Pruning Operations Research Articles

Optimization of a Rural Portfolio Credit Granting System Using Improved Two-Dimensional Strip Packing Grouping Delay Problem

Rural preferential loans usually take the form of portfolio credits. From the perspective of public interest, the total delay time for obtaining loans is expected to be minimized. To use rural portfolio credits effectively, the two-dimensional strip packing grouping delay problem (2SPGDP) is improved to optimize the rural portfolio credit granting system. First, 2SPGDP is established by adding grouping constraints and the latest start time constraints to the two-dimensional strip packing problem, and the total delay is taken as the optimization objective. Second, based on the depth search reverse spanning tree (DSRST) and the insert spare space (ISS) method, the branch-and-bound reverse order insert algorithm (BB-RIA) is designed. Finally, the lag pruning operator (LPO) is designed to reduce lag. The improved model (2SPGDP) and BB-RIA-LPO algorithm are used to solve several classical two-dimensional strip packing problems and a specific rural portfolio credit case. Compared with the Bottom-Left and Branch and Bound Algorithm, our model and algorithm improve the success rate by 25% and reduce the total delay by 6%. The case of rural portfolio credit illustrates the operability and effectiveness of this method.

Low‐Voltage and High Thermal Stability Single‐Element Te Selector with Failed Bit Pruning Operation Enabling Robust Cross‐Point Memory

AbstractThe breakdown (BD) of one‐selector‐one‐resistor memory cells incurs increasing crosstalk and power consumption in the cross‐point memory array. In this work, failed bit pruning (FBP) operation of selectors is presented to cope with the side effects due to the BD cells. First, the FBP concept and its requirements on the device parameters is presented. Then the wide existence of FBP operation is demonstrated by investigating five different materials. Among them, the single‐element (Te) selector is highlighted. It not only shows high resistance after the prune operation (>50 MΩ) under a low prune voltage (2 V) but also achieves low threshold voltage (1.3 V) and high thermal stability (430 °C). This work demonstrates a new universal character for selector devices to enable robust high‐density cross‐point memory.

Tree Trunk and Obstacle Detection in Apple Orchard Based on Improved YOLOv5s Model

In this paper, we propose a tree trunk and obstacle detection method in a semistructured apple orchard environment based on improved YOLOv5s, with an aim to improve the real-time detection performance. The improvement includes using the K-means clustering algorithm to calculate anchor frame and adding the Squeeze-and-Excitation module and 10% pruning operation to ensure both detection accuracy and speed. Images of apple orchards in different seasons and under different light conditions are collected to better simulate the actual operating environment. The Gradient-weighted Class Activation Map technology is used to visualize the performance of YOLOv5s network with and without improvement to increase interpretability of improved network on detection accuracy. The detected tree trunk can then be used to calculate the traveling route of an orchard carrier platform, where the centroid coordinates of the identified trunk anchor are fitted by the least square method to obtain the endpoint of the next time traveling rout. The mean average precision values of the proposed model in spring, summer, autumn, and winter were 95.61%, 98.37%, 96.53%, and 89.61%, respectively. The model size of the improved model is reduced by 13.6 MB, and the accuracy and average accuracy on the test set are increased by 5.60% and 1.30%, respectively. The average detection time is 33 ms, which meets the requirements of real-time detection of an orchard carrier platform.

Clustering-Guided Particle Swarm Feature Selection Algorithm for High-Dimensional Imbalanced Data With Missing Values

Feature selection (FS) in data with class imbalance or missing values has received much attention from researchers due to their universality in real-world applications. However, for data with both the two characteristics above, there is still a lack of the corresponding FS algorithm. Due to the complex coupling relationship between missing data and class imbalance, the need for better FS method becomes essential. To tackle high-dimensional imbalanced data with missing values, this article studies a new evolutionary FS method. First, an improved <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F$ </tex-math></inline-formula> -measure based on filling risk (RF-measure) is defined to evaluate the influence of missing data on the performance of FS in the case of class imbalance. Following that taking the RF-measure as an objective function, a particle swarm optimization-based FS method with fuzzy clustering (PSOFS-FC) is proposed. Two new problem-specific operators or strategies, i.e., the swarm initialization strategy guided by fuzzy clustering and the local pruning operator based on feature importance, are developed to improve the performance of PSOFS-FC. Compared with state-of-the-art FS algorithms on several public datasets, experimental results show that PSOFS-FC can achieve excellent classification performance with relatively less running time, indicating its superiority on tackling high-dimensional imbalanced data with missing values.

