Background and Objectives: Reliable data transmission and congestion control are considered as the transport layer primary functions in Wireless Sensor Networks (WSNs). WSNs are a specific category of wireless ad-hoc networks where their performance is highly affected by their characteristics and limitations. These limitations necessitate an effective data transport control in WSNs which considers quality of service (QoS), energy efficiency, and congestion control.Methods: Congestion affects normal data transmission and ends in packet loss. Furthermore, wireless channels introduce packet loss because of high bit-error rate which wastes energy and affects reliability. The major problems regarding transport protocols in WSNs are congestion and reliability where the latter is classified and reviewed in the current paper.Results: In this paper, reliable data transport protocols are classified as the traffic direction, the parameter the reliability focuses on, and loss detection, notification, and recovery. Traffic direction-based reliable data transport protocols can be upstream, downstream or bidirectional, however, the parameter-based ones can be packet-based, event-based or destination-based, the loss detection and notification-based ones can be ACK-based, NACK-based, ACK and NACK-based or SACK-based, and the loss recovery-based reliable data transport protocols can be E-2-E or H-by-H. Thereafter, a comprehensive review of different reliable data transport protocols in wireless sensor networks is presented. Also, different performance metrics are used to compare these schemes.Conclusion: In this paper, reliable data transport protocols in WSNs are classified, reviewed and compared using different performance metrics. Finally, the current work attempts to provide specific directives to design and develop novel reliable data transport protocols in wireless sensor networks.
Background and Objectives: In order to compensate the nonlinearity, several linearization approaches such as feedback, feed-forward, and predistortion have been proposed. Among these linearization methods, the analog predistortion (APD) method is very suitable for the power amplifier and TWTA linearization, because it has a good compromise between complexity, linearity improvement and bandwidth. On the other hand, analog predistortion circuit can be added to existing amplifiers as a separate circuit. Many of the reported linearizer circuits are capable of linearizing power amplifiers with high gain and phase variations. However, these circuits are complex and bulky due to the use of distortion producer, phase shifter, adjustable attenuator, combiner/divider, and control unit. The objective of this paper is increasing the dynamic range of the predistorter by a simple proposed circuit. Hence, linearization capability of the linearizer is boosted.Methods: A new analog predistortion linearizer based on a coupler and a Schottky diode is presented. The proposed structure satisfies linearization requirements of the solid-state power amplifiers (SSPAs) and traveling wave tube amplifiers (TWTAs). Using a parallel combination of two Schottky diodes along with transmission line in port 2 and 3 of the coupler, the dynamic range of reflection coefficient of each port is increased compared to using a single diode in each branch. By increasing the range of reflection signal, the linearization capability has been increased to linearize power amplifiers and TWTAs. The AM/AM and AM/PM of the linearizer is controlled by changing the bias voltage of power supply.Results: The simulation results show that about 30° phase shift and 5 dB gain expansion can be compensated for power amplifiers and TWTAs. Because of utilizing two diodes, the linearization capability of the new linearizer is augmented compared to the conventional linearizer.Conclusion: A novel analog predistortion circuit based on the hybrid coupler and Schottky diodes is presented. The suggested topology increases the dynamic range of reflected power from each port. Using the proposed idea, AM/AM and AM/PM characteristics are expanded such that this characteristic can linearize the power amplifier with high linearity.
Background and Objectives: COVID-19 disease still has a devastating effect on society health. The use of X-ray images is one of the most important methods of diagnosing the disease. One of the challenges specialists are faced is no diagnosing in time. Using Deep learning can reduce the diagnostic error of COVID-19 and help specialists in this field. Methods: The aim of this study is to provide a method based on a combination of deep learning(s) in parallel so that it can lead to more accurate results in COVID-19 disease by gathering opinions. In this research, 4 pre-trained (fine-tuned) deep model have been used. The dataset of this study is X-ray images from Github containing 1125 samples in 3 classes include normal, COVID-19 and pneumonia contaminated.Results: In all networks, 70% of the samples were used for training and 30% for testing. To ensure accuracy, the K-fold method was used in the training process. After modeling and comparing the generated models and recording the results, the accuracy of diagnosis of COVID-19 disease showed 84.3% and 87.2% when learners were not combined and experts were combined respectively. Conclusion: The use of machine learning techniques can lead to the early diagnosis of COVID-19 and help physicians to accelerate the healing process. This study shows that a combination of deep experts leads to improved diagnosis accuracy.
