Loss Of Information Research Articles

Bayesian Safety and Futility Monitoring in Phase II Trials Using One Utility-Based Rule.

For phase II clinical trials that determine the acceptability of an experimental treatment based on ordinal toxicity and ordinal response, most monitoring methods require each ordinal outcome to be dichotomized using a selected cut-point. This allows two early stopping rules to be constructed that compare marginal probabilities of toxicity and response to respective upper and lower limits. Important problems with this approach are loss of information due to dichotomization, dependence of treatment acceptability decisions on precisely how each ordinal variable is dichotomized, and ignoring association between the two outcomes. To address these problems, we propose a new Bayesian method, which we call U-Bayes, that exploits elicited numerical utilities of the joint ordinal outcomes to construct one early stopping rule that compares the mean utility to a lower limit. U-Bayes avoids the problems noted above by using the entire joint distribution of the ordinal outcomes, and not dichotomizing the outcomes. A step-by-step algorithm is provided for constructing a U-Bayes rule based on elicited utilities and elicited limits on marginal outcome probabilities. A simulation study shows that U-Bayes greatly improves the probability of determining treatment acceptability compared to conventional designs that use two monitoring rules based on marginal probabilities.

Adaptive fuzzy neighborhood decision tree

Decision tree algorithms have gained widespread acceptance in machine learning, with the central challenge lying in devising an optimal splitting strategy for node sample subspaces. In the context of continuous data, conventional approaches typically involve fuzzifying data or adopting a dichotomous scheme akin to the CART tree. Nevertheless, fuzzifying continuous features often entails information loss, whereas the dichotomous approach can generate an excessive number of classification rules, potentially leading to overfitting. To address these limitations, this study introduces an adaptive growth decision tree framework, termed the fuzzy neighborhood decision tree (FNDT). Initially, we establish a fuzzy neighborhood decision model by leveraging the concept of fuzzy inclusion degree. Furthermore, we delve into the topological structure of misclassified samples under the proposed decision model, providing a theoretical foundation for the construction of FNDT. Subsequently, we utilize conditional information entropy to sift through original features, prioritizing those that offer the maximum information gain for decision tree nodes. By leveraging the conditional decision partitions derived from the fuzzy neighborhood decision model, we achieve an adaptive splitting method for optimal features, culminating in an adaptive growth decision tree algorithm that relies solely on the inherent structure of real-valued data. Experimental evaluations reveal that, compared with advanced decision tree algorithms, FNDT exhibits a simple tree structure, stronger generalization capabilities, and superior performance in classifying continuous data.

Global-Local Continual Transfer Network for Intelligent Fault Diagnosis of Rotating Machinery

Existing fault diagnosis methods face three fundamental challenges when deployed in the dynamic environment, including insufficient continuous diagnostic capability, poor model generalization performance, and inadequate data privacy protection. To address these problems, we develop a novel continual fault diagnosis framework named Global-Local Continual Transfer Network (GLCTN) for fault classification of unlabeled target samples under different working conditions without any source samples. Specifically, a consistency loss and a mutual information loss are introduced in the proposed GLCTN to transfer the learned diagnostic knowledge. Moreover, a dual-speed optimization strategy is utilized to preserve the acquired diagnostic knowledge and to endow the model with the ability to acquire new knowledge. Validation experiments conducted on an automobile transmission dataset demonstrate that the proposed GLCTN achieves satisfactory diagnostic performance on multiple continuous transfer diagnostic tasks.

CNNCat: categorizing high-energy photons in a Compton/Pair telescope with convolutional neural networks

A Compton/Pair telescope, designed to provide spectral resolved images of cosmic photons from sub-MeV to GeV energies, records a wealth of data in a combination of tracking detector and calorimeter. Onboard event classification can be required to decide on which data to down-link with priority, given limited data-transfer bandwidth. Event classification is also the first and one of the most crucial steps in reconstructing data. Its outcome determines the further handling of the event, i.e., the type of reconstruction (Compton, pair) or, possibly, the decision to discard it. Errors at this stage result in misreconstruction and loss of source information. We present a classification algorithm driven by a Convolutional Neural Network. It provides classification of the type of electromagnetic interaction, based solely on low-level detector data. We introduce the task, describe the architecture and the dataset used, and present the performance of this method in the context of the proposed (e-)ASTROGAM and similar telescopes.

