−4. [ABSTRACT FROM AUTHOR]

In recent times, there has been notable and swift advancement in the field of image dehazing. Several deep learning techniques have demonstrated remarkable proficiency in resolving homogeneous dehazing issues. Nonetheless, the current dehazing approaches are generally formulated to deal with homogeneous haze, which is often undermined in real-world scenarios due to the uncertain haze dispersion. In this paper, we propose a dehazing model named RepDehazeNet by combining a structurally Reparameterization Encoder-Decoder subnet and a Full-Resolution Attention subnet. To be specific, the structural reparameterization idea is introduced into the encoder–decoder subnet to strengthen the feature extraction of dehazed images and improve the feature extraction speed. RepDehazeNet is compared with seven SOTA models on different datasets in terms of PSNR, SSIM, parameter quantity, and inference time. Compared to the DW-GAN model, the proposed RepDehazeNet model reduces the number of parameters by 2.7 million, and improves the inference speed by 90.3%, while achieving a higher PSNR of 0.5 dB on the NH-Haze2021 dataset. The experimental results demonstrate that the proposed RepDehazeNet model can effectively improve the real-time performance, accuracy of dehazing synthesized and nonhomogeneous haze images. [Display omitted] • Structural reparameterization dehazenet: outstanding performance, faster speed. • Replacing Tanh with ReLU leads to better results. • Transfer learning addresses the problem of insufficient samples. • Dual subnets method proves highly effective in datasets of different scales. [ABSTRACT FROM AUTHOR]

Error-correcting codes (ECCs) employed in the state-of-the-art DNA digital storage (DDS) systems suffer from a trade-off between error-correcting capability and the proportion of redundancy. To address this issue, in this study, we introduce soft-decision decoding approach into DDS by proposing a DNA-specific error prediction model and a series of novel strategies. We demonstrate the effectiveness of our approach through a proof-of-concept DDS system based on Reed-Solomon (RS) code, named as Derrick. Derrick shows significant improvement in error-correcting capability without involving additional redundancy in both in vitro and in silico experiments, using various sequencing technologies such as Illumina, PacBio and Oxford Nanopore Technology (ONT). Notably, in vitro experiments using ONT sequencing at a depth of 7× reveal that Derrick, compared with the traditional hard-decision decoding strategy, doubles the error-correcting capability of RS code, decreases the proportion of matrices with decoding-failure by 229-fold, and amplifies the potential maximum storage volume by impressive 32 388-fold. Also, Derrick surpasses 'state-of-the-art' DDS systems by comprehensively considering the information density and the minimum sequencing depth required for complete information recovery. Crucially, the soft-decision decoding strategy and key steps of Derrick are generalizable to other ECCs' decoding algorithms. [ABSTRACT FROM AUTHOR]

Many families of binary nonlinear codes (e.g., Kerdock, Goethals, Delsarte–Goethals, Preparata) can be very simply constructed from linear codes over the Z 4 ring (ring of integers modulo 4), by applying the Gray map to the quaternary symbols. Generalized Kerdock codes represent an extension of classical Kerdock codes to the Z 2 S ring. In this paper, we develop two novel soft-input decoders, designed to exploit the unique structure of these codes. We introduce a novel soft-input ML decoding algorithm and a soft-input soft-output MAP decoding algorithm of generalized Kerdock codes, with a complexity of O (N S log 2 N) , where N is the length of the Z 2 S code, that is, the number of Z 2 S symbols in a codeword. Simulations show that our novel decoders outperform the classical lifting decoder in terms of error rate by some 5 dB. [ABSTRACT FROM AUTHOR]

Remote sensing is one of the major domains witnessing the increasingly significant interest in Hyperspectral image (HSI) classification. One recent approach achieving great success in HSI classification is deep learning. However, most current HSI classification methods are performed on small datasets, using overlapped sub-regions both for training and testing, causing information leakage. Data leaks lead to improper ideal classification results. Thus, more research work is still needed to boost classification performance for non-leaking methods. This paper proposes an Encoder-Decoder deep learning-based method that can further improve the accuracy of HSI classification. The method contains two main parts: an encoder and a decoder. The encoder consists of depthwise separable convolution, squeeze, and excitation blocks based on the popular MobileNetV3 deep learning network, and the decoder is inherited from the U-Net deep learning model. This encoder-decoder model aims to take into account the relationships between neighboring pixels when performing HSI pixel classification. Since the pixel distribution in an HSI dataset is usually imbalanced, the focal loss function is employed during the model's training process to counterbalance the weight difference between the pixel classes and avoid overfitting the classes with few pixels. For performance assessment, we carried out experiments on the AeroRIT dataset, consisting of non-overlapping training, validation, and test sets. We achieved an overall accuracy of 95.54% and a mean intersection over union score of 83.53%, setting state-of-the-art results on this dataset. [ABSTRACT FROM AUTHOR]

Motivation While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. Augmenting LLMs with domain-specific tools such as database utilities can facilitate easier and more precise access to specialized knowledge. In this article, we present GeneGPT, a novel method for teaching LLMs to use the Web APIs of the National Center for Biotechnology Information (NCBI) for answering genomics questions. Specifically, we prompt Codex to solve the GeneTuring tests with NCBI Web APIs by in-context learning and an augmented decoding algorithm that can detect and execute API calls. Results Experimental results show that GeneGPT achieves state-of-the-art performance on eight tasks in the GeneTuring benchmark with an average score of 0.83, largely surpassing retrieval-augmented LLMs such as the new Bing (0.44), biomedical LLMs such as BioMedLM (0.08) and BioGPT (0.04), as well as GPT-3 (0.16) and ChatGPT (0.12). Our further analyses suggest that: First, API demonstrations have good cross-task generalizability and are more useful than documentations for in-context learning; second, GeneGPT can generalize to longer chains of API calls and answer multi-hop questions in GeneHop, a novel dataset introduced in this work; finally, different types of errors are enriched in different tasks, providing valuable insights for future improvements. Availability and implementation The GeneGPT code and data are publicly available at https://github.com/ncbi/GeneGPT. [ABSTRACT FROM AUTHOR]