Background and Objectives: Applications and systems software that are running constantly become obsolete due to the accumulation of error conditions or the depletion of resources like physical memory or performance degradation. In this regard, software rejuvenation has been proposed to deal with such a phenomenon and prevent software failure in the future. This paper proposes a multiple objective of software rejuvenation models with several policies. The purpose is to identify the right rejuvenation policy in practical situations.Methods: We model software system with four policies using the Markov process. These policies are: (a) Software system without rejuvenation; (b) Software system with partial rejuvenation; (c) Software system with partial and full rejuvenation; and (d) Software system with four different types of rejuvenation. In the models and each policy, we consider assigning the level of performance on which the availability and operating costs are calculated. Results: To evaluate the models with the four policies, many numerical experiments were performed. For each policy, we evaluated and compared three objectives, namely performance, availability and operating costs. The experimental results states that for Software System with the policy of four different type of rejuvenation has about 18 and 16 percent improvement in performance and availability, respectively, compared with those other policies. Moreover, the operating cost of the software system with partial rejuvenation policy is lower and more efficient than other policies.Conclusion: According to the calculated objectives and the results of the policies, it can be concluded that in systems with lower operational costs, the most appropriate policy is the software system with four different types of rejuvenation because this policy bring the maximum possible value for the performance and availability.
Background and Objectives: The principal aim of this paper is to show an independent vector control of two five-phase Linear Induction Motors (LIMs) that are supplied from a single VSI. Methods: The LIMs are running at the same speed but with different load conditions. This concept can be especially beneficial in long trains with distributed power. To achieve excellent control characteristics and to reduce the undesirable tension forces between the train mechanical couplers, Fuzzy Logic Controllers (FLCs) have been utilized.Results: As a result, the fault occurrence of the train control systems decreases, and the system reliability increases. The results prove the electrical independence in control of a five-phase two-LIM drive supplied with a single VSI. Furthermore, in the presence of the train mechanical couplers and connections, the application of FLC offers excellent control characteristics and reduces the undesirable tension forces. Furthermore, to obtain a more worthwhile validation of the theoretical results, an experimental set up has been constructed and results have also been presented.Conclusion: According to the results, the undesirable tension forces imposed on train couplers are reduced. Consequently, it leads to higher system efficiency, lower deterioration of the train couplers and connections, greater system reliability, and higher passenger safety and comfort.
Background and Objectives:The target tracking problem is an essential component of many engineering applications.The extended Kalman filter (EKF) is one of the most well-known suboptimal filter to solve target tracking. However, since EKF uses the first-order terms of the Taylor series nonlinear extension functions, it often makes large errors in the estimates of state. As a result, target tracking based on EKF may diverge. Methods: In this manuscript, an adaptive square root cubature Kalman filter (ASRCKF) is poposed to solve the maneuvering target tracking problem. In the proposed method, the covariance of process and measurement noises is estimated adaptively. Thus, the performance of proposed method does not depend on the noise statistics and its performance is robust with unknown prior knowledge of the noise statistics. Morover, it has a consistently improved numerical stability why the matrices of covariance are guaranteed to remain semi- positive. The performance of the proposed method is compared with EKF, and the unscented Kalman filter (UKF) for target tracking problem. Results:To evaluate the proposed method, many experiments is performed. The proposed method is evaluated on the non-maneuvering and maneuvering target tracking. Conclusion: The results show that the proposed method has lower estimation errors with faster convergence rate than other methods. The proposed method can track the tates of moving target effectively and improve the accuracy of the system.