CORK: A privacy-preserving and lossless federated learning scheme for deep neural network

With the advance of machine learning technology and especially the explosive growth of big data, federated learning, which allows multiple participants to jointly train a high-quality global machine learning model, has gained extensive attention. However, in federated learning, it has been proved that inference attacks could reveal sensitive information from both local updates and global model parameters, which threatens user privacy greatly. Aiming at the challenge, in this paper, a privacy-preserving and lossless federated learning scheme, named CORK, is proposed for deep neural network. With CORK, multiple participants can train a global model securely and accurately with the assistance of an aggregation server. Specifically, we first design a drop-tolerant secure aggregation algorithm FTSA, which ensures the confidentiality of local updates. Then, a lossless model perturbation mechanism PTSP is proposed to protect sensitive data in global model parameters. Furthermore, the neuron pruning operation in PTSP can reduce the scale of models, which thus improves the computation and communication efficiency significantly. Detailed security analysis shows that CORK can resist inference attacks on both local updates and global model parameters. In addition, CORK is implemented with real MNIST and CIFAR-10 datasets, and the experimental results demonstrate that CORK is indeed effective and efficient.

The impact of season on heart rate variability and workload of workers in young tree tending operations of a Larix kaempferi (Lamb.) Carr. stand: a preliminary study

ABSTRACT Larix kaempferi (Lamb.) Carr. plantations are a reasonable alternative to timber production for producing high-quality wood for South Korean industrial applications that need appropriate and high-quality practice of silvicultural operations. Weeding and tree pruning operations, which can favor trees in their competition with vegetation, require intensive manual labor. Therefore, the objective of this study was to determine the effect of these operations on the heart rate variability, relative heart rate (RHR), and physical workload of workers in April (spring) and July (summer) months. Our results showed that the mean heart rate variability and RHR for weeding (108.0 bpm and 49.4%, and 105.8 bpm and 46.8% for worker A and B, respectively) and tree pruning (104.5 bpm and 46.1%, and 114.4 bpm and 55.9% for worker A and B, respectively) in July were higher than those in April. In addition, the level of workload in July was characterized as heavy to very heavy, and as moderate to heavy in April. The results from this study provide useful information for appropriate young tree tending operations from the perspective of the safety and health of workers.

TopoNet: Topology Learning for 3D Reconstruction of Objects of Arbitrary Genus

AbstractWe propose a deep reinforcement learning‐based solution for the 3D reconstruction of objects of complex topologies from a single RGB image. We use a template‐based approach. However, unlike previous template‐based methods, which are limited to the reconstruction of 3D objects of fixed topology, our approach learns simultaneously the geometry and topology of the target 3D shape in the input image. To this end, we propose a neural network that learns to deform a template to fit the geometry of the target object. Our key contribution is a novel reinforcement learning framework that enables the network to also learn how to adjust, using pruning operations, the topology of the template to best fit the topology of the target object. We train the network in a supervised manner using a loss function that enforces smoothness and penalizes long edges in order to ensure high visual plausibility of the reconstructed 3D meshes. We evaluate the proposed approach on standard benchmarks such as ShapeNet, and in‐the‐wild using unseen real‐world images. We show that the proposed approach outperforms the state‐of‐the‐art in terms of the visual quality of the reconstructed 3D meshes, and also generalizes well to out‐of‐category images.

Effect of different pruning operations on the plant growth, phytohormones and transcriptome profiles of the following spring tea shoots

Pruning as an important agronomic operation plays a crucial role in the regulation of tea plant growth, development and dry tea quality. The effects of different pruning operations on the plant growth, phytohormones and transcriptome profiles of the following spring tea shoots were studied. Pruning-treated samples had generally increased median of the weight of 100 buds (two leaves and one bud, 15.5−20.5 g) and longer stem diameter (1.7−1.8 mm) whereas shorter shoot length (34.6−59.2 mm) at the stage of two leaves and one bud, compared with unpruned samples (14.0 g, 1.7 mm, 87.4 mm), among which heavy pruning in mid April and early May greatly accelerated the development of the following spring tea shoots. The levels of phytohormones (auxin, gibberellin 1, gibberellin 3, and <italic>trans</italic>-zeatin) were significantly increased in the spring buds of tea plants heavily pruned in May. The KEGG result indicated that the pathways of plant–pathogen interaction, plant hormone signal transduction and circadian rhythm were regulated by different pruning treatments. Heavy pruning in April or May, without autumn pruning was suitable for producing premium green tea due to the early development and the higher weight of 100 buds. This study provides scientific guidance to regulate the growth of the following spring tea shoots using plant pruning operations.