Background: Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities enables proactive measures to mitigate the risk of severe back pain and disability. Methods: We explore the use of shape auto-encoders for vertebrae, advancing the state of the art through robust automatic segmentation models trained without fracture labels and recent geometric deep learning techniques. Our shape auto-encoders are pre-trained on a large set of vertebrae surface patches. This pre-training step addresses the label scarcity problem faced when learning the shape information of vertebrae for fracture detection from image intensities directly. We further propose a novel shape decoder architecture: the point-based shape decoder. Results: Employing segmentation masks that were generated using the TotalSegmentator, our proposed method achieves an AUC of 0.901 on the VerSe19 testset. This outperforms image-based and surface-based end-to-end trained models. Our results demonstrate that pre-training the models in an unsupervised manner enhances geometric methods like PointNet and DGCNN. Conclusion: Our findings emphasize the advantages of explicitly learning shape features for diagnosing osteoporotic vertebrae fractures. This approach improves the reliability of classification results and reduces the need for annotated labels. [ABSTRACT FROM AUTHOR]

Given an observed low frame rate video, video frame interpolation (VFI) aims to generate a high frame rate video, which has smooth video frames with higher frames per second (FPS). Most existing VFI methods often focus on generating one frame at a specific timestep, e.g., 0.5, between every two frames, thus lacking the flexibility to increase the video's FPS by an arbitrary scale, e.g., 3. To better address this issue, in this paper, we propose an arbitrary timestep video frame interpolation (ATVFI) network with time-dependent decoding. Generally, the proposed ATVFI is an encoder–decoder architecture, where the interpolation timestep is an extra input added to the decoder network; this enables ATVFI to interpolate frames at arbitrary timesteps between input frames and to increase the video's FPS at any given scale. Moreover, we propose a data augmentation method, i.e., multi-width window sampling, where video frames can be split into training samples with multiple window widths, to better leverage training frames for arbitrary timestep interpolation. Extensive experiments were conducted to demonstrate the superiority of our model over existing baseline models on several testing datasets. Specifically, our model trained on the GoPro training set achieved 32.50 on the PSNR metric on the commonly used Vimeo90k testing set. [ABSTRACT FROM AUTHOR]

Each brain response to a stimulus is, to a large extent, unique. However this variability, our perceptual experience feels stable. Standard decoding models, which utilise information across several areas to tap into stimuli representation and processing, are fundamentally based on averages. Therefore, they can focus precisely on the features that are most stable across stimulus presentations. But which are these features exactly is difficult to address in the absence of a generative model of the signal. Here, I introduce genephys, a generative model of brain responses to stimulation publicly available as a Python package that, when confronted with a decoding algorithm, can reproduce the structured patterns of decoding accuracy that we observe in real data. Using this approach, I characterise how these patterns may be brought about by the different aspects of the signal, which in turn may translate into distinct putative neural mechanisms. In particular, the model shows that the features in the data that support successful decoding—and, therefore, likely reflect stable mechanisms of stimulus representation—have an oscillatory component that spans multiple channels, frequencies, and latencies of response; and an additive, slower response with a specific (cross-frequency) relation to the phase of the oscillatory component. At the individual trial level, still, responses are found to be highly variable, which can be due to various factors including phase noise and probabilistic activations. [ABSTRACT FROM AUTHOR]

Brain machine interfaces (BMI) connect brains directly to the outside world, bypassing natural neural systems and actuators. Neuronal-activity-to-motion transformation algorithms allow applications such as control of prosthetics or computer cursors. These algorithms lie within a spectrum between bio-mimetic control and bio-feedback control. The bio-mimetic approach relies on increasingly complex algorithms to decode neural activity by mimicking the natural neural system and actuator relationship while focusing on machine learning: the supervised fitting of decoder parameters. On the other hand, the bio-feedback approach uses simple algorithms and relies primarily on user learning, which may take some time, but can facilitate control of novel, non-biological appendages. An increasing amount of work has focused on the arguably more successful bio-mimetic approach. However, as chronic recordings have become more accessible and utilization of novel appendages such as computer cursors have become more universal, users can more easily spend time learning in a bio-feedback control paradigm. We believe a simple approach which leverages user learning and few assumptions will provide users with good control ability. To test the feasibility of this idea, we implemented a simple firing-rate-to-motion correspondence rule, assigned groups of neurons to virtual "directional keys" for control of a 2D cursor. Though not strictly required, to facilitate initial control, we selected neurons with similar preferred directions for each group. The groups of neurons were kept the same across multiple recording sessions to allow learning. Two Rhesus monkeys used this BMI to perform a center-out cursor movement task. After about a week of training, monkeys performed the task better and neuronal signal patterns changed on a group basis, indicating learning. While our experiments did not compare this bio-feedback BMI to bio-mimetic BMIs, the results demonstrate the feasibility of our control paradigm and paves the way for further research in multi-dimensional bio-feedback BMIs. [ABSTRACT FROM AUTHOR]

