Muhammad Bilal, Lukumon O. Oyedele, Junaid Qadir et al.
Hasil untuk "Electrical engineering. Electronics. Nuclear engineering"
Menampilkan 20 dari ~8860808 hasil · dari DOAJ, CrossRef, Semantic Scholar
Jeetendra Kumar, Rashmi Gupta, Suvarna Sharma et al.
Presents corrections to the paper, (Corrections to “IoT-Enabled Advanced Water Quality Monitoring System for Pond Management and Environmental Conservation”).
Mathieu Calvat, Chris Bean, Dhruv Anjaria et al.
Abstract To leverage advancements in machine learning for metallic materials design and property prediction, it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of current physics-based discrete microstructure descriptors. This need is particularly relevant for metallic materials processed through additive manufacturing, which exhibit complex hierarchical microstructures that cannot be adequately described using the conventional metrics typically applied to wrought materials. Furthermore, capturing the spatial heterogeneity of microstructures at the different scales is necessary within such framework to accurately predict their properties. To address these challenges, we propose the physical spatial mapping of metal diffraction latent space features. This approach integrates (i) point diffraction data encoding via variational autoencoders or contrastive learning and (ii) the physical mapping of the encoded values. Together, these steps offer a method to comprehensively describe metal microstructures. We demonstrate this approach on a wrought and additively manufactured alloy, showing that it effectively encodes microstructural information and enables direct identification of microstructural heterogeneity not directly possible by physics-based models. This data-reduced microstructure representation opens the application of machine learning models in accelerating metallic material design and accurately predicting their properties.
Mohammad Ebrahim Hajiabadi, Mahdi Samadi, Mohammad Hassan Nikkhah et al.
Abstract One of the primary challenges faced by generation companies (GenCos), which operate multiple generation units within the electricity market, is the determination of the optimal bid price for these units to maximize profit. This paper proposes a novel approach to ascertain the optimal bid price direction for GenCos by leveraging the gradient vector of the profit function within the constraints of the electricity market. First, the Jacobian matrix of unit profits is computed using the electricity market structural decomposition method. This matrix highlights how the profit of generation units is affected by market input parameters, including the bid prices of the units. Then, the gradient vector of the GenCos' profit function and the optimal bid price direction are derived from the Jacobian matrix. The methodology is applied to a 24‐bus IEEE network, with results validated against those from a simulation method to confirm the efficacy of the proposed approach. The simulation results show that the highest and lowest profit changes with a step increase of 0.1$/MWh are observed for GenCo 4 and GenCo 6 with values of 60.28 and 2.20 $/h, respectively. The proposed approach can be effective in the changes of bid direction of the units of a GenCo to achieve the highest possible profit.
Lihui ZHANG, Shuo XIE, Mingfa LUO et al.
Objectives: Bone tissue grinding is one of the common and basic applications in orthopedic surgery clinics. The grinding process is energy-intensive and generates a lot of grinding heat. The accumulation of this heat may cause thermal damage to biological tissues. This paper presents experimental research to investigate the bone-grinding heat and the cooling method. Methods: The combined influence of nozzle position and feed direction on the cooling effect of bone grinding under cryogenic spray cooling conditions is experimentally investigated. A bone grinding platform with three-dimensional motion, as well as a cryogenic spray generation device, is designed and constructed. A spherical diamond grinding head with a diameter of 4 mm and a grit size of #150 is utilized. Fresh bovine cortical bone is used as the processing sample. The temperature at the nozzle outlet is 13 ℃, and the flow rate valve regulates the coolant flow rate to 400 mL/h. A three-dimensional force transducer (DJSW-40, China) is connected to a data acquisition system, which captures the forces applied to the bone sample along the X, Y, and Z directions at a frequency of 100 Hz. Simultaneously, a 0.1 mm diameter type K thermocouple (Omega Inc., TT-K-36) is embedded inside the bone sample to measure the grinding temperature in real-time. Three different nozzle arrangements were designed: above, in front of, and to the side of the abrasive tool, with the nozzles 10 mm away from the spray surface. Six sets of experiments (3×2) were designed using three nozzle orientations and two feeding directions. Each set of experiments was repeated three times to study the cooling effect of the spray under the combined influence of nozzle orientation and feed direction. Results: (1) During bone grinding, the