Journal of Advanced Applied Scientific Research (JOAASR)
Not a member yet
259 research outputs found
Sort by
Prediction System for Covid-19 Upcoming Cases Using Ensemble Classification
Get PDFAn epidemic of the novel destructive Coronavirus has been spreading rapidly around the world since 2019 and has caused a great number of deaths. Providing patients with appropriate and most timely care is crucial to combating COVID-19 spread. Testing for the disease must be done quickly and accurately. Therefore, this paper developed an ensemble classification-based country-wise COVID-19 upcoming cases prediction model. This ensemble classification and prediction model shows the upcoming month's Corona virus cases, including newly confirmed cases, recovered cases, and deaths. This analysis is carried out based on these three cases occurring in different countries on sequential dates. The proposed model uses three famous classifiers, namely ANN, Gaussian Process and SVM which have different learning characteristics and architectures at the first stage. In the second stage, they combine their predictions with average calculations. Training and assessment of the proposed model were conducted using 75065 observations comprised of 61 features from John Hopkins University in Maryland. For data preparation, the envisioned work clusters the dataset based on world countries affected by COVID-19 separately. As a result, this set of clusters fetched data once again based on death, newly confirmed, and recovered cases. The experimental result shows the proposed ensemble model provides better performance when compared with previous classification algorithms
Bacterial 16s rRNA and antibiotic susceptibility test - A potential marker for forensic individual identification on the basis of profession
Get PDFMicroorganisms are indistinguishable parts of the environment. They are distributed almost everywhere on the earth’s environment and they form the inseparable bond with that particular environment. Similarly, they are distributed inside and outside our body and forms an inextricable conjugation and takes part in the day-to-day’s body functions. These bacteria also contribute to form a skin microflora of a person staying at the particular region and performing particular type of job. According to Locard’s exchange principle when two objects come in contact with each other the exchange of matter takes place from one object to another object of the crime scene which is used in forensic science to connect the suspects with the crime scene. In accordance to this fact the skin bacteria can be transferred from one object to another when touched on the scene of crime. Another advent that exacts sequences of DNA that encodes for 16s rRNA are not identical between organisms, but stays stable and unchanged throughout the life duration, can be used as an exploratory forensic individualization tool. Literature survey says that the ownership and locality of the person, can be identified by Next Generation Sequencing (NGS) on the basis of communities of the skin bacteria. This research is focussed on proving the variations in 16s rRNA sequences clusters on the basis of professions, which can help in identification of the. Bacterial identification can be a useful tool in identifying suspects and workplace or the profession of the suspect/s. In this paper, the results showing clustering of 16s rRNA sequences is shown clearly on the basis of professions. These clustering results were indicative of possibility of use of sanger sequencing for individualization can be used rather than using expensive analysis like pyrosequencing and NGS with careful sample collection from the scene of crime. The same strains that were used for sanger sequence were also tested for antibiotic susceptibility test, which showed that different professions show difference in antibiotic susceptibility
Nanopesticides: Promising Future in Sustainable Pest Management
Get PDFInsects form the most successful and diverse group of animals present on earth today. Humans have shared a complex relationship with the insects. Though insects are indispensable as pollinators of crops yet at the same time they act as major destroyer of grains, pulses and fruits in the fields along with their post- harvest storage. Many of the dreadful diseases are also being transmitted by insect vectors to humans, livestock and other animals. Economic damage caused by insect pests is enormous. Adoption of advanced pest management strategies can alleviate the monetary losses substantially. Nanotechnological approach for pest control is an emerging and effective technique since it encompasses a wide range of objectives of an efficient pesticide like increased dispersion and solubility, slow release, controlled delivery system and protection against degradation. Newer formulations of pesticides with the intervention of nanotechnology are aimed to enhance their pesticidal properties. Insecticide formulations using nanomaterials as carriers of active ingredient have shown promising results for mitigation of pests of agriculture, storage and disease vectors. However, at present the knowledge is limited. There is a need for extensive evaluation of the toxicity of nanopesticides and the risks involved for humans and environment before their large-scale production and adoption.
In this review article nanoformulations of pesticides with special emphasis on metal-based nanopesticides and their role as efficient alternatives in sustainable control of insect pests without much adverse impact on the environment has been summarized.
