Algorithm Vector Research Articles

A method for optimizing text preprocessing and text classification using multiple cycles of learning with an application on shipbrokers emails

Optimizing text preprocessing and text classification algorithms is an important, everyday task in large organizations and companies and it usually involves a labor-intensive and time-consuming effort. For example, the filtering and sorting of a large number of electronic mails (emails) are crucial to keeping track of the received information and converting it automatically into useful and profitable knowledge. Business emails are often unstructured, noisy, and with many abbreviations and acronyms, which makes their handling a challenging procedure. To overcome those challenges, a two-step classification approach is proposed, along with a two-cycle labeling procedure in order to speed up the labeling process. Every step incorporates a heuristic classification approach to assign emails to predefined classes by comparing several classification and text vectorization algorithms. These algorithms are compared and evaluated using the F1 score and balanced accuracy. The implementation of the proposed algorithm is demonstrated in a shipbroker agent operating in Greece with excellent performance, improving organization and administration while reducing expenses.

Deep convolutional neural network and IoT technology for healthcare.

Deep convolutional neural network and IoT technology for healthcare.

Optimal power flow calculation in hybrid power system involving solar, wind, and hydropower plant using weighted mean of vectors algorithm

One of the most complex and motivating issues in power system is optimal power flow (OPF), which is a constrained optimization problem characterized by non-linearity and non-convexity. From these specifications, researchers competed in the past decades to find optimal solutions to OPF problem while keeping system stability. This paper presents an efficient optimization approach to deal with OPF problem in the hybrid renewable energy systems involving wind turbines, solar photovoltaic and small hydropower plant using optimization method depends on weighted mean of vectors INFO. Total generation cost, active power losses, and combined cost and emission are the principle goal, taking into account both reserve and penalty cost appropriate to over and under estimation respectively in the generation cost model. To evaluate the performance of INFO in solving OPF problem, modified IEEE 30-bus and IEEE 57-bus test systems will be utilized. The obtained results are compared with several algorithms such as Gorilla troop optimizer GTO, artificial ecosystem-based optimization AEO, Barnacles Mating Optimizer BMO for the same test systems keeping the same conditions. Simulation results have indicated the superiority of INFO while respecting all constraints. INFO can minimize total generation cost to 788.9417 $/h for IEEE 30-bus and 5259.2040 $/h for IEEE 57-bus. The results demonstrate clearly that the INFO is a highly efficient algorithm that is an encouraging tool for solving OPF problem. The promising findings highlight the potential of the INFO algorithm to smoothest the integration of RES, and its role in promoting sustainable energy solutions. Furthermore, the one-way analysis of variance (ANOVA) test, a statistical approach, was employed to evaluate the superiority of the proposed algorithm and to highlight a certain level of confidence to our study.

Moving scene object tracking method based on deep convolutional neural network

The effect of target tracking is not ideal when facing various complex tracking scenarios such as non-rigid deformation of target, frequent occlusion, clutter of target background and interference of similar objects. In this paper, the feature based on deep convolutional neural network is used for target tracking in moving scenes, and a sliding window target segmentation method is proposed to study the impact of data normalization and data set expansion on the final result. In order to select more distinguishing features, principal component analysis is used to process the features of Deep Convolution Neural Network (DCNN), and the features of different network layers of DCNN are compared. The feature coding algorithm is studied, and the extracted DCNN features are encoded by Fisher Vectors algorithm, and compared with the locality-constrained linear encoding technique. Experiments show that the feature based on deep convolutional neural network in this paper can obtain higher accuracy than the traditional feature fusion method. According to the result analysis, the tracking accuracy of deep convolutional neural network algorithm is improved under the condition of illumination variation. In the case of local occlusion, the tracking accuracy is also improved.

Parsing millions of URLs per second

AbstractURLs are fundamental elements of web applications. By applying vector algorithms, we built a fast standard‐compliant C++ implementation. Our parser uses three times fewer instructions than competing parsers following the WHATWG standard (e.g., Servo's rust‐url) and up to eight times fewer instructions than the popular curl parser. The Node.js environment adopted our C++ library. In our tests on realistic data, a recent Node.js version (20.0) with our parser is four to five times faster than the last version with the legacy URL parser.

