Series - 1 [April - 2022]

Paper Title :: Case-Based Reasoning Recommender System for Diagnosing Breast Cancer Disease: Confusable Disease Using Genetic Algorithm
Author Name :: Jatto Joshua O. || Okengwu Ugochi A.
Page Number :: 01-09
:: 10.9790/1813-1104010109  

Most countries are still struggling and suffering to have a better health delivery system. The disease commonly found among ladies is breast cancer regarded as a confusable disease and results of researchers reveals that if the breast cancer disease is detected at early stage, the chances of overcoming the disease will be very high compared to when the disease is been treated or detected at later stage. A lot of ladies have lost their lives regards to the confusability of the disease (breast cancer).In this paper the Genetic and SVM Algorithms are employed to detect and ascertain the level or stages of human confusable breast cancer disease. The genetic algorithm (GA) performed better than the Support Vector Machine (SVM) model in terms of detection accuracy, precision and recall. The system was successfully trained and tested compared to 92.40% and 71.99% accuracy level with GA and SVM respectively.


KEYWORDS: Recommendation Engine, Confusable Disease, Genetic Algorithm, SVM, Case-Based reasoning.

@article{key:article,
author = {Jatto Joshua O. || Okengwu Ugochi A.},
title = {Case-Based Reasoning Recommender System for Diagnosing Breast Cancer Disease: Confusable Disease Using Genetic Algorithm},
journal = {The International Journal of Engineering and Science},
year = {2022},
volume = {11},
number = {04},
pages = {01-09},
month = {April}
}
Paper Title :: Effects of Septic Tank Proximity to Boreholes on groundwater contamination at Igwuruta, Rivers State, Nigeria
Author Name :: J.N. Ugbebor || U.B. Ntesat
Page Number :: 10-17
:: 10.9790/1813-1104011017  

The study aims to assess the effects of pollutant infiltration from septic tank on groundwater contamination. Water and effluent samples were collected from the surrounding boreholes and cesspools in selected residents in Igwuruta communities. Physical and biochemical analysis using standard techniques and protocols were employed. The results indicated that the pH of Borehole A, B and C were 4.52, 4.36 and 6.79 respectively. Boreholes A and B were acid indicating acidity when compared with the permissible drinking water standards from WHO (2017) with benchmarks of 6.5-8.5, respectively. This must have been influenced by the cesspools proximity to the Borehole water source. Fe, Zn and Pb from Boreholes were 0.75, 0.88, 0.39; 6.23,6.89 4.78; and 0.08, 0.06, ND for boreholes A, B and C, respectively were high when compared.......

KEYWORDS: Effluent, Cesspools, contamination, coli form bacteria, sewage percolation.

@article{key:article,
author = {J.N. Ugbebor || U.B. Ntesat},
title = {Effects of Septic Tank Proximity to Boreholes on groundwater contamination at Igwuruta, Rivers State, Nigeria},
journal = {The International Journal of Engineering and Science},
year = {2022},
volume = {11},
number = {04},
pages = {10-17},
month = {April}
}
Paper Title :: Implementation Of Demand Side Management At Siantan Substation for Load Factor Improvement
Author Name :: Gita Pratiwi || Rudy Gianto || Rudi Kurnianto || Redi R Yacoub || Bomo Wibowo Sanjaya || Fitri Imansyah || Leonardus Sandy Ade Putra || Jannus Marpaung
Page Number :: 18-25
:: 10.9790/1813-1104011825  

Siantan substations located within the west Kalimantan electrical system, known as Khatulistiwa GI system consists of 11 feeders. Including cottage, beting, navigasi, hoktong, tugu, wilmar, pangeran, selat panjang, vitamo, malaya dan puring 1. in 2019, the usage of electrical energy at the Siantan substation from customers is still suboptimal yet, cause the uneven use of electrical energy during peak load times (PLT) and outside peak load times (OPLT), causing a low load factor value of 0.84. This is certainly detrimental to all parties, both for PLN itself and for customers. Thus, it is necessary to have a system to assist in increasing the value of the load factor, namely by Demand Side Management (DSM) with the load shifting method. DSM is the scheming, implementation, and monitoring of utility activities designed to affect........