Marine oil spills are currently among the most challenging problems in marine environments. Synthetic Aperture Radar (SAR), with all-day and all-weather observation, has demonstrated great potential in oil disaster monitoring. A simple encoder-decoder network model was proposed by using SAR images for effective oil spill detection. The proposed model incorporates an optimized U-Net architecture that reduces computational requirements while maintaining detection performance. This is achieved through shortened encoder and decoder stages, depthwise separable convolutions, group normalization, and bilinear interpolation-based upsampling. To improve the model's generalization, the auto-learning rate and focal loss function are also included. Two public SAR datasets acquired by different sensors have been used to illustrate the efficiency of the proposed model. In addition, the polarimetric information has also been assessed for the detection of oil spill monitoring. The results show that the model can achieve high efficiency at a small model size. The sub-dataset with polarimetric features also achieves a high F1-score of 91.65% and an IoU of 84.59%. [ABSTRACT FROM AUTHOR]

A power line carrier (PLC) communication characteristics‐based method is proposed for single‐phase‐to‐ground fault location in neutral isolated medium voltage meshed distribution networks in this paper. The carrier signals with a time‐varying frequency and constant amplitude are processed by a set of PLC transmitters and receivers, whose placement is optimized by regarding the power network as an undirected graph. Two signal encoding and decoding algorithms for the PLC terminals are proposed to avoid using expensive timing systems between the terminals. The fault location technique is implemented by comparing the cosine similarity of amplitude attenuation and phase offset between the fault and a feature library. The node corresponding to the maximum cosine similarity of the characteristics between the present fault and the library is selected as the location of the current fault. Only one set of low‐cost PLC communication terminals and the widely available power lines are needed in the fault location system, making this approach highly practical. Numerical simulations using MATLAB/Simulink have been performed to verify the technique's feasibility. The results show that the method can accurately locate faults in neutral isolated medium voltage meshed distribution networks. Besides, the presented approach achieves a high level of accuracy in estimating transition resistance values. [ABSTRACT FROM AUTHOR]

Objective: Seventy-five percent of stroke survivors, caregivers, and health care professionals (HCP) believe current therapy practices are insufficient, specifically calling out the upper extremity as an area where innovation is needed to develop highly usable prosthetics/orthotics for the stroke population. A promising method for controlling upper extremity technologies is to infer movement intention non-invasively from surface electromyography (EMG). However, existing technologies are often limited to research settings and struggle to meet user needs. Approach: To address these limitations, we have developed the NeuroLife® EMG System, an investigational device which consists of a wearable forearm sleeve with 150 embedded electrodes and associated hardware and software to record and decode surface EMG. Here, we demonstrate accurate decoding of 12 functional hand, wrist, and forearm movements in chronic stroke survivors, including multiple types of grasps from participants with varying levels of impairment. We also collected usability data to assess how the system meets user needs to inform future design considerations. Main results: Our decoding algorithm trained on historical- and within-session data produced an overall accuracy of 77.1 ± 5.6% across 12 movements and rest in stroke participants. For individuals with severe hand impairment, we demonstrate the ability to decode a subset of two fundamental movements and rest at 85.4 ± 6.4% accuracy. In online scenarios, two stroke survivors achieved 91.34 ± 1.53% across three movements and rest, highlighting the potential as a control mechanism for assistive technologies. Feedback from stroke survivors who tested the system indicates that the sleeve's design meets various user needs, including being comfortable, portable, and lightweight. The sleeve is in a form factor such that it can be used at home without an expert technician and can be worn for multiple hours without discomfort. Significance: The NeuroLife EMG System represents a platform technology to record and decode high-resolution EMG for the real-time control of assistive devices in a form factor designed to meet user needs. The NeuroLife EMG System is currently limited by U.S. federal law to investigational use. [ABSTRACT FROM AUTHOR]

Summary: Power lines have complex transmission characteristics and noise interference when used as information transmission channel, thus limiting their data‐carrying rate and reliability. Impulsive noise is the most dominant factor degrading the performance of communication systems over power lines. To combat the impulsive noise, polar codes are introduced into the orthogonal frequency division multiplexing (OFDM)‐based power line communication (PLC) system. Because the successive cancelation list bit‐flip (SCLF) decoding algorithm of polar codes has high decoding complexity, a low complexity segmented cyclic redundancy check (CRC)‐aided SCLF decoding is proposed to improve the decoding performance. The decoding process can be terminated early with segmented CRC, which can reduce the bit‐flip decoding complexity significantly with short and medium block lengths. Experimental results demonstrate that for various configurations, the proposed decoder outperforms the traditional CRC‐aided SCL decoder in terms of decoding performance and complexity, and the suggested polar codes‐based OFDM‐based PLC system can reduce the bit error rate of the system in the presence of impulsive noise. [ABSTRACT FROM AUTHOR]