Background and Objectives: The future demands of multimedia and signal processing applications forced the IC designers to utilize efficient high performance techniques in more complex SoCs to achieve higher computing throughput besides energy/power efficiency improvement. In recent technologies, variation effects and leakage power highly affect the design specifications and designers need to consider these parameters in design time. Considering both challenges as well as boosting the computation throughput makes the design more difficult.Methods: In this article, we propose a simple serial core for higher energy/power efficiency and also utilize data level parallel structures to achieve required computation throughput.Results: Using the proposed core we have 35% (75%) energy (power) improvement and also using parallel structure results in 8x higher throughput. The proposed architecture is able to provide 76 MIPS computation throughput by consuming only 2.7 pj per instruction. The outstanding feature of this processor is its resiliency against the variation effects.Conclusion: Simple serial architecture reduces the effect of variations on design paths, furthermore, the effect of process variation on throughput loss and energy dissipation is negligible and almost zero. Proposed processor architecture is proper for energy/power constrained applications such as internet of things (IoT) and mobile devices to enable easy energy harvesting for longer lifetime.
Background and Objectives: Due to the increased sensitive loads, improving power quality in distribution grids by custom power tools is one of the important fields of electrical engineering. This paper proposes a new kind of three-phase three-wire dynamic voltage restorer (without including storage sources or DC link) and also its control method.Methods: The proposed structure includes an AC/AC converter, low-pass filters at the input and output sides, and three-phase injection transformers. The control system is based on the combination of feedback and feedforward control that its advantages are high speed, good response quality, and very simple implementation. To overcome the harmonics raised from AC/AC converter switching on the main line, a SOGI-PLL has been used. Also, SOGI-PLL operates independently on each phase so that the asymmetric voltage variations can be identified.Results: The proposed control method is capable to compensate the power quality problems such as voltage sag, swell, and harmonics in balanced and unbalanced conditions. The detailed modelling and design of the proposed controller are verified through computer simulations and experimental results under different operating conditions. Simulation and experimental results show that the proposed control strategy can compensate the power quality events as close as possible to the desired values under different operation modes.Conclusion: In this paper, a three-phase three-wire dynamic voltage restorer (DVR) was assessed using direct AC/AC converters without a supply source and DC link. A control system based on combined feedback and feedforward control (CFBFFC) and SOGI-PLL has been proposed for the DVR. The simulation results on a three-phase 20kV system as well as the experimental results obtained from a single-phase 220V system verified the performance of the DVR and the control system. It was shown that this structure can compensate for 0.5pu voltage sag, above 1pu voltage swell, and all kinds of harmonic faults.
Background and Objectives: Current and voltage signals' distortion caused by the fault in the power system has negative effects upon the operation of the protective devices. One of the influencing factors is the existence of the exponential DC which can significantly distort the signals and lead to a possible malfunction of the protective devices, especially distance and over-current relays. The main problem is the lack of clarity about this component due to the dependence of its time constant and initial amplitude to the configuration of the electrical grid, location and resistance of faulty point. This makes it hard to extract the main frequency phasors of the voltage and current.Methods: Considering the importance of a fast clearance of the fault, this paper offers a method for an effective and fast removal of the decaying-DC that employs a data window with a length that is equal to the half cycle of the main frequency, while the conventional methods mostly use data from one cycle or even more. The proposed method is based upon the extraction of the decaying-DC component's parameters.Results: The efficiency of this method is compared to the conventional Fourier algorithm of Half-Cycle (HCFA) and the mimic filter plus the HCFA.Conclusion: The outcomes display that the proposed method presents a better efficiency from the point of view of the speed and the accuracy of convergence to the final results.
