Insufficient Memory Research Articles

TrajPredRNN+: A new approach for precipitation nowcasting with weather radar echo images based on deep learning

：Short-term rainfall prediction is a crucial and practical research area, with the accuracy of rainfall prediction, particularly for heavy rainfall, significantly impacting people's lives, property, and even their safety. Existing models, such as ConvLSTM, TrajGRU, and PredRNN, exhibit limitations in capturing fine-grained appearances due to insufficient memory units or addressing positional misalignment issues, thereby compromising the accuracy of model predictions. In this study, we propose trajPredRNN+, an innovative approach that integrates the trajectory segmentation model and the PredRNN deep learning model to address both limitations in nowcasting precipitation using weather radar echo images. By incorporating attention mechanisms, the model demonstrates an enhanced focus on short-term and imminent heavy rainfall events. To ensure improved stability during training, a residual network is introduced. Lastly, a more rational and effective training loss function is proposed, encompassing weight mechanism, SSIM index, and GAN loss. To validate the proposed model, we conducted a comparative experiment and an ablation experiment using the radar echo map dataset obtained from the Shenzhen Meteorological Bureau. The results of these experiments demonstrate that our model has achieved significant improvements across multiple key performance indicators.

A Systematic Investigation on Botnet Intrusion Detection Using Various Machine Learning Techniques

The Internet of Things (IoT) is growing rapidly in an exponential manner due to its versatility in technology. This has led to many challenges in securing the IoT environment. Devices in IoT environments are vulnerable to various cyberattacks. Botnet-based attacks are predominant and widespread in nature. Due to insufficient memory and computational power, the IoT environment cannot handle the botnet attack that affects security. Identifying intrusions in IoT environments is another challenge for researchers. Finding unknown patterns in the data generated through IoT networks helps improve security in the IoT environment. Machine learning (ML) is a platform that helps identify patterns in the provided data. In this study, we present our research on classifying incoming data from the IoT as malicious or benign using machine learning techniques. We propose an ML-based botnet attack detection framework for nine commercial IoT devices that primarily target BASHLITE and Mirai botnet attacks. Rigorous pragmatic research was conducted on the N-BaIoT dataset, which was extracted from realtime IoT devices connected to a network. Using this framework, the results have been depicted, which can efficiently detect botnet attacks and can also be applied to any other types of attacks.

Testing Error Handling Code With Software Fault Injection and Error-Coverage-Guided Fuzzing

Real-world programs require error handling code to handle various kinds of possible errors. However, these errors just infrequently occur due to special conditions, so error handling code is difficult to test. Coverage-guided fuzzing and software fault injection (SFI) are two common techniques that can test error handling code, but they still have major limitations. Specifically, existing fuzzing approaches generate program inputs guided by code coverage, but many occasional errors (such as insufficient memory) are unrelated to inputs, and code coverage cannot effectively reflect the execution contexts of these errors; existing SFI approaches often inject single or random faults, without exploring fault space or using program feedback. In this paper, we propose a new fuzzing framework named EH-Fuzz, to effectively test error handling code. EH-Fuzz uses a context-sensitive SFI-based fuzzing approach to explore fault space and perform fault injection, guided by a new metric named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">error coverage</i> . We evaluate EH-Fuzz on 9 user-level programs and 6 kernel-level modules, and find 45 new real bugs, 31 of which have been confirmed and fixed. We compare EH-Fuzz to existing fuzzing approaches (including AFL, AFL++, Syzkaller, FIZZER and FIFUZZ), and EH-Fuzz finds many real bugs missed by these approaches with higher testing coverage.