abrasive tool is subjected to three orthogonal directional forces, namely FX (the tangential grinding force used for removing material), FY (the axial grinding force, representing the resistance of the abrasive tool during its feed), and FZ (the normal grinding force, which serves as the support force of the workpiece on the abrasive tool). For forward feed, the average values of the individual forces are: FX = 0.37 N, FY = -0.72 N, FZ = 1.38 N. For backward feed, FX = 0.46 N, FY = 0.78 N, FZ = 1.67 N. Since the grinding tool remains in the same rotational direction, the tangential force FX is consistently positive. For forward/backward feed, the axial force FY is in the -Y and +Y directions respectively, thus the sign of the FY value changes. When feeding forward/backward, the tangential force (FX) is 0.37 N and 0.46 N, respectively, which are relatively similar to each other, in accordance with the grinding theory. The power consumed for grinding is approximately 1.6 W and 1.9 W for forward and backward feed, respectively. (2) The nerve tissue is more heat-sensitive than bone tissue. Taking the human body's 37 ℃ as the base temperature, the threshold for the occurrence of thermal injury is 43 ℃, so the temperature rise threshold for thermal injury of nerve tissue is 6 ℃. In our experiment, the maximum temperature rise of bone under low-temperature spray cooling was lower than 4 ℃, indicating that the cooling method is effective. The effect of the nozzle arrangement was investigated under a fixed forward or backward feeding direction. When the abrasive tool is fed forward, the cooling of the thermocouple under the front nozzle is obvious. This is because, in addition to the contact arc area between the abrasive tool and the bone sample, a portion of the coolant from the front nozzle is sprayed onto the bone sample surface, resulting in a pre-cooling effect within the bone. When the abrasive tool is fed backward, the grinding temperature is lowest when the nozzle is placed above. For the different nozzle orientations, the side nozzles are in a perpendicular plane to the feed direction (Y-direction) of the grinding tool, so the feed direction has the least influence on the grinding temperature. The upper and front nozzles are in the same plane as the feed direction of the abrasive tool, so the influence of the feed direction is more significant. Conclusions: (1) The average tangential grinding force is 0.42 N, axial grinding force is 0.75 N, normal grinding force is 1.53 N, and the average power consumed by grinding is approximately 1.75 W when bone grinding is performed at a depth of 0.5 mm using a spherical diamond abrasive tool with a diameter of 4 mm. (2) Under the cooling effect of the cryogenic spray, the maximum temperature rise of grinding is less than 4 ℃, which can effectively prevent the occurrence of thermal damage in biological tissues. The temperatures of the two thermocouples in the same set of experiments were more consistent when the nozzle was placed above or side, while there was a significant difference in the temperatures of the two thermocouples when the nozzle was placed in front. This indicates that the cooling effect is more uniform when the nozzle is placed above and to the side. (3) The coupling of the nozzle arrangement and the feeding mode has a greater impact on the grinding temperature. When the nozzle is placed on top, it is favorable to backward feeding; when the nozzle is placed in front, it is conducive to forward feeding; and when the nozzle is placed on the side, there is no significant difference in the temperature between forward and backward feeding.
Zhang Donghai, Pan Mingxu, Li Xu, Xu Yong, Xiong Hao
The new process of EAF→VOD→LF+VD→ pouring 6 t electrode rod → vacuum consumable remelting (VAR) with lower smelting cost was adopted to produce 15-5PH stainless steel instead of the traditional VIM+VAR process, the causes of point defects were analyzed by scanning electron microscopy and ASPEX detection methods. The results show that calcium aluminate and aluminum spinite exist in the self-consuming electrode, the instability of vacuum consumable remelting process will draw the ingot crown and non-metallic float into the melting pool and remain in the consumable ingot, resulting in point defects after forging.Through process optimization and improvement, the VOD reduction slag is adjusted from 9 kg/t aluminum to 8 kg/t ferrosilicon and 5 kg/t aluminum, the composition of refining slag is adjusted from (mass fraction)CaO 50%-55%, SiO2 10%-15%, Al2O3 20%-25% to CaO 45%-50%, SiO2 5%-10%, Al2O3 33%-38%, vacuum consumable remelting speed is increased from 4.2 kg/min to 6 kg/min, and the melting drop time is increased from 0.23 s to 0.27 s, the cleanliness of consumable electrode has been greatly improved, the melting speed has been controlled steadily, the non-metal floating matter on the liquid surface of the molten pool has been removed, low and high magnification inspection of the finished material have met the standard requirements, and the inspection pass rate has been increased to more than 98%.
