scholarly journals Employee Attrition Prediction Using Deep Neural Networks

Computers ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 141
Author(s):  
Salah Al-Darraji ◽  
Dhafer G. Honi ◽  
Francesca Fallucchi ◽  
Ayad I. Abdulsada ◽  
Romeo Giuliano ◽  
...  
Keyword(s):  
Prediction Accuracy ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
Planning Process ◽  
Imbalanced Dataset ◽  
Efficient Tool ◽  
Original Dataset ◽  
Learning Technique ◽  
Employee Attrition ◽  
The Right

Decision-making plays an essential role in the management and may represent the most important component in the planning process. Employee attrition is considered a well-known problem that needs the right decisions from the administration to preserve high qualified employees. Interestingly, artificial intelligence is utilized extensively as an efficient tool for predicting such a problem. The proposed work utilizes the deep learning technique along with some preprocessing steps to improve the prediction of employee attrition. Several factors lead to employee attrition. Such factors are analyzed to reveal their intercorrelation and to demonstrate the dominant ones. Our work was tested using the imbalanced dataset of IBM analytics, which contains 35 features for 1470 employees. To get realistic results, we derived a balanced version from the original one. Finally, cross-validation is implemented to evaluate our work precisely. Extensive experiments have been conducted to show the practical value of our work. The prediction accuracy using the original dataset is about 91%, whereas it is about 94% using a synthetic dataset.

scholarly journals CoCoNet: Boosting RNA contact prediction by convolutional neural networks

2020 ◽  
Author(s):  
Mehari B Zerihun ◽  
Fabrizio Pucci ◽  
Alexander Schug
Keyword(s):  
Neural Networks ◽  
Structure Prediction ◽  
Prediction Accuracy ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
Rna Structures ◽  
Contact Prediction ◽  
Contact Maps ◽  
Direct Coupling Analysis ◽  
Protein Contact Maps

Physics-based co-evolutionary models such as direct coupling analysis (DCA) in combination with machine learning (ML) techniques based on deep neural networks are able to predict protein contact maps with astonishing accuracy. Such contacts can be used as constraints in structure prediction and massively increase prediction accuracy. Unfortunately, the same ML methods cannot readily be applied to RNA as they rely on large structural datasets only available for proteins but not for RNAs. Here, we demonstrate how the small amount of data available for RNA can be used to significantly improve prediction of RNA contact maps. We introduce an algorithm called CoCoNet that is based on a combination of a Coevolutionary model and a shallow Convolutional Neural Network. Despite its simplicity and the small number of trained parameters, the method boosts the contact prediction accuracy by about 70% with respect to straightforward DCA as tested by cross-validation on a dataset of about sixty RNA structures. Both our extensive robustness tests and the limited number of parameters allow the generalization properties of our model. Finally, applications to other RNAs highlight the power of our approach. CoCoNet is freely available and can be found at https://github.com/KIT-MBS/coconet.

scholarly journals Towards computer-aided severity assessment via deep neural networks for geographic and opacity extent scoring of SARS-CoV-2 chest X-rays

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
A. Wong ◽  
Z. Q. Lin ◽  
L. Wang ◽  
A. G. Chung ◽  
B. Shen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Monte Carlo ◽  
Lung Disease ◽  
Disease Severity ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
X Rays ◽  
Computer Aided ◽  
Monte Carlo Cross Validation ◽  
Validation Experiments

AbstractA critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause for the coronavirus disease 2019 (COVID-19) pandemic, is the assessment of the severity of disease progression. Chest x-rays (CXRs) are often used to assess SARS-CoV-2 severity, with two important assessment metrics being extent of lung involvement and degree of opacity. In this proof-of-concept study, we assess the feasibility of computer-aided scoring of CXRs of SARS-CoV-2 lung disease severity using a deep learning system. Data consisted of 396 CXRs from SARS-CoV-2 positive patient cases. Geographic extent and opacity extent were scored by two board-certified expert chest radiologists (with 20+ years of experience) and a 2nd-year radiology resident. The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent scoring and 50 to perform opacity extent scoring) using random subsets of CXRs from the study, and we evaluated the networks using stratified Monte Carlo cross-validation experiments. The COVID-Net S deep neural networks yielded R$$^2$$ 2 of $$0.664 \pm 0.032$$ 0.664 ± 0.032 and $$0.635 \pm 0.044$$ 0.635 ± 0.044 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments. The best performing COVID-Net S networks achieved R$$^2$$ 2 of 0.739 and 0.741 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively. The results are promising and suggest that the use of deep neural networks on CXRs could be an effective tool for computer-aided assessment of SARS-CoV-2 lung disease severity, although additional studies are needed before adoption for routine clinical use.

