Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101666
Seme Sarker, Khadija Akter, Nursadul Mamun
With the advancement of deep learning approaches, the performance of speech emotion recognition (SER) has shown significant improvements. However, system performance degrades substantially when number of emotional states increased. Therefore, this study proposes a text independent SER system that can classify eight emotional states. The proposed system uses joint Mel frequency cepstral coefficient (MFCC) and Log-Mel spectrogram (LMS) to represent the speech signals and a convolutional neural network (CNN) to classify these features in to different emotional states. Results show that the proposed system can achieve an average accuracy of 93%. Two widely used datasets RAVDSESS and TESS have been used in this work to test the model performance. Experimental results present that the proposed framework can achieve significant improvement using a joint feature of MFCC and LMS. Furthermore, the proposed network outperforms state-of-art networks in terms of classification accuracy. This network could be reliably applied to recognize emotion from speech in naturalistic environment.
{"title":"A Text Independent Speech Emotion Recognition Based on Convolutional Neural Network","authors":"Seme Sarker, Khadija Akter, Nursadul Mamun","doi":"10.1109/ECCE57851.2023.10101666","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101666","url":null,"abstract":"With the advancement of deep learning approaches, the performance of speech emotion recognition (SER) has shown significant improvements. However, system performance degrades substantially when number of emotional states increased. Therefore, this study proposes a text independent SER system that can classify eight emotional states. The proposed system uses joint Mel frequency cepstral coefficient (MFCC) and Log-Mel spectrogram (LMS) to represent the speech signals and a convolutional neural network (CNN) to classify these features in to different emotional states. Results show that the proposed system can achieve an average accuracy of 93%. Two widely used datasets RAVDSESS and TESS have been used in this work to test the model performance. Experimental results present that the proposed framework can achieve significant improvement using a joint feature of MFCC and LMS. Furthermore, the proposed network outperforms state-of-art networks in terms of classification accuracy. This network could be reliably applied to recognize emotion from speech in naturalistic environment.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133264505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101596
Tanvir Ibn Touhid, Mahbub Anam, Mohammad Rafiqul Alam, Mahir Foysal, Shibly Shaiham
Near-infrared spectroscopy (NIRS) is a recently developed technique that can reveal hemodynamic and metabolic changes during cortical activation. NIRS has been used during cognitive tasks to study hemodynamic responses such as the change of oxyhemoglobin concentration. In the field of Brain Computer Interfacing (BCI), the use of fNIRS is an efficient approach. In this paper, fNIRS data from mental arithmetic tasks were proposed to classify with the help of the Discrete Wavelet Transform (DWT) based feature extraction method along with different classifiers. Raw data was preprocessed at first and stored in different frames to analyze brain activity. Using both the approximate and detail coefficients of DWT for framed data, features were extracted and used to compare brain activity during the mental arithmetic tasks and rest conditions. Finally, efficiencies of oxyhemoglobin, deoxyhemoglobin, and total hemoglobin data were measured for different channel combinations, and a satisfactory level of 95.54 % accuracy was achieved with the GentleBoost algorithm for the HAAR wavelet.
{"title":"Study on Accuracy Improvement of Mental Arithmetic Task Classification Using Different Classifiers with DWT Feature Extraction Method","authors":"Tanvir Ibn Touhid, Mahbub Anam, Mohammad Rafiqul Alam, Mahir Foysal, Shibly Shaiham","doi":"10.1109/ECCE57851.2023.10101596","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101596","url":null,"abstract":"Near-infrared spectroscopy (NIRS) is a recently developed technique that can reveal hemodynamic and metabolic changes during cortical activation. NIRS has been used during cognitive tasks to study hemodynamic responses such as the change of oxyhemoglobin concentration. In the field of Brain Computer Interfacing (BCI), the use of fNIRS is an efficient approach. In this paper, fNIRS data from mental arithmetic tasks were proposed to classify with the help of the Discrete Wavelet Transform (DWT) based feature extraction method along with different classifiers. Raw data was preprocessed at first and stored in different frames to analyze brain activity. Using both the approximate and detail coefficients of DWT for framed data, features were extracted and used to compare brain activity during the mental arithmetic tasks and rest conditions. Finally, efficiencies of oxyhemoglobin, deoxyhemoglobin, and total hemoglobin data were measured for different channel combinations, and a satisfactory level of 95.54 % accuracy was achieved with the GentleBoost algorithm for the HAAR wavelet.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117184732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101526
Akil Uddin Chowdhury, Md. Sazzad Hossen, M. Zahed
Currently, the world is moving towards data-driven cloud-based services for diverse applications. In such applications, the user is more willing to request space and computational resources from a virtual machine (VM) rather than investing in building more costly and space-consuming physical machines. This ever-increasing demand for VMs introduces a growing need for optimal task allocations. The goal of this study is to develop a model to allocate user requests for tasks into the least possible number of available VMs. The problem is designed as an integer linear programming (ILP) optimization problem. To solve the problem in a practical time span, a heuristic algorithm is also designed. The simulation results show that the heuristic approach achieves a near-optimal solution for task allocation and eventually leads to reduced setup and operational costs for the service providers.