Zihan CUI, Bing HAN, Pengcheng WU et al.
Objectives: Femtosecond laser technology has become the primary method for micropore processing due to its high precision and low energy consumption. However, during the process, it is easy to cause microcracks and burrs in the micropores. Additionally, due to the small size, low structural stability and weak wear resistance of the micropores, conventional methods are ineffective in polishing them. To address the challenge of polishing femtosecond laser-processed micropores, the abrasive water jet polishing method is employed. This method leverages the stable removal function and strong adaptability of the abrasive water jet to improve the quality of femtosecond laser-processed micropores. Methods: Computational fluid dynamics (CFD) simulations of the abrasive water jet micropore polishing process under different process parameters were carried out by using Fluent software. A finite element model of abrasive water jet polishing for femtosecond laser-processed micropores was established under various working conditions. The flow field distribution, the erosion rate and the wall shear force under different parameters were analyzed. Corresponding experiments were conducted for each variable discussed in the Fluent simulation, and the variation patterns of micropore inner wall roughness were summarized. Subsequently, optimization experiments were conducted on the three factors, namely jet target distance, jet pressure and abrasive particle size, using the response surface method. The mean square error of shear force on the inner wall of the hole was taken as the response value Y, and the response surface equation was established. The optimal polishing parameter combination was obtained through the response surface equation and experimentally verified. Results: A jet impact angle of 90° is suitable for polishing the inner wall of the micropore, as wall erosion is uniform and the shear force distribution is concentrated at this angle. At a target distance of 4.2 to 6.0 mm, the jet on the end face enters the deceleration stage, and the jet velocity decreases as the target distance increases. The shear force increases with increasing jet pressure. When the jet pressure is 0.80 MPa, the shear force is the smallest, concentrated in the range of 1 500 to 3 500 Pa. At a jet pressure of 1.50 MPa, the shear force is the largest, concentrated in the range of 3 500 to 5 500 Pa. When jet pressure increases from 0.80 to 1.50 MPa, the shear force on the inner wall of the hole increases more than twice. The effects of abrasive particle size and jet pressure on wall shear force are similar. When the abrasive particle size is 1.0 μm, the shear force is the smallest, concentrated in the range of 1 000 to 2 500 Pa. At an abrasive particle size of 30.0 μm, the shear force reaches its maximum, concentrated between 3 000 and 5 500 Pa. Corresponding tests are carried out for each variable discussed in the simulation, and the minimum roughness Ra of the inner wall of the micropore was 0.386 μm. The optimal process parameter combination obtained through response surface analysis is as follows: jet impact angle of 90°, jet target distance of 3.5 mm, jet pressure of 1.10 MPa, and abrasive particle size of 15.0 μm. Under the optimal parameter combination, with an abrasive mass fraction of 5% and a polishing time of 5.0 minutes, the surface roughness Ra of the polished micropore inner wall surface was reduced to 0.354 µm, which is better than the minimum roughness of 0.386 µm observed in the simulation. Polishing efficiency is improved by about 3%, and the quality of the micropore inner wall surface is further enhanced. Conclusions: When the impact angle is constant, the shear force on the inner wall of the hole increases with increasing jet pressure and abrasive particle size. It increases first and then decreases with the increase in jet target distance, with jet pressure having the greatest influence on the wall shear force. Different structural segments of the jet can be applied to different working conditions due to different properties. Additionally, the simulation and experimental results are in good agreement, and the improvement in roughness is significant. This indicates that abrasive water jet polishing significantly enhances the quality of micropore walls, and the data model for response surface prediction has high accuracy.
Hao Cui, Yu-Yue Zhao, Qiong Wu et al.
The clinical application of cancer immunotherapy is unsatisfied due to low response rates and systemic immune-related adverse events. Microwave hyperthermia can be used as a synergistic immunotherapy to amplify the antitumor effect. Herein, we designed a Gd-based metal-organic framework (Gd-MOF) nanosystem for MRI-guided thermotherapy and synergistic immunotherapy, which featured high performance in drug loading and tumor tissue penetration. The PD-1 inhibitor (aPD-1) was initially loaded in the porous Gd-MOF (Gd/M) nanosystem. Then, the phase change material (PCM) and the cancer cell membrane were further sequentially modified on the surface of Gd/MP to obtain Gd-MOF@aPD-1@CM (Gd/MPC). When entering the tumor microenvironment (TME), Gd/MPC induces immunogenic death of tumor cells through microwave thermal responsiveness, improves tumor suppressive immune microenvironment and further enhances anti-tumor ability of T cells by releasing aPD-1. Meanwhile, Gd/MPC can be used for contrast-enhanced MRI. Transcriptomics data revealed that the downregulation of MSK2 in cancer cells leads to the downregulation of c-fos and c-jun, and ultimately leads to the apoptosis of cancer cells after treatment. In general, Gd/MPC nanosystem not only solves the problem of system side effect, but also achieves the controlled drug release via PCM, providing a promising theranostic nanoplatform for development of cancer combination immunotherapy.
