Decoding Mechanism Research Articles

Cap2Seg: leveraging caption generation for enhanced segmentation of COVID-19 medical images

Incorporating medical text annotations compensates for the quality deficiencies of image data, effectively overcoming the limitations of medical image segmentation. Many existing approaches achieve high-quality segmentation results by integrating text into the image modality. However, these approaches require matched image-text pairs during inference to maintain their performance, and the absence of corresponding text annotations results in degraded model performance. Additionally, these methods often assume that the input text annotations are ideal, overlooking the impact of poor-quality text on model performance in practical scenarios. To address these issues, we propose a novel generative medical image segmentation model, Cap2Seg (Leveraging Caption Generation for Enhanced Segmentation of COVID-19 Medical Images). Cap2Seg not only segments lesion areas but also generates related medical text descriptions, guiding the segmentation process. This design enables the model to perform optimal segmentation without requiring text input during inference. To mitigate the impact of inaccurate text on model performance, we consider the consistency between generated textual features and visual features and introduce the Scale-aware Textual Attention Module (SATaM), which reduces the model’s dependency on irrelevant or misleading text information. Subsequently, we design a word-pixel fusion decoding mechanism that effectively integrates textual features into visual features, ensuring that the text information effectively supplements and enhances the image segmentation task. Extensive experiments on two public datasets, MosMedData+ and QaTa-COV19, demonstrate that our method outperforms the current state-of-the-art models under the same conditions. Additionally, ablation studies have been conducted to demonstrate the effectiveness of each proposed module. The code is available at https://github.com/AllenZzzzzzzz/Cap2Seg.

Mixed integer programming and multi-objective enhanced differential evolution algorithm for human–robot responsive collaborative disassembly in remanufacturing system

The recycling of waste products is essential for resource reuse. However, turning operation direction causes significant fatigue to operators handling end-of-life (EoL) products, consequently degrading the recycling efficiency. Accordingly, this study employs responsive collaboration robots to aid operators in turning the operation direction of disassembled products. To solve the human-robot responsive collaboration disassembly line balancing problem (HRRC-DLBP), a mixed integer programming (MIP) model is constructed, and a decoding mechanism is designed in this study. Additionally, a multi-objective enhanced differential evolution algorithm (MEDE) in which the decoding mechanism is incorporated is devised and applied to solve the HRRC-DLBP. The MEDE algorithm is validated by comparing its solution results with those of the MIP model. Finally, the MEDE is used to optimise the EoL printer case for the HRRC-DLBP and the disassembly line balancing problem in which the operation direction is turned by humans (H-DLBP). The optimisation results show that the recycling of EoL products is more efficient using the HRRC-DLBP than employing the H-DLBP.

BaseNet: A Transformer-Based Toolkit for Nanopore Sequencing Signal Decoding

Nanopore sequencing provides a rapid, convenient and high-throughput solution for nucleic acid sequencing. Accurate basecalling in nanopore sequencing is crucial for downstream analysis. Traditional approaches such as Hidden Markov Models (HMM), Recurrent Neural Networks (RNN), and Convolutional Neural Networks (CNN) have improved basecalling accuracy but there is a continuous need for higher accuracy and reliability. In this study, we introduce BaseNet (https://github.com/liqingwen98/BaseNet), an open-source toolkit that utilizes transformer models for advanced signal decoding in nanopore sequencing. BaseNet incorporates both autoregressive and non-autoregressive transformer-based decoding mechanisms, offering state-of-the-art algorithms freely accessible for future improvement. Our research indicates that cross-attention weights effectively map the relationship between current signals and base sequences, joint loss training through adding a pair of forward and reverse decoder facilitate model converge, and large-scale pre-trained models achieve superior decoding accuracy. This study helps to advance the field of nanopore sequencing signal decoding, contributes to technological advancements, and provides novel concepts and tools for researchers and practitioners.

Revealing unexpected complex encoding but simple decoding mechanisms in motor cortex via separating behaviorally relevant neural signals.

In motor cortex, behaviorally relevant neural responses are entangled with irrelevant signals, which complicates the study of encoding and decoding mechanisms. It remains unclear whether behaviorally irrelevant signals could conceal some critical truth. One solution is to accurately separate behaviorally relevant and irrelevant signals at both single-neuron and single-trial levels, but this approach remains elusive due to the unknown ground truth of behaviorally relevant signals. Therefore, we propose a framework to define, extract, and validate behaviorally relevant signals. Analyzing separated signals in three monkeys performing different reaching tasks, we found neural responses previously considered to contain little information actually encode rich behavioral information in complex nonlinear ways. These responses are critical for neuronal redundancy and reveal movement behaviors occupy a higher-dimensional neural space than previously expected. Surprisingly, when incorporating often-ignored neural dimensions, behaviorally relevant signals can be decoded linearly with comparable performance to nonlinear decoding, suggesting linear readout may be performed in motor cortex. Our findings prompt that separating behaviorally relevant signals may help uncover more hidden cortical mechanisms.

