A Novel Approach to Detect Anomalies in Business Process Event Logs Using Deep Learning Algorithm

2021 ◽  
pp. 363-374
Author(s):  
M. Vijayakamal ◽  
D. Vasumathi
Keyword(s):  
Deep Learning ◽  
Business Process ◽  
Learning Algorithm ◽  
Deep Learning Algorithm ◽  
Event Logs ◽  
Novel Approach ◽  
Process Event

scholarly journals Forewarned is forearmed: Using AI to detect SDR tendencies as personnel selection tools

2021 ◽  
Author(s):  
Tony Lee ◽  
Matthias Ziegler
Keyword(s):  
Deep Learning ◽  
Personnel Selection ◽  
Learning Algorithm ◽  
Job Applicants ◽  
Baseline Model ◽  
Deep Learning Algorithm ◽  
Novel Approach ◽  
Deep Image ◽  
Selection For ◽  
Social Desirable Responding

Current practices of personnel selection often use questionnaires and interviews to assess candidates’ personality, but the effectiveness of both approaches can be hampered if social desirable responding (SDR) occurs. Detecting biases like SDR is important to ensure valid personnel selection for any organization, yet current instruments for assessing SDR are either inefficient or insufficient. In this paper, we propose a novel approach to appraise job applicants’ SDR tendency by employing Artificial Intelligence (AI)-based techniques. Our study extracts thousands of image and voice features from the video presentation of 91 simulated applicants to train two deep learning models for predicting their SDR tendency. The result shows that our two models, namely the Deep Image Model and Deep Voice Model, can predict SDR tendency with 82.55% and 88.89% accuracy rate, respectively. The Deep Voice Model moreover outperformed the baseline model built on a popular deep learning algorithm ResNet by 4.35%. These findings suggest that organizations can use AI driven technologies to assess job applicants’ SDR tendency during recruitment and improve the performance of their personnel selection.

An Improved Deep Learning Algorithm for Diabetes Prediction

2022 ◽  
pp. 103-119
Author(s):  
Basetty Mallikarjuna ◽  
Supriya Addanke ◽  
Anusha D. J.
Keyword(s):  
Deep Learning ◽  
Random Forest ◽  
Early Detection ◽  
Learning Algorithm ◽  
The Novel ◽  
Random Forest Algorithm ◽  
Deep Learning Algorithm ◽  
Novel Approach ◽  
Diabetes Prediction ◽  
Two Parameters

This chapter introduces the novel approach in deep learning for diabetes prediction. The related work described the various ML algorithms in the field of diabetic prediction that has been used for early detection and post examination of the diabetic prediction. It proposed the Jaya-Tree algorithm, which is updated as per the existing random forest algorithm, and it is used to classify the two parameters named as the ‘Jaya' and ‘Apajaya'. The results described that Pima Indian diabetes dataset 2020 (PIS) predicts diabetes and obtained 97% accuracy.

scholarly journals A Nonlinear Distortion Removal Based on Deep Neural Network for Underwater Acoustic OFDM Communication with the Mitigation of Peak to Average Power Ratio

2020 ◽  
Vol 10 (14) ◽  
pp. 4986 ◽  
Author(s):  
Xuefei Ma ◽  
Waleed Raza ◽  
Zhiqiang Wu ◽  
Muhammad Bilal ◽  
Ziqi Zhou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Power Efficiency ◽  
Learning Algorithm ◽  
Average Power ◽  
Decision Feedback ◽  
Power Ratio ◽  
Underwater Acoustic ◽  
Deep Learning Algorithm ◽  
Novel Approach

Machine learning and deep learning algorithms have proved to be a powerful tool for developing data-driven signal processing algorithms for challenging engineering problems. This paper studies the modern machine learning algorithm for modeling nonlinear devices like power amplifiers (PAs) for underwater acoustic (UWA) orthogonal frequency divisional multiplexing (OFDM) communication. The OFDM system has a high peak to average power ratio (PAPR) in the time domain because the subcarriers are added coherently via inverse fast Fourier transform (IFFT). This causes a higher bit error rate (BER) and degrades the performance of the PAs; hence, it reduces the power efficiency. For long-range underwater acoustic applications such as the long-term monitoring of the sea, the PA works in full consumption mode. Thus, it becomes a challenging task to minimize power consumption and unnecessary distortion. To mitigate this problem, a receiver-based nonlinearity distortion mitigation method is proposed, assuming that the transmitting side has enough computation power. We propose a novel approach to identify the nonlinear power model using a modern deep learning algorithm named frequentative decision feedback (FFB); PAPR performance is verified by the clipping method. The simulation results prove the better performance of the PA model with a BER with the shortest learning time.

scholarly journals Study on Radar Echo-Filling in an Occlusion Area by a Deep Learning Algorithm

2021 ◽  
Vol 13 (9) ◽  
pp. 1779
Author(s):  
Xiaoyan Yin ◽  
Zhiqun Hu ◽  
Jiafeng Zheng ◽  
Boyong Li ◽  
Yuanyuan Zuo
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
Learning Algorithm ◽  
Weather Radar ◽  
Loss Functions ◽  
Training Dataset ◽  
Echo Intensity ◽  
Common Mean ◽  
Deep Learning Algorithm ◽  
Radar Beam

Radar beam blockage is an important error source that affects the quality of weather radar data. An echo-filling network (EFnet) is proposed based on a deep learning algorithm to correct the echo intensity under the occlusion area in the Nanjing S-band new-generation weather radar (CINRAD/SA). The training dataset is constructed by the labels, which are the echo intensity at the 0.5° elevation in the unblocked area, and by the input features, which are the intensity in the cube including multiple elevations and gates corresponding to the location of bottom labels. Two loss functions are applied to compile the network: one is the common mean square error (MSE), and the other is a self-defined loss function that increases the weight of strong echoes. Considering that the radar beam broadens with distance and height, the 0.5° elevation scan is divided into six range bands every 25 km to train different models. The models are evaluated by three indicators: explained variance (EVar), mean absolute error (MAE), and correlation coefficient (CC). Two cases are demonstrated to compare the effect of the echo-filling model by different loss functions. The results suggest that EFnet can effectively correct the echo reflectivity and improve the data quality in the occlusion area, and there are better results for strong echoes when the self-defined loss function is used.

Sign in / Sign up

Export Citation Format

Share Document