K. Niendorf, B. Raeymaekers
The ability to fabricate polymer matrix composite materials with continuous or discontinuous filler material, oriented in a user‐specified direction, enables implementing designer material properties, such as anisotropic mechanical, thermal, and electrical properties. Conventional fabrication methods rely on a mold, which limits specimen geometry and is difficult to implement. In contrast, additive manufacturing, including fused filament fabrication or fused deposition modeling, direct ink writing, or stereolithography, combined with a method to align filler material such as a mechanical force or an electric, magnetic, shear force, or ultrasound wave field, enables 3D printing polymer matrix composite material specimens with complex geometry and aligned filler material, without the need for a mold. Herein, we review the combinations of fabrication and filler material alignment methods used to fabricate polymer matrix composite materials, in terms of operating and design parameters including size, resolution, print speed, filler material alignment time, polymer matrix and filler material requirements, and filler manipulation requirements. The operating envelope of each fabrication method is described and their advantages, disadvantages, and limitations are discussed. Finally, different combinations of 3D printing and filler material alignment methods in the context of important engineering applications, such as structural materials, flexible electronics, and shape‐changing materials, are illustrated.
A. Hanif, Donghyeon Yoo, Dohui Kim et al.
Alfredo Velazquez Iba˜nez, Juan Rodriguez, M. Paternina et al.
Power Hardware in the Loop (P-HIL) systems and Battery Energy Storage Systems (BESS) are essential tools in the transition to a more sustainable and efficient energy matrix. These systems work together to analyze the integration of intermittent renewable energy sources to improve the stability and reliability of electrical grids. This, in turn, contributes to the reduction of greenhouse gas emissions and the development of a low-carbon economy. This paper presents an experimental working platform and real-time simulation based on P-HIL technology and scaled power electronics prototypes. The platform allows the analysis of the interaction of BESS devices in electrical distribution grids. A case study is presented to demonstrate the combination of two main qualities of a BESS: improving voltage stability and reducing peak demand. To this end, an experimental 1 kW BESS consisting of a Dual Active Bridge (DAB) and a Voltage Source Converter (VSC) is connected to a 13-bus IEEE distribution network. The attained results demonstrate the ability of the platform to bridge two areas of electrical engineering and highlight its significant advantages.
Alexander S. Novikov, Evgeniy A. Sudarev, A. Mostovshchikov
Relevance. The need to develop new methods for metal waste disposal. This direction, with the participation of various intensifying influences, refers to resource-saving, technological, minimizing the volume of capital costs for raw materials, production and subsequent sale. Aim. To obtain copper ferrite from iron and copper waste of microelectronics. Copper ferrite is a useful and highly demanded product in this branch of domestic industry, especially now, when many sanctions have been imposed on our country, including in terms of microelectronics. To study its magnetic properties and draw a conclusion about the possibility of its application. Objects. Samples of iron and copper waste in the form of plates, wire and shavings. Methods. Volumetric analysis, electron microscopy, X-ray phase analysis, study of magnetic susceptibility. Results. The authors have produced finely dispersed iron (III) oxide from iron-containing microelectronics waste. This oxide is used in electrical engineering as part of high-voltage resistors for grounding the neutral of networks, lithium-ion batteries, as a carrier of analog and digital information. In the radio engineering industry it is used as part of low-voltage resistors, high-frequency chokes, small-sized pulse transformers. The authors produced finely dispersed copper (II) oxide from copper-containing waste. This oxide is used in production of phosphors and dry batteries – in batteries with liquid cells as a cathode, with lithium as an anode and dioxalane mixed with lithium perchlorate as an electrolyte. In addition, it finds application as a p-type semiconductor, since it has a narrow bandgap of 1.2 eV, and manufacturing photovoltaic cells in solar panels. Copper ferrite was synthesized from the obtained oxides by sintering. Rings made of such alloy serve as a core in transformers. The part increases the magnetic field strength by several thousand times, making the devices transmit more power than they could with a non-ferrite core. Ferrite ring cores are found not only in transformers, but also in other electronics (e.g. magnetic memory).