HB-RRT:A path planning algorithm for mobile robots using Halton sequence-based rapidly-exploring random tree

Path planning remains crucial for efficient robot operation. A Halton Biased Rapidly-exploring Random Tree (HB-RRT) path planning algorithm is introduced in this study. The Halton sequence, known for its uniform distribution and low discrepancy, is employed for sampling. Issues arising from the pseudo-random sequence in the standard RRT algorithm, leading to uneven distribution of sampling points, are addressed. A mouse-inspired goal-oriented strategy and a candidate sampling pool strategy are incorporated to enhance the sampling point quality, thereby addressing the challenge of insufficient memory during node expansion. Path optimization is further achieved through a multi-level planning approach, which aims to minimize redundancy. A subsequent smoothing of the path is conducted using a cubic B-spline method. Comparisons with the RRT, Bionic Target Bias-RRT, and Informed-RRT* algorithms, through both numerical simulations and real-world testing, confirm the superiority of the HB-RRT algorithm in terms of planning time, path length, and overall path quality.

A real-time approximation algorithm of nonlinear filtering based on image pyramid

In the field of real-time rendering, post-processing filters are crucial techniques for achieving global illumination and photorealistic rendering in real-time rasterization and ray tracing rendering pipelines. Due to the power consumption limitations and insufficient memory bandwidth of mobile devices, filters can cause significant performance bottlenecks. To reduce the cost of filters on mobile devices, this paper proposes a real-time approximation method for nonlinear filtering. Our method reduce the number of texture samplings and memory usage. Through experiments conducted on mobile devices, it has been demonstrated that the proposed method can effectively reduce the number of texture samplings in feature images within scenes of similar complexity, as compared to mainstream industrial methods. This reduction in texture samplings leads to improved rendering quality while maintaining the same frame rate. Our method eliminates performance bottlenecks and enhances the quality of global illumination on mobile devices. By reducing the computational complexity of the non-linear filter, it provides users with a smoother experience.

Empirical Analysis of Vocabulary Teaching in Middle Schools Based on Situational Language Teaching

With the continuous development of globalization, English has become one of the important languages of China and international communication, playing an important role in our life. English has always been the traditional main subject of education at all levels in China, whether primary school, middle school, high school and university, all occupy a pivotal position. And in middle school education, English performance can affect the situation of admission, and English is also a subject with a huge gap. Middle school is a key period to learn English. How should we learn English well? As we all know, the important condition for learning English well is vocabulary. Only by mastering vocabulary can we learn English well. Vocabulary is the basis of learning English well. However, from the current situation of junior high school students learning vocabulary, it is not optimistic, and students face many difficulties to master vocabulary. The main difficulties we have include: firstly, students, only have single memory method and insufficient memory s in vocabulary memory skills, which make them difficult to master the vocabulary. secondly, the traditional classroom teaching approach is single, boring and inefficient; thirdly, many teachers ignore thinking and interest cultivation, and students can only memorize words and phrases, difficult to use flexibly in life, so that students often lack interest in vocabulary, and will be afraid when they face with vocabulary. we can’t learn English well in such a situation. Now, it is a common challenge for teachers and students to change the situation at present. In order that students can better master vocabulary, for this reason, teachers can find more appropriate teaching methods to change the dilemma they face. With the further research on the theories of vocabulary teaching, we understand some relevant teaching approaches and theories gradually, such as situational language teaching (SLT). Due to introduction of SLT, it has played a great influence in China’s basic education and made great progress in China’s education. Although the current situational teaching method is often used in English teaching, it has not always been applied to vocabulary teaching. It is unclear whether SLT is suitable for vocabulary teaching and can improve the efficiency of vocabulary teaching and change the current situation. Therefore, this article studies whether SLT is applicable to English vocabulary teaching in middle schools and verifies whether it is effective. However, SLT through the data analysis of post-trial test and questionnaire is suitable and feasible. By creating a real situation, let the students experience the true feelings, and then master the vocabulary, improve the interest in learning, improve the classroom efficiency. By creating a real situation, let the students experience the true feelings, and then master the vocabulary, improve the interest in learning, improve the classroom efficiency.