{"title":"An Optimal Technique for Computation-intensive Task Allocation at Virtual Machines","authors":"Akil Uddin Chowdhury, Md. Sazzad Hossen, M. Zahed","doi":"10.1109/ECCE57851.2023.10101526","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101526","url":null,"abstract":"Currently, the world is moving towards data-driven cloud-based services for diverse applications. In such applications, the user is more willing to request space and computational resources from a virtual machine (VM) rather than investing in building more costly and space-consuming physical machines. This ever-increasing demand for VMs introduces a growing need for optimal task allocations. The goal of this study is to develop a model to allocate user requests for tasks into the least possible number of available VMs. The problem is designed as an integer linear programming (ILP) optimization problem. To solve the problem in a practical time span, a heuristic algorithm is also designed. The simulation results show that the heuristic approach achieves a near-optimal solution for task allocation and eventually leads to reduced setup and operational costs for the service providers.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124381485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101569
Niful Islam, Most. Fatema-Tuj-Jahra, Md. Tarek Hasan, D. Farid
Classification in supervised learning is one of the major issues in machine learning and data science. K-Nearest Neighbour (KNN) and Decision Tree (DT) are one of the most widely used classification techniques that are commonly applying for single model and ensemble processes. KNN is known as lazy learner as it doesn't build any decision line from the training data. DT, on the other hand, is a top-down recursive divide-and-conquer technique that used for both classification and regression problems. DT has several advantages e.g, is requires little prior knowledge and non-linear relationship of features don't affect the tree performance. In this paper, we have proposed a new learning algorithm named KNNTree which is a hybrid model of KNN and DT algorithms. The proposed model is basically a decision tree, but leaf nodes are replaced by the KNN classifier. We have tested the proposed method with KNN and DT algorithms on 10 benchmark datasets taken from UC Irvine Machine Learning Repository and found the proposed method outperforms both KNN and DT classifiers.
{"title":"KNNTree: A New Method to Ameliorate K-Nearest Neighbour Classification using Decision Tree","authors":"Niful Islam, Most. Fatema-Tuj-Jahra, Md. Tarek Hasan, D. Farid","doi":"10.1109/ECCE57851.2023.10101569","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101569","url":null,"abstract":"Classification in supervised learning is one of the major issues in machine learning and data science. K-Nearest Neighbour (KNN) and Decision Tree (DT) are one of the most widely used classification techniques that are commonly applying for single model and ensemble processes. KNN is known as lazy learner as it doesn't build any decision line from the training data. DT, on the other hand, is a top-down recursive divide-and-conquer technique that used for both classification and regression problems. DT has several advantages e.g, is requires little prior knowledge and non-linear relationship of features don't affect the tree performance. In this paper, we have proposed a new learning algorithm named KNNTree which is a hybrid model of KNN and DT algorithms. The proposed model is basically a decision tree, but leaf nodes are replaced by the KNN classifier. We have tested the proposed method with KNN and DT algorithms on 10 benchmark datasets taken from UC Irvine Machine Learning Repository and found the proposed method outperforms both KNN and DT classifiers.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124484806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101669
Asif Al Suny, R. B. Sultan, Samina Tohfa, A. J. Haque, M. Chowdhury
Cadmium Telluride (CdTe) thin film solar cells (TFSCs) have recently become one of the most favorable candidates to replace the traditional amorphous Si TFSCs because of its high absorption coefficient, close to ideal band gap energy and low production cost. This computational study investigates ways to enhance the opto-electronic performance levels of CdTe TFSCs by coupling plasmonic silver nanoparticles on the CdTe absorbing substrate. The finite-difference time-domain (FDTD) numerical analysis technique has been used to analyze different performance parameters including short circuit current density (Jsc), open-circuit voltage (Voc), fill-factor, output power, efficiency and others. Furthermore, this study also compares the opto-electronic performance levels of “plasmonic” CdTe TFSCs with “plasmonic” amorphous Si TFSCs. Additionally, investigations of the robustness of “plasmonic” CdTe TFSCs due to temperature variation and the performance of ultrathin CdTe absorber layer (< 250 nm thickness) is also presented. The results of this study show 13.47% increase in efficiency can be achieved for CdTe TFSCs by the use of plasmonic metal nanoparticles. Additionally, the results also strongly suggest that “plasmonic” CdTe TFSC performance levels are relatively stable across large temperature variations and can be up to 21 times more efficient than “plasmonic” Si TFSC for ultra-thin absorber layers.