Leaf Identification in High-Density LiDAR-RGB Data

Abstract. Leaf detection through automated segmentation of 3D data is becoming a crucial technique in many applications of digital agriculture. Some 3D segmentation techniques that can be mentioned are based on normal differences and median normalised vector growth. However, applying these approaches to high canopy density data remains challenging. In this study, we propose a processing flow for leaf detection in high canopy density LiDAR-RGB point clouds. First, a noise removal technique inspired by Moving Least Squares (MLS) was applied to the LiDAR point cloud, and a RGB colour was assigned to each point by combining computer vision and photogrammetric methods. Moreover, once the data were suitable for leaf detection, the branches were filtered using the Statistical Outlier Removal (SOR) filter based on an analysis of the statistical behaviour of the neighbourhood. Afterwards, an unsupervised DBSCAN (Density-Based Clustering Non-Parametric Algorithm) method was used to segment similar points. Finally, the points within each cluster were identified as leaf or non-leaf using the RGB values implemented by our method; ground points were filtered out using a maximum height threshold. As a result, the leaf, non-leaf, and ground point identifiers were correct in 98.9% of cases, with the branch filtering technique SOR proving effectiveness in removing branches with low information loss and without additional complex point densification steps in reconstruction. This SOR-based solution overcomes major challenges in semantic segmentation (leaves and branches) in high-density data and potentially contributes to precision agriculture.

A small‐target traffic sign detection algorithm based on partial conv and atrous spatial pyramid

AbstractTraffic sign detection is essential to an intelligent driving assistance system. The deep learning‐based algorithm proposed in this paper aims to address the issue of low detection accuracy caused by the small size and high density of traffic signs in real‐world traffic scenarios. First, to improve the feature extraction module of the backbone network and to increase the model's ability to capture contextual information, partial convolution (PConv) is introduced. Second, to prevent information loss during the downsampling process, a cross‐stage atrous spatial pyramid (ASPPFCSPC) is constructed using atrous convolution. This method combines feature map information from various scales and expands the receptive field. Lastly, the small‐target detection precision is improved by incorporating an additional small‐target detection head, which uses high‐resolution feature maps for shallow features. The detection head is decoupled to extract the location and class information of the predicted target separately, thereby enhancing the generalization ability of the proposed model. Experiments have demonstrated the superiority of the proposed algorithm, as testing on the TT100K dataset resulted in a mAP@0.5 of 91.2% and a mAP@0.5:0.95 of 71.8% using the proposed algorithm.

Enhanced Disease Detection for Apple Leaves with Rotating Feature Extraction

Leaf diseases such as Mosaic disease and Black Rot are among the most common diseases affecting apple leaves, significantly reducing apple yield and quality. Detecting leaf diseases is crucial for the prevention and control of these conditions. In this paper, we propose incorporating rotated bounding boxes into deep learning-based detection, introducing the ProbIoU loss function to better quantify the difference between model predictions and real results in practice. Specifically, we integrated the Plant Village dataset with an on-site dataset of apple leaves from an orchard in Weifang City, Shandong Province, China. Additionally, data augmentation techniques were employed to expand the dataset and address the class imbalance issue. We utilized the EfficientNetV2 architecture with inverted residual structures (FusedMBConv and S-MBConv modules) in the backbone network to build sparse features using a top–down approach, minimizing information loss. The inclusion of the SimAM attention mechanism effectively captures both channel and spatial attention, expanding the receptive field and enhancing feature extraction. Furthermore, we introduced depth-wise separable convolution and the CAFM in the neck network to improve feature fusion capabilities. Finally, experimental results demonstrate that our model outperforms other detection models, achieving 93.3% mAP@0.5, 88.7% Precision, and 89.6% Recall. This approach provides a highly effective solution for the early detection of apple leaf diseases, with the potential to significantly improve disease management in apple orchards.

L2T-DFM: Learning to Teach with Dynamic Fused Metric

The loss function plays a crucial role in the construction of machine learning algorithms. Employing a teacher model to set loss functions dynamically for student models has attracted attention. In existing works, (1) the characterization of the dynamic loss suffers from some inherent limitations, ie, the computational cost of loss networks and the restricted similarity measurement handcrafted loss functions; and (2) the states of the student model are provided to the teacher model directly without integration, causing the teacher model to underperform when trained on insufficient amounts of data. To alleviate the above-mentioned issues, in this paper, we select and weigh a set of similarity metrics by a confidence-based selection algorithm and a temporal teacher model to enhance the dynamic loss functions. Subsequently, to integrate the states of the student model, we employ statistics to quantify the information loss of the student model. Extensive experiments demonstrate that our approach can enhance student learning and improve the performance of various deep models on real-world tasks, including classification, object detection, and semantic segmentation scenarios.

