Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 35
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The Convolutional Neural Network (CNN) model is one of the most effective models for load forecasting with hyperparameters which can be used not only to determine the CNN structure and but also to train the CNN model. This paper proposes a framework for Grid Search hyperparameters of the CNN model. In a training process, the optimal models will specify conditions that satisfy requirement for minimum of accuracy scores of Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). In the testing process, these optimal models will be used to evaluate the results along with all other ones. The results indicated that the optimal models have accuracy scores near the minimum values. Load demand data of Queensland (Australia) and Ho Chi Minh City (Vietnam) were utilized to verify the accuracy and reliability of the Grid Search framework.
Go to article

Bibliography

[1] Walther J., Spanier D., Panten N., Abele E., Very short-term load forecasting on factory level – A machine learning approach, Procedia CIRP, vol. 80, pp. 705–710 (2019).
[2] Aydarous A.A., Elshahed M.A., Hassan M.M.A., Short-Term Load Forecasting Approach Based on Different Input Methods of One Variable: Conceptual and Validation Study, 2018 Twentieth International Middle East Power Systems Conference (MEPCON), Cairo, Egypt, pp. 179–184 (2018).
[3] Raza M.Q., Khosravi A., A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings, Renew. Sustain. Energy Rev., vol. 50, pp. 1352–1372 (2015).
[4] Walther J., Spanier D., Panten N., Abele E., Very short-term load forecasting on factory level – A machine learning approach, Procedia CIRP, vol. 80, pp. 705–710 (2019).
[5] Khan S., Javaid N., Chand A., Abbasi R.A., Khan A.B.M., Faisal H.M., Forecasting day, week and month ahead electricity load consumption of a building using empirical mode decomposition and extreme learning machine, 2019 15th InternationalWireless Communications and Mobile Computing Conference (IWCMC), Tangier, Morocco, pp. 1600–1605 (2019).
[6] Joshi M., Singh R., Short-term load forecasting approaches: A review, International Journal of Recent Engineering Research and Development (IJRERD), no. 01, pp. 9–17 (2015).
[7] Cao Z., Member S., Wan C., Zhang Z., Hybrid Ensemble Deep Learning for Deterministic and Probabilistic Low-voltage Load Forecasting, IEEE Trans. Power Syst., p. 1 (2019).
[8] Yu Y., Ji T.Y., Li M.S., Wu Q.H., Short-term Load Forecasting Using Deep Belief Network with Empirical Mode Decomposition and Local Predictor, 2018 IEEE Power and Energy Society General Meeting (PESGM), Portland, OR, pp. 1–5 (2018).
[9] Yang J.,Wang Q., A Deep Learning Load Forecasting Method Based on Load Type Recognition, 2018 International Conference on Machine Learning and Cybernetics (ICMLC), Chengdu, pp. 173–177 (2018).
[10] Krishnakumari K., Sivasankar E., Radhakrishnan S., Hyperparameter tuning in convolutional neural networks for domain adaptation in sentiment classification (HTCNN-DASC), Soft Comput., vol. 24, no. 5, pp. 3511–3527 (2020).
[11] Subramanian S.V., Rao A.H., Deep-learning based time series forecasting of go-around incidents in the national airspace system, AIAA Model. Simul. Technol. Conf. 2018, no. 209959 (2018).
[12] Zahid M. et al., Electricity price and load forecasting using enhanced convolutional neural network and enhanced support vector regression in smart grids, Electronics, vol. 8, no. 2, pp. 1–32 (2019).
[13] Nurshazlyn Mohd Aszemi, Dhanapal Durai Dominic Panneer Selvam, Hyperparameter optimization in convolutional neural network using genetic algorithms, Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 6, pp. 269–278 (2019).
[14] Brownlee J., Deep Learning for Time Series Forecasting, Ebook (2019).
[15] https://keras.io/optimizers/
[16] Brownlee J., Deep Learning with Python, Ebook (2019).
[17] Chen K., Chen K., Wang Q., He Z., Hu J., He J., Short-Term Load Forecasting With Deep Residual Networks, IEEE Transactions on Smart Grid, vol. 10, no. 4, pp. 3943–3952 (2019).
[18] Jojo Moolayil, Learn Keras for Deep Neural Networks: A Fast-Track Approach to Modern Deep Learning with Python, Apress (2018).
[19] Xishuang Dong, Lijun Qian, Lei Huang, Short-term load forecasting in smart grid: A combined CNN and K-means clustering approach, IEEE Int. Conf. Big Data Smart Comput., pp. 119–125 (2017).
[20] Dong X., Qian L., Huang L., A CNN based bagging learning approach to short-term load forecasting in smart grid, 2017 SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI, San Francisco, CA, 2017, pp. 1–6 (2017).
[21] Voß M., Bender-Saebelkampf C., Albayrak S., Residential Short-Term Load Forecasting Using Convolutional Neural Networks, 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, 2018, pp. 1–6 (2018).
[22] Amarasinghe K., Marino D.L., Manic M., Deep neural networks for energy load forecasting, IEEE Int. Symp. Ind. Electron., pp. 1483–1488 (2017).
[23] Koprinska I., Wu D., Wang Z., Convolutional Neural Networks for Energy Time Series Forecasting, Proc. Int. Jt. Conf. Neural Networks, pp. 1–8 (2018), DOI: 10.1109/IJCNN.2018.8489399.
[24] Valentino Zocca et al., Python Deep Learning, Packt Publishing (2019).
[25] https://www.aemo.com.au/
[26] Haiqing Liu, Weijian Lin, Yuancheng Li, Ultra-short-term wind power prediction based on copula function and bivariate EMD decomposition algorithm, Archives of Electrical Engineering, vol. 69, no. 2, pp. 271–286 (2020).
[27] Wang Y., Ma X., Wang F., Hou X., Sun H., Zheng K., Dynamic electric vehicles charging load allocation strategy for residential area, Archives of Electrical Engineering, vol. 67, no. 3, pp. 641–654 (2018).
Go to article

