Library Of Algorithms Research Articles

A characterization method for reprocessed spent nuclear fuel through neutron and gamma-ray multiplicity counting

It is difficult to measure neutrons and gamma rays coming directly from uranium and plutonium atoms in pyroprocessed ingot, which is of great interest to nuclear safeguards. Most neutrons of the ingot are emitted from 244Cm isotope and gamma rays from its fission products. Therefore, it is necessary to identify spent fuel characteristics such as initial enrichment, burnup and cooling time from measurement and estimate plutonium mass from calibration curve or burnup calculations.In this study, we explored the possibility of characterizing pyroprocessed ingots using neutron and gamma-ray multiplicity counting. We particularly focused on finding the possible correlation between neutron and gamma-ray multiplicity properties (singles, doubles, and triples) and spent fuel properties for U/TRU/RE preprocessed ingot. We examined neutron and gamma-ray correlation for spent fuel, using the Cascading Gamma-ray Multiplicity with Fission (CGMF) and the Fission Reaction Event Yield Algorithm (FREYA) library in MCNP6.2. Due to high spontaneous fission rate, neutron and gamma-ray multiplicity parameters did not strongly correlate with multiplication factor from the point model but was proportional to 244Cm mass. The results based on the CGMF and FREYA fission library showed the similar trends for neutron and gamma-ray cases. The sum of two multiplicity data yielded best linearity with the 244Cm effective mass. Although total neutron counting (S) alone was sufficient for effectively characterizing spent fuel due to its strong linearity, this feasibility study confirmed that, in principle, it will be more effective to calculate the sum of neutron and gamma-ray multiplicity properties to directly estimate the mass of 244Cm, rather than relying on the conventional method of calculating the multiplication factor.

Real-Time Optimal Scheduling of a Water Diversion System Using an Improved Wolf-Pack Algorithm and Scheme Library

A water diversion system (WDS) with cascade pumping stations (CPSs) plays an important role in the application of water resources. However, high energy consumption is reported due to unreasonable scheduling schemes and long decision times. Herein, this paper presents a new method to achieve optimal scheduling schemes effectively, including the head allocation of CPSs, the number of running pumps, and pump blade angles. A double-layer mathematical model for a WDS was established with the goal of achieving minimal energy consumption, considering the constraints of flow rate, water level, and the characteristics of pump units. The inner-layer model was used to obtain scheduling schemes of single-stage pumping stations, as well as the water levels and flow rates of water channels, while the outer-layer model was used to optimize inter-stage head allocation. An improved wolf-pack algorithm (IWPA) was proposed to solve the model, using a Halton sequence to obtain the uniform initial population distribution and introducing simulated annealing (SA) to improve the global searchability. Moreover, an idea for a pre-established scheme library was suggested for inner-layer models to obtain the solutions in real time with less calculation workload. Taking an actual project as a case, in contrast with the actual schemes, the optimal scheduling method could result in energy savings of 14.37–20.39%, a CO2 emission reduction of 13–32 tons per day, and water savings of 0.14–18.34%. Moreover, the time complexity decreased to square order, and the CPU time of the optimal method was about 1% that of the traditional method. This study provides an efficient method for the high-value utilization of energy and water resources for a WDS.

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

ObjectivesTo develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset.Materials and methodsRetrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions.ResultsThe Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort.ConclusionThe multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model.Clinical relevance statementPredicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

Parallel intersection counting on shared-memory multiprocessors and GPUs

Computing intersections among sets of one-dimensional intervals is an ubiquitous problem in computational geometry with important applications in bioinformatics, where the size of typical inputs is large and it is therefore important to use efficient algorithms. In this paper we propose a parallel algorithm for the 1D intersection-counting problem, that is, the problem of counting the number of intersections between each interval in a given set A and every interval in a set B. Our algorithm is suitable for shared-memory architectures (e.g., multicore CPUs) and GPUs. The algorithm is work-efficient because it performs the same amount of work as the best serial algorithm for this kind of problem. Our algorithm has been implemented in C++ using the Thrust parallel algorithms library, enabling the generation of optimized programs for multicore CPUs and GPUs from the same source code. The performance of our algorithm is evaluated on synthetic and real datasets, showing good scalability on different generations of hardware.