Background and Objectives: In recent years, linear generators have been broadly utilized to harness wave motion energy. There are various types of linear generators with different magnetic and geometric structures. Among these generators, linear permanent magnet synchronous generator provides a higher energy density than other generators. Due to the simplicity of the structure and the low cost of producing a flat double-sided structure, this type of structure is investigated in this paper.Methods: The purpose of the paper can be divided into two main categories: first, modeling of the flat double-sided linear permanent magnet synchronous generator by using magnetic equivalent circuit (MEC) method and second, deriving the generator electrical equations which are used in analysis and design process.Results: The behavior of the linear permanent magnet synchronous generator is studied and the induced voltages are calculated. The no-load and loaded conditions of the generator with different loads are investigated and the voltage and the current of the load are obtained. Conclusion: In order to confirm the results, finite element method (FEM) is employed. The designed linear generator is simulated by FEM. Comparing the results obtained by MEC and FEM show good agreements between two methods, validating the presented modelling method.
Background and Objectives: Self-supported rear-radiating feeds have been widely used as reflector antenna feeds for mini terrestrial and satellite links. While in most terrestrial and satellite links a dual-polarized antenna for send and receive applications are required, all of the reported works regarding this topic are presenting a single polarized self-supported reflector antenna. In this paper, a dual-polarized hat feed reflector antenna with a low sidelobe and low cross-polarization level is presented. Methods: The proposed antenna consists of an orthogonal mode transducer (OMT), a 60 cm ring focus reflector, and a rear radiating waveguide feed known as the hat feed. 21 parameters of hat feed structure are selected and optimized with a genetic algorithm (GA). A predefined ring focus curve is used as a reflector in the optimization procedure. Dual polarization for send and receive applications is also obtained by an OMT at the rear side of the reflector antenna.Results: A prototype of the proposed hat feed reflector antenna is fabricated and the measurement results are compared with simulation ones. The proposed antenna has return loss better than 15 dB at both polarizations in the 17.7~19.7 GHz frequency range. The 60cm reflector antenna has 40dBi gain which means that the proposed antenna has about 70% radiation efficiency. About 20dB sidelobe level and more than 40 dB cross-polarization have also been realized in the measurement patterns of the proposed antenna. Conclusion: A dual-polarized hat feed reflector antenna with excellent radiation efficiency, high sidelobe, and low cross-polarization level is proposed. The proposed antenna can be a good candidate for high-frequency terrestrial and satellite communications.
Background and Objectives: Text summarization plays an essential role in reducing time and cost in many domains such as medicine, engineering, etc. On the other hand, manual summarization requires much time. So, we need an automated system for summarizing. How to select sentences is critical in summarizing. Summarization techniques that have been introduced in recent years are usually greedy in the choice of sentences, which leads to a decrease in the quality of the summary. In this paper, a non-greedily method for selecting essential sentences from a text is presented.Methods: The present paper presents a method based on a generative adversarial network and attention mechanism called GAN-AM for extractive summarization. Generative adversarial networks have two generator and discriminator networks whose parameters are independent of each other. First, the features of the sentences are extracted by two traditional and embedded methods. We extract 12 traditional features. Some of these features are extracted from sentence words and others from the sentence. In addition, we use the well-known Skip-Gram model for embedding. Then, the features are entered into the generator as a condition, and the generator calculates the probability of each sentence in summary. A discriminator is used to check the generated summary of the generator and to strengthen its performance. We introduce a new loss function for discriminator training that includes generator output, real and fake summaries of each document. During training and testing, each document enters the generator with different noises. It allows the generator to see many combinations of sentences that are suitable for quality summaries.Results: We evaluate our results on CNN/Daily Mail and Medical datasets. Summaries produced by the generator show that our model performs better than other methods compared based on the ROUGE metric. We apply different sizes of noise to the generator to check the effect of noise on our model. The results indicate that the noise-free model has poor results.Conclusion: Unlike recent works, in our method, the generator selects sentences non-greedily. Experimental results show that the generator with noise can produce summaries that are related to the main subject.