{"title":"The Use of Plasmonic Metal Nanoparticles to Enhance The Opto-electronic Performance of Thin-Film/Ultrathin Film CdTe Solar Cells","authors":"Asif Al Suny, R. B. Sultan, Samina Tohfa, A. J. Haque, M. Chowdhury","doi":"10.1109/ECCE57851.2023.10101669","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101669","url":null,"abstract":"Cadmium Telluride (CdTe) thin film solar cells (TFSCs) have recently become one of the most favorable candidates to replace the traditional amorphous Si TFSCs because of its high absorption coefficient, close to ideal band gap energy and low production cost. This computational study investigates ways to enhance the opto-electronic performance levels of CdTe TFSCs by coupling plasmonic silver nanoparticles on the CdTe absorbing substrate. The finite-difference time-domain (FDTD) numerical analysis technique has been used to analyze different performance parameters including short circuit current density (Jsc), open-circuit voltage (Voc), fill-factor, output power, efficiency and others. Furthermore, this study also compares the opto-electronic performance levels of “plasmonic” CdTe TFSCs with “plasmonic” amorphous Si TFSCs. Additionally, investigations of the robustness of “plasmonic” CdTe TFSCs due to temperature variation and the performance of ultrathin CdTe absorber layer (< 250 nm thickness) is also presented. The results of this study show 13.47% increase in efficiency can be achieved for CdTe TFSCs by the use of plasmonic metal nanoparticles. Additionally, the results also strongly suggest that “plasmonic” CdTe TFSC performance levels are relatively stable across large temperature variations and can be up to 21 times more efficient than “plasmonic” Si TFSC for ultra-thin absorber layers.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123226581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101546
Taieba Taher, Nursadul Mamun, Md.Azad Hossain
Recently, joint bandwidth expansion and speech enhancement has been a topic of interest in the field of speech processing. The main challenge in this task is to increase the bandwidth of speech signals while enhancing their quality, simultaneously. Deep neural networks (DNNs) have shown great promise in addressing this challenge, as they can learn complex relationships between the input and output signals. In this study, a joint bandwidth expansion and speech enhancement approach using DNNs have been proposed, which is designed to simultaneously increase the bandwidth of speech signals and reduce noise, while preserving speech quality and intelligibility. This approach leverages the capability of DNNs to simultaneously estimate the missing speech components and the noise profile in the degraded speech signal. The estimated speech components and the noise profile are then used to synthesize a full-band speech signal from a noisy signal with limited bandwidth with improved quality. The network employs three different phases such as oracle, imaged, and noisy phase along with the magnitude spectra to recover high band components. The joint approach demonstrates that the DNN-based bandwidth extension and speech enhancement can be effectively combined to produce high-quality speech signals, outperforms traditional speech enhancement methods, and offers promising solutions for various applications, including speech communication, speech recognition, and speech synthesis.