Authors and Affiliations

Thanh Ngoc Tran
1

  1. Faculty of Electrical Engineering Technology, Industrial University of Ho Chi Minh City, 12 Nguyen Van Bao, Ward 4, Go Vap District, Ho Chi Minh City, Vietnam
Download PDF Download RIS Download Bibtex

Abstract

In this paper, we have researched implementing convolutional neural network (CNN) models for devices with limited resources, such as smartphones and embedded computers. To optimize the number of parameters of these models, we studied various popular methods that would allow them to operate more efficiently. Specifically, our research focused on the ResNet-101 and VGG-19 architectures, which we modified using techniques specific to model optimization. We aimed to determine which approach would work best for particular requirements for a maximum accepted accuracy drop. Our contribution lies in the comprehensive ablation study, which presents the impact of different approaches on the final results, specifically in terms of reducing model parameters, FLOPS, and the potential decline in accuracy. We explored the feasibility of implementing architecture compression methods that can influence the model’s structure. Additionally, we delved into post-training methods, such as pruning and quantization, at various model sparsity levels. This study builds upon our prior research [1] to provide a more comprehensive understanding of the subject matter at hand.
Go to article

Authors and Affiliations

Artur Sobolewski
1
Kamil Szyc
1

  1. Wrocław University of Scienceand Technology, Wrocław, Poland
Download PDF Download RIS Download Bibtex

Abstract

To better extract feature maps from low-resolution (LR) images and recover high-frequency information in the high-resolution (HR) images in image super-resolution (SR), we propose in this paper a new SR algorithm based on a deep convolutional neural network (CNN). The network structure is composed of the feature extraction part and the reconstruction part. The extraction network extracts the feature maps of LR images and uses the sub-pixel convolutional neural network as the up-sampling operator. Skip connection, densely connected neural networks and feature map fusion are used to extract information from hierarchical feature maps at the end of the network, which can effectively reduce the dimension of the feature maps. In the reconstruction network, we add a 3×3 convolution layer based on the original sub-pixel convolution layer, which can allow the reconstruction network to have better nonlinear mapping ability. The experiments show that the algorithm results in a significant improvement in PSNR, SSIM, and human visual effects as compared with some state-of-the-art algorithms based on deep learning.
Go to article

Authors and Affiliations

Xin Yang
1
Yifan Zhang
1
Dake Zhou
1

  1. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, 210016 Nanjing, Jiangsu, China
Download PDF Download RIS Download Bibtex

Abstract

Detection of audio spoofing attacks has become vital for automatic speaker verification systems. Spoofing attacks can be obtained with several ways, such as speech synthesis, voice conversion, replay, and mimicry. Extracting discriminative features from speech data can improve the accuracy of detecting these attacks. In fact, a frame-wise weighted magnitude spectrum is found to be effective to detect replay attacks recently. In this work, discriminative features are obtained in a similar fashion (frame-wise weighting), however, a cosine normalized phase spectrum is used since phase-based features have shown decent performance for the given task. The extracted features are then fed to a convolutional neural network as input. In the experiments ASVspoof 2015 and 2017 databases are used to investigate the proposed system’s spoof detection performance for both synthetic and replay attacks, respectively. The results showed that the proposed approach achieved 34.5% relative decrease in the average EER for ASVspoof 2015 evaluation set, compared to the ordinary cosine normalized phase features. Furthermore, the proposed system outperformed the others at detecting S10 attack type of ASVspoof 2015 database.
Go to article