Euler Kernel Mapping for Hyperspectral Image Clustering via Self-Paced Learning

Clustering, as a classical unsupervised artificial intelligence technology, is commonly employed for hyperspectral image clustering tasks. However, most existing clustering methods designed for remote sensing tasks aim to solve a non-convex objective function, which can be optimized iteratively, beginning with random initializations. Consequently, during the learning phase of the clustering model, it may easily fall into bad local optimal solutions and finally hurt the clustering performance. Additionally, prevailing approaches often exhibit limitations in capturing the intricate structures inherent in hyperspectral images and are very sensitive to noise and outliers that widely exist in remote sensing data. To address these issues, we proposed a novel Euler kernel mapping for hyperspectral image clustering via self-paced learning (EKM-SPL). EKM-SPL first employs self-paced learning to learn the clustering model in a meaningful order by progressing samples from easy to complex, which can help to remove bad local optimal solutions. Secondly, a probabilistic soft weighting scheme is employed to measure complexity across the data sample, which makes the optimization process more reasonable. Thirdly, in order to more accurately characterize the intricate structure of hyperspectral images, Euler kernel mapping is used to convert the original data into a reproduced kernel Hilbert space, where the nonlinearly inseparable clusters may become linearly separable. Moreover, we innovatively integrate the coordinate descent technique into the optimization algorithm to circumvent the computational inefficiencies and information loss typically associated with conventional kernel methods. Extensive experiments conducted on classic benchmark hyperspectral image datasets illustrate the effectiveness and superiority of our proposed model.

A Model-Based Reinforcement Learning Algorithm for Multi-Agent Cooperation Nash Equilibrium With Unstable Communication

Solving Nash equilibrium is important to multi-agent systems, in which the communication is an important factor. However, many proposed reinforcement learning (RL) based algorithms take into account the communication factors by assuming stable communication conditions, which does not hold in the real environment. In this paper, we analyze the effect of a typical RL algorithm in the cases of unstable communication and communication failure, which causes information loss between agents, leading to isolation of agents and affecting algorithm convergence. Then, we propose a model-based RL algorithm to solve Nash equilibrium for multi-agent systems when agents are isolated, and prove its convergence and rationality through mathematical proofs. The simulations results show the effectiveness of the proposed algorithm.

Fluid Grey 2: How Well Does Generative Adversarial Networks Learn Deeper Topology Structure in Architecture That Matches Images?

Taking into account the regional characteristics of ‘intrinsic’ and ‘extrinsic’ properties of space is an essential issue in architectural design and urban renewal, which is often achieved step by step using image and graph-based GANs. However, each model nesting and data conversion may cause information loss, and it is necessary to streamline the tools to facilitate architects and users to participate in the design. Therefore, this study hopes to prove that I2I GAN also has the potential to recognize topological relationships autonomously. Therefore, this research proposes a method for quickly detecting the ability of pix2pix to learn topological relationships, which is achieved by adding two Grasshopper-based detection modules before and after GAN. At the same time, quantitative data is provided and its learning process is visualized, and changes in different input modes such as greyscale and RGB affect its learning efficiency. There are two innovations in this paper: 1) It proves that pix2pix can automatically learn spatial topological relationships and apply them to architectural design. 2) It fills the gap in detecting the performance of Image-based Generation GAN from a topological perspective. Moreover, the detection method proposed in this study takes a short time and is simple to operate. The two detection modules can be widely used for customizing image datasets with the same topological structure and for batch detection of topological relationships of images. In the future, this paper may provide a theoretical foundation and data support for the application of architectural design and urban renewal that use GAN to preserve spatial topological characteristics.

Drug-Target Prediction Based on Dynamic Heterogeneous Graph Convolutional Network.

Novel drug-target interaction (DTI) prediction is crucial in drug discovery and repositioning. Recently, graph neural network (GNN) has shown promising results in identifying DTI by using thresholds to construct heterogeneous graphs. However, an empirically selected threshold can lead to loss of valuable information, especially in sparse networks, a common scenario in DTI prediction. To make full use of insufficient information, we propose a DTI prediction model based on Dynamic Heterogeneous Graph (DT-DHG). And progressive learning is introduced to adjust the receptive fields of node. The experimental results show that our method significantly improves the performance of the original GNNs and is robust against the choices of backbones. Meanwhile, DT-DHG outperforms the state-of-the-art methods and effectively predicts novel DTIs.