Background and Objectives: Stock markets have a key role in the economic situation of the countries. Thus one of the major methods of flourishing the economy can be getting people to invest their money in the stock market. For this purpose, reducing the risk of investment can persuade people to trust the market and invest. Hence, Productive tools for predicting the future of the stock market have an undeniable effect on investors and traders’ profit.Methods: In this research, a two-stage method has been introduced to predict the next week's index value of the market, and the Tehran Stock Exchange Market has been selected as a case study. In the first stage of the proposed method, a novel clustering method has been used to divide the data points of the training dataset into different groups and in the second phase for each cluster’s data, a hybrid regression method (HHO-SVR) has been trained to detect the patterns hidden in each group. For unknown samples, after determining their cluster, the corresponding trained regression model estimates the target value. In the hybrid regression method, HHO is hired to select the best feature subset and also to tune the parameters of SVR.Results: The experimental results show the high accuracy of the proposed method in predicting the market index value of the next week. Also, the comparisons made with other metaheuristics indicate the superiority of HHO over other metaheuristics in solving such a hard and complex optimization problem. Using the historical information of the last 20 days, our method has achieved 99% accuracy in predicting the market index of the next 7 days while PSO, MVO, GSA, IPO, linear regression and fine-tuned SVR has achieved 67%, 98%, 38%, 4%, 5.6% and 98 % accuracy respectively.Conclusion: in this research we have tried to forecast the market index of the next m (from 1 to 7) days using the historical data of the past n (from 10 to 100) days. The experiments showed that increasing the number of days (n), used to create the dataset, will not necessarily improve the performance of the method.
Background and Objectives: The Ant-Miner algorithm works based on Ant Colony Optimization as a tool for data analysis , and is used to explore classified laws from a set of data. In the current study, two new methods have been proposed for the purpose of optimizing this algorithm. The first method adopted logical negation operation on the records of the produced laws, while the second employed a new Pheromone Update strategy called “Generalized exacerbation of quality conflict”. The two proposed methods were executed in Visual studio C#.Net , and 8 public datasets were applied in the test. Each one of these datasets was executed 10 times both in an independent way and combined with others, and the average results were recorded.Methods: In this study, we have proposed two approaches for the earlier method. Using the first method in the construction of rule records, idioms that include the rules can be made in the form of . Compared to the idioms of the early algorithm, these idioms are more compatible while constructing rules with high coverage. The advantage of this generalization is the reduction of the produced rules, which results in greater understandability of the output. During the process of pheromone update in the ordinary ACO algorithms, the amount of the sprayed pheromone is a function of the quality of rules. The objective of the second method is to strengthen the conflict between not-found, weak, good, and superior solutions. This method is a new strategy of pheromone update where ants with high-quality solutions are motivated through increasing the amount of pheromone sprayed on the trail that they have found; conversely, the ants that find weaker solutions are punished through eliminating pheromone from their trails. Results: The optimization of the initial algorithm using the two proposed methods produces a smaller number of rules, but increases the number of construction diagrams and prevents the production of low-quality rules.Conclusion: The results of tests performed on the dataset indicated the enhancement of algorithm efficiency in idioms of fewer tests, increased prediction accuracy of laws, and improved comprehensibility of the produced laws using the proposed methods.