Authors and Affiliations

Gökay Dişken
1

  1. Department of Electrical-Electronics Engineering, Adana Alparslan Türkes Science and Technology University, Adana, Turkey
Download PDF Download RIS Download Bibtex

Abstract

In the last few years, a great attention was paid to the deep learning Techniques used for image analysis because of their ability to use machine learning techniques to transform input data into high level presentation. For the sake of accurate diagnosis, the medical field has a steadily growing interest in such technology especially in the diagnosis of melanoma. These deep learning networks work through making coarse segmentation, conventional filters and pooling layers. However, this segmentation of the skin lesions results in image of lower resolution than the original skin image. In this paper, we present deep learning based approaches to solve the problems in skin lesion analysis using a dermoscopic image containing skin tumor. The proposed models are trained and evaluated on standard benchmark datasets from the International Skin Imaging Collaboration (ISIC) 2018 Challenge. The proposed method achieves an accuracy of 96.67% for the validation set .The experimental tests carried out on a clinical dataset show that the classification performance using deep learning-based features performs better than the state-of-the-art techniques.

Go to article

Authors and Affiliations

Fatma Sherif
Wael A. Mohamed
A.S. Mohra
Download PDF Download RIS Download Bibtex

Abstract

Accurate and fast access to Vernier caliper readings is a critical issue in automated verification of Vernier calipers. To address this problem, this paper proposes a machine vision-based algorithm for reading the Vernier caliper’s displayed value. The suggested method first employs threshold segmentation and template matching to determine the region of interest and obtain the main ruler digit position by alternate projection. Then, we apply the improved LeNet5 network to identify the main ruler of the Vernier caliper, Moreover, we developed the first and last inscription method for reading the decimal part of the Vernier caliper and established our data set for model training. Extensive experiments on reading the displayed value have demonstrated our algorithm’s accuracy, which achieves a displayed value reading accuracy of 100%. Compared to other methods, the proposed technique affords better stability and accuracy.
Go to article

Authors and Affiliations

Wen-Meng Chen
1
Hong-Xi Wang
1
Guan-Wei Wang
1
Wen-Hong Liang
1

  1. Xi’an Technological University, School of Electrical and Mechanical Engineering, Xi’an, Shanxi 710021 China
Download PDF Download RIS Download Bibtex

Abstract

Thousands of low-power micro sensors make up Wireless Sensor Networks, and its principal role is to detect and report specified events to a base station. Due to bounded battery power these nodes are having very limited memory and processing capacity. Since battery replacement or recharge in sensor nodes is nearly impossible, power consumption becomes one of the most important design considerations in WSN. So one of the most important requirements in WSN is to increase battery life and network life time. Seeing as data transmission and reception consume the most energy, it’s critical to develop a routing protocol that addresses the WSN’s major problem. When it comes to sending aggregated data to the sink, hierarchical routing is critical. This research concentrates on a cluster head election system that rotates the cluster head role among nodes with greater energy levels than the others.We used a combination of LEACH and deep learning to extend the network life of the WSN in this study. In this proposed method, cluster head selection has been performed by Convolutional Neural Network (CNN). The comparison has been done between the proposed solution and LEACH, which shows the proposed solution increases the network lifetime and throughput.
Go to article

Authors and Affiliations

Hardik K Prajapati
1
Rutvij Joshi
2

  1. Gujarat Technological University, Ahmedabad, Gujarat, India
  2. Parul University, Vadodara, Gujarat, India
Download PDF Download RIS Download Bibtex

Abstract

Skin Cancer is one of the most widely present forms of cancer. The correct classification of skin lesions as malignant or benign is a complex process that has to be undertaken by experienced specialists. Another major issue of the class imbalance of data causes a bias in the results of classification. This article presents a novel approach to the usage of metadata of skin lesions' images to classify them. The usage of techniques addresses the problem of class imbalance to nullify the imbalances. Further, the use of a convolutional neural network (CNN) is proposed to finetune the skin lesion data classification. Ultimately, it is proven that an ensemble of statistical metadata analysis and CNN usage would result in the highest accuracy of skin color classification instead of using the two techniques separately.
Go to article

Authors and Affiliations

Sachin Nayak
1
Shweta Vincent
1
Sumathi K
2
Om Prakash Kumar
3
Sameena Pathan
4

  1. Department of Mechatronics Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India
  2. Department of Mathematics, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India
  3. Department of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India
  4. Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