Real-Time Wildfire Monitoring Using Low-Altitude Remote Sensing Imagery

With rising global temperatures, wildfires frequently occur worldwide during the summer season. The timely detection of these fires, based on unmanned aerial vehicle (UAV) images, can significantly reduce the damage they cause. Existing Convolutional Neural Network (CNN)-based fire detection methods usually use multiple convolutional layers to enhance the receptive fields, but this compromises real-time performance. This paper proposes a novel real-time semantic segmentation network called FireFormer, combining the strengths of CNNs and Transformers to detect fires. An agile ResNet18 as the encoding component tailored to fulfill the efficient fire segmentation is adopted here, and a Forest Fire Transformer Block (FFTB) rooted in the Transformer architecture is proposed as the decoding mechanism. Additionally, to accurately detect and segment small fire spots, we have developed a novel Feature Refinement Network (FRN) to enhance fire segmentation accuracy. The experimental results demonstrate that our proposed FireFormer achieves state-of-the-art performance on the publicly available forest fire dataset FLAME—specifically, with an impressive 73.13% IoU and 84.48% F1 Score.

A Novel Lightweight Language Model Architecture with Flexible Parameters

In this paper, we introduce SwiFTeDLM, a groundbreaking Language Model architecture that leverages the power of SwiGLU for enhanced decoding capabilities. SwiFTeDLM stands for SwiGLU Enabled Fine-Tuned Decoder based Language Model, representing a fusion of state-of-the-art techniques in natural language processing. Our model achieves superior performance through the integration of SwiGLU, a recently developed activation function, enabling more effective information flow within the decoding mechanism. We conduct extensive experiments to demonstrate the effectiveness of SwiFTeDLM in various language tasks, showcasing its ability to challenge existing models. Additionally, we explore the fine-tuning aspect of the architecture, highlighting its adaptability to specific domains. SwiFTeDLM not only advances the field of language modeling but also opens avenues for further exploration and improvement in natural language understanding and generation. Also we have introduced a new pre-training method and further fine-tuned version of the model.

An efficient high throughput BCH module for multi-bits error correction mechanism on hardware platform

The bose-chaudhuri-hocquenghem (BCH) codes are a cyclic error correction codes (ECC) class. The BCH is constructed by using a polynomial over the Galois field. The BCH codes can detect and correct the multi-bits with an easy decoding mechanism. The BCH codes are used in most of the storage device's cryptography, disk drives, and satellite applications. This manuscript presents an efficient high-throughput BCH module with an encoding and decoding mechanism for multi-bit corrections. The BCH code of (15, k) is used to construct the encoder and decoder architectures. The BCH encoder decoder (ED) module with single error correction (SEC), double error correction (DEC), and triple-error correction (TEC) are discussed in detail. The BCH encoder module uses a linear feedback shift register (LFSR). The BCH decoder with SEC and DEC is constructed using the syndrome generator module (SGM) and chien search module (CSM). The BCH decoder with TEC is designed using SGM, inversion-based berlekamp-massey-algorithm (BMA), and CSMs. The BCH-ED module with SEC, DEC, and TEC utilizes <1 % chip area on Artix-7 FPGA. The BCH-ED with SEC, DEC, and TEC achieves a throughput of 7.13 Gbps, 1.2 Gbps, and 0.803 Gbps, respectively. Lastly, the BCH module is compared with existing BCH approaches with better improvement in chip area, frequency, and throughput parameters.

An online transfer learning based multifactorial evolutionary algorithm for solving the clustered Steiner tree problem

The rapid increase in the number and computing power of devices interacting through the network over the past few years has led to a growing trend of decentralized clustering network architecture. The Clustered Steiner Tree Problem (CluSteiner) is a recently introduced NP-Hard problem and is assessed to be the core of efficient multicast routing in such networks. However, research on this problem in terms of theory and algorithmic design is still in its infancy as current solving approaches are limited in the literature. Lately, the Multifactorial Evolutionary Algorithm (MFEA) has been applied to solve several clustering-structure network design problems for the reason that these problems rarely exist independently and are often deployed concurrently in practice. To effectively transfer knowledge between problems while solving them simultaneously, this paper proposes an approach based on the novel data-driven MFEA-II to deal with the CluSteiner problem. In the proposal, an efficient encoding and a two-level decoding mechanism are introduced, combined with a module capable of online learning the amount of knowledge transferred between tasks that help the algorithm to explore potential regions of the search space. Experiments are undertaken on various test instances to evaluate the efficacy of the proposed algorithm. The empirical results indicate that our proposal can perform well on both metric and non-metric graphs with the statistical tests used to verify its efficiency over other baseline algorithms regarding the solution quality and convergence trend.