O. Pishchukhina
The Covid-19 pandemic brought dramatic changes to higher education settings, particularly for curriculum delivery, moving quickly to online learning in March 2020, which for many was the first experience of teaching and learning in the virtual environment.This paper discusses the experience of redesigning the MSc Computing Foundations module and adapting it to a distance learning model using both synchronous and asynchronous delivery at the School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast in response to the challenges brought to higher education by the pandemic. The module is a fundamental compulsory module with an intake of 100+ students in the part-time class studying the conversional MSc course in Software Development.This paper focuses on the challenges and opportunities faced by large class students during this unprecedented move online, and changes made to the curriculum to facilitate the move to online teaching and learning using the conceptual framework for effective online courses. The paper reflects on student feedback to online educational activities including synchronous and asynchronous content delivery, discussion forums, ungraded formative quizzes, formative and summative assessments delivered online for a postgraduate cohort studying part-time. Sustained level of student engagement was evidenced through statistics collected from the virtual learning environment.This paper further discusses how the above has transformed teaching of the Computing Foundations module for the large cohort, focusing on the student experience only, and reflecting on how these online teaching practices contribute to provision of education with a view what developments became a success and could be turn to advantage and what was not effective and should be eliminated post-pandemic. Adaptation of the Computing Foundation module to the new model of online delivery has been successful in the 2020-2021 academic year, and the module has become a distance module delivered fully online in the 2021-2022 academic year. The transformation has helped to cope with a "new normal" in an increasingly hybrid higher education ecosystem as students’ and educators’ involvement into learning activities continued to be altered in the post-pandemic society.
Mai Nguyen Thi Bich, Ngoc Thien Le
The practice course about electric motor controlling is essential in establishing undergraduate students’ skills in many electronics and electrical engineering majors. However, due to the current COVID-19 situation, teaching this practical subject has become unlearnable in the laboratory room. Therefore, the urgent requirement is to find a solution to virtualize many electrical-motor control lessons for online learning during the distant social period. In this paper, we propose a potential solution to online practical electrical motor control coursework based on Proteus software. Unlike the common Matlab Simulink approach, the Proteus has the advantage of digitizing both the Arduino device and the electric circuits. We demonstrate the usefulness of Proteus 8.2 software by implementing a circuit to control a 3-phase asynchronous motor using the pulse width control method, named sine PWM. Through the learning on Proteus software, students not only review the theoretical knowledge of electrical motors but also learn how to apply the theory through simulating virtualized Arduino devices and building a control circuit with the control block to control the motor in real-time. Furthermore, Proteus also supports printing out the control circuit board for the user. Proteus is, therefore, a suitable solution for online teaching of practice subjects for related majors.
W. Munim, H. Che, M. Tousizadeh et al.
Due to the COVID-19 pandemic, traditional laboratory sessions or face-to-face demonstrations for advanced electrical engineering level students in the field of power electronics and drives had to be substituted by e-learning to accommodate the new virtual teaching environment. This paper explains the operation of a symmetrical six-phase induction drive having two isolated neutrals configuration (2N) under one open phase fault (OPF) as a case study. The whole system, including the OPF, has been modeled in MATLAB Simulink which is intended for teaching and research purposes in the field of power electronics and drives. The aim of this paper is to elaborate the pre- and post-fault behaviour of the stator current, speed and torque. The machine model presented here is based on vector space decomposition (VSD) and controller using Indirect Rotor Field Oriented Control (IRFOC). In addition, this paper explains the external resistance used to initiate the OPF. The described MATLAB simulation helps the students to understand and observed the amplitude of stator current during pre- and post-fault conditions with respect to the mechanical loading. This model allows preliminary analysis for monitoring and comparison of machine performance.
Ahmad Nikoobakht, J. Aghaei, M. Shafie‐khah et al.
aDepartment of Electrical Engineering, Higher Education Center of Eghlid, Eghlid, Iran-(a.nikoobakht@eghlid.ac.ir). bSchool of Energy Systems, Lappeenranta-Lahti University of Technology (LUT), Lappeenranta, Finland Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering, Shiraz University of Technology, Shiraz, Iran. cSchool of Technology and Innovations, University of Vaasa, Vaasa, Finland. dFaculty of Engineering of University of Porto and INESC TEC, 4200-465 Porto, Portugal (e-mail: catalao@fe.up.pt).