Parameter estimation of ECM model for Li-Ion battery using the weighted mean of vectors algorithm

Accurate parameter estimation of the equivalent circuit model (ECM) for Li-Ion batteries (LiBs) allows for better behavior modeling and understanding. This is crucial for various applications, such as battery management systems (BMSs) and renewable energy systems, as it enables more precise performance prediction and optimization. This article introduces a novel artificial intelligence (AI) approach to estimate the ECM parameters of LiBs. The proposed method leverages the innovative weIghted meaN oF vectOrs (INFO) algorithm to optimize ECM parameter values. INFO combines multiple vectors, considering their relative importance, to generate a single vector. The algorithm minimizes the disparity between the ECM’s estimated voltage and the battery’s measured voltage. The effectiveness of the proposed method is assessed using a test profile based on real-world driving data. Furthermore, A comparative analysis is conducted with other state-of-the-art optimization algorithms, including Artificial Ecosystem Optimizer (AEO), Grey Wolf Optimizer (GWO), Artificial Hummingbird Algorithm (AHA), Harris Hawks Optimization (HHO), Leader Harris Hawks Optimization (LHHO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Adolescent Identity Search Algorithm (AISA). Results demonstrate that the INFO outperforms these methods in terms of accuracy and convergence speed. The proposed INFO algorithm offers a promising approach for accurate parameter estimation in LIB modeling, contributing to improved BMS and enhanced performance prediction.

Patent text mining based hydrogen energy technology evolution path identification

With the rise of the hydrogen energy industry, countries worldwide have introduced relevant policies to elevate the development of the hydrogen energy industry to the height of national energy strategy, and hydrogen energy will become a significant factor affecting the future industrial structure and national competitiveness. The path of technology evolution can trace the history of technology development and predict the trend of technology development, which can help to grasp the first opportunity of technological innovation and lead the direction of technological development. However, there are fewer studies on technology evolution in hydrogen energy. The existing studies mainly use bibliometrics to mine a single technology, and the studies using text mining suffer from the defect that keywords are difficult to decipher. Given this, this paper conducts research on identifying the technology evolution path in the field of hydrogen energy, adopts text mining methods to mine patent data, and introduces document vectorization and phrase mining algorithms to improve the mining depth while increasing the interpretability of the results. It is found that the hydrogen energy industry is in a period of rapid development; the succession and integration of hydrogen energy technologies are good, and the technological development trend focuses on hydrogen storage materials, hydrogen fuel cell vehicles, and green hydrogen preparation.

Visual Communication Design Features Based on Traditional Animal and Plant Patterns

Abstract This paper contributes to the visual communication design of traditional animal and plant patterns by recreating the traditional pattern graphics based on the specific skeletal laws of traditional patterns. Based on the demand for vectorization of traditional animal and plant tattoos, a vectorization algorithm based on edge structure extraction is proposed to pre-process the tattoos using the gradient minimization model, and the tattoos are processed by image vectorization using the edge structure extraction algorithm of clustered segmentation and the Bézier curve fitting algorithm of the least squares method. Based on the image vectorization rendering of traditional animal and plant patterns, the visual communication design is carried out, and the color matching effect is analyzed in terms of single-factor color matching and comprehensive color matching. 10 extracted colors are analyzed in terms of the hue angle difference on the color ring, and the two comparative colors are the contrasting colors when the angle difference is 120~180°. The contrast height is highest when the difference value is 180°.

Driver behaviour prediction and enhanced ad hoc on‐demand distance vector routing protocol in VANET

SummaryMobility pattern recognition is a complex task in vehicle ad hoc networks (VANET) because the driving state of each vehicle is different. An intelligent transportation system on VANET is used for traffic control and accident prevention. For this reason, human driver behaviour is first analysed to identify mobility patterns. A novel driver behaviour prediction model using a Siamese deep learning architecture is proposed to achieve the goal. Here, an image‐based behaviour prediction model is performed to achieve the highly accurate driving state of the driver. A warning message is forwarded to the neighbouring vehicles based on the driver's behaviour. Due to the dynamic properties of real‐time vehicle mobility, a faster data transmission model is achieved using the ad hoc on‐demand distance vector routing protocol. To achieve faster data transmission and nullified retransmission, here a weighted location‐based routing model is framed. The optimization problem in the location‐aided routing protocol is solved using the vector algorithm's weighted mean. As a result, the proposed method improved the throughput of ASHLOSR to 8.1% and AODV to 7.6%.