Spatial cross-validation is not the right way to evaluate map accuracy

2021 ◽  
Vol 457 ◽  
pp. 109692
Author(s):  
Alexandre M.J.-C. Wadoux ◽  
Gerard B.M. Heuvelink ◽  
Sytze de Bruin ◽  
Dick J. Brus
Keyword(s):  
Cross Validation ◽  
The Right ◽  
Map Accuracy

scholarly journals PHASED MULTI‐TARGET AREAL DEVELOPMENT COMPETITIONS: ALGORITHMS FOR COMPETITOR ALLOCATION

2009 ◽  
Vol 13 (1) ◽  
pp. 1-22 ◽  
Author(s):  
Pertti Lahdenperä
Keyword(s):  
Real Estate ◽  
Planning Process ◽  
Selection Process ◽  
Development Project ◽  
Real Estate Development ◽  
Urban Structure ◽  
Public And Private ◽  
Competition Process ◽  
The Right ◽  
Private Actors

The prevailing practice in new areal real estate development is for public and private actors to perform their duties by turns. Yet, the planning process could benefit from simultaneous contributions from society and developers and their designers. That, again, requires that the municipality selects the private partner consortia prior to completion of the local detailed plan through a competition in order to find the most potential actors and the best ideas for implementation of an urban structure of high quality. Candidates will be attracted by offering them the right to implement a residential/business block as a developer. The several blocks involved in an areal development project, and the laboriousness of producing competitive solutions, require a well planned selection process. A novel multi‐target competition process was developed which is presented in this paper with special emphasis on the allocation algorithms that allow selecting the most qualified competitors for parallel follow-up competitions from among a large group of registered candidates. The approach was tested in an actual real estate development project in the municipal district of Vuores which was the original reason for launching the study. Santruka Pletojant nekilnojamaji turta naujose teritorijose, vieši ir privatūs asmenys dažniausiai savo pareigas vykdo paeiliui. Tačiau planavimo procesui būtu tik geriau, jei tuo pačiu metu prisidetu ir visuomene, ir vystytojai, ir projektuotojai. Tam velgi reikia, kad savivaldybe paskelbtu konkursa ir pasirinktu privačiu partneriu grupes prieš užbaigdama vietini detaluji plana didžiausia potenciala turintiems dalyviams aptikti ir geriausioms idejoms surinkti, kokybiškai miesto struktūrai išvystyti. Kai teritoriju pletros projektas apima kelis kvartalus, o kuriant konkurencingus sprendimus idedama daug darbo, reikia gerai suplanuoto atrankos proceso. Yra sukurtas novatoriškas daugiatikslis konkurso procesas, pristatomas šiame darbe, daugiau demesio skiriama paskirstymo algoritmams, kuriuos naudojant iš daugybes registruotu kandidatu galima atrinkti tinkamiausius tolesniems tuo pat metu vykdomiems konkursams. Toks būdas patikrintas realiame nekilnojamojo turto pletros projekte, kuris vyko Vuores savivaldybes teritorijoje, ir būtent del šios priežasties pradetas šis tyrimas.

scholarly journals Versatile Framework for Medical Image Processing and Analysis with Application to Automatic Bone Age Assessment

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Chen Zhao ◽  
Jungang Han ◽  
Yang Jia ◽  
Lianghui Fan ◽  
Fan Gou
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Medical Image Processing ◽  
Bone Age ◽  
Age Assessment ◽  
Image Processing And Analysis ◽  
Learning Technique ◽  
Bone Age Assessment