Realization of a database‐driven PID control system using a CMAC memory

AbstractAs a nonlinear control approach, a database‐driven PID (DD‐PID) controller has been proposed that uses distance calculations of an initial database to tune PID parameters. However, sorting operations are required in extracting neighborhood data from the database, which imposes a large computational load. Therefore, it is impossible to finish this computation within a restricted sampling period in control systems with fast response time and insufficient memory capacity. On the other hand, the cerebellar model articulation controller (CMAC) has advantages for these problems and has similar constructs to the DD approach. Therefore, this paper combines advantages of these two approaches, and proposes a CMAC‐PID controller design based on off‐line optimization of a database. Finally, a comparison with conventional off‐line CMAC‐PID controller and DD‐PID controller through simulations are considered.

An Alternate GPU-Accelerated Algorithm for Very Large Sparse LU Factorization

The LU factorization of very large sparse matrices requires a significant amount of computing resources, including memory and broadband communication. A hybrid MPI + OpenMP + CUDA algorithm named SuperLU3D can efficiently compute the LU factorization with GPU acceleration. However, this algorithm faces difficulties when dealing with very large sparse matrices with limited GPU resources. Factorizing very large matrices involves a vast amount of nonblocking communication between processes, often leading to a break in SuperLU3D calculation due to the overflow of cluster communication buffers. In this paper, we present an improved GPU-accelerated algorithm named SuperLU3D_Alternate for the LU factorization of very large sparse matrices with fewer GPU resources. The basic idea is “divide and conquer”, which means dividing a very large matrix into multiple submatrices, performing LU factorization on each submatrix, and then assembling the factorized results of all submatrices into two complete matrices L and U. In detail, according to the number of available GPUs, a very large matrix is first divided into multiple submatrices using the elimination tree. Then, the LU factorization of each submatrix is alternately computed with limited GPU resources, and its intermediate LU factors from GPUs are saved to the host memory or hard disk. Finally, after finishing the LU factorization of all submatrices, these factorized submatrices are assembled into a complete lower triangular matrix L and a complete upper triangular matrix U, respectively. The SuperLU3D_Alternate algorithm is suitable for hybrid CPU/GPU cluster systems, especially for a subset of nodes without GPUs. To accommodate different hardware resources in various clusters, we designed the algorithm to run in the following three cases: sufficient memory for GPU nodes, insufficient memory for GPU nodes, and insufficient memory for the entire cluster. The results from LU factorization test on different matrices in various cases show that the larger the matrix is, the more efficient this algorithm is under the same GPU memory consumption. In our numerical experiments, SuperLU3D_Alternate achieves speeds of up to 8× that of SuperLU3D (CPU only) and 2.5× that of SuperLU3D (CPU + GPU) on the hybrid cluster with six Tesla V100S GPUs. Furthermore, when the matrix is too big to be handled by SuperLU3D, SuperLU3D_Alternate can still utilize the cluster’s host memory or hard disk to solve it. By reducing the amount of data exchange to prevent exceeding the buffer’s limit of the cluster MPI nonblocking communication, our algorithm enhances the stability of the program.

Application of image recognition based on neural network algorithm in multimedia dance teaching

Neural network recognition algorithm is a deep learning-based convolutional neural network, which has been applied to target detection, image recognition, sound recognition and other fields. Although the recognition technology of convolutional neural network has been gradually stabilized, it is mainly implemented in single-machine serial mode. Therefore, there will be problems such as too long training time and insufficient memory capacity. According to the previous work, this paper has carried out related research and obtained some useful results. This paper focuses on the introduction of image recognition technology based on neural network algorithm. At the same time, this paper proposes a fast real-time image recognition algorithm, which has high recognition accuracy. In this paper, the existing algorithms mentioned in the paper are analyzed, the characteristics and shortcomings of all algorithms are summarized, and the appropriate combination of algorithms is selected for specific problems. On this basis, the acceleration method of artificial neural network is used to improve the algorithm of convolutional neural network image recognition technology. With the continuous development of education and the increase of the number of students year by year, the effect of classroom teaching becomes particularly important. Therefore, modern information technology is used to transfer the classroom teaching mode to the network and realize a new method of online remote online dance teaching. According to the actual situation of dance teaching, the advantages of multimedia dance teaching are analyzed. The software of multimedia dance teaching system is tested comprehensively, from the aspects of computer system memory occupancy rate and temperature, to test whether the activities of B/S mode multimedia dance teaching system meet the expected goals and requirements of each core module of multimedia dance teaching system.