Context and Background: This paper addresses the challenge of encoding and decoding numerical data by introducing innovative algorithms utilizing Neutrosophic ASCII codes and ASCII Neutrosophic codes. These codes serve to represent uncertain or imprecise character values through the incorporation of neutrosophic numbers, encompassing degrees of truth, falsity, and indeterminacy. Motivation: The study stems from the necessity to effectively represent uncertain or imprecise character values in numerical data. This is crucial in diverse applications where handling uncertain or ambiguous data is a prevalent concern. Hypothesis: We hypothesize that employing Neutrosophic ASCII codes and ASCII Neutrosophic codes in encoding and decoding numerical data can provide a robust solution for representing uncertain or imprecise character values. Methods: The encoding algorithm in this study transforms each character in the ASCII string into its corresponding ASCII code, utilizing either 7 or 8 bits based on the code type. This algorithm calculates the degree of truth, falsity, and indeterminacy for each bit, considering the uncertainty or ambiguity associated with the character. The resulting neutrosophic numbers are appended to create the Neutrosophic ASCII code or ASCII Neutrosophic code. The decoding algorithm partitions the code into groups of neutrosophic numbers, calculates the associated degrees of truth, falsity, and indeterminacy for each ASCII bit, and converts the neutrosophic numbers back to ASCII codes, reconstructing the original ASCII character string. Results: Our study yields a novel and effective approach for encoding and decoding numerical data, demonstrating the potential of Neutrosophic ASCII codes and ASCII Neutrosophic codes in representing uncertain or imprecise character values. Conclusions: The proposed algorithms offer a promising solution for handling uncertain or ambiguous data in numerical encoding and decoding. The specific and quantitative results highlight the efficacy of Neutrosophic ASCII codes and ASCII Neutrosophic codes, showcasing their potential applicability in various domains requiring robust solutions for uncertain or imprecise character representation in numerical data. [ABSTRACT FROM AUTHOR]

Computational fluid dynamics (CFD) plays a critical role in many scientific and engineering applications, with aerodynamic design optimization being a primary area of interest. Recently, there has been much interest in using artificial intelligence approaches to accelerate this process. One promising method is the graph convolutional neural network (GCN), a deep learning method based on artificial neural networks (ANNs). In this paper, we propose a novel GCN-based aerodynamic design optimization acceleration framework, GCN-based aerodynamic design optimization acceleration framework. The framework significantly improves processing efficiency by optimizing data flow and data representation. We also introduce a network model called GCN4CFD that uses the GCF framework to create a compact data representation of the flow field and an encoder–decoder structure to extract features. This approach enables the model to learn underlying physical laws in a space-time efficient manner. We then evaluate the proposed method on an airfoil aerodynamic design optimization task and show that GCN4CFD provides a significant speedup compared to traditional CFD solvers while maintaining accuracy. Our experimental results demonstrate the robustness of the proposed framework and network model, achieving a speedup average of 3. 0 ×. [ABSTRACT FROM AUTHOR]

Encoding a dictionary into another representation means that all the words can be stored in the dictionary in a more efficient way. In this way, we can complete common operations in dictionaries, such as (1) searching for a word in the dictionary, (2) adding some words to the dictionary, and (3) removing some words from the dictionary, in a shorter time. Binary decision diagrams (BDDs) are one of the most famous representations of such encoding and are widely popular due to their excellent properties. Recently, some people have proposed encoding dictionaries into BDDs and some variants of BDDs and showed that it is feasible. Hence, we further investigate the topic of encoding dictionaries into decision diagrams. Tagged sentential decision diagrams (TSDDs), as one of these variants based on structured decomposition, exploit both the standard and zero-suppressed trimming rules. In this paper, we first introduce how to use Boolean functions to represent dictionary files and then design an algorithm that encodes dictionaries into TSDDs with the help of tries and a decoding algorithm that restores TSDDs to dictionaries. We utilize the help of tries in the encoding algorithm, which greatly accelerates the encoding process. Considering that TSDDs integrate two trimming rules, we believe that using TSDDs to represent dictionaries would be more effective, and the experiments also show this. [ABSTRACT FROM AUTHOR]

This paper studies binary reverse multi-delimiter (RMD) data compression codes. RMD codes have a range of useful properties, such as unique decodability, completeness, universality, synchronizability, recognition using a finite automaton, and the ability for rapid data retrieval within an encoded file. The authors have constructed a simple monotonic mapping from the set of non-negative integers to the codeword set. Based on this mapping, they have developed a fast byte-aligned decoding algorithm. Computer experiments demonstrate that we can decode RMD codes nearly as quickly as the SCDC code and several times faster than the Fibonacci code. Compared to known codes of a similar type, RMD codes exhibit a better compression ratio for natural language texts (more than four times closer to the entropy bound than SCDC). Additionally, the paper describes a technology for preprocessing natural language texts, which, combined with encoding using RMD codes, enhances the efficiency of powerful modern archivers. [ABSTRACT FROM AUTHOR]

In the context of the rapid development of quantum computing technology, in order to meet the security requirements of cryptographic applications, this paper proposed an ElGamal public key cryptosystem based on Polar codes. The paper adopted Polar codes as the public code in the ElGamal public key cryptosystem based on error-correcting codes, used SC decoding algorithm to decode, and analyzed the decoding failure probability and security of the scheme. The results show that the algorithm has a high transmission rate, the selected parameters meet the requirements of information set decoding complexity and decoding failure probability, and the algorithm meets IND-CPA security. [ABSTRACT FROM AUTHOR]

The residual belief propagation (RBP) algorithm, which is the most classic informed dynamic scheduling strategy, achieves outstanding performance in error correction and can drastically accelerate convergence speed. However, the greedy algorithmic property of this iterative decoding will inevitably cause loss of decoding performance. To address this, a novel algorithm called the partial average bundle residual belief propagation (PABRBP) is proposed in this paper. According to the construction characteristics of a base matrix of protograph‐LDPC codes, informed dynamic scheduling (IDS) strategies are applied to an edge bundle of base matrices for the first time. This edge bundle of the base matrix can be applied to a corresponding cyclic permutation matrix. Furthermore, the update level of each bundle is determined by the value of the Partially Average Bundle Residual (PABR). Therefore, the edge message with the maximum residual in each bundle is updated in order, and the process of iterative decoding is less likely to become trapped in a local optimum. Additionally, the generation of silent nodes is reduced as much as possible. To further improve the PABRBP decoding performance for medium and long codes over the fading channel, the adjusted compensation term is periodically introduced. Analysis and simulation results show that PABRBP demonstrates a notable convergence quality and decoding performance improvement over the fading channels compared to existing state‐of‐art IDS algorithms. [ABSTRACT FROM AUTHOR]