Dynamic feature and context enhancement network for faster detection of small objects

While traditional object detection methods have achieved significant success in recent years, their performance in detecting small objects in aerial remote sensing images remains unsatisfactory. Small objects often occupy only a few pixels, leading to a loss of fine-grained information. This paper proposes a dynamic feature and context enhancement network (DFCE) to address noise and pixel-level region weighting issues in small object detection. The DFCE network effectively detects small objects by dynamically selecting features within regions and establishing connections between local and global contextual information. The introduced dynamic multi-dimensional attention (DMA) module selects key information via a crossover mechanism and assigns different weights to highlight important features. Based on DMA, the regional feature processing (RFP) module and multi-dimensional pool transformer (MPT) module are developed to capture key information and contextual information, respectively. Experimental results demonstrate that the DFCE network improves average precision (AP) by 3.1%, 9%, and 2.2% on two remote sensing datasets and one conventional dataset, achieving an inference speed of 30 frames per second (FPS). Given these advancements, the DFCE model’s powerful key feature extraction and contextual association capabilities show strong potential for broader applications, including sign language recognition, defect detection in industrial settings, and more.

MGFNet: Cross-scene Crowd Counting via Multistage Gated Fusion Network

Existing crowd counting methods are mainly trained and tested in similar scenarios. When the testing and training scenarios of the model are different, the counting accuracy of these methods will sharply decrease, which seriously limits their practical application. To address this problem, we propose a multistage gated fusion network (MGFNet) for cross-scene crowd counting. MGFNet is primarily composed of dynamic gated convolution units (DGCU) and multilevel scale attention blocks (MSAB) modules. Specifically, DGCU uses a dynamic gating path to supplement detailed information to reduce the loss of crowd information and overestimation of background in different scenarios. MSAB calibrates crowd information at different scales and perspectives in different scenes by generating attention maps with discriminative information. In addition, we used a new global local consistency loss to optimize the model to adapt to changes in crowd density and distribution. Extensive experiments on four different types of scene counting benchmarks show that the proposed MGFNet achieves superior cross-scene counting performance.

Pruned tree-structured temporal convolutional networks for quality variable prediction of industrial process

In real industrial processes, the rapid and accurate acquisition of quality variables is essential. Therefore, this paper proposes a pruned tree-structured temporal convolutional network (PT-TCN) for efficient and accurate variables prediction. First, a novel tree network is developed, utilizing dilated causal convolution blocks as nodes to avoid the loss of local information. Each node extracts distinct local information, and by concatenating all tree nodes, the network can capture a comprehensive range of temporal scales. Then, to avoid the increased complexity caused by the tree structure, we design an online two-stage pruning strategy to compress the tree network without introducing additional computations. During the training process, blocks are initially pruned based on the correlation assessment between quality variables and tree nodes. Subsequently, weight normalization layers are employed to evaluate the importance of output channels in blocks, thereby enabling intra-block channel pruning. The effectiveness of PT-TCN is verified on Tennessee Eastman benchmark process. In addition, experiments on the real zinc flotation process demonstrate that the proposed PT-TCN improves in R2 and MAE by 1.32% and 1.26% respectively in predicting quality variables, and it can reduce 91.8% parameters of the initial tree-structured TCN without sacrificing accuracy.

Fall detection method based on spatio-temporal coordinate attention for high-resolution networks

Fall behavior is closely related to the high mortality rate of the elderly, so fall detection has become an important and urgent research area in human behavior recognition. However, the existing fall detection methods, suffer from the loss of detailed action information during feature extraction due to the downsampling operation, resulting in subpar performance when detecting falls with similar behaviors such as lying and sitting. To solve the challenges, this study proposes a high-resolution spatio-temporal feature extraction method based on a spatio-temporal coordinate attention mechanism. The method employs 3D convolutions to extract spatio-temporal features and utilizes gradual down-sampling to generate a multi-resolution sub-network, thus realizing multi-scale fusion and perception enhancement of details. In particular, this study designs a pseudo-3D basic block, which simulates the ability of 3D convolution, to ensure the running speed of the network while controlling the number of parameters. Further, a spatio-temporal coordinate attention mechanism is designed to accurately extract the spatio-temporal positional changes of key skeletal points and the interrelationships among them. Long-term dependencies in horizontal, vertical, temporal directions are captured through three one-dimensional global pooling operations. Then the long-range relationships and channel correlations among features are captured by cascading and slicing operations. Finally, the key information is effectively highlighted by performing dot-multiplication operations between the feature maps from the horizontal, vertical and temporal directions and the input feature maps. Experimental results on three typical public datasets show that the proposed method can better extract motion features and improve the accuracy of fall detection.