Huaxia Zhan, Haimeng Wu, M. Muhammad et al.
Haimeng Wu Department of Mathematics, Physics & Electrical Engineering Ellison Building, Northumbria University, Newcastle upon Tyne, NE1 8ST, United Kingdom. Email: Haimeng.wu@northumbria.ac.uk Abstract Electric vehicles (EVs) require an onboard battery charger unit and a battery management system (BMS) unit that balances the voltage levels for each battery cell. So far, both units are two completely autarkic power electronics systems. The circuit presented here operates as a battery charger when the EV is connected to the grid and as a voltage balancer when the EV is driving. Thus, the proposed circuit utilises two functions in one and therefore eliminates the need of having two autarkic units reducing complexity and reduction in component count. The proposed circuit operates as a flyback converter and achieves power factor correction during battery charging. The constant‐current constant‐ voltage (CC–CV) charging method is employed to charge the batteries. However, to limit the number of sensors that will be employed as a result of varying cells during charging, the battery current is estimated using a single current transducer and embedding a converter model in the controller. The operation of the circuit is presented in detail and is supported by simulation results. A laboratory prototype is built to verify the effectiveness of the proposed topology. Experiment results show that the proposed method provides an integrated solution of on‐board charging and voltage equalisation.
Da Tao, Zhaopeng Liu, Xiaofeng Diao et al.
Demographics, personality traits and attitudes are related to safety behaviors in varied workplaces, but their roles in nuclear power plants (NPPs) have not been fully understood. This study was conducted to explore the roles of a set of demographic, personality and attitudinal factors on self-reported safety behaviors (including safety participation and human errors) among NPP commissioning workers. Survey data were collected from 157 Chinese commissioning workers. Results showed that age and work experience were significantly associated with human errors, but not with safety participation. Neuroticism and conscientiousness were significantly related to human errors, while neuroticism, conscientiousness and agreeableness were significantly related to safety participation. Attitude towards questioning was observed as an antecedent of safety participation, and functioned as a mediating variable in the relation between conscientiousness and safety behaviors. The findings provide evidence-based implications on the design of diverse interventions and strategies for the promotion of safety behaviors in NPPs.
Zhaoxin Wang, Huaping Liu, Xinying Xu et al.
Abstract Material recognition plays an important role in the interaction between robots and the external environment. For example, household service robots need to replace humans in the home environment to complete housework, so they need to interact with daily necessities and obtain their material performance. Images provide rich visual information about objects; however, it is often difficult to apply when objects are not visually distinct. In addition, tactile signals can be used to capture multiple characteristics of objects, such as texture, roughness, softness, and friction, which provides another crucial way for perception. How to effectively integrate multi‐modal information is an urgent problem to be addressed. Therefore, a multi‐modal material recognition framework CFBRL‐KCCA for target recognition tasks is proposed in the paper. The preliminary features of each model are extracted by cascading broad learning, which is combined with the kernel canonical correlation learning, considering the differences among different models of heterogeneous data. Finally, the open dataset of household objects is evaluated. The results demonstrate that the proposed fusion algorithm provides an effective strategy for material recognition.
Shaikh Shakeela, N. Sai Shankar, P Mohan Reddy et al.
Cyber-attacks are increasing day by day. The generation of data by the population of the world is immensely escalated. The advancements in technology, are intern leading to more chances of vulnerabilities to individual’s personal data. Across the world it became a very big challenge to bring down the threats to data security. These threats are not only targeting the user data and also destroying the whole network infrastructure in the local or global level, the attacks could be hardware or software. Central objective of this paper is to design an intrusion detection system using ensemble learning specifically Decision Trees with distinctive feature selection univariate ANOVA-F test. Decision Trees has been the most popular among ensemble learning methods and it also outperforms among the other classification algorithm in various aspects. With the essence of different feature selection techniques, the performance found to be increased more, and the detection outcome will be less prone to false classification. Analysis of Variance (ANOVA) with F-statistics computations could be a reasonable criterion to choose distinctives features in the given network traffic data. The mentioned technique is applied and tested on NSL KDD network dataset. Various performance measures like accuracy, precision, F-score and Cross Validation curve have drawn to justify the ability of the method.
Halaman 30 dari 443041