Jose Ogosi, Francisco Hilario, Jorge Mayhuasca, Ciro Rodriguez, Pervis Paredes
This article details how fundamental pension insurance is, taking into account that there are two systems: The Private Pension
System (AFP), in which the worker receives what he has received throughout the period he has worked, such as a personal
savings account and the National Pension Insurance (ONP), which is a public body that allocates the money contributed by
workers (common fund) and is disbursed as a concept of pensions to retirees. Taking into account the problem of the lack of
information on Pension Insurance provided by both public and private entities, it was decided to build an algorithm for
adequate information and thus achieve relevant decision-making for each worker who accesses the payroll forthe first time or
for those who decide to start independently,
Keywords: Decision tree, Private Pension System, National Pension System, active worker, unemployed worker, algorithm
Yatish Subhash Sawant and S. D. Agashe
Optimization in the investment casting industry is a difficult task as it contains multiple-stage operations for pro- duction.
Although taking care of all the parameters investment casting industry is facing issues due to defects in the final product.
This leads to a decrease in production, loss of production resources, and efficiency by analyzing the parameters and defects
from the previous batches. We can predict the occurrence of defects for the given batch using a suitable machine learning
technique. The Naive Bayes method, a supervised machine learning technique, is introduced to predict defects for the given
batch from the model developed for it. Naive Bayes method includes four different models as, Gaussian NB, Multinomial
NB, Complement NB, Bernoulli NB. This paper compared results for each model and analyzes which Naive Bayes model is
best suitable for the Investment Casting industry and can predict the defect in the final product before it occurs.
Keywords: Machine Learning, Naive Bayes, Gaussian NB, Multinomial NB, Complement NB, Bernoulli NB, prediction
Ivan Petrlik, Jorge Mayhuasca, Ciro Rodriguez, Jose Covena, Roberto Esparza
The purpose of this research is to determine the effect of the use of mobile augmented reality applied as a learning strategy
for early childhood education students. The research is applied, pre-experimental and quantitative design. The population
consisted of children in the initial grade of an educational institution in Peru. The sample consisted of 20 students of 5 years
old as experimental and control group. As a result of the intervention, it was possible to improve learning through
competencies in 80% of an expected level of achievement and 20% of an outstanding level of achievement, concluding that
the use of mobile augmented reality improved learning in early education. The use of this technology is recommended as a
pedagogical tool for the early education sector in Peru.
Keywords: Augmented reality, Mobile, learning, competences, strategies
Guramritpal Singh Saggu, Keshav Gupta, K. V. Arya
Depression has been the prime cause of mental-health illness globally. A major depressive disorder is a common mental
health disorder that affects both psychologically and physically, which could lead to the loss of life in extreme cases.
Detection of depression from the recording of an interview could help with early diagnosis. This paper proposes a three-stage
framework multimodal machine learning approach called DepressNet for depression detection using the PHQ-8
Questionnaire score. Bidirectional Long Short-Term Memory (BLSTM) layer network has been proposed, and Extended
Distress Analysis Interview Corpus (E-DAIC) dataset was used for the training and validation of the proposed method with
the uses multiscale temporal features from audio, video, and text modality and attention mechanisms for fusion. The method
achieved the RMSE of 4.32 and CCC of 0.662 on the development set, and on the test set, we got RMSE of 5.36 and CCC of
0.457, outperforming the other methods.
Keywords: Depression, multimodal, attention mechanism, multiscale temporal, audio-visual-text, BLSTM
Aniket H. Nandede, Yogesh K. Bhateshwar, Kamal C. Vora
Rising the emission level from conventional vehicles (CV) is a major concern of today’s world. Electric vehicle (EV) and
hybrid electric vehicles (HEV) technology are two ways to deal with it. EV technology is an emerging technology but they
have some challenges in adopting the EV technology. So, this paper deals with modelling and simulation of a hybrid electric
vehicle such as series hybrid electric vehicle and parallel hybrid electric vehicle with different energy management strategies.
The heart of HEV development is energy management strategy (EMS), on which vehicle’s performance and fuel
consumption can be optimized. For series HEV charge depleting charge sustaining (CDCS) EMS has been used and for
parallel HEV rule-based (RB) EMS has been used. Supervisory control algorithms play important role to allow smooth power
flow between the engine and electric source. There are different EMSs such as rule-based, optimization-based (OB), and
learning-based (LB). These EMSs are used to split the power flow. In this paper, fuzzy logic controller (FLC) as an energy
management strategy is proposed for a parallel hybrid electric vehicle, further this strategy is compared with RBEMS. The
simulation results are compared and analyzed which shows there is improvement in range and reduction fuel consumption. In
this study, MATLAB/Simulink and QSS toolbox are used for the simulation.
Keywords: Electric vehicle, hybrid electric vehicle, energy management strategy, rule based, optimisation based, learning
based, fuzzy logic controller
SCMR is a centre for multi-disciplinary research work, A few activities of SCMR for the benefit of industry.
© 2018, SPJ Centre for Multi-disciplinary Research . All rights reserved | Design by Design For U