Automatic branch detection of jujube trees based on 3D reconstruction for dormant pruning using the deep learning-based method

Pruning is a time-consuming and labor-intensive practice for managing of dormant jujube orchards, in which dormant pruning is still mainly dependent on manual operation. Automated pruning using a robotic platform could be a better solution to overcome the skilled labor shortage and increased labor costs. With the development of dwarf and dense planting of jujube trees, the tree architectures are suitable for robotic pruning. This study concentrated on the detection and identification of pruning branches, which was a critical step for automating pruning operations. The method in this study mainly consisted of three steps: first, present a vision system based on two synchronous consumer-level RGB-D cameras to obtain the high-quality 3D point cloud in filed; second, propose the reconstruction pipeline for the desired three-dimensional model (basically a complete 3D model) using only two perspectives; and third, automatically segment the trunks and branches based on deep learning method (SPGNet), and then apply the DBSCAN clustering algorithm for estimating branch counts of jujube trees. For the reconstruction of jujube tree, registration errors II (0°-180°) were greater than errors I (0°-55°), and registration errors I (0°-55°) were less than 1 mm under different light conditions. Experimental results demonstrated that trunks and branches were segmented successfully with class accuracies of 0.93 and 0.84, and another metric intersection-over-union (IoU) was 0.85 and 0.76, respectively; the coefficient of determination (R2) values analyzed between the ground-truth and cluster results were 0.83, 0.88, and 0.89 in sunny, cloudy, and night conditions, respectively. These results showed that the proposed method for detecting branches could be utilized to generate substantial information, such as the diameter length and diameter of the branch, which was critical for the automated dormant pruning of jujube trees in the future orchard field.

Anytime Ranking on Document-Ordered Indexes

Inverted indexes continue to be a mainstay of text search engines, allowing efficient querying of large document collections. While there are a number of possible organizations, document-ordered indexes are the most common, since they are amenable to various query types, support index updates, and allow for efficient dynamic pruning operations. One disadvantage with document-ordered indexes is that high-scoring documents can be distributed across the document identifier space, meaning that index traversal algorithms that terminate early might put search effectiveness at risk. The alternative is impact-ordered indexes, which primarily support top- disjunctions but also allow for anytime query processing, where the search can be terminated at any time, with search quality improving as processing latency increases. Anytime query processing can be used to effectively reduce high-percentile tail latency that is essential for operational scenarios in which a service level agreement (SLA) imposes response time requirements. In this work, we show how document-ordered indexes can be organized such that they can be queried in an anytime fashion, enabling strict latency control with effective early termination. Our experiments show that processing document-ordered topical segments selected by a simple score estimator outperforms existing anytime algorithms, and allows query runtimes to be accurately limited to comply with SLA requirements.

Industrial fault diagnosis based on active learning and semi-supervised learning using small training set

Industrial fault diagnosis has been investigated for many years, and many approaches have been proposed to identify industrial faults. However, the size of the actual training set is usually small, which severely degrades the performance of existing fault diagnostic models. To solve this problem, a new fault diagnosis method was proposed based on active and semi-supervised learning. First, uncertain unlabelled samples were selected by estimating the first two values in the class probability distribution of the samples. They were labelled by experts to update the performance of the models learned from a small training set. Second, heterogeneous classifiers were adopted to increase the diversity of the base classifiers, and noise samples were deleted using a sample pruning operation. The weights of the base classifier were designed for ensemble learning based on the test error rates. An evaluation using the Case Western Reserve University and Intelligent Maintenance Systems data showed that the performance of the proposed method was better than those of the other methods in the experiment. The experimental results showed that this study provided a promising and useful methodology for fault diagnosis under a small training set.