Disentangled feature fusion network for lightweight image super-resolution

Recently, the quality of generated images in image super-resolution (SR) has significantly improved due to the widespread application of convolutional neural networks. Existing super-resolution methods often overlook the importance of network width and instead prioritize designing deeper network structures to improve performance. Deeper networks, however, demand greater computational resources and are more challenging to train, making them less suitable for devices with limited performance. To address this issue, we propose a novel method called the disentangled feature fusion network (DFFN). Specifically, we construct dual feature extraction streams (DFES) using the strategies of feature disentanglement and parameter sharing, which increase the network's width without increasing the number of parameters. To facilitate the interaction of information between the dual feature extraction streams, we design a feature interaction module (FIM) that separately enhances high and low-frequency features. Furthermore, a feature fusion module (FFM) is presented to efficiently fuse different levels of high and low-frequency feature information. The proposed DFFN integrates DFES, FIM, and FFM, which not only widens the network without increasing parameters but also minimizes the loss of crucial feature information. Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms other state-of-the-art lightweight super-resolution methods, achieving a superior balance between parameter quantity, reconstruction performance, and model complexity. The code is available at https://github.com/zhoujy-aust/DFFN.

A hybrid CNN-transformer network: Accurate and efficient semantic segmentation of crops and weeds on resource-constrained embedded devices

Weed control plays a crucial role in agricultural production. The utilization of advanced vision algorithms on intelligent weeding robots enables the autonomous and efficient resolution of weed-related issues. Vision transformers are highly sensitive to plant texture and shape, but their computational cost is too high. Consequently, we propose a novel hybrid CNN-transformer network for the semantic segmentation of crops and weeds on Resource-Constrained Embedded Devices. Our network follows an encoder–decoder structure, incorporating the proposed concat extended downsampling block in the encoder, which increases inference speed by reducing memory access time and improves the accuracy of feature extraction. For global semantic extraction, we introduce the proposed Parallel input transformer semantic enhancement module, which employs a shared transformer block to increase the computation rate. Additionally, Global-Local semantic fusion block mitigates the semantic gap problem well. To fully utilize the transformer’s ability to process plant texture and shape, we employ the fusion enhancement block in the decoder, thus minimizing the loss of feature information. Segmentation results on three publicly benchmark datasets show that our network outperforms the commonly used CNN-based, transformer-based, and hybrid CNN-transformer-based methods in terms of segmentation accuracy. Moreover, our network comprises only 0.1887M parameters and 0.2145G floating-point operations. We also evaluate the inference speed on an NVIDIA Jetson Orin NX embedded system, which result for inference single image 28.28 msec, and achieving a detection speed of 35.36 FPS. The experimental results highlight that our network maintains the best inference speed and exhibits the strongest segmentation performance on resource-constrained embedded systems.

Translation of catch phrases in an audiovisual text

The article discusses the problem of interlinguistic and intercultural transfer of winged words (catch phrases) in an audiovisual text of the Soviet period. The source of the material is the Russian motion picture "Moscow Does Not Believe in Tears" and its translation into English (subtitling), the material is 34 winged words (catch phrases) which were selected with verification based on Internet sources. The purpose of the research is to study the methods/techniques of transferring catch phrases in audiovisual translation (subtitling) from Russian into English, as well as to analyze the results obtained from the point of view of preserving the characteristics inherent in catch phrases and preserving the national cultural component. The main methods are the method of continuous sampling, the method of comparative analysis, the method of contextual analysis, etc. The direction of the translation (Russian-English translation) and the approach chosen by the authors indicate the novelty of the research. Having analyzed the translation of catch phrases, the authors made observations regarding the methods/techniques used which contributed to conveying meaning and complying with the norms of audiovisual translation, as well as to the conclusions that a partial loss of cultural information may occur during translation and that in a situation where a film subsequently becomes a precedent text, postediting may be required, as the conditions of how the text/part of the text functions in the linguoculture of the original language change. The results may be of interest to specialists in the field of audiovisual translation, as well as to philologists, linguists, and to ordinary readers who are interested in translation studies and/or cinematography.

Local Reference Feature Transfer (LRFT): A simple pre-processing step for image enhancement

Low-light, nighttime haze, and underwater images captured in harsh environments typically exhibit color deviations and reduced visibility due to light scattering and absorption. Additionally, we observe an almost complete loss of information in at least one color channel in these degraded images. To repair the lost information in each channel, we present an image preprocessing strategy called Local Reference Feature Transfer (LRFT), which employs the local feature to compensate for the color loss automatically. Specifically, we design a dedicated reference image by fusing the detail, salience, and uniform grayscale images of the raw image that ensures a balanced chromaticity distribution. Subsequently, we employ the local reference feature transfer strategy to migrate the local mean and variance of the reference image to the raw image to get a color-corrected image. Extensive evaluation experiments demonstrate that our proposed LRFT method has good preprocessing performance for the subsequent enhancement of images of different degradation types. The code is publicly available at: https://www.researchgate.net/publication/383528251_2024-LRFT.