Deep reinforcement learning based decision making for radar jamming suppression

Due to the need for the real-time participation of a large number of professionals, existing decision-making methods for radar interference suppression are characterized by a slow decision-making speed, unstable decision-making effects, and insufficient decision-making intelligence. In this paper, a deep reinforcement learning (DRL)-based decision-making method for radar interference suppression is proposed. This method has a fast decision speed and a stable and accurate decision effect, and can complete decision-making tasks by itself with high intelligence. To enhance the ability of the agent to acquire high-value experiences, the variable greedy algorithm (VGA) is proposed. The VGA adjusts the fixed greedy value in the original action strategy into a declining greedy curve that mimics the human learning process via a combination of the ideas in the win or learn fast–policy hill-climbing (WoLF-PHC) algorithm and the Ebbinghaus forgetting curve. To improve the efficiency of the agent in utilizing high-value experiences, the double-depth prioritized experience replay (DDPER) algorithm is proposed. The DDPER algorithm changes the uniform random experience replay into prioritized experience replay (PER), and performs sorting and extraction learning based on experience values in the form of additive trees to achieve better learning results. Further, the accuracy and speed of decision-making are improved via the double-depth experience replay system. The findings of a simulation experiment show that the agent can efficiently learn the most optimal radar interference suppression method by knowing that the interference suppression algorithm library contains algorithms that can deal with current environmental interference signals. Furthermore, compared to the PER–double deep Q-Network (PER-DDQN) presented by Zhang, the average accuracy, speed, and stability of decision-making are respectively increased by 6.4%, 2.51%, and 102.12%.

Attention mechanism-aided model ensemble method of chiller energy consumption prediction

The chiller energy consumption prediction plays an important role in reducing the building energy consumption. Continuously improving the performance of the prediction model is the key to ensuring the accuracy of the chiller energy consumption prediction. As a result, a new improved ensemble model of the chiller energy consumption prediction is proposed, based on the idea of algorithmic ensemble aided by an attention mechanism (AM). To guarantee that the proposed model can see information from many spatial and structural viewpoints, the improved ensemble model incorporates the benefits of several base prediction methods. The suggested approach chooses crucial features to simplify the model input by utilizing AM, thereby reducing the complexity of the samples. The improved ensemble model was experimentally verified in an actual multi-chiller system, and the results showed that the established model could obtain good prediction results. Finally, the proposed model was compared with existing, well-known prediction models. To evaluate the accuracy of these models, the mean absolute error (MAE), mean absolute percentage error (MAPE), mean square error (MSE), variance accounted for (VAF), and coefficient of determination (R2) were used as the evaluation indices. With an MAE of 2.858, an MAPE of 1.2755 %, an MSE of 20.1878, a VAF of 93.6058, and an R2 of 0.9923, the findings demonstrate that the improved ensemble model has a greater prediction accuracy than the other well-known prediction methods. The suggested model enhances the variety of empirical model algorithm libraries.

Refinement and Computation Method for Line/Body Topological Relationships

Three-dimensional topological relationships serve as a theoretical foundation for quality control, update processing, and spatial analysis of three-dimensional spatial data in real-world three-dimensional GIS. The existing 3D topological relationship models are all basic relationship models that cannot distinguish the refined topological relationship between the line and the body with multiple intersections. In this study, we develop a 3D refined topological relationship description framework that draws from the two-dimensional refined topological relationship model, defines the unit intersection between the line and the body based on manifold topology, and proposes a method for describing the unit intersections between the line and the body considering Euler numbers and adjacency types. In total, 23 basic types between the line and the body are deduced. An example is provided to illustrate the distinguished refined topological relationship between the line and the body with multiple intersections. Subsequently, an algorithm for determining the basic type of line/body is developed. Finally, a line/body refined topological relationship computation prototype system is developed using the Nef polyhedron model, C++ language, and an open-source geometric algorithm library, and the effectiveness of our method is verified using actual building and pedestrian data.