Background and Objectives: Determining effective factors in cloud computing adoption on employees of Noor credit institution in South Khorasan province, Iran, is the purpose of the present study. A practical oriented method is applied regarding the research objective and a descriptive-survey method is used for collecting field data. Employees of Noor credit institution of South Khorasan province (50 people) are selected as the research sample.Methods: Accurate questionnaires are analyzed. Two researcher-made questionnaires are conducted as research tools. These questionnaires consist of effective factors in cloud computing adoption (12 factors including 47 items) and cloud computing adoption intention (3 items). The reliability of the research is evaluated using Cronbach's alpha coefficient which is obtained α=0.54% for the questionnaire of effective factors in cloud computing adoption and has various values for the questionnaire of the cloud computing adoption intention. Also, the descriptive statistics approach is used to define variables, and confirmatory factor analysis and path analysis are applied in the inferential section. Structural equation modeling using Smart-PLS software is used to determine the effective factors in cloud computing adoptionResults: All 12 determined factors in cloud computing adoption are considered as dependent variables and cloud computing adoption intention is considered as an independent variable. 12 effective factors in cloud computing adoption on Noor credit institution of South Khorasan in Iran are determined and examined.Conclusion: It can be concluded that all factors (except the support of the top manager) have a positive and significant effect on cloud computing adoption intention, nonetheless, the value of statistic t for path analysis of the support of the top manager on cloud computing adoption intention is less than 1.96. This shows that the support of the top manager does not have a significant effect on cloud computing adoption intention.
Background and Objectives: The smart energy hub framework encompasses physical assets such as thermal storage, boiler, wind turbine, PV panel, water storage and, water desalination unit to ensure continuity of electricity, water, thermal, and gas provision in the case of unexpected outages in the upstream networks. In this regard, the smart energy hub as an integrated structure provides a suitable platform for energy supply. Considering the drinking water resources in the smart hub structure can cause operational efficiency improvement. Methods: This paper proposes an integrated scheduling model for energy and water supply. To address the issue of increasing operational flexibility, a set of new technologies such as Compressed Air Energy Storage (CAES) and Power-to-Gas (P2G) system are provided. Also, the energy price is modeled as an uncertain parameter using a robust optimization approach. The proposed model is established as a Mixed Integer Linear Function (MILP). The mentioned model is implemented using the CPLEX solver in GAMS software. The proposed model is simulated in different scenarios in the energy hub and the optimization results are compared with each other to validate the proposed method. Results: The results show that using CAES technology and the P2G system can lead to reducing the operating costs to a desirable level. Moreover, the impact of the P2G unit on the operation cost is more than the CAES unit.Conclusion: The energy hub operator should tradeoff between robustness and operation cost of the system. The obtained results ensured that the proposed methodology was robust, optimal, and economical for energy hub schedules.
Background and Objectives: The area of enterprise architecture encompasses various domains, the most complicated of which concerns developing an enterprise business architecture. Although many state-of-the-art enterprise architecture frameworks describe the architecture by abstract levels, they still fail to provide accurate syntactic and semantic descriptions. Several previous conducted studies were looking for different objectives elaborated on modeling enterprise architectures. However, none of those studies tried to develop a modeling that generates test cases which would later be used for validation and/or verification. Therefore, the main contribution of this study is generating a set of test cases based on the descriptions yielded from enterprise business processes in early steps; then, the amount of later reviews and changes can be significantly lessened.Methods: Following the objective of accurate validation and/or verification of the enterprise business processes within an enterprise's architecture development, this paper proposes a new method based on the enterprise architecture design. Throughout the iterative cycle of the proposed method, initially, the enterprise goals will be extracted based on the TOGAF framework. Afterwards, it will be subjected to syntactical modeling based on the Archimate language. Then, semantics will be added to the syntactic model of the enterprise business processes based on the WSMO framework and formalize manually to B language by using defined transition rule. Therefore, in order to discover test cases, a set of test coverage will be tested on the formal model. Results: The proposed method has been implemented in the marketing and sales department of a petrochemical corporation, where the results show the validity and also the effectiveness of the method. Based on the implementation of our method on the selected case study, the details of the business process have been defined based on an enterprise level, the level of abstraction is decreased by syntactic and semantic modeling of enterprise architecture description, the formal descriptions created using the proposed transition rules for sampling.Conclusion: The proposed method starts from the goals of enterprises; therefore, the output samples are efficiently precise. By adding semantics to the syntactic models of enterprise architecture, the degree of abstraction has been decreased. By creating a formal model, the model can be subjected to sampling. For future work, it is suggested to use the proposed method for the automatic generation of codes.