KEYWORDS: Substation, DSM, Load Shifting, Load Factor.

@article{key:article,
author = {Gita Pratiwi || Rudy Gianto || Rudi Kurnianto || Redi R Yacoub || Bomo Wibowo Sanjaya || Fitri Imansyah || Leonardus Sandy Ade Putra || Jannus Marpaung},
title = {Implementation Of Demand Side Management At Siantan Substation for Load Factor Improvement},
journal = {The International Journal of Engineering and Science},
year = {2022},
volume = {11},
number = {04},
pages = {18-25},
month = {April}
}
Paper Title :: KNN and SVM Machine learning to Predict Staff Due for Promotions and Training
Author Name :: Ijeoma Lilian Emmanuel-Okereke || Sylvanus Okwudili Anigbogu
Page Number :: 26-34
:: 10.9790/1813-1104012634  

The hope of every organization to achieve its set goal depends mainly on its human resources. Promotions and training exercise can help retain staff perceived to leave an organization which can help improve employee performance and guarantee job satisfaction. Any Organization or firms were Employees are denied of promotions and training opportunities may experience poor workplace moral behaviour among staff members. It can fuel mistakes or errors and bring about job dissatisfaction and the organization may not perform well as required, leading to even lower retention and turnover rate. The lack of promotions and training exercise directly affects the general performance; it can lead to financial loss and exit of experience employees from the organization. The KNN and SVM model was developed, trained, tested and evaluated using the same dataset with the help of grid search cross validation test. The grid search technique was employed to select the best and optimal kernel and support vector value in predicting those due for promotions and training. The experimental results of KNN produced 78% and SVM that gave 91% success rate as the best.

KEYWORDS: Machine learning, K-nearest neighbor, support vector machine, promotions, Training.

@article{key:article,
author = {Ijeoma Lilian Emmanuel-Okereke || Sylvanus Okwudili Anigbogu},
title = {KNN and SVM Machine learning to Predict Staff Due for Promotions and Training},
journal = {The International Journal of Engineering and Science},
year = {2022},
volume = {11},
number = {04},
pages = {26-34},
month = {April}
}
Paper Title :: A laser mechanical pen for power generation based on human body temperature
Author Name :: Feng Wang || Li-Wei Jiang || Jun Huang || Li-Fang Yu || Ding-Bo Hu || Zi-Yan Hu || Yao-Qian Wang || Sen-Da Qi
Page Number :: 35-38
:: 10.9790/1813-1104013538  

In order to collect the weak energy generated by human body temperature difference, a writable laser mechanical pen using human body temperature difference to generate electricity is studied and manufactured based on the principle of thermoelectric effect Seebeck effect of thermoelectric semiconductor materials. The device mainly uses the body temperature difference of the human body, converts and collects the generated energy through the thermoelectric generator, and then supplies it to the storable battery. Finally, the power of the storable battery will be used to light the laser lamp. In this study, through the three-dimensional modeling and real rendering of the device, the working performance of the device is preliminarily estimated and the digital structure design is carried out. The research results will further improve the thermoelectric power generation equipment system.


KEYWORDS: Semiconductor thermoelectric power generation; 3D rendering; Mechanical laser pen

@article{key:article,
author = {Feng Wang || Li-Wei Jiang || Jun Huang || Li-Fang Yu || Ding-Bo Hu || Zi-Yan Hu || Yao-Qian Wang || Sen-Da Qi},
title = {A laser mechanical pen for power generation based on human body temperature},
journal = {The International Journal of Engineering and Science},
year = {2022},
volume = {11},
number = {04},
pages = {35-38},
month = {April}
}