Development of Tools for Creating Parallel Data Mining Algorithms

The purpose of this work is to develop tools for building parallel data mining algorithms for execution in a distributed environment. A formal model of a data mining algorithm is proposed, characterized by a representation of the algorithm in the form of a set of independent operations that change the state of the knowledge model and structural blocks that allow modifying the structure of the algorithm, including for parallel execution. A method is proposed for creating parallel algorithms for data mining, in contrast to existing ones, using a decomposition of the algorithm into thread-safe functional blocks and allowing parallelization, both by changing the structure of the parallel algorithm and by configuring its execution. A methodology is proposed for parallelizing data mining algorithms, which differs from those known in that the proposed method of creating parallel data mining algorithms taking into account the characteristics of a distributed environment is applied to sequential analysis algorithms. To create parallel data mining algorithms, software templates built on the basis of a formal model and separating the implementation of the algorithm from distributed execution tools are proposed. A library of parallel data mining algorithms has been developed for execution in a distributed environment, including the proposed templates.

Forest Fire Detection System for Preventing Flora &amp; Fauna from Fire Using Computer Vision

Forest fires present a significant threat to ecosystems, endangering both human and animal life while causing irreversible environmental damage. To address this pressing issue in this research paper introduces an innovative &amp; Affordable forest fire detection system that utilises the HSV algorithm and various computer vision libraries with the use of AI. Our advance system aims to detect &amp; respond to forest fires in real-time, mitigating potential harm to flora and fauna. Our proposed System employs deploy camera sensors distributed at the Sensitive Parts of the forest, continually monitoring the environment. The HSV algorithm enhances the system's capability to accurately identify fire-related hues, ensuring reliable fire detection. Upon detecting a fire, an automatic alarm is triggered, initiating a series of measures to protect the ecosystem proactively. In response to a detected fire, the system automatically reroutes animal pathways to minimize their exposure to danger. Concurrently, the system sends immediate notifications to the local fire department and forest authorities via direct email, providing vital information on the fire's location and severity. This rapid communication facilitates timely intervention and improves the chances of successful firefighting efforts. We can put our system at Jim Corbett National Park &amp; at different Sensitive forest Regions. Furthermore, the system features live monitoring capabilities, enabling authorities to observe the fire's real-time progression. This live feed supports informed decision making and facilitates the swift deployment of resources to contain and extinguish the fire. Through the integration of advanced computer vision technology, our system aims to redefine forest fire detection &amp; response mechanisms, ultimately safeguarding the delicate balance of flora and fauna in ecosystems.

A Survey on Artificial Intelligence Assurance

Abstract: Artificial Intelligence (AI) algorithms are decreasingly furnishing decision-timber and functional support across multiple disciplines. AI includes a wide (and growing) library of algorithms that could be applied to different problems. One important notion for the relinquishment of AI algorithms into functional decision processes is the conception of assurance. The literature on assurance, unfortunately, conceals its issues within an involved geography of clashing approaches, driven by contradicting provocations, hypotheticals, and anticipations. Consequently, albeit a rising and new area, this handwriting provides a methodical review of exploration works that apply to AI assurance, between the times 1985 and 2021 and aims to give a structured volition to the geography. A new AI assurance description is espoused and presented, and assurance styles are varied and tabulated. also, a ten-metric scoring system is developed and introduced to estimate and compare styles. Incipiently, in this handwriting, we give foundational perceptivity, conversations, unborn directions, a roadmap, and applicable recommendations for the development and deployment of AI assurance.

Brain Tumor Detection and Classification Using VGG16 Deep Learning Algorithm and Python Imaging Library

Early diagnosis and treatment of brain cancer depend on the detection and categorization of brain tumors. Deep learning algorithms have produced amazing results in medical imaging applications including tumor identification. Most of this field's research has concentrated on applying CNN algorithms like VGG16, DNN, and ANN to this problem. This work describes the identification and classification of brain tumors using the Python Imaging Library (PIL) and the VGG16 deep learning algorithm. A dataset of 7000 MRI pictures categorized by tumor type served as the foundation for the research. The main objective of this study was to develop a high-efficiency, high-accuracy model. We suggested utilizing the VGG16 architecture and preprocessing images with PIL to ensure consistent images for training on a sizable dataset of brain magnetic resonance imaging (MRI) images. A novel technique we have used in our work is one that can analyze a single image and predict the presence of a tumor from the results. The research's methods produced robust tumor detection across the dataset with 96, 9% accuracy, indicating the value of the method in helping medical professionals make informed decisions when diagnosing the presence of tumors.