Controller design for automatic voltage regulator system using modified opposition-based weighted mean of vectors algorithm

ABSTRACT This paper proposes a modified optimization technique to determine the parameters of a real proportional-integral-derivative plus second-order derivative (real PIDD2) controller adopted in an automatic voltage regulator (AVR). In this regard, a modified opposition learning (mOBL) based weighted mean of vectors (INFO) algorithm (mOBL-INFO) is proposed for the first time. The performance of the proposed algorithm was initially tested on several benchmark functions with unimodal, multimodal, and low-dimensional properties. The obtained results against test functions were compared with the original INFO algorithm as the latter has already been shown to present superior results against several recent and effective metaheuristic algorithms. The developed mOBL-INFO algorithm was then used to adjust a real PIDD2 controller for the AVR system. The performance of the proposed method was tested using several analyses such as transient response, stability, and robustness. The related analyses demonstrated good promise of the proposed method for AVR system control. Furthermore, previously reported 26 effective methods were also employed to assess the performance of the mOBL-INFO-based real PIDD2 controller for the AVR system. The obtained results demonstrated that the proposed method in this study has an excellent transient response performance for AVR system control.

Node authentication and encrypted data transmission in mobile ad hoc network using the swarm intelligence‐based secure ad‐hoc on‐demand distance vector algorithm

AbstractIn a mobile ad hoc network (MANET), all nodes are communicated with one another across wireless networks to create a temporary network without the support of centralised management. Due to dynamic topology in MANET, secure routing is a crucial issue. The existing secure routing protocol and their security concerns are analysed in this work. The suggested Swarm Intelligence‐based Secure Ad‐hoc On‐demand Distance Vector (SIS‐AODV) algorithm offers security by applying a secret key and hash mechanism to prevent the involvement of malicious nodes in routing operations. A secure routing system of MANET guards against internal and external network attacks. The proposed SIS‐AODV algorithm consists of two sections: the secret key value generated by applying Elliptical Curve Cryptography (ECC)‐based algorithm and the PRESENT algorithm to encrypt the data packets. Besides, authentication and non‐repudiation are applied using the H‐PRESENT 128 algorithm. The PRESENT algorithm and H‐PRESENT 128 hash function require less computational power. Centralised management is optional in this scheme, so overhead decreases. The second section of SIS‐AODV consists of Ant Colony Grey Wolf Optimization over the AODV algorithm to improve network performance while implementing a security algorithm over MANET. Analysis results show maximum performance with a packet delivery ratio of 98% and throughput of 85%. In addition, end‐to‐end delay is reduced by up to 25%, and routing overhead decreases by up to 20%. Keywords: AODV, Elliptical Curve, PRESENT, H‐PRESENT, Euclidean Algorithm, ACO, GWO, Blackhole attack.

A quantum algorithm for finding collision-inducing disturbance vectors in SHA-1

Modern cryptographic protocols rely on sophisticated hash functions to generate quasi-unique numbers that serve as signatures for user authentication and other security verifications. The security could be compromised by finding texts hash-mappable to identical numbers, forming so-called collision attack. Seeding a disturbance vector in the hash mapping to obtain a successful collision is that a major focus of cryptography study in the past two decades to improve hash protocols. We propose an algorithm that takes advantage of entangled quantum states for concurrent seeding of candidate disturbance vectors, out of which the one entailing collision is selected through a combination of quantum search, phase gating, diffusion gating, and information feedbacks from classical computing machinery. The complexity reduction is shown to be on the order of where n is the number of qubits encoding addresses. We demonstrate the practicality of the proposed by an implementation scheme based on degenerate optical parametric oscillators.

Randomized vector iterative linear solvers of high precision for large dense system

Abstract In this paper we suggest randomized linear solvers with a focus on refinement issue to achieve a high precision while maintaining all the advantages of the Monte Carlo method for solving systems of large dimension with dense matrices. It is shown that each iterative refinement step reduces the error by one order of magnitude. The crucial point of the suggested method is, in contrast to the standard Monte Carlo method, that the randomized vector algorithm computes the entire solution column at once, rather than a single component. This makes it possible to efficiently construct the iterative refinement method. We apply the developed method for solving a system of elasticity equations.

Price Prediction Using Web Scraping and Machine Learning Algorithms in the Used Car Market

The development of technology increases data traffic and data size day by day. Therefore, it has become very important to collect and interpret data. This study, it is aimed to analyze the car sales data collected using web scraping techniques by using machine learning algorithms and to create a price estimation model. The data needed for analysis was collected using Selenium and BeautifulSoup and prepared for analysis by applying various data preprocessing steps. Lasso regression and PCA analysis were used for feature selection and size reduction, and the GridSearchCV method was used for hyperparameter tuning. The results were evaluated with machine learning algorithms. 
 Random Forest, K-Nearest Neighbor, Gradient Boost, AdaBoost, Support Vector and XGBoost regression algorithms were used in the analysis. The obtained analysis results were evaluated together with Mean Square Error (MSE), Root Mean Square Error (RMSE) and Coefficient of Determination (R-square). When the results for data set 1 were examined, the model that gave the best results was XGBoost Regression with 0.973 R2, 0.026 MSE and 0.161 RMSE values. When the results for data set 2 were examined, the model that gave the best results was K-Nearest Neighbor Regression with 0.978 R2, 0.021 MSE and 0.145 RMSE values.