An Energy-Efficient Computing-in-Memory (CiM) Scheme Using Field-Free Spin-Orbit Torque (SOT) Magnetic RAMs

The separation of memory and computing units in the von Neumann architecture leads to undesirable energy consumption due to data movement and insufficient memory bandwidth. Energy-efficient in-memory computing platforms have the potential to address such issues. Due to its non-volatility and advantageous features over CMOS (such as low power, near-zero leakage current and high integration density), spin-based devices have been advocated for in-memory computing. This paper proposes a field-free Spin Orbit Torque (FF-SOT) MRAM based computing-in-memory (CiM) scheme that realizes XNOR/XOR logic and a cascading adder. This novel FF-SOT-CiM design does not require expensive peripheral circuits for computation while using the same memory cell design as a SOT-MRAM. Furthermore, FF-SOT-CiM does not require additional write cycles to save the result of its computations in the memory. The design offers higher write speed and; lower operating energy compared to CiM schemes based on other technologies; it also alleviates the source degeneration effect by leveraging an advanced switching mechanism. Extensive simulation results show that the proposed FF-SOT-CiM achieves up to 3.1x (2.6x) latency (energy) reduction compared to SRAM-based CiM, with negligible hardware overhead when performing in-memory XOR. ADD operations; the proposed FF-SOT-CiM can be to 5.0X and 1.5X faster and 3.4X and 1.1X more energy efficient than existing STT-based and FeFET-based schemes, respectively.

CMACメモリによるデータベース駆動型PID制御系の実現

As a nonlinear control approach, a database-driven PID (DD-PID) controller has been proposed that uses distance calculations of an initial database to tune PID parameters. However, sorting operations are required in extracting neighborhood data from the database, which imposes a large computational load. Therefore, it is impossible to finish this computation within a restricted sampling period in control systems with fast response time and insufficient memory capacity. On the other hand, the cerebellar model articulation controller (CMAC) has advantages for these problems and has similar constructs to the DD approach. Therefore, this paper combines advantages of these two approaches, and proposes a CMAC-PID controller design based on off-line optimization of a database. Finally, a comparison with conventional off-line CMAC-PID controller and DD-PID controller through simulations are considered.

Partial quantisation scheme for optimising the performance of hopfield network

The ideal Hopfield network would be able to remember information and recover the missing information based on what has been remembered. It is expected to have applications in areas such as associative memory, pattern recognition, optimisation computation, parallel implementation of VLSI and optical devices, but the lack of memory capacity and the tendency to generate pseudo-attractors make the network capable of handling only a very small amount of data. In order to make the network more widely used, we propose a scheme to optimise and improve its memory and resilience by introducing quantum perceptrons instead of Hebbian rules to complete its weight matrix design. Compared with the classical Hopfield network, our scheme increases the threshold of each node in the network while training the weights, and the memory space of the Hopfield network changes from being composed of the weight matrix only to being composed of the weight matrix and the threshold matrix together, resulting in a dimensional increase in the memory capacity of the network, which greatly solves the problem of the Hopfield network’s memory The problem of insufficient memory capacity and the tendency to generate pseudo-attractors was solved to a great extent. To verify the feasibility of the proposed scheme, we compare it with the classical Hopfield network in four different dimensions, namely, non-orthogonal simple matrix recovery, incomplete data recovery, memory capacity and model convergence speed. These experiments demonstrate that the improved Hopfield network with quantum perceptron has significant advantages over the classical Hopfield network in terms of memory capacity and recovery ability, which provides a possibility for practical application of the network.