Background and Objectives: Distributed generation (DG) sources are modeled using an ideal DC voltage source connected to the microgrid via voltage source converters (VSCs). Model predictive control presents a distinct method for energy processing.Methods: In this method, the electric power converter is considered a power amplifier with a discrete and nonlinear structure. Therefore, unlike linear control methods, the discrete and nonlinear nature of the converter is considered in this method. In this paper, the distributed model predictive controller was selected from among different methods of load allocation among DG sources due to its more advantages compared to the linear quadratic regulator (LQR) controller.Results: It has been Proposed that we could obtain better results in predictive control, utilizing similarity transform in the state matrix and its modification. In this research, all the simulations have been performed in the MATLABSimpower environment of MATLAB software.Conclusion: Moreover, to demonstrate the superior performance of the model predictive controller compared to the LQR controller, both performance modes of the microgrid, namely the grid-connected and islanding modes, have been considered.
Background and Objectives: The Hemispherical Resonator Gyroscope (HRG) has been a valuable choice for the aerospace industry due to its low noise, good performance, and long lifetime. Its main part consists of a hemispherical shell resonator (HSR). Recently, with the idea of using MEMS technology and using materials such as Pyrex in the construction of HSR, a significant reduction in the size, weight, and power consumption of this gyroscope along with the special gyroscopic characteristics of HRG, Today, the Micro-HRG has been introduced as a sensor in the strategic class.Methods: Micro-HSR can be implemented in three ways: micromachining, blowtorching, and glass blowing. In this paper, after a brief introduction and comparison of possible approaches to make an HSR, the glass blowing method is selected and the sub-processes of this method are introduced and the results of its implementation are presented.Results: The proposed sensor is made by performing the glass blowing method, with a radius of 1.536 mm, a middle base radius of 252 µm, and a shell height of 355 µm. Also, the most important fabrication parameters for achieving the desired geometrical shell were as follows: The appropriate initial thickness of Pyrex is 200 µm and the depth of the cavity under the silicon layer is 532 µm. The bonding process to create a stable connection between Si and Pyrex must be performed at a voltage of 800 V at a temperature of 550 °C for the 30s. And the blowing process with a heating rate of 4 °C/s and a cooling rate of 9.5 °C/s has been evaluated as a suitable thermal profile. By optimally controlling the temperature process in the blowing sub-process, the crystallization phenomenon is prevented, which will lead to the improvement of the HSR quality factor.Conclusion: Achieving the technology of making this hemispherical glass shell in sub-millimeter dimensions, which plays the role of the resonator in an HRG, due to the superior features of this gyroscope such as low noise, good performance, and long lifetime and its application in strategic industries, like navigation and smart weapons, it is of particular importance.
Background and Objectives: Time series classification (TSC) means classifying the data over time and based on their behavior. TSC is one of the main machine learning tasks related to time series. Because the classification accuracy is of particular importance, we have decided to increase it in this research.Methods: In this paper, we proposed a simple method for TSC problems to achieve higher classification accuracy than other existing methods. Fast Fourier transform is a method that uses in raw time series data preprocess. In this study, we apply the fast Fourier transform (FFT) over the raw datasets. Then we use the polar form of a complex number to create a histogram. The proposed method consists of three steps: preprocessing using FFT, feature extraction by histogram computation, and decision making using a random forest classifier.Results: The presented method was tested on 12 datasets of the UCR time series classification archive from different domains. Evaluation of our method was performed using k-fold cross-validation and classification accuracy. The experimental results state that our model has been achieved classification accuracy higher or comparable than related methods. Computational complexity has also been significantly reduced.Conclusion: In the latest years, the TSC problems have been increased. In this work, we proposed a simple method with extracted features from fast Fourier transforms that is efficient to gain more high accuracy.