Background: Computer‐aided diagnosis is of great significance to improve the diagnostic accuracy of pancreatic cancer that has an insidious course and does not have obvious symptoms at first. However, segmentation of pancreatic cancer is challenging because the tumors vary in size with the smallest tumor having a size of about 0.5 cm$cm$ in diameter, and most of them have irregular shapes and unclear boundaries. Purpose: In this study, we developed a deep learning architecture Multi‐Scale Channel Attention Unet (MSCA‐Unet) for pancreatic tumor segmentation and collected CT images of 419 patients from The Affiliated Hospital of Qingdao University and a public dataset. We embedded the multi‐scale network into the encoder to extract semantic information at different scales and the decoder to provide supplemental information to overcome the loss of information in the upsampling and the drift of the localized tumor due to the upsampling and skip connections. Methods: We adopted the channel attention unit after the multi‐scale convolution to emphasize the informative channels, which was observed to have the effects of accelerating the positioning process, reducing false positives, and improving the accuracy of outlining very small, irregular pancreatic tumors. Results: Our results show that our network outperformed the other current mainstream segmentation networks and achieved a Dice index of 68.03%, a Jaccard of 59.31%, and an FPR of 1.36% on the private dataset Task‐01 without data pre‐processing. Compared with the other pancreatic tumor segmentation networks on the public dataset Task‐02, our network produced the best Dice index, 80.12%, with the assistance of the data pre‐processing scheme. Conclusions: This study strategically utilizes the multi‐scale convolution and channel attention mechanism of the architecture to provide a dedicated network for segmentation of small and irregular pancreatic tumors. [ABSTRACT FROM AUTHOR]

Automatically describing the detail and content of the image is a meaningful but difficult task. In this paper, we propose a variety of optimization improvements to enhance the encoder and decoder for image captioning, called multi-channel weighted fusion. In the presented model, we propose multi-channel encoder which is able to extract different features of the same image by combining various models and algorithms. In order to avoid dimensional explosion caused by multi-channel encoder, we employ the reducing multilayer perceptron to reduce the dimension and discuss how to train the reducing multilayer perceptron. For the decoder part, we discuss how the decoder receives features from different channels and propose a technique for fusing independent and identically typed decoders. To get a better description generated by the decoder, we exploit the voting weight strategy for decoder fusion and explore the entropy function to choose the best distribution. The experiment on datasets Flickr-8k, Flickr-30k and MS COCO demonstrates that the proposed model is compatible with most features with low error rate. For instance, our model is specifically outstanding on METEOR score. [ABSTRACT FROM AUTHOR]

Skin cancer, also known as melanoma, is a deadly form of skin cancer that can significantly improve survival rates when diagnosed at an early stage. It is usually diagnosed visually from dermoscopic images, and such visual assessment of skin cancer by the naked eye is a challenging and arduous task. Therefore, the detection of melanoma from dermoscopic images using trained artificial intelligence models is of great importance today. However, since melanoma is a rare disease, existing databases of skin lesions often contain highly unbalanced numbers of benign and malignant samples. In this paper, we propose a new one‐class classification‐based skin lesion classification strategy for small and unbalanced datasets. One‐class classification (OCC) is a special case of multi‐classification. OCC aims to learn a descriptive paradigm from positive class data (true data) during training and reject pseudo data (fake data) that do not conform to the paradigm during inference. OCC has great potential for application in anomaly detection problems. We have analyzed several approaches to the OCC task in recent years and propose a new design paradigm for the OCC problem, taking into account the unbalanced data set of the melanoma classification task. We have designed an improved OCC network based on this design paradigm, where the network is based on the architecture of a residual neural network, combining the coding and decoding idea of variational self‐encoder and the adversarial training idea of an adversarial neural network, using binary cross‐entropy as the loss function and introducing the channel attention mechanism. Tests on several publicly available dermatology datasets show that this improved OCC network addresses the unbalanced dataset situation in melanoma image classification to some extent while having relatively excellent performance. Compared with some traditional networks, it can obtain more stable training results and perform more consistently on complex datasets. [ABSTRACT FROM AUTHOR]

In the systems of industrial robotics and autonomous vehicles, instance segmentation is widely employed. However, manually labelling an object outline is time‐consuming. In order to reduce annotation costs, we present a weakly supervised instance segmentation method in this article. A deeply convolutional network is first used to construct multi‐scale feature maps for each object in the input image. After that, the encoder‐decoder framework with dynamic convolution is utilised to enhance model capacity and efficiency, while avoiding the issues of anchor design, proposal selection, and RoIAlign implementation. In particular, Dynamic Heads are used in the encoder to create dynamic convolution kernels, while Instance Heads are used in the decoder to provide the global feature map. With dynamic convolution, each instance can be segmented independently, reducing interference with other instances and improving segmentation accuracy. Under the supervision of projection loss and pixel point colour pairing loss, the contours of each object are finally outlined. On the PASCAL VOC and MS COCO datasets, the proposed method is competitive with more sophisticated approaches. In the VOC dataset, segmentation performance achieved 37.6% average precision with ResNet‐101 and FPN networks. The extensively visualised results demonstrate the effectiveness of the proposed encoder‐decoder framework with dynamic convolution. [ABSTRACT FROM AUTHOR]