Application of the Learning Vector Algorithm Quantization On Smart Barcodes

Penerapan algoritma Learning Vector Quantization (LVQ) pada barcode cerdas memiliki tujuan untuk meningkatkan efisiensi dan akurasi dalam pengenalan serta pelacakan data barang. Dalam konteks ini, barcode berfungsi sebagai representasi visual yang mengandung informasi penting tentang produk. Algoritma LVQ digunakan untuk mengoptimalkan proses klasifikasi dan pencocokan data barcode dengan referensi yang tepat. Melalui pelatihan berulang, algoritma ini mengadaptasi vektor pembelajaran untuk mengenali variasi barcode dengan lebih baik. Dalam penelitian ini, peneliti menganalisis dampak penerapan algoritma LVQ pada sistem barcode cerdas dalam hal akurasi identifikasi, efisiensi komputasi, dan kemampuan beradaptasi terhadap perubahan. Hasil eksperimen menunjukkan penerapan barcode pada sistem inventory barang membawa manfaat yang signifikan dalam pengelolaan stok dan efisiensi bisnis secara keseluruhan. Dengan pemanfaatan teknologi barcode, proses pelacakan dan pencatatan data produk menjadi lebih cepat, akurat, dan terotomatisasi. Penggunaan barcode meminimalkan kesalahan manusia, mengoptimalkan waktu, dan mengurangi biaya operasional. Dengan menggabungkan kecerdasan algoritma LVQ dan potensi barcode, penelitian ini mengilustrasikan perkembangan penting dalam domain integrasi teknologi untuk pengembangan sistem yang lebih canggih dan efektif.

Efficient Compressed Sensing Reconstruction Algorithm for Nonnegative Vectors in Wireless Data Transmission

With the rapid development of 5G communication and wireless Internet of Things technology, the application of intelligent wearable devices based on wireless data transmission technology is becoming more and more popular. However, due to the bandwidth of wireless data transmission nodes and the power consumption of the device system, the use time and data storage of wearable devices are severely restricted. The compressed sensing (CS) technology has become an effective method to tackle this problem. CS technology includes data compressive sensing at the transmission end and data reconstruction at the receiving end. In this paper, we consider the reconstruction of nonnegative sparse vectors, an important problem in the area of CS for wireless data transmission. It is known that the interval-passing (IP) algorithm is a low-complexity message-passing type method for the problem. However, the reconstruction performance of the IP algorithm is inferior to that of the other state-of-the-art CS reconstruction algorithms such as the orthogonal matching pursuit (OMP) algorithm. In order to address the problem, we propose a two-stage reconstruction algorithm in this paper. The proposed algorithm applies the IP algorithm for the first stage of reconstruction. If the reconstruction fails, the OMP algorithm is then used on the basis of the results in the first stage. The proposed algorithm is evaluated and compared with other state-of-the-art algorithms by the probability of perfect reconstruction under the given sparsity order value. Simulation results suggest that the proposed two-stage algorithm can greatly improve the reconstruction performance of the IP algorithm and can even outperform the OMP algorithm. In addition, the low-complexity advantages of the IP algorithm are maintained in the proposed algorithm.

Revolutionizing Vehicle Cruise Control: An Elite Opposition-Based Pattern Search Mechanism Augmented INFO Algorithm for Enhanced Controller Design