 
Review on Electric Vehicle Technologies
Get PDFSociety is more concern by the causes and effect of Internal Combustion (IC) engine emission on the climate and environment. The major reason due to which the automobile sector had to conceive, discover, design, build, and bring the Electric vehicle (EV) technology into existence. Electric vehicle has the potential to address greenhouse emission and also it acts as an emerging tool for reducing air pollution and providing a clean transportation system. Just in few numbers of years the rapid rise in EV technology has been observed with a huge growth and demand of public. Keeping the advantages and disadvantages in mind of EV from environmental point of view has been discussed. The most important factor for EV technology used is the batteries, hence a thorough study of battery technology- from Lithium batteries to lead acid batteries is analysed. The charging method, standards, and optimization techniques is also been discussed with the essential characteristics of EV technology used in vehicle. Further future trends, demand, supply in EV technology is provided
Systematic review on heritability of craniofacial characteristics between the generations of the family
Get PDFFace recognition is one of the most required problems in applied Biometrics. It has been likely to improve feasible techniques for physical world applications after ages of study in this particular area. This study describing findings from various research papers of the genetic of the human face and the aim of this review were to describe the heritability of the facial dimensions and facial features between the generations of the family to better understand the genetic architecture of facial dimensions and facial features also. The study result revealed that the maximum correlation was found between father-son and mother-daughter, while the smallest relationship was observed for numerous of the factors in other-sex couples. The girl demonstrated the same heritage from both parents. Overall face size, lip prominence, and chin demonstrated the strongest heritability, but nose and lip shape indicated the least relationship. The outcome of this analysis shows that there is a relatively effective genetic control in the transfer of facial soft tissue traits. In common, consistent data illustrating soft-tissue facial summaries can be attained from pictures of subjects in correct head poses. Additionally large sample size studies should perform using the parameters from this study that showed the highest correlation
Structural Analysis of URL For Malicious URL Detection Using Machine Learning
Get PDFMalicious websites are intentionally created websites that aid online criminals in carrying out illicit actions. They commit crimes like installing malware on the victim's computer, stealing private data from the victim's system, and exposing the victim online. Malicious codes can also be found on legitimate websites. Therefore, locating such a website in cyberspace is a difficult operation that demands the utilization of an automated detection tool. Currently, machine learning/deep learning technologies are employed to detect such malicious websites. However, the problem persists since the attack vector is constantly changing. Most research solutions use a limited number of URL lexical features, DNS information, global ranking information, and webpage content features. Combining several derived features involves computation time and security risk. Additionally, the dataset's minimal features don't maximize its potential. This paper exclusively uses URLs to address this problem and blends linguistic and vectorized URL features. Complete potential of the URL is utilized through vectorization. Six machine learning algorithms are examined. The results indicate that the proposed approach performs better for the count vectorizer with random forest algorith
Condition monitoring of gearbox
Get PDFGears are one of the most important elements of rotating machineries and plays a key role in many industrial applications. If there is an unexpected failure in the gearbox it may lead to large economic losses. The fault diagnostic of rotating elements has drawn attention for its role in preventing disastrous accidents and beneficially assuring maintenance. Recently, fault diagnosis has paved its way in the multidisciplinary direction. Vibration analysis has always been a crucial component of preventative maintenance methods. and plays a significant role in assessing the health of the machinery and has supported decisions on machinery maintenance. An early fault identification of the gearbox is feasible by analyzing the vibration signal using various signal processing techniques since the vibration signal of a gearbox contains the signature of the defect in gear. This work aims to address fault diagnosis method based on vibrational analysis on gear box. Here an attempt has been made to use a diagnosis technique that when applied to gearbox highlights faults and these fault detection techniques are based on vibrational analysis approach
Retransmission Reduction using Checkpoint based Sub-Path Routing for Wireless IoT
Get PDFWireless IoT has been one of the major breakthroughs of the current decade. It has improved the quality of life and has also aided in several improvements in domains like healthcare. Effective routing and energy conservation has been the major challenges in creating and maintaining a successful IoT network. This work presents a checkpoint based routing model, CSPR, to improve the transmission efficiency by reducing retransmission. This work selects checkpoints in the network prior to transmission. The checkpoints are used to build the final path. This process ensures that the routes created are dynamic and reactive, leading to improved security and increased path reliability. Comparison with existing routing model shows improved network lifetime and reduced selection overhead levels, exhibiting the high efficiency of CSPR
Rain Fall Prediction using Ada Boost Machine Learning Ensemble Algorithm
Get PDFEvery government takes initiative for the well-being of their citizens in terms of environment and climate in which they live. Global warming is one of the reason for climate change. With the help of machine learning algorithms in the flash light of Artificial Intelligence and Data Mining techniques, weather predictions not only rainfall, lightings, thunder outbreaks, etc. can be predicted. Management of water reservoirs, flooding, traffic - control in smart cities, sewer system functioning and agricultural production are the hydro-meteorological factors that affect human life very drastically. Due to dynamic nature of atmosphere, existing Statistical techniques (Support Vector Machine (SVM), Decision Tree (DT) and logistic regression (LR)) fail to provide good accuracy for rainfall forecasting. Different weather features (Temperature, Relative Humidity, Dew Point, Solar Radiation and Precipitable Water Vapour) are extracted for rainfall prediction. In this research work, data analysis using machine learning ensemble algorithm like Adaptive Boosting (Ada Boost) is proposed. Dataset used for this classification application is taken from hydrological department, India from 1901-2015. Overall, proposed algorithm is feasible to be used in order to qualitatively predict rainfall with the help of R tool and Ada Boost algorithm. Accuracy rate and error false rates are compared with the existing Support Vector Machine (SVM) algorithm and the proposed one gives the better result
Isolation And Comparison Of Collagen Yield From Skin Of Rhizoprionodon acutus, Scomberomorus guttatus and Rachycentron canadum
Get PDFFish waste generation is estimated to be about 4 million metric tons in India, which is mostly dumped into the environment indiscriminately. A sustainable way of managing this waste is to valorise it by generating products like enzymes, bio-polymers and bioactive peptides suitable for biotechnological and pharmaceutical applications. Collagen, an abundant extracellular matrix protein, is a high-value product that can be extracted from fish waste like skin. In the current study, collagen has been isolated from the skin of three different species of fish - Rhizoprionodon acutus (Milk shark), Scomberomorus guttatus (Indo-pacific king mackerel) and Rachycentron canadum (Cobia fish). Acid and pepsin extraction methods were followed for isolation of collagen and the mean yield of collagen was calculated on a wet-weight basis. Attenuated Total Reflectance- Fourier Transform Infrared Spectroscopy (AT-FTIR) and Sodium Dodecyl Sulphate- Polyacrylamide Gel Electrophoresis (SDS-PAGE) techniques were carried out for characterisation of extracted collagen. Results showed that collagen yield was 10.81%, 7.91 and 3.62% for Rachycentron canadum (Cobia fish), Rhizoprionodon acutus (Milk shark) and Scomberomorus guttatus (Indo-pacific king mackerel) respectively. Characterisation confirmed that it was type I collagen and comparable with standard mammalian type I collagen. Fish skin can thus, be an acceptable source of type I collagen which can be explored for diverse industrial applications