Migration-based algorithm library enrichment for constrained multi-objective optimization and applications in algorithm selection

Migration-based algorithm library enrichment for constrained multi-objective optimization and applications in algorithm selection

SafeCity: A Heterogeneous Mobile Crowd Sensing System for Urban Public Safety

As important indicators of urban public safety, Public Safety and Environmental Security (PSES) is related to residents’ living security and greatly affects their quality of life and happiness index. Due to PSES characteristics such as diverse forms, wide distribution, and unpredictable occurrence times, traditional solutions consume huge manpower and time in the implementation process. Although some professional software and hardware systems have emerged to assist in solving the problems, there are still challenges such as limited sensing coverage and monotonous sensing modes, lack of interaction and understanding between systems and tasks, and scarcity of effective system architecture and functional modules. To meet these challenges, we design a PSES multi-terminal fusion system (SafeCity) based on the idea and technology of heterogeneous mobile crowd sensing. With collaboration among Humans, Machines, and Things (H-M-T), the proposed system makes full use of the idle mobility, sensing and computing resources in the city, and systematically provides a solution to the various PSES issues. Apart from the system architecture, functions, core mechanism, and algorithm libraries, the task execution flow is explained in depth through the description of several cases. We implement a prototype to verify the rationality and effectiveness of SafeCity. And comprehensive comparison and evaluation show that SafeCity is far superior to other solutions in terms of function, performance, and stability.

GWDALI: A Fisher-matrix based software for gravitational wave parameter-estimation beyond Gaussian approximation

We introduce GWDALI, a new Fisher-matrix, python based software that computes likelihood gradients to forecast parameter-estimation precision of arbitrary network of terrestrial gravitational wave detectors observing compact binary coalescences. The main new feature with respect to analogous software is to assess parameter uncertainties beyond Fisher-matrix approximation, using the derivative approximation for Likelihood (DALI). The software makes optional use of the LSC algorithm library LAL and the stochastic sampling algorithm Bilby, which can be used to perform Monte-Carlo sampling of exact or approximate likelihood functions. As an example we show comparison of estimated precision measurement of selected astrophysical parameters for both the actual likelihood, and for a variety of its derivative approximations, which turn out particularly useful when the Fisher matrix is not invertible.

Development of deep reinforcement learning for inverted pendulum

This paper presents a modification of the deep Q-network (DQN) in deep reinforcement learning to control the angle of the inverted pendulum (IP). The original DQN method often uses two actions related to two force states like constant negative and positive force values which apply to the cart of IP to maintain the angle between the pendulum and the Y-axis. Due to the changing of too much value of force, the IP may make some oscillation which makes the performance system could be declined. Thus, a modified DQN algorithm is developed based on neural network structure to make a range of force selections for IP to improve the performance of IP. To prove our algorithm, the OpenAI/Gym and Keras libraries are used to develop DQN. All results showed that our proposed controller has higher performance than the original DQN and could be applied to a nonlinear system.

Формирование концепции спутниковой группировки для раннего обнаружения лесных пожаров

The paper considers concept formation of a satellite constellation for early detection of fires in Siberia. Within the framework of the stated concept, an orbit was selected for deployment of a satellite constellation, and the flight path of satellites in a circular sun-synchronous orbit was constructed. The CubeSat platform is proposed as the basis for potentially applicable spacecraft for remote sensing of the Earth, the satellite expected appearance was created in the form of a 3D model, and the principle of satellites’ operation is described. It is assumed that the satellite would only take images and transmit them to the ground control station. To analyze images received from the satellites, the software is proposed that automatically detects fires and implements an algorithm using the OpenCV computer vision algorithm library. As a means of launching the satellite constellation, it is proposed to use the light-class Angara-1.2 launch vehicle.

Reconstruction of interactions in the ProtoDUNE-SP detector with Pandora

The Pandora Software Development Kit and algorithm libraries provide pattern-recognition logic essential to the reconstruction of particle interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at ProtoDUNE-SP, a prototype for the Deep Underground Neutrino Experiment far detector. ProtoDUNE-SP, located at CERN, is exposed to a charged-particle test beam. This paper gives an overview of the Pandora reconstruction algorithms and how they have been tailored for use at ProtoDUNE-SP. In complex events with numerous cosmic-ray and beam background particles, the simulated reconstruction and identification efficiency for triggered test-beam particles is above 80% for the majority of particle type and beam momentum combinations. Specifically, simulated 1 GeV/c charged pions and protons are correctly reconstructed and identified with efficiencies of 86.1pm 0.6% and 84.1pm 0.6%, respectively. The efficiencies measured for test-beam data are shown to be within 5% of those predicted by the simulation.