Summary: A novel scheme for designing polar codes with specific decoding schemes in the additive white Gaussian noise channel is presented in this paper. The code construction strategy is built on the genetic algorithm (GA) where successive evolution of populations (or group of information sets) leads toward fittest candidate to attain finest error‐rates. In this work, it is shown that better error‐rates can be attained by both successive cancelation list decoding using GA with no cyclic redundancy check (CRC) and belief propagation decoding using GA with no CRC and no list, compared to existing polar decoding schemes. Our proposed polar code design scheme using GA has the ability to attain a target block error rates with the least possible SNR and using no additional CRC by exploiting least belief propagation iterations or lesser successive cancelation list list size with no self‐alterations in the decoding algorithm. [ABSTRACT FROM AUTHOR]

A key component of many graph neural networks (GNNs) is the pooling operation, which seeks to reduce the size of a graph while preserving important structural information. However, most existing graph pooling strategies rely on an assignment matrix obtained by employing a GNN layer, which is characterized by trainable parameters, often leading to significant computational complexity and a lack of interpretability in the pooling process. In this paper, we propose an unsupervised graph encoder–decoder model to detect abnormal nodes from graphs by learning an anomaly scoring function to rank nodes based on their degree of abnormality. In the encoding stage, we design a novel pooling mechanism, named LCPool, which leverages locality-constrained linear coding for feature encoding to find a cluster assignment matrix by solving a least-square optimization problem with a locality regularization term. By enforcing locality constraints during the coding process, LCPool is designed to be free from learnable parameters, capable of efficiently handling large graphs, and can effectively generate a coarser graph representation while retaining the most significant structural characteristics of the graph. In the decoding stage, we propose an unpooling operation, called LCUnpool, to reconstruct both the structure and nodal features of the original graph. We conduct empirical evaluations of our method on six benchmark datasets using several evaluation metrics, and the results demonstrate its superiority over state-of-the-art anomaly detection approaches. [ABSTRACT FROM AUTHOR]

Polar codes, as the coding scheme for the control channel in fifth-generation mobile communication technology (5G), have attracted widespread attention since their proposal. As a mainstream decoding algorithm for polar codes, the successive cancellation list (SCL) decoder usually improves the error correction performance by increasing the list size, but this method suffers from the problems of high decoding complexity. To address this problem, this paper proposes a layered-search bit-flipping (LS-SCLF) decoding algorithm based on SCL decoding. Firstly, a new flip-bit metric is proposed, which derives a formula to approximate the probability of an error occurring in an information bit. This formula introduces a perturbation parameter to improve the calculation accuracy. Secondly, a compromise scheme for determining the perturbation parameter is proposed. The scheme uses Monte Carlo simulation to determine an optimized parameter for the precise positioning of the first erroneous decoded bit under different decoding conditions. Finally, a layered search strategy is adopted to sequentially search the erroneous decoded bits from the low order to high order, which can correct up to multiple bits at the same time. Simulation results show that the proposed algorithm achieves improved error correction performance with a slight increase in decoding complexity compared to the generalized SCL-Flip (GSCLF) decoding algorithm. This algorithm also achieves a good balance between the error correction performance and decoding complexity. [ABSTRACT FROM AUTHOR]

JPEG is the international standard for still image encoding and is the most widely used compression algorithm because of its simple encoding process and low computational complexity. Recently, many methods have been developed to improve the quality of JPEG images by using deep learning. However, these methods require the use of high-performance devices since they need to perform neural network computation for decoding images. In this paper, we propose a method to generate high-quality images using deep learning without changing the decoding algorithm. The key idea is to reduce and smooth colors and gradient regions in the original images before JPEG compression. The reduction and smoothing can suppress red block noise and pseudo-contour in the compressed images. Furthermore, high-performance devices are unnecessary for decoding. The proposed method consists of two components: a color transformation network using deep learning and a pseudo-contour suppression model using signal processing. The experimental results showed that the proposed method outperforms standard JPEG in quality measurements correlated with human perception. [ABSTRACT FROM AUTHOR]

OPC is a very time consuming process for mask synthesis. Quick and accurate OPC using GCN with layout encoder and mask decoder is proposed. (1) GCN performs a series of aggregation with MLP for correction process. A feature of a particular polygon is aggregated with weighted features of neighbor polygons; this is a key motivation of using GCN since one polygon should be corrected while its neighbors are taken into account for more accurate correction. (2) GCN inputs are provided by a layout encoder, which extracts a feature from each layout polygon. GCN outputs, features corresponding to corrected polygons, are processed by a mask decoder to yield the final mask pattern. (3) The encoder and decoder originate from respective autoencoders. High fidelity of decoder is a key for OPC quality. This is achieved by collective training of the two autoencoders with a single loss function while the encoder and decoder are connected. Experiments demonstrate that the proposed OPC achieves 47% smaller EPE than OPC using a simple MLP model. [ABSTRACT FROM AUTHOR]

The study uses phase triangulation methods to examine the development of image processing algorithms for measuring a three-dimensional (3D) surface profile. An algorithm is proposed for decoding images of an object in structured light based on an iterative search for the minimum deviation of the model function using measurement results and compensating for the nonlinearity of the transceiver path of the measuring complex. A distinctive feature of the proposed method is that the search for the model function is desired in the form of a second-degree polynomial, ensuring the stability of the method against nonlinear distortions caused by power-law transformations of the transceiver path. The interval search method is used to reduce algorithmic complexity qualitatively. The proposed algorithm provides a stable search for the value of the initial phase shift in object images, is resistant to noise and nonlinear distortions, and allows image processing in 3D scanning systems based on triangulation methods using structured illumination and phase triangulation. Thus, the algorithm will be useful for data processing during the operation of measuring systems with a nonlinear transceiver path and measurement time constraints. [ABSTRACT FROM AUTHOR]