Fast prototype selection algorithm based on adjacent neighbourhood and boundary approximation

The unceasing increase of data quantity severely limits the wide application of mature classification algorithms due to the unacceptable execution time and the insufficient memory. How to fast incrementally obtain high decision reference set and adapt to incremental data environment is urgently needed in incremental environments, large dataset, etc. This paper proposes a novel prototype selection algorithm by integrating the strategies between condensing method and editing method. To an unlearned pattern, this algorithm extends the references scope from its single nearest neighbour to its k nearest neighbourhood that can expand the judgment information to obtain its detailed neighbour relationship. Then a pattern was determined whether it is a prototype using its neighbour relationship and classification boundary asymptotically strategy. To maintain the higher reference set, this algorithm periodically updates those prototypes that locates in the non-boundary zone or is long-time unlearned. The empirical study shows that this algorithm obtains the smaller and higher boundary prototypes without decreasing classification accuracy and reduction rate than the compared algorithms.

A Memory-Aware Spark Cache Replacement Strategy

&lt;p&gt;Spark is currently the most widely used distributed computing framework, and its key data abstraction concept, Resilient Distributed Dataset (RDD), brings significant performance improvements in big data computing. In application scenarios, Spark jobs often need to replace RDDs due to insufficient memory. Spark uses the Least Recently Used (LRU) algorithm by default as the cache replacement strategy. This algorithm only considers the most recent use time of RDDs as the replacement basis. This characteristic may cause the RDDs that need to be reused to be evicted when performing cache replacement, resulting in a decrease in Spark performance. In response to the above problems, this paper proposes a memory-aware Spark cache replacement strategy, which comprehensively considers the cluster memory usage, RDD size, RDD dependencies, usage times and other information when performing cache replacement and selects the RDDs to be evicted. Furthermore, this paper designs extensive corresponding experiments to test and analyze the performance of the memory-aware Spark cache replacement strategy. The experimental data show that the proposed strategy can improve the performance by up to 13% compared with the LRU algorithm in different scenarios.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

Global-Local Generation Adversarial Learning Based Low-Light Image Enhancement

In the field of low-light image enhancement, the existing unsupervised methods still have some problems, such as the lack of authenticity and the unclear effect of image enhancement in extremely dark conditions. To address this issue, we propose a highly-effective unsupervised approach to directly recover normal light image from low-light image by designing an effective cyclic generation adversarial network, Firstly, in order to solve the problem of insufficient memory caused by large-size input, a global and local generator has been designed. Secondly, we develop an adaptive two-stage discriminator. Among it, by discriminating the whole image, the local region that needs to be discriminated again is obtained adaptively. Finally, the loss in frequency domain is employed to avoid image distortion. We employ the focal frequency loss which allows the model to adaptively focus on frequency components that are hard to synthesize. The PI index of the method in this paper reaches on NPE, LIME, MEF, DICM and VV datasets respectively 2.81, 2.78, 2.40, 3.15, 3.69. On LOL datasets, PSNR and SSIM index reached 19.89 dB, 0.782 3, with good robustness.

AIOPS FRAMEWORK FOR ALERTING PERFORMANCE ISSUES IN MICROSERVICES USING TIME SERIES FORECASTING

For large scale applications based on Microservices architecture and hosted on scalable platforms like Pivotal Cloud Foundry or OpenShift, it is imperative to monitor the performance of microservices on a continuous basis and trigger performance critical alerts upfront when abnormal patterns are observed in the immediate past. One of the critical application performance indicators is Major Garbage Collection (Major GC), an increase of which causes application performance bottlenecks and might indicate insufficient memory allocation to the JVM or a potential memory leak. In this paper, we discuss a solution built using machine learning Algorithms that forecasts Major GC cycles (Number of Major Garbage Collection) of business critical microservices for the near future time periods. This paper discusses various algorithms within python’s stats models. tsa package that were explored and details the concepts and results of forecast models trained using Seasonal Autoregressive Integrated Moving Average, or SARIMA algorithm that was finally considered for forecasting based on model performance. The paper also elucidates the Forecast accuracy of the model, showing results of the forecast vs actual occurrences of Major Garbage collection. The objective of this solution based on AIOps framework is to enable development and production support teams get proactive notification when forecast Major GC patterns breach the set threshold limits, so that corrective action can be taken to improve the application performance by reducing frequency of Major GC cycles.