Authors and Affiliations

Jianwei Wang
1 2
ORCID: ORCID
Deyun Chen
1

  1. College of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
  2. College of Computer Science and Technology, Heilongjiang Institute of Technology, Harbin 150050, China
Download PDF Download RIS Download Bibtex

Abstract

In industrial drive systems, one of the widest group of machines are induction motors. During normal operation, these machines are exposed to various types of damages, resulting in high economic losses. Electrical circuits damages are more than half of all damages appearing in induction motors. In connection with the above, the task of early detection of machine defects becomes a priority in modern drive systems. The article presents the possibility of using deep neural networks to detect stator and rotor damages. The opportunity of detecting shorted turns and the broken rotor bars with the use of an axial flux signal is presented.

Go to article

Authors and Affiliations

M. Skowron
Download PDF Download RIS Download Bibtex

Abstract

In this paper deep neural networks are proposed to diagnose inter-turn short-circuits of induction motor stator windings operating under the Direct Field Oriented Control method. A convolutional neural network (CNN), trained with a Stochastic Gradient Descent with Momentum method is used. This kind of deep-trained neural network allows to significantly accelerate the diagnostic process compared to the traditional methods based on the Fast Fourier Transform as well as it does not require stationary operating conditions. To assess the effectiveness of the applied CNN-based detectors, the tests were carried out for variable load conditions and different values of the supply voltage frequency. Experimental results of the proposed induction motor fault detection system are presented and discussed.

Go to article

Authors and Affiliations

M. Skowron
M. Wolkiewicz
G. Tarchała
Download PDF Download RIS Download Bibtex

Abstract

In this work, we present a failure detection system in sensors of any robot. It is based on the k-fold cross-validation approach and built from N neural networks, where N is the number of signals read from sensors. Our tests were carried out using an unmanned aerial vehicle (UAV, quadrocopter), where signals were read from three sensors: accelerometer, magnetometer and gyroscope. Artificial neural network was used to determine Euler angles, based on signals from these sensors. The presented system is an extension of the system that we proposed in one of our previous papers. The improvement shown in this work took place on two levels. The first one was related to improvement of a neural network՚s reproduction quality – we have replaced a recurrent neural network with a convolutional one. The second level was associated with the improvement of the validation process, i.e. with adding some new criteria to check the values of Euler՚s angles determined by the convolutional neural network in subsequent time steps. To highlight the proposed system improvement we present a number of indicators such as RMSE, NRMSE and NDR (Normalized Detection Ratio).

Go to article

Authors and Affiliations

A. Świetlicka
K. Kolanowski
Download PDF Download RIS Download Bibtex

Abstract

The current machine vision-based surface roughness measurement mainly relies on the design of feature indicators associated with roughness to measure the surface roughness. However, the process is tedious and complicated. Moreover, most existing deep learning methods for workpiece surface roughness measurement use a monochromatic light source to acquire images. In the case of surface roughness in a grinding process with low roughness and random texture characteristics, the feature information obtained by monochromatic light source acquisition is relatively small. It is difficult to extract the workpiece surface roughness features, which can easily cause problems for subsequent measurement. Based on the problems above, this paper proposes a grinding surface roughness measurement method combining red-green information and a convolutional neural network. The technique uses a particular red-green block to highlight the grinding surface texture features. Finally, it classifies the grinding surface roughness measurement with a classification detection technique of the convolutional neural network. Experimental results show that the accuracy of the grinding surface roughness measurement method combining red-green information and the convolutional neural network is significantly improved compared with that of the grinding surface roughness measurement method without using the red-green data.
Go to article

Authors and Affiliations

Jiefeng Huang
1 2
Huaian Yi
1 2
Runji Fang
1 2
Kun Song
1 2

  1. Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Guilin, China, 541006
  2. School of Mechanical and Control Engineering, Guilin University of Technology, Guilin, China, 541006
Download PDF Download RIS Download Bibtex

Abstract

Infrasound signal classification is vital in geological hazard monitoring systems. The traditional classification approach extracts the features and classifies the infrasound events. However, due to the manual feature extraction, its classification performance is not satisfactory. To deal with this problem, this paper presents a classification model based on variational mode decomposition (VMD) and convolutional neural network (CNN). Firstly, the infrasound signal is processed by VMD to eliminate the noise. Then fast Fourier transform (FFT) is applied to convert the reconstructed signal into a frequency domain image. Finally, a CNN model is established to automatically extract the features and classify the infrasound signals. The experimental results show that the classification accuracy of the proposed classification model is higher than the other model by nearly 5%. Therefore, the proposed approach has excellent robustness under noisy environments and huge potential in geophysical monitoring.
Go to article