Deep learning technique has made a tremendous impact on medical image processing and analysis. Typically, the procedure of medical image processing and analysis via deep learning technique includes image segmentation, image enhancement, and classification or regression. A challenge for supervised deep learning frequently mentioned is the lack of annotated training data. In this paper, we aim to address the problems of training transferred deep neural networks with limited amount of annotated data. We proposed a versatile framework for medical image processing and analysis via deep active learning technique. The framework includes (1) applying deep active learning approach to segment specific regions of interest (RoIs) from raw medical image by using annotated data as few as possible; (2) generative adversarial Network is employed to enhance contrast, sharpness, and brightness of segmented RoIs; (3) Paced Transfer Learning (PTL) strategy which means fine-tuning layers in deep neural networks from top to bottom step by step to perform medical image classification or regression tasks. In addition, in order to understand the necessity of deep-learning-based medical image processing tasks and provide clues for clinical usage, class active map (CAM) is employed in our framework to visualize the feature maps. To illustrate the effectiveness of the proposed framework, we apply our framework to the bone age assessment (BAA) task using RSNA dataset and achieve the state-of-the-art performance. Experimental results indicate that the proposed framework can be effectively applied to medical image analysis task.

scholarly journals Strategi Marketing Public Relations Kopi Kenangan dalam Membangun Brand Awareness

Prologia ◽  
2021 ◽  
Vol 5 (1) ◽  
pp. 175
Author(s):  
Scelly Alvionita Chayadi ◽  
Riris Loisa ◽  
Sudarto Sudarto
Keyword(s):  
Strategic Planning ◽  
Public Relations ◽  
Planning Process ◽  
Brand Awareness ◽  
High Quality ◽  
Coffee Shop ◽  
Strategic Planning Process ◽  
Data Collection Technique ◽  
The Right ◽  
Public Relations Strategy

The rapid growth of the coffee business in Indonesia especially JABODETABEK, has resulted in very tight competition for entrepreneurs in the coffee sector, this has made coffee shop entrepreneurs have to be able and must have the right strategy in dealing with this competition. The purpose of this study is to determine the Marketing Public Relations strategy of Kopi Kenangan in building brand awareness for the last 3 years. The theory used in this research is Whalen's 7 step Strategic Planning Process. The method used in this research is qualitative with the case study method. The data collection technique used was in-depth interviews. The results of this study indicate that the Marketing Public Relations of Kopi Kenangan wants to instill the mindset of "Affordable with High Quality Coffee" into the minds of consumers by using the Marketing Public Relations strategy consisting of pull, push and pass carried out by PR & Communications Kopi Kenangan. So that the process of maintaining brand awareness starts from not realizing the original brand of Kopi Kenangan, to the peak of the mind which means the success of Kopi Kenangan as a coffee brand that is able to develop and compete.Pesatnya pertumbuhan bisnis kopi yang ada di Indonesia terutama JABODETABEK sehingga menimbulkan persaingan yang sangat ketat bagi para pengusaha bidang kopi, hal tersebut membuat para pengusaha kedai kopi harus mampu dan harus mempunyai strategi yang tepat dalam menghadapi persaingan tersebut. Tujuan dari penelitian ini adalah mengetahui strategi Marketing Public Relations Kopi Kenangan dalam membangun brand awareness selama 3 tahun terakhir. Teori yang digunakan dalam penelitian ini adalah Whalen’s 7 step Strategic Planning Process. Metode yang digunakan dalam penelitian ini adalah kualitatif dengan metode studi kasus. Teknik pengumpulan data yang digunakan adalah wawancara mendalam (depth interview). Hasil penelitian ini menunjukan bahwa Marketing Public Relations Kopi Kenangan ingin menanamkan mindset “Affordable with High Quality Coffee” kedalam benak konsumen dengan menggunakan strategi Marketing Public Relations yang terdiri dari pull, push and pass yang dilakukan oleh PR & Communications Kopi Kenangan. Sehingga proses untuk mempertahankan brand awareness yang dimulai dari tidak menyadari merek awal Kopi Kenangan berdiri, sampai pada puncak pikiran yang berarti keberhasilan Kopi Kenangan sebagai brand kopi yang mampu berkembang dan bersaing.

scholarly journals Forecasting Reservoir Water Levels Using Deep Neural Networks: A Case Study of Angat Dam in the Philippines