Imaginative Reflexivity in Decolonizing Expert–Client Relationships. A Response to J. Vink: Designing for Plurality in Democracy by Building Reflexivity

Imaginative Reflexivity in Decolonizing Expert–Client Relationships. A Response to J. Vink: Designing for Plurality in Democracy by Building Reflexivity

DDPQN: An Efficient DNN Offloading Strategy in Local-Edge-Cloud Collaborative Environments

With the rapid development of the Internet of Things (IoT) and communication technology, Deep Neural Network (DNN) applications like computer vision, can now be widely used in IoT devices. However, due to the insufficient memory, low computing capacity, and low battery capacity of IoT devices, it is difficult to support the high-efficiency DNN inference and meet users’ requirements for Quality of Service (QoS). Worse still, offloading failures may occur during the massive DNN data transmission due to the intermittent wireless connectivity between IoT devices and the cloud. In order to fill this gap, we consider the partitioning and offloading of the DNN model, and design a novel optimization method for parallel offloading of large-scale DNN models in a local-edge-cloud collaborative environment with limited resources. Combined with the coupling coordination degree and node balance degree, an improved Double Dueling Prioritized deep Q-Network (DDPQN) algorithm is proposed to obtain the DNN offloading strategy. Compared with existing algorithms, the DDPQN algorithm can obtain an efficient DNN offloading strategy with low delay, low energy consumption, and low cost under the premise of ensuring “delay-energy-cost” coordination and reasonable allocation of computing resources in a local-edge-cloud collaborative environment.

A Computational Study of Using Black-box QR Solvers for Large-scale Sparse-dense Linear Least Squares Problems

Large-scale overdetermined linear least squares problems arise in many practical applications. One popular solution method is based on the backward stable QR factorization of the system matrix A . This article focuses on sparse-dense least squares problems in which A is sparse except from a small number of rows that are considered dense. For large-scale problems, the direct application of a QR solver either fails because of insufficient memory or is unacceptably slow. We study several solution approaches based on using a sparse QR solver without modification, focussing on the case that the sparse part of A is rank deficient. We discuss partial matrix stretching and regularization and propose extending the augmented system formulation with iterative refinement for sparse problems to sparse-dense problems, optionally incorporating multi-precision arithmetic. In summary, our computational study shows that, before applying a black-box QR factorization, a check should be made for rows that are classified as dense and, if such rows are identified, then A should be split into sparse and dense blocks; a number of ways to use a black-box QR factorization to exploit this splitting are possible, with no single method found to be the best in all cases.

Using Image Recognition to Process Unbalanced Data in Genetic Diseases From Biobanks.

With precision medicine as the goal, the human biobank of each country should be analyzed to determine the complete research results related to genetic diseases. In addition, with the increase in medical imaging data, automatic image processing with image recognition has been widely studied and applied in biomedicine. However, case–control data imbalance often occurs in human biobanks, which is usually solved by the statistical method SAIGE. Due to the huge amount of genetic data in human biobanks, the direct use of the SAIGE method often faces the problem of insufficient computer memory to support calculations and excessive calculation time. The other method is to use sampling to adjust the data to balance the case–control ratio, which is called Synthetic Minority Oversampling Technique (SMOTE). Our study employed the Manhattan plot and genetic disease information from the Taiwan Biobank to adjust the imbalance in the case–control ratio by SMOTE, called “TW-SMOTE.” We further used a deep learning image recognition system to identify the TW-SMOTE. We found that TW-SMOTE can achieve the same results as that of SAIGE and the UK Biobank (UKB). The processing of the technical data can be equivalent to the use of data plots with a relatively large UKB sample size and achieve the same effect as that of SAIGE in addressing data imbalance.