Automated guided vehicles (AGVs) are one of the core technologies for building unmanned autonomous integrated automated electric meter verification workshops in metrology centers. However, complex obstacles on the verification lines, frequent AGV charging, and multi-AGV collaboration make the scheduling problem more complicated. Aiming at the characteristics and constraints of AGV transportation scheduling for metrology verification, a multi-AGV scheduling model was established to minimize the maximum completion time and charging cost, integrating collision-avoidance constraints. An improved snake optimization algorithm was proposed that first assigns and sorts tasks based on AGV-order-address three-level mapping encoding and decoding, then searches optimal paths using an improved A* algorithm solves multi-AGV path conflicts, and finally finds the minimum-charging-cost schedule through large neighborhood search. We conducted simulations using real data, and the calculated results reduced the objective function value by 16.4% compared to the traditional first-in-first-out (FIFO) method. It also reduced the number of charges by 60.3%. In addition, the proposed algorithm is compared with a variety of cutting-edge algorithms and the results show that the objective function value is reduced by 8.7–11.2%, which verifies the superiority of the proposed algorithm and the feasibility of the model. [ABSTRACT FROM AUTHOR]

Phase retrieval in holographic data storage by expanded spectrum combined with dynamic sampling method is proposed, which serves to both reduce media consumption and to shorten the iterative number of phase code retrieval. Generally, high-fidelity phase retrieval requires twice Nyquist frequency in phase-modulated holographic data storage. To increase storage density, we only recorded and captured the signal with Nyquist size and used the frequency expanded method to realize high-fidelity phase retrieval. In the decoding process, the iterative Fourier transform algorithm is used to retrieve the phase information of the reconstructed beam. The expanded spectrum is dynamically sampled, which can provide a faster convergence path for the phase retrieval. We aimed to demonstrate the possibility of integrating various methods on the Fourier domain and providing a potential way to improve the performance of holographic data storage systems. The simulation and experimental results proved the combination of processing methods in frequency spectrum was benefit. [ABSTRACT FROM AUTHOR]

Accurately segmenting polyp from colonoscopy images is essential for early screening and diagnosis of colorectal cancer. In recent years, with the proposed encoder‐decoder architecture, many advanced methods have been applied to this task and have achieved significant improvements. However, accurate segmentation of polyps has always been a challenging task due to the irregular shape and size of polyps, the low contrast between the polyp and the background in some images, and the influence of the environment such as illumination and mucus. In order to tackle these challenges, we propose a novel uncertain area attention and cross‐image context extraction network for accurate polyp segmentation, which consists of the uncertain area attention module (UAAM), the cross‐image context extraction module (CCEM), and the adaptive fusion module (AFM). UAAM is guided by the output prediction of the adjacent decoding layer, and focuses on the difficult region of the boundary without neglecting the attention to the background and foreground so that more edge details and uncertain information can be captured. CCEM innovatively captures multi‐scale global context within an image and implicit contextual information between multiple images, fusing them to enhance the extraction of global location information. AFM fuses the local detail information extracted by UAAM and the global location information extracted by CCEM with the decoding layer feature for multiple fusion and adaptive attention to enhance feature representation. Our method is extensively experimented on four public datasets and generally achieves state‐of‐the‐art performance compared to other advanced methods. [ABSTRACT FROM AUTHOR]

Aiming at effectively improving photovoltaic (PV) park operation and the stability of the electricity grid, the current paper addresses the design and development of a novel system achieving the short-term irradiance forecasting for the PV park area, which is the key factor for controlling the variations in the PV power production. First, it introduces the Xception long short-term memory (XceptionLSTM) cell tailored for recurrent neural networks (RNN). Second, it presents the novel irradiance forecasting model that consists of a sequence-to-sequence image regression NNs in the form of a spatio-temporal encoder–decoder including Xception layers in the spatial encoder, the novel XceptionLSTM in the temporal encoder and decoder and a multilayer perceptron in the spatial decoder. The proposed model achieves a forecast skill of 16.57% for a horizon of 5 min when compared to the persistence model. Moreover, the proposed model is designed for execution on edge computing devices and the real-time application of the inference on the Raspberry Pi 4 Model B 8 GB and the Raspberry Pi Zero 2W validates the results. [ABSTRACT FROM AUTHOR]

Recently, graph-based neural networks have been investigated in hyperspectral image (HSI) classification to address the limited global feature representation capability issue of HSI classification methods based on convolutional neural networks (CNN). However, most of the existing graph-based neural networks for HSI classification methods either characterize the relation information by the pair-wise modeling or rely on the CNNs to extract the local spectral–spatial features. To solve this problem, in this paper, a concise hypergraph convolutional network (HGCN) is proposed for semi-supervised HSI classification. To effectively and efficiently capture the global and local features of HSI, the hypergraph model is established on superpixel level which characterizes the spectral affinities rather than the spatial distance. The designed hypergraph model not only incorporates the local homogeneity and complex correlations of HSI but also consumes little computation. Two hypergraph convolution layers are designed to propagate and update the features of nodes. To construct an end-to-end architecture, a mapping matrix is defined for pixels encoding and superpixels decoding. The proposed method is hinged on the goodness the clustering algorithm used in superpixel segmentation and the experiments has shown that the clustering algorithm affects the effectiveness of proposed method. Thus, we give a strategy for selecting the segmentation parameter. The comparison experiments conducted on four real-world benchmark HSI data sets demonstrate that the proposed method provides more stable and effective classification performance than some state-of-the-art deep approaches with very limited training samples. The overall accuracies are 95.42% on Indian Pines, 98.48% on Kennedy Space center, 98.23% on Salinas Valley and 96.91% on Pavia University. [ABSTRACT FROM AUTHOR]