Physico-chemical properties and associated active microbes of tea garden waste of Golaghat district of Assam, India

Tea Gardens generally produce two kinds of waste materials such as Tea Factory waste (TFW) and Pruning Litter (PL). Minimum 2 % of TFW is produced as by - product during processing of tea contributing a huge quantity as waste material.Similarly during pruning operations considerable amount of biomass are produced. Both the bio-waste materials can be managed by biological process to produce value added organic supplement to enrich the soil of tea plantation. During the present study different physico-chemical properties, viz. pH, P2O2 , K2O and nitrogen’s of TFW were analyzed. In TFW the value of Total soluble solids ranged (27.2-31.1%) and Crude fiber ranged (25.83-31.12%) and Caffenine amount ranged (23.14- 27.94%) and Total ash ranged (3.15-6.54%) The aflavin ranged (0.45-0.76%) and the arubignins ranged (18.45-21.32%). In TFW and PL some beneficial and active microbial populations are found which can be used in tea plants after making value added compost to increase their natural productivity. In this study focus was given to explore the beneficial and active microorganisms found in TFW and PL and found some beneficial microbes such as Actinomycetes, Azotobacter, Azospirillum and Phosphate solubilizing bacteria respectively

Dynamical Pruning of Rooted Trees with Applications to 1-D Ballistic Annihilation

We introduce generalized dynamical pruning on rooted binary trees with edge lengths that encompasses a number of discrete and continuous pruning operations, including the tree erasure and Horton pruning. The pruning removes parts of a tree T, starting from the leaves, according to a pruning function defined on descendant subtrees within T. We prove the invariance of critical binary Galton–Watson tree with exponential edge lengths with respect to the generalized dynamical pruning for an arbitrary admissible pruning function. These results facilitate analysis of the continuum 1-D ballistic annihilation model $$A+A \rightarrow \varnothing $$ for a constant particle density and initial velocity that alternates between the values of $$\pm 1$$ . We show that the model’s shock wave is isometric to the level set tree of the potential function, and the model evolution is equivalent to the generalized dynamical pruning of the shock wave tree.

Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings

This paper proposes a new stacked pruning sparse denoising autoencoder (sPSDAE) model for intelligent fault diagnosis of rolling bearings. Different from the traditional autoencoder, the proposed sPSDAE model, including a fully connected autoencoder network, uses the superior features extracted in all the previous layers to participate in the subsequent layers. This means that some new channels are created to connect the front layers and the back layers, which reduces information loss. To improve the training efficiency and precision of the sPSDAE model, a pruning operation is added into the sPSDAE model so as to prohibit non-superior units from participating in all the subsequent layers. Meanwhile, a feature fusion mechanism is introduced to ensure the uniqueness of the feature dimensions. After that, the sparse expression of the sPSDAE model is strengthened, thereby improving the generalization ability. The proposed method is evaluated by using a public bearing dataset and is compared with other popular fault diagnosis models. The results show that the ability of the sPSDAE model to extract features is significantly enhanced and the phenomenon of gradient disappearance is further reduced. The proposed model achieves higher diagnostic accuracy than other popular fault diagnosis models.

Valorisation of urban green areas for producing renewable energy and biochar as growing substrate of Sicilian aromatic and nutraceutical species in a circular economy

This work is aimed at evaluating the possible building up of a gasifier for the energy valorisation of residual biomass deriving from urban areas and their surroundings. The area and the volumes of supply and economic convenience have been determined by implementing a GIS-based geographic method to the localisation and quantification of non-uniform elements of plant biomass. The pyrolysis and gasification processes of the lignocellulosic biomass obtained from pruning and maintenance operations of the urban and ornamental green include the production of a residual amount of biochar. The biochar can be used in agriculture as a soil improver and a substrate alternative to peat in the sustainable production of Sicilian aromatic and nutraceutical species grown in pots within a circular economy.

MECHANIZED MANAGEMENT OF PRUNING RESIDUES IN SWEET CHESTNUT ORCHARDS

In Italy, Dryocosmus kuriphilus is a major insect pest of chestnut orchards causinggall formation and significant yield losses. The use of the parasitoid wasp Torymussinensis is an effective biological control method that requires the appropriatemanagement of the pruning residues, to preserve the woody galls in which T.sinensis adults overwinter. An innovative tractor-pulled combined mechanicalshredder was tested for treating the residues, once the pruning operations arecompleted. The machine processes the residues in a single-step, picking-up theprunings from the orchard floor, shredding them to appropriate size, and collectingthem into a rear container. The shredded residues may then be concentrated into afew piles for the long-term field storage, until next spring. The aim of the studywas to evaluate the machinery’s operative performance, the quality of the shreddedbiomass and the impact on gall integrity. In the field trials, the machineryeffectively shredded the residues achieving an average operative capacity of 1.19ha∙h-1 and a work capacity of 1.79 t∙h-1. Moisture content, apparent bulk density,and particle size distribution of the shredded biomass were determined. Over 95%of wood chips were included in the 3.15-45 mm size range, making them suitablefor use in residential biomass furnaces. The calorific power of the chestnut residueswas similar to that reported for other hardwood species (18-20 MJ∙kg-1). Also, themechanical action of the shredder preserved at least two thirds of the winter galls,safeguarding the parasitoid’s life cycle.