Water ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 34
Author(s):  
Sebastian C. Ibañez ◽  
Carlo Vincienzo G. Dajac ◽  
Marissa P. Liponhay ◽  
Erika Fille T. Legara ◽  
Jon Michael H. Esteban ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
The Philippines ◽  
Water Levels ◽  
Short Term ◽  
Exogenous Variables ◽  
Reservoir Water ◽  
Forecasting Performance

Forecasting reservoir water levels is essential in water supply management, impacting both operations and intervention strategies. This paper examines the short-term and long-term forecasting performance of several statistical and machine learning-based methods for predicting the water levels of the Angat Dam in the Philippines. A total of six forecasting methods are compared: naïve/persistence; seasonal mean; autoregressive integrated moving average (ARIMA); gradient boosting machines (GBM); and two deep neural networks (DNN) using a long short-term memory-based (LSTM) encoder-decoder architecture: a univariate model (DNN-U) and a multivariate model (DNN-M). Daily historical water levels from 2001 to 2021 are used in predicting future water levels. In addition, we include meteorological data (rainfall and the Oceanic Niño Index) and irrigation data as exogenous variables. To evaluate the forecast accuracy of our methods, we use a time series cross-validation approach to establish a more robust estimate of the error statistics. Our results show that our DNN-U model has the best accuracy in the 1-day-ahead scenario with a mean absolute error (MAE) and root mean square error (RMSE) of 0.2 m. In the 30-day-, 90-day-, and 180-day-ahead scenarios, the DNN-M shows the best performance with MAE (RMSE) scores of 2.9 (3.3), 5.1 (6.0), and 6.7 (8.1) meters, respectively. Additionally, we demonstrate that further improvements in performance are possible by scanning over all possible combinations of the exogenous variables and only using a subset of them as features. In summary, we provide a comprehensive framework for evaluating water level forecasting by defining a baseline accuracy, analyzing performance across multiple prediction horizons, using time series cross-validation to assess accuracy and uncertainty, and examining the effects of exogenous variables on forecasting performance. In the process, our work addresses several notable gaps in the methodologies of previous works.

scholarly journals Using General System Approach For Product Lifecycle Management Software Selection And Evaluation

2009 ◽  
Vol 13 (1) ◽  
Author(s):  
Keh-Wen “Carin” Chuang ◽  
Kuan C. Chen
Keyword(s):  
Planning Process ◽  
General System ◽  
Product Lifecycle Management ◽  
Third Party ◽  
Software Selection ◽  
Product Lifecycle ◽  
Systems Model ◽  
The Right ◽  
Business Requirements ◽  
Lifecycle Management

Product Lifecycle Management (PLM) is the process of managing the entire lifecycle of a product from its conception, through design and manufacture, to service and disposal. One of the toughest aspects of PLM implementations is choosing the appropriate software. In order to choose the right software that meets the business requirements, it is necessary to have a systematic view to serve as an evaluation guideline for advice from an independent third-party and that can guide decision makers through a structured process and understands the entire PLM market. This is an important aspect of the PLM assessment and planning process. This study built a systems model to fulfill the PLM software selection and evaluation needs.

scholarly journals MHC*IMP – Imputation of Alleles for Genes in the Major Histocompatibility Complex

2020 ◽  
Author(s):  
David McG. Squire ◽  
Allan Motyer ◽  
Richard Ahn ◽  
Joanne Nititham ◽  
Zhi-Ming Huang ◽  
...  
Keyword(s):  
Major Histocompatibility Complex ◽  
Prediction Accuracy ◽  
Cross Validation ◽  
Whole Genome Sequencing Data ◽  
Major Histocompatibility ◽  
Sequencing Data ◽  
Imputation Model ◽  
Human Major Histocompatibility Complex ◽  
Histocompatibility Complex ◽  
Snp Data

AbstractWe report the development of MHC*IMP, a method for imputing non-classical HLA and other genes in the human Major Histocompatibility Complex (MHC). We created a reference panel for 25 genes in the MHC using allele calls from Whole Genome Sequencing data, combined with SNP data for the same individuals. We used this to construct an allele imputation model, MHC*IMP, for each gene. Cross-validation showed that MHC*IMP performs very well, with allele prediction accuracy 93% or greater for all but two of the genes, and greater than 95% for all but four.

Sign in / Sign up

Export Citation Format

Share Document