In the field of intelligent vehicle technology, there is a high dependence on images captured under challenging conditions to develop robust perception algorithms. However, acquiring these images can be both time-consuming and dangerous. To address this issue, unpaired image-to-image translation models offer a solution by synthesizing samples of the desired domain, thus eliminating the reliance on ground truth supervision. However, the current methods predominantly focus on single projections rather than multiple solutions, not to mention controlling the direction of generation, which creates a scope for enhancement. In this study, we propose a generative adversarial network (GAN)–based model, which incorporates both a style encoder and a content encoder, specifically designed to extract relevant information from an image. Further, we employ a decoder to reconstruct an image using these encoded features, while ensuring that the generated output remains within a permissible range by applying a self-regression module to constrain the style latent space. By modifying the hyperparameters, we can generate controllable outputs with specific style codes. We evaluate the performance of our model by generating snow scenes on the Cityscapes and the EuroCity Persons datasets. The results reveal the effectiveness of our proposed methodology, thereby reinforcing the benefits of our approach in the ongoing evolution of intelligent vehicle technology. [ABSTRACT FROM AUTHOR]

This paper focuses on the matrix sequences that represent negative indices Pell and Pell–Lucas number. It will specifically provide the important relationships between negative indices Pell and Pell–Lucas number and Pell and Pell–Lucas matrix sequences. The research of new error correcting codes has received a lot of attention in recent years, specifically due to its potential use in quantum-resistant cryptosystems. These matrices are then applied in cryptology and have a great opportunity to report some cases that might be a mistake between the sender and the receiver by using Lucas blocking algorithm. [ABSTRACT FROM AUTHOR]

3D point set reconstruction is an important and challenging 3D shape analysis task. Current state-of-the-art algorithms for 3D point set reconstruction employ a deep neural network (DNN) having an encoder–decoder architecture. Recently, the decoder DNNs that transform multiple 2D planar patches to reconstruct a 3D shape have seen some success. These "patch-folding" decoders are adept at approximating smooth surfaces in 3D objects. However, 3D point sets generated by these decoders often lack local geometrical details, as 2D planar patches tend to overly constrain the patch folding process. In this paper, we propose a novel decoder DNN for 3D point sets called Hyperplane Mixing and Folding Net (HMF-Net). HMF-Net uses less constrained hyperplane, not 2D plane, patches as its input to the folding process. HMF-Net has, as its core building block, a stack of token-mixing layers to effectively learn global consistency among the hyperplane patches. In addition to HMF-Net, we also propose a novel loss for 3D point set reconstruction called Weighted Chamfer Distance (WCD). WCD tries to weight, or amplify, loss from parts of shape that are highly variable across training samples by emphasizing higher point-pair distance values between a generated point set and a groundtruth point set. This helps the decoder DNN learn shape details better. We comprehensively evaluate our algorithm under three 3D point set reconstruction scenarios, that are, shape completion, shape upsampling, and shape reconstruction from 2D images. Experimental results demonstrate that our algorithm yields accuracies higher than the existing algorithms for 3D point set reconstruction. [ABSTRACT FROM AUTHOR]

At present, there are many semantic segmentation algorithms with excellent performance for intelligent driving vehicles, but most of them only work well on scenes with good illumination. In order to solve the problem of scene segmentation under low illumination, this paper proposes a novel semantic segmentation algorithm that combines visible and infrared images. In this algorithm, two parallel encoders are designed as the input of the images, and the decoder divides the fused images output from the encoder. The model is based on ResNet algorithm, and the residual attention module is used in each branch to mine and enhance the spatial features of multilevel channels to extract images information. Experiments are carried out on publicly available thermal infrared and visible datasets. The results show that the algorithm proposed in this paper is superior to the algorithm using only visible images in semantic segmentation of traffic environment. [ABSTRACT FROM AUTHOR]

Generating the decision map with accurate boundaries is the key to fusing multi-focus images. In this paper, we introduce edge-preservation (EP) techniques into neural networks to improve the quality of decision maps, supported by an interesting phenomenon we found: the maps generated by traditional EP techniques are similar to the feature maps in the trained network with excellent performance. Based on the manifold theory in the field of edge-preservation, we propose a novel edge-aware layer derived from isometric domain transformation and a recursive filter, which effectively eliminates burrs and pseudo-edges in the decision map by highlighting the edge discrepancy between the focused and defocused regions. This edge-aware layer is incorporated to a Siamese-style encoder and a decoder to form a complete segmentation architecture, termed Y-Net, which can contrastively learn and capture the feature differences of the sourced images with a relatively small number of training data (i.e., 10,000 image pairs). In addition, a new strategy based on randomization is devised to generate masks and simulate multi-focus images with natural images, which alleviates the absence of ground-truth and the lack of training sets in multi-focus image fusion (MFIF) task. The experimental results on four publicly available datasets demonstrate that Y-Net with the edge-aware layers is superior to other state-of-the-art fusion networks in terms of qualitative and quantitative comparison. [ABSTRACT FROM AUTHOR]