Pruning operator for minimum deck wind in carrier aircraft launch

Launch resources and flight safety are important for carrier-based aircraft to takeoff. Aimed at making full use of marine wind resources, a pruning operator added to linear random search algorithm is developed to solve the minimum deck wind for carrier aircraft launch. On the basis of problem statement, the catapult safety criteria are quantified as the boundary condition of the critical solution. Then the mathematical model is established for the algorithm including pruning schematic. The influence of deck wind on aircraft catapult launch is analyzed. With the algorithm proceeding and the feedback results of aircraft catapult launch simulation, the optimal solution of the minimum deck wind is determined in a few simulation times. The main contribution of this research is the development of the pruning operator to greatly shorten the search times under permissible error for the discrete linear problems. And the minimum deck wind is solved in full takeoff weight range due to combining linear random search algorithm and simulation.

Evolutionary Compression of Deep Neural Networks for Biomedical Image Segmentation.

Biomedical image segmentation is lately dominated by deep neural networks (DNNs) due to their surpassing expert-level performance. However, the existing DNN models for biomedical image segmentation are generally highly parameterized, which severely impede their deployment on real-time platforms and portable devices. To tackle this difficulty, we propose an evolutionary compression method (ECDNN) to automatically discover efficient DNN architectures for biomedical image segmentation. Different from the existing studies, ECDNN can optimize network loss and number of parameters simultaneously during the evolution, and search for a set of Pareto-optimal solutions in a single run, which is useful for quantifying the tradeoff in satisfying different objectives, and flexible for compressing DNN when preference information is uncertain. In particular, a set of novel genetic operators is proposed for automatically identifying less important filters over the whole network. Moreover, a pruning operator is designed for eliminating convolutional filters from layers involved in feature map concatenation, which is commonly adopted in DNN architectures for capturing multi-level features from biomedical images. Experiments carried out on compressing DNN for retinal vessel and neuronal membrane segmentation tasks show that ECDNN can not only improve the performance without any retraining but also discover efficient network architectures that well maintain the performance. The superiority of the proposed method is further validated by comparison with the state-of-the-art methods.

Toward Compact ConvNets via Structure-Sparsity Regularized Filter Pruning.

The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits their usage on resource-limited environments, such as mobile systems or embedded devices. To this end, the research of CNN compression has recently become emerging. In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speed up the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries. Concretely, the proposed scheme incorporates two different regularizers of structured sparsity into the original objective function of filter pruning, which fully coordinates the global output and local pruning operations to adaptively prune filters. We further propose an alternative updating with Lagrange multipliers (AULM) scheme to efficiently solve its optimization. AULM follows the principle of alternating direction method of multipliers (ADMM) and alternates between promoting the structured sparsity of CNNs and optimizing the recognition loss, which leads to a very efficient solver ( 2.5× to the most recent work that directly solves the group sparsity-based regularization). Moreover, by imposing the structured sparsity, the online inference is extremely memory-light since the number of filters and the output feature maps are simultaneously reduced. The proposed scheme has been deployed to a variety of state-of-the-art CNN structures, including LeNet, AlexNet, VGGNet, ResNet, and GoogLeNet, over different data sets. Quantitative results demonstrate that the proposed scheme achieves superior performance over the state-of-the-art methods. We further demonstrate the proposed compression scheme for the task of transfer learning, including domain adaptation and object detection, which also show exciting performance gains over the state-of-the-art filter pruning methods.

Mining recent frequent cooccurring items from transaction stream

The work presents a simple but novel scheme to determine the recent frequent cooccurring items from transaction streams. It enables to follow the current trend, pattern of occurrence of the items and also help in recommendation. Proposed methodology works on a sequence of transaction forming a time-window. Based on the items present in a transaction, item-sets are formed and encoded. An in-memory structure maintains the frequency of the item-sets. Frequency is time-decayed count that prioritises the recent occurrences. To limit the size of in-memory structure, a pruning operation is carried out to remove the less frequent item-sets. Threshold for pruning is chosen dynamically. Impacts of decaying parameter and window size are also analysed. Experiment has been carried out on two datasets and performance has been compared with two recent works. Proposed methodology provides a better accuracy. Low time and space complexity make it suitable for stream analytic.