This paper presents a groundbreaking approach to enhance the performance of a vehicle cruise control system—a crucial aspect of road safety. The work offers two key contributions. Firstly, a state-of-the-art metaheuristic algorithm is proposed by augmenting the performance of the weighted mean of vectors (INFO) algorithm using pattern search and elite opposition-based learning mechanisms. The resulting boosted INFO (b-INFO) algorithm surpasses the original INFO, marine predators, and gravitational search algorithms in terms of performance on benchmark functions, including unimodal, multimodal, and fixed-dimensional multimodal functions. Secondly, a novel proportional, fractional order integral, derivative plus double derivative with filter (P{I}^{lambda }DN{D}^{2}{N}^{2}) controller is proposed as a more efficient control structure for vehicle cruise control systems. An objective function is utilized to determine the optimal values for the controller parameters, and the proposed method's performance is compared against a range of recent approaches. Results demonstrate that the b-INFO algorithm-based P{I}^{lambda }DN{D}^{2}{N}^{2} controller is the most efficient and superior method for controlling a vehicle cruise control system. Moreover, this work represents the first report of a P{I}^{lambda }DN{D}^{2}{N}^{2} controller’s implementation for vehicle cruise control systems, underscoring the novelty and significance of this research. The proposed method's exceptional ability is further confirmed by comparisons with the genetic algorithm, ant lion optimizer, atom search optimizer, arithmetic optimization algorithm, slime mold algorithm, Lévy flight distribution algorithm, manta ray foraging optimization, and hunger games search-based proportional–integral–derivative (PID), along with Harris hawks optimization-based PID and fractional order PID controllers. This work marks a remarkable milestone toward safer and more efficient vehicle cruise control systems.

Improving Structured Grid-Based Sparse Matrix-Vector Multiplication and Gauss–Seidel Iteration on GPDSP

Structured grid-based sparse matrix-vector multiplication and Gauss–Seidel iterations are very important kernel functions in scientific and engineering computations, both of which are memory intensive and bandwidth-limited. GPDSP is a general purpose digital signal processor, which is a very significant embedded processor that has been introduced into high-performance computing. In this paper, we designed various optimization methods, which included a blocking method to improve data locality and increase memory access efficiency, a multicolor reordering method to develop Gauss–Seidel fine-grained parallelism, a data partitioning method designed for GPDSP memory structures, and a double buffering method to overlap computation and access memory on structured grid-based SpMV and Gauss–Seidel iterations for GPDSP. At last, we combined the above optimization methods to design a multicore vectorization algorithm. We tested the matrices generated with structured grids of different sizes on the GPDSP platform and obtained speedups of up to 41× and 47× compared to the unoptimized SpMV and Gauss–Seidel iterations, with maximum bandwidth efficiencies of 72% and 81%, respectively. The experiment results show that our algorithms could fully utilize the external memory bandwidth. We also implemented the commonly used mixed precision algorithm on the GPDSP and obtained speedups of 1.60× and 1.45× for the SpMV and Gauss–Seidel iterations, respectively.

Analysis and optimization of junction between cylindrical part and end dome of filament wound pressure vessels using data driven evolutionary algorithms

The junction between cylindrical part and end dome is the most critical place of the filament wound composite pressure vessels because the shear forces and bending moments occur in this area. The strength analyses of junction between cylindrical part and different types of known end domes based on influence coefficients method were performed for filament wound composite pressure vessels manufactured using glass-epoxy and carbon-epoxy composites. Four known end domes were considered that is, a spherical shell, a geodesic-isotensoid shell, a shell based on minimizing of the Tsai-Hill’s strength criterion and shell designed in authors’ previous work (Hoffman 1 shell). Moreover, the study is also dealing with design of optimal end dome shape which takes account to the junction area. Finding of optimal end dome shape was based on data-driven evolutionary algorithms. Using input dataset from the analytical simulation surrogate models were created using Evolutionary Deep Neural Nets (EvoDN2) algorithm. The multicriterial optimization procedure was performed using Constrained Reference Vector Algorithm (cRVEA) optimization algorithm. Results indicates that the optimal end dome shape highly depend on material properties.

An improved weighted mean of vectors algorithm for microgrid energy management considering demand response

The integration of demand response programs (DRPs) into the energy management (EM) system of microgrids (MGs) helps in improving the load characteristics by allowing consumers to interoperate for achieving techno-economic advantages. In this paper, an improved algorithm is called LINFO is proposed for modifying search ability of the original weIghted meaN oF vectOrs (INFO) algorithm as well as avoiding its weaknesses like trapping in a local optima. The improved algorithm's efficiency is confirmed by comparing its results with those obtained by the original INFO and other optimization techniques using different standard benchmark test functions. Moreover, this improved algorithm and the original version are applied for solving the EM problem with the aim of optimizing the operation cost of the MGs in the presence DRPs. They are used to solve day-ahead EM problem for optimal operation of renewable energy resources, the optimal generation from a conventional diesel engines (DEs); taking into account the participation of customers in DRP for minimizing MG operating cost, which includes the cost of DEs fuel and the power transactions cost with the main grid. To demonstrate the efficacy of the proposed LINFO, simulation results are compared with the results of well-known and newly developed optimization techniques.