Energy, cost and job-tardiness-minimized scheduling of energy-intensive and high-cost industrial production systems

Energy consumption, production cost, and efficiency are highly concerned by decision makers of energy-intensive and high-cost industrial production systems. Intelligent production scheduling is a necessary means to achieve their optimization. This work delves into a novel multi-objective production scheduling problem arising from a steel hot-rolling process, which is a representative energy-intensive and high-cost industrial process. The challenge of the problem involves scheduling customized production jobs subject to intricate process constraints with the goal to minimize three objective functions, i.e., energy consumption, setup cost, and the number of tardy jobs. A mixed integer linear programming model is formulated for the problem. In order to solve it, an improved multi-objective evolutionary algorithm based on decomposition is presented. The algorithm incorporates problem-specific encoding and model-based decoding mechanisms, rendering it well-suited for addressing the concerned multi-constrained multi-objective optimization problem. The introduced modified Tchebycheff approach mitigates the impact of objective functions with varying value ranges on the algorithm’s convergence. Additionally, a Metropolis acceptance criterion is integrated to facilitate the escape from local optimal solutions, enhancing the algorithm’s global optimization capability. Numerous experiments are conducted to verify the effectiveness of the improvements and to compare the performance of the presented algorithm against its competitive peers. The results demonstrate its high performance, suggesting its significant potential for its application to steel hot-rolling systems.

Irregular text block recognition via decoupling visual, linguistic, and positional information

Scene text recognition has made great progress in regular formats, and the recent research has focused on irregular text recognition. In this work, we investigate a new challenge problem of recognizing a text block instance with irregular arrangement of characters, which is referred to as irregular text block recognition (ITBR). This problem is prevalent in daily scenarios, especially with the increasing use of rich text designs in signboards, logos, posters, and other mediums. The primary challenge arises from the weakened position clues and the highly complex reading order, which can often only be deciphered by a heavy reliance on understanding the intrinsic linguistic information. Hence, conventional recognition methods that employ inflexible character grouping rules, coupled with positional information, or constrained by vocabulary reliance, may struggle with the ITBR problem. To this end, we propose a progressive layout reasoning network (PLRN) to recognize the irregular text block by decoupling visual, linguistic, and positional information. PLRN comprises a character spotting module that recognizes the character set based solely on visual features with a new TopK-rank decoding mechanism, and a linkage reasoning module to interpret the character relationships within this set with a progressive refinement strategy. The linkages are initially reasoned by linguistic information and then progressively refined through the incorporation of proximity and tendency information, allowing for explicit decoupling and improved reasoning accuracy. To assess the effectiveness of the proposed method, we construct a new dataset called TextBlock600. This dataset consists of 600 images of irregular text blocks, each with complete sequence annotations. Experimental results demonstrate that PLRN shows promising performance in ITBR, opening up possibilities for further research in this field. Code and datasets will be available at https://github.com/eezyli/PLRN.

Distinct but correct: generating diversified and entity-revised medical response

Medical Dialogue Generation (MDG) is intended to build a medical dialogue system for intelligent consultation, which can communicate with patients in real-time, thereby improving the efficiency of clinical diagnosis with broad application prospects. This paper presents our proposed framework for the Chinese MDG organized by the 2021 China conference on knowledge graph and semantic computing (CCKS) competition, which requires generating context-consistent and medically meaningful responses conditioned on the dialogue history. In our framework, we propose a pipeline system composed of entity prediction and entity-aware dialogue generation, by adding predicted entities to the dialogue model with a fusion mechanism, thereby utilizing information from different sources. At the decoding stage, we propose a new decoding mechanism named Entity-revised Diverse Beam Search (EDBS) to improve entity correctness and promote the length and quality of the final response. The proposed method wins both the CCKS and the International Conference on Learning Representations (ICLR) 2021 Workshop Machine Learning for Preventing and Combating Pandemics (MLPCP) Track 1 Entity-aware MED competitions, which demonstrate the practicality and effectiveness of our method.

Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks

The low-frequency line spectrum of the radiated noise signals of hydroacoustic targets contains features describing the intrinsic properties of the target that make the target susceptible to exposure. In order to extract the line spectral features of underwater acoustic targets, a method combining image processing and a deep autoencoder network (DAE) is proposed in this paper to enhance the low-frequency weak line spectrum of underwater targets in an extremely low signal-to-noise ratio environment based on the measured data of large underwater vehicles. A Gauss–Bernoulli restricted Boltzmann machine (G–BRBM) for real-value signal processing was designed and programmed by introducing a greedy algorithm. On this basis, the encoding and decoding mechanism of the DAE network was used to eliminate interference from environmental noise. The weak line spectrum features were effectively enhanced and extracted under an extremely low signal-to-noise ratio of 10–300 Hz, after which the reconstruction results of the line spectrum features were obtained. Data from large underwater vehicles detected by far-field sonar arrays were processed and the results show that the method proposed in this paper was able to adaptively enhance the line spectrum in a data-driven manner. The DAE method was able to achieve more than double the extractable line spectral density in the frequency band of 10–300 Hz. Compared with the traditional feature enhancement extraction method, the DAE method has certain advantages for the extraction of weak line spectra.

Constructing Perturbation Matrices of Prototypes for Enhancing the Performance of Fuzzy Decoding Mechanism

Granular computing (GrC) embraces a spectrum of concepts, methodologies, methods, and applications, which dwells upon information granules and their processing. Fuzzy C-means (FCM) based encoding and decoding (granulation-degranulation) mechanism plays a visible role in granular computing. Fuzzy decoding mechanism, also known as the reconstruction (degranulation) problem, has become an intensively studied category in recent years. This study mainly focuses on the improvement of the fuzzy decoding mechanism, and an augmented version achieved through constructing perturbation matrices of prototypes is put forward. Particle swarm optimization is employed to determine a group of optimal perturbation matrices to optimize the prototype matrix and obtain an optimal partition matrix. A series of experiments are carried out to show the enhancement of the proposed method. The experimental results are consistent with the theoretical analysis and demonstrate that the developed method outperforms the traditional FCM-based decoding mechanism.

EGFormer: An Enhanced Transformer Model with Efficient Attention Mechanism for Traffic Flow Forecasting

Due to the regular influence of human activities, traffic flow data usually exhibit significant periodicity, which provides a foundation for further research on traffic flow data. However, the temporal dependencies in traffic flow data are often obscured by entangled temporal regularities, making it challenging for general models to capture the intrinsic functional relationships within the data accurately. In recent years, a plethora of methods based on statistics, machine learning, and deep learning have been proposed to tackle these problems of traffic flow forecasting. In this paper, the Transformer is improved from two aspects: (1) an Efficient Attention mechanism is proposed, which reduces the time and memory complexity of the Scaled Dot Product Attention; (2) a Generative Decoding mechanism instead of a Dynamic Decoding operation, which accelerates the inference speed of the model. The model is named EGFormer in this paper. Through a lot of experiments and comparative analysis, the authors found that the EGFormer has better ability in the traffic flow forecasting task. The new model has higher prediction accuracy and shorter running time compared with the traditional model.

A topical VAEGAN-IHMM approach for automatic story segmentation.

Feature representations with rich topic information can greatly improve the performance of story segmentation tasks. VAEGAN offers distinct advantages in feature learning by combining variational autoencoder (VAE) and generative adversarial network (GAN), which not only captures intricate data representations through VAE's probabilistic encoding and decoding mechanism but also enhances feature diversity and quality via GAN's adversarial training. To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. Hidden Markov model (HMM) is a popular approach for story segmentation, in which stories are viewed as instances of topics (hidden states). The number of states has to be set manually but it is often unknown in real scenarios. To solve this problem, we proposed an infinite HMM (IHMM) approach which utilized an HDP prior on transition matrices over countably infinite state spaces to automatically infer the state's number from the data. Given a running text, a Blocked Gibbis sampler labeled the states with topic classes. The position where the topic changes was a story boundary. Experimental results on the TDT2 corpus demonstrated that the proposed topical VAEGAN-IHMM approach was significantly better than the traditional HMM method in story segmentation tasks and achieved state-of-the-art performance.