Multi-objective structural profile optimization of ships based on improved Artificial Bee Colony Algorithm and structural component library

This paper addresses the multi-objective, design variables discrete problem of river boat profile structure optimization. The study considers not only the economic performance but also the stability of the boat to a certain extent when selecting the optimization objectives. First, the standard component library of the vessels is established and the discrete structural model is converted into a continuous optimization model based on the component library index. Second, to balance the global search and local search capability of the optimization algorithm, an adaptive Artificial Bee Colony Algorithm (I-ABC) is proposed. I-ABC uses a modified chaotic mapping to improve the diversity of nectar sources, and adaptive search and following mechanisms are adopted for the leading and following bee stages, respectively. Then, a Dominating Artificial Bee Colony Algorithm (D-ABC) is proposed for multi-objective optimization by introducing Pareto domination and considering the degree of individual crowding in terms of hypersphere neighborhood. Then, numerical simulations and comparative analysis of the proposed algorithm are performed using different test functions, and the results show that I-ABC and D-ABC have excellent performance in both single-objective and multi-objective optimization. Finally, using the component library established in this paper and the proposed improved Bee Colony Algorithm to optimize the profile structure of a chemical-liquid tanker, the optimization results show that the maximum reduction of the ship profile area is 5.08% and the maximum reduction of the vertical center height is 7.427%. The proposed optimization algorithm is also applicable to other river boats.

CapRadar: Real-time adaptive bandwidth prediction for dynamic wireless networks

With the emergence of 4G/5G cellular networks, mobile Internet is becoming increasingly popular and numerous mobile applications have emerged, which puts higher demands on the accuracy of predicting available bandwidth. However, compared to WiFi and wired networks, the links of 4G/5G cellular networks are highly dynamic, and the unstable nature of their network environments makes the bandwidth trajectories vary. Traditional bandwidth prediction models rarely consider the bandwidth characteristics of various network scenarios, and a single prediction model is difficult to be applied to all scenarios, which makes it challenging to achieve high accuracy of available bandwidth prediction. To solve the above problems, we propose a real-time bandwidth prediction method called CapRadar. The method classifies bandwidth into scenarios and matches the optimal prediction model for each type of scenario, i.e., switches the prediction model in real time according to the changes of the scenario. Specifically, we first extract the statistical characteristics of the bandwidth using statistical method, and based on the extracted characteristics, a SVM classifier is used to detect different network scenarios. After that, the best prediction model is matched for them in the algorithm library based on the scenario classification results. The experimental results show that CapRadar can reduce the root mean square error (RMSE) by about 18.9% and the mean error (MAE) by about 21.5%. For practical applications, we use a pre-trained SVM model for real-time scenario detection, and then we can dynamically switch the prediction model.

Electric Machine Design by a Novel Fast Model Predictive Optimization Strategy Treating Dimension-Expensive Problem

As a crucial preprocessing for motor products, design optimization methodologies have been widely explored. However, existing studies always indicate some issues. Analytical model-based optimization involves complex mechanisms. The surrogate-based optimization can hardly satisfy the accuracy of multiple objectives or in scenarios with high dimensions. The numerical tool-based optimization is time-consuming even with the multi-level technique. Accordingly, a novel fast model predictive optimization (MPO) strategy is proposed. It follows a parametric analysis stage to quantify the intrinsic mechanisms between variable-objective pairs. The space-filling sampling technique and parameter correlation are applied. By searching in a library of machine learning algorithms, MPO constructs a trustable model with only limited case evaluations. To treat the objectives with different sensitivities, the proposed MPO strategy learns the algorithms, hyperparameters, and parameters. A novel ranking regularization is introduced to the ordinary loss function for examining the model accuracy or validity. Hence, finite element analysis can be avoided in the subsequent optimization. After performing the sensitivity analysis, the optimal design of permanent magnet machine is prototyped and tested to verify the proposed design methodology. In short, MPO finds a more complete Pareto frontier more efficiently than the FEA-based optimization.