Authors and Affiliations

Quanbo Lu
1
ORCID: ORCID
Mei Li
1

  1. School of Information Engineering, China University of Geosciences, Beijing, China
Download PDF Download RIS Download Bibtex

Abstract

Biometrics provide an alternative to passwords and pins for authentication. The emergence of machine learning algorithms provides an easy and economical solution to authentication problems. The phases of speaker verification protocol are training, enrollment of speakers and evaluation of unknown voice. In this paper, we addressed text independent speaker verification using Siamese convolutional network. Siamese networks are twin networks with shared weights. Feature space can be learnt easily by training these networks even if similar observations are placed in proximity. Extracted features from Siamese then can be classified using difference or correlation measures. We have implemented a customized scoring scheme that utilizes Siamese’ capability of applying distance measures with the convolutional learning. Experiments made on cross language audios of multi-lingual speakers confirm the capability of our architecture to handle gender, age and language independent speaker verification. Moreover, our designed Siamese network, SpeakerNet, provided better results than the existing speaker verification approaches by decreasing the equal error rate to 0.02.

Go to article

Authors and Affiliations

Hafsa Habib
Huma Tauseef
Muhammad Abuzar Fahiem
Saima Farhan
Ghousia Usman
Download PDF Download RIS Download Bibtex

Abstract

The tomato crop is more susceptible to disease than any other vegetable, and it can be infected with over 200 diseases caused by different pathogens worldwide. Tomato plant diseases have become a challenge to food security globally. Currently, diagnosing and preventing tomato plant diseases is a challenge due to the lack of essential methods or tools. The traditional techniques of detecting plant disease are arduous and error-prone. Utilizing precise or automatic detection methods in spotting early plant disease can improve the quality of food production and reduce adverse effects. Deep learning has significantly increased the recognition accuracy of image classification and object detection systems in recent years. In this study, a 15-layer convolutional neural network is proposed as the backbone for single shot detector (SSD) to improve the detection of healthy, and three classes of tomato fruit diseases. The proposed model performance is compared with ResNet-50, AlexNet, VGG 16, and VGG19 as the backbone for Single shot detector. The findings of the experiment showed that the proposed CNN-SDD achieved 98.87% higher detection accuracy, which outperformed state-of-the-art models.
Go to article

Authors and Affiliations

Benedicta Nana Esi Nyarko
1
ORCID: ORCID
Wu Bin
1
Zhou Jinzhi
1
ORCID: ORCID
Justice Odoom
1
ORCID: ORCID

  1. School of Information Engineering, Southwest University of Science and Technology, Mianyang, Sichuan, China
Download PDF Download RIS Download Bibtex

Abstract

Increasing interest, enthusiasm of sport lovers, and economics involved offer high importance to sports video recording and analysis. Being crucial for decision making, ball detection and tracking in soccer has become a challenging research area. This paper presents a novel deep learning approach for 2D ball detection and tracking (DLBT) in soccer videos posing various challenges. A new 2-stage buffer median filtering background modelling is used for moving objects blob detection. A deep learning approach for classification of an image patch into three classes, i.e. ball, player, and background is initially proposed. Probabilistic bounding box overlapping technique is proposed further for robust ball track validation. Novel full and boundary grid concepts resume tracking in ball_track_lost and ball_out_of_frame situations. DLBT does not require human intervention to identify ball from the initial frames unlike the most published algorithms. DLBT yields extraordinary accurate and robust tracking results compared to the other contemporary 2D trackers even in presence of various challenges including very small ball size and fast movements.

Go to article

Authors and Affiliations

P.R. Kamble
A.G. Keskar
K.M. Bhurchandi
Download PDF Download RIS Download Bibtex

Abstract

The field programmable gate array (FPGA) is used to build an artificial neural network in hardware. Architecture for a digital system is devised to execute a feed-forward multilayer neural network. ANN and CNN are very commonly used architectures. Verilog is utilized to describe the designed architecture. For the computation of certain tasks, a neural network’s distributed architecture structure makes it potentially efficient. The same features make neural nets suitable for application in VLSI technology. For the hardware of a neural network, a single neuron must be effectively implemented (NN). Reprogrammable computer systems based on FPGAs are useful for hardware implementations of neural networks.
Go to article

Authors and Affiliations

B A Sujatha Kumari
1
Sudarshan Patil Kulkarni
1
C G Sinchana
1

  1. Sri Jayachamarajendra College of Engineering, JSS Science and Technology University, Mysore, India

This page uses 'cookies'. Learn more