Enhancing Sign Language Recognition: Leveraging EfficientNet-B0 with Transformer-based Decoding

Sign language recognition (SLR) plays a crucial role in facilitating communication for the hearing-impaired community. Conventional methods for SLR have encountered difficulties in attaining both high precision and efficiency because of the intricate characteristics of sign language motions and the variability in articulation. We propose a novel framework for enhancing SLR by leveraging the efficiency of EfficientNet-B0 as a feature extractor and incorporating a transformer-based decoding mechanism for classification. The objective of our method is to enhance the precision and computational effectiveness of SLR systems, thereby making them more viable for real-world applications. Experimental results on two standard, commonly used sign language datasets: American Sign Language (ASL) and ASL with Digits. The proposed model achieves accuracies of 99.59% on the ASL dataset and an outstanding accuracy of 99.97% on the ASL with Digits dataset, outperforming all other state-of-the-art methods. These results highlight the effectiveness of our framework in accurately recognizing sign language gestures, making it highly suitable for realworld applications. Our study contributes to the advancement of SLR research by introducing a novel methodology that combines the efficiency of EfficientNet-B0 with the expressive capabilities of transformer-based decoding, ultimately improving communication accessibility for individuals who rely on sign language.

A genetic algorithm for the personnel task rescheduling problem with time preemption

In this paper, we study the personnel task rescheduling problem with time preemption. We assume a baseline task schedule has been composed some time in advance that has been rendered infeasible due to operational uncertainty. When restoring the schedule feasibility, the personnel planner takes several considerations into account encompassing the provided service level, resource stability, and task adherence. The latter stems from the possibility that in the problem under study tasks can be interrupted and resumed later, better known as time preemption. We propose a genetic algorithm complemented with local search techniques to compose an operational schedule in an effective manner. The genetic algorithm operates on a dedicated decoding mechanism to compose high-quality duties for individual workers efficiently. Computational experiments are conducted to benchmark the performance of the proposed procedure with other exact and (meta-)heuristic solution procedures, and to demonstrate the value of the algorithm design choices. Furthermore, the impact of preempting tasks in time is assessed by changing the objective function structure and the proportion of non-preemptive tasks.

Modified Proficient Adjacent Error Correcting Codes

As the technology scales down, the soft errors manifested from faults appear in memories due to radiation effects. This paper suggests two decoding mechanisms using hamming bits, extended hamming bits and vertical parity bits applied on matrix codes. Among the proposed two ways of decoding, the method-2 induces less number of errors if the number of adjacent bits exceeds N/2 for N-bit data. Both decoding mechanisms are capable of correcting a maximum of N/2 adjacent errors in N data bits. The codes are modelled in Verilog HDL and are verified in Xilinx Vivado 2021.2 Tool for Zynq 7000 series FPGA. The results prove that the minimum bit overhead of 31.25% and maximum code rate of 76.19% can be achieved if 64-bits of data are processed at a time using proposed AEDAC codes but with a trade-off in terms of area.

Asymmetric solid burst correcting integer codes

With the development of technology, communication channels are increasingly experiencing burst faults of various forms caused by noise elements. To get around this, an appropriate encoding and decoding mechanism should be designed while taking into account things like redundancy, memory usage, efficiency, etc. Motivated by these facts, in this paper, we present a class of integer codes capable of correct asymmetric solid burst errors. In addition to the theoretical foundations, the paper also derives the expressions for the probabilities of incorrect and correct decoding for the proposed codes. Lastly, we compare the proposed codes with other similar codes in terms of code rate and memory consumption.

Proposing Signaling Molecules as Key Optimization Targets for Intensifying the Phytochemical Biosynthesis Induced by Emerging Nonthermal Stress Pretreatments of Plant-Based Foods: A Focus on γ-Aminobutyric Acid.

Emerging evidence has confirmed the role of emerging nonthermal stressors (e.g., electromagnetic fields, ultrasonication, plasma) in accumulating bioactive metabolites in plant-based food. However, the signal decoding mechanisms behind NonTt-driven phytochemical production remain unclear, hindering postharvest bioactive component intensification. This study aims to summarize the association between signaling molecules and bioactive secondary metabolite production under nonthermal conditions, demonstrating the feasibility of enhancing phytochemical accumulation through signaling molecule crosstalk manipulation. Nonthermal elicitors were found to be capable of inducing stress metabolisms and activating various signaling molecules, similar to conventional abiotic stress. A simplified pathway model for nonthermally induced γ-aminobutyric acid accumulation was proposed with reactive oxygen species and calcium signaling being versatile pathways responsive to nonthermal elicitors. Manipulating signal molecules/pathways under nonthermal conditions can intensify phytochemical biosynthesis. Further research is needed to integrate signaling molecule responses and metabolic network shifts in nonthermally stressed plant-based matrices, balancing quality modifications and intensification of food functionality potential.