{"title":"A Joint Bandwidth Expansion and Speech Enhancement Approach Using Deep Neural Network","authors":"Taieba Taher, Nursadul Mamun, Md.Azad Hossain","doi":"10.1109/ECCE57851.2023.10101546","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101546","url":null,"abstract":"Recently, joint bandwidth expansion and speech enhancement has been a topic of interest in the field of speech processing. The main challenge in this task is to increase the bandwidth of speech signals while enhancing their quality, simultaneously. Deep neural networks (DNNs) have shown great promise in addressing this challenge, as they can learn complex relationships between the input and output signals. In this study, a joint bandwidth expansion and speech enhancement approach using DNNs have been proposed, which is designed to simultaneously increase the bandwidth of speech signals and reduce noise, while preserving speech quality and intelligibility. This approach leverages the capability of DNNs to simultaneously estimate the missing speech components and the noise profile in the degraded speech signal. The estimated speech components and the noise profile are then used to synthesize a full-band speech signal from a noisy signal with limited bandwidth with improved quality. The network employs three different phases such as oracle, imaged, and noisy phase along with the magnitude spectra to recover high band components. The joint approach demonstrates that the DNN-based bandwidth extension and speech enhancement can be effectively combined to produce high-quality speech signals, outperforms traditional speech enhancement methods, and offers promising solutions for various applications, including speech communication, speech recognition, and speech synthesis.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115282196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101495
Mamady Kebe, Shakeeb Abdullah, R. Amaya, M. Yagoub
This paper presents the architecture, design, and simulation of a new vector-sum phase shifter for prospected use in applications that require low amplitude loss. The architecture is based on non-quadrature phase generation and synthesis. The phase generation is done by splitting the input signal into two equal-phase output vectors and delaying one signal vector to the other; while the phase synthesis is implemented by subjecting the vectors through path selection and variable amplification & attenuation before subtracting the different paths. A two-bit phase path selection was employed for achieving 360° of coarse & fine tuning. EM simulations of the phase shifter architecture was carried out using RT-Duroid 5880 specifications $(varepsilon_{r}=2.2,boldsymbol{tandelta=0.004)}$ at center frequency of 10 GHz. A maximum phase error of $mathbf{1.82^{circ}}$ was obtained for the entire interval of 360 degrees of phase shift. With less than $2^{mathrm{o}}$ of phase error, the proposed phase shifter architecture is feasible for millimeter-wave phase array beamforming applications; as it offers the possibility of lower power consumption with the use of lesser compartmental blocks (i.e. compared to a T-bridge phase shifter which uses a chain of multiple blocks that can lead to excessive losses of more than 30 dB).
{"title":"Architecture and Design of a New Non-Quadrature Vector-Sum Microwave Phase Shifter at 10 GHz With Maximum Residual Phase Error of 1.80°","authors":"Mamady Kebe, Shakeeb Abdullah, R. Amaya, M. Yagoub","doi":"10.1109/ECCE57851.2023.10101495","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101495","url":null,"abstract":"This paper presents the architecture, design, and simulation of a new vector-sum phase shifter for prospected use in applications that require low amplitude loss. The architecture is based on non-quadrature phase generation and synthesis. The phase generation is done by splitting the input signal into two equal-phase output vectors and delaying one signal vector to the other; while the phase synthesis is implemented by subjecting the vectors through path selection and variable amplification & attenuation before subtracting the different paths. A two-bit phase path selection was employed for achieving 360° of coarse & fine tuning. EM simulations of the phase shifter architecture was carried out using RT-Duroid 5880 specifications $(varepsilon_{r}=2.2,boldsymbol{tandelta=0.004)}$ at center frequency of 10 GHz. A maximum phase error of $mathbf{1.82^{circ}}$ was obtained for the entire interval of 360 degrees of phase shift. With less than $2^{mathrm{o}}$ of phase error, the proposed phase shifter architecture is feasible for millimeter-wave phase array beamforming applications; as it offers the possibility of lower power consumption with the use of lesser compartmental blocks (i.e. compared to a T-bridge phase shifter which uses a chain of multiple blocks that can lead to excessive losses of more than 30 dB).","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121586143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101637
M. Shiblee, M. Rahman, Hasan Monir, Md. Ahsan Kabir
In this paper, a net-metering-based rooftop solar PV system for a residential building in Mirpur DOHS, Dhaka is designed. The results show that a rooftop PV system with net metering for residential load has a very high energy output and yield. The economic analysis shows that the system has a low Levelized cost of energy (LCOE), and a positive Net Present Value (NPV), making such a system financially and technically very attractive. The total net metering-based PV generation potential of the DOHS community area has also been studied. The study concluded that the rooftop PV net-metering system for residential load is feasible and can be incorporated into the current net-metering guideline of Bangladesh.
{"title":"Exploratory Perspective of PV Net-Energy-Metering for Residential Prosumers: A Case Study in Dhaka, Bangladesh","authors":"M. Shiblee, M. Rahman, Hasan Monir, Md. Ahsan Kabir","doi":"10.1109/ECCE57851.2023.10101637","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101637","url":null,"abstract":"In this paper, a net-metering-based rooftop solar PV system for a residential building in Mirpur DOHS, Dhaka is designed. The results show that a rooftop PV system with net metering for residential load has a very high energy output and yield. The economic analysis shows that the system has a low Levelized cost of energy (LCOE), and a positive Net Present Value (NPV), making such a system financially and technically very attractive. The total net metering-based PV generation potential of the DOHS community area has also been studied. The study concluded that the rooftop PV net-metering system for residential load is feasible and can be incorporated into the current net-metering guideline of Bangladesh.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"193 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113991393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101655
Nagib Mahfuz, P. C. Shill
Class is one of the fundamental concepts of the object-oriented paradigm and has been scrutinized since the developers moved on from procedural programming design. In software fault prediction, the legalization of software metrics is essential. As a handful of software metrics suites exist, it is a very hard task to predict the defective classes flawlessly using a particular set of metrics suites. However, it is a rational approach to use only the object-oriented metrics that are directly relatable to the class definitions in the code that helps the developers foresee the errors in defining the classes and minimize the errors as much as possible. This paper utilized twelve object-oriented metrics selected from various metrics suites. The dagging ensemble model is merged with three well-known classification algorithms (Naive Bayes, Multilayer Perceptron, J48 Decision Tree) individually and applied to twelve java projects. The study depicts that the proposed ensemble method gives improved outcomes that are statistically significant when merged with Naive Bayes and Multilayer Perceptron. The proposed ensemble method shows improvements up to 12.5% in accuracy and 15% in F-Score.
{"title":"Faulty Classes Prediction in Object-Oriented Programming Using Composed Dagging Technique","authors":"Nagib Mahfuz, P. C. Shill","doi":"10.1109/ECCE57851.2023.10101655","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101655","url":null,"abstract":"Class is one of the fundamental concepts of the object-oriented paradigm and has been scrutinized since the developers moved on from procedural programming design. In software fault prediction, the legalization of software metrics is essential. As a handful of software metrics suites exist, it is a very hard task to predict the defective classes flawlessly using a particular set of metrics suites. However, it is a rational approach to use only the object-oriented metrics that are directly relatable to the class definitions in the code that helps the developers foresee the errors in defining the classes and minimize the errors as much as possible. This paper utilized twelve object-oriented metrics selected from various metrics suites. The dagging ensemble model is merged with three well-known classification algorithms (Naive Bayes, Multilayer Perceptron, J48 Decision Tree) individually and applied to twelve java projects. The study depicts that the proposed ensemble method gives improved outcomes that are statistically significant when merged with Naive Bayes and Multilayer Perceptron. The proposed ensemble method shows improvements up to 12.5% in accuracy and 15% in F-Score.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116934518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101593
M. Alam, Mohd Herwan Bin Sulaiman, M. Sayem, Shahriar Imtiaz, M. M. A. Ringku, R. Khan
The optimal power flow (OPF) the most crucial instrument for power facility design and performance is analysis, load scheduling, and cost-effective dispatch. To determine the evidence of a steady state for a power system network, an optimal power flow analysis is required. This study introduces a novel optimization method called Superiority of Feasible Solutions-Moth Flame Optimization (SH-MFO) to answer the optimal power flow problem. As part of the MATLAB development, SH-MFO is implemented on the IEEE-30 bus standard experiment structure network. When compared to the reliable outcomes produced by other algorithms, the current study employing SH-MFO estimates a Generation and Emission Costs $ 48.6827 $/h for minimizing the different fuels, which ultimately proves to be the best value. Analyze the poorest options suggested by the comparison algorithm, it saves money by 0.9873 % per hour. Based on simulation results, the SH-MFO method provides an improved and effective optimization algorithm for optimal power flow problems.
{"title":"Emission and Valve Point Loading Cost Using Superiority of Feasible Solutions-Moth Flame Optimization","authors":"M. Alam, Mohd Herwan Bin Sulaiman, M. Sayem, Shahriar Imtiaz, M. M. A. Ringku, R. Khan","doi":"10.1109/ECCE57851.2023.10101593","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101593","url":null,"abstract":"The optimal power flow (OPF) the most crucial instrument for power facility design and performance is analysis, load scheduling, and cost-effective dispatch. To determine the evidence of a steady state for a power system network, an optimal power flow analysis is required. This study introduces a novel optimization method called Superiority of Feasible Solutions-Moth Flame Optimization (SH-MFO) to answer the optimal power flow problem. As part of the MATLAB development, SH-MFO is implemented on the IEEE-30 bus standard experiment structure network. When compared to the reliable outcomes produced by other algorithms, the current study employing SH-MFO estimates a Generation and Emission Costs $ 48.6827 $/h for minimizing the different fuels, which ultimately proves to be the best value. Analyze the poorest options suggested by the comparison algorithm, it saves money by 0.9873 % per hour. Based on simulation results, the SH-MFO method provides an improved and effective optimization algorithm for optimal power flow problems.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115723843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：