International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Analysis of Job Failure Prediction in a Cloud Environment by Applying Machine Learning Techniques
Cloud Services are the on-demand availability of resources like storage, data, and compute power. Nowadays, cloud computing and storage systems are continuing to expand, there is an imperative requirement for CSP (cloud service providers) to ensure a reliable and consistent supply of resources to users and businesses in case of any failure. Consequently, the large cloud service providers are concentrating on mitigating any failures that transpire in a cloud system environment. In this research work, we examined the bit brains dataset for the job failure prediction which keeps traces of 3 years of cloud system VMs. The dataset contains data about the resources used in a cloud environment. We proposed the performance of two machine learning algorithms which are Logistic-Regression and KNN. The performance of these ML algorithms has been assessed using cross-validation. KNN and Logistic Regression give the optimal results with an accuracy of 99% and 95%. Our research study shows that using KNN and Logistic Regression increases the detection accuracy of job failures and will relieve cloud-service providers from diminishing future failures in cloud resources. Thus, we believe our approach is feasible and can be transformed to apply in an existing cloud environment
Climate Induced Coastline Changes: A Case Study In Togo (West Africa)
Changing climate is a global distress these days. Global warming is one of the men driven outcome of climate change which causes the glaciers to melt, shoreline regression and raises the level of sea. The regression of shoreline in Togo resulted in vandalization of human habitat and infrastructure. This research aims to monitor the coastal erosion utilizing the geospatial techniques in Togo from 1988 to 2020. The process of extraction and existence of change in shoreline is analyzed. Scientific problems regarding the precision of classification algorithms methods utilized for shoreline extraction using various satellite images are also considered. Thus, NDWI index derived from multisource satellite images were used in this research paper. The performance of Iso Cluster Unsupervised Classification, Otsu threshold segmentation and Sup- port Vector Machine (SVM) Supervised Classification techniques are monitored for the shoreline extraction. This study also takes into account the topographic morphology including non linear and linear coastal surfaces. The rate of change of shoreline was estimated through the statistical linear regression method (LRR). The results demonstrated that the SVM Supervised Classification method worked accurately for topographic morphology than other methods.
Full Tex
Isolation of Keratinolytic from Chicken (Gallus gallus domesticus) Farms and Assessment of their Efficacy in Feathers Degradation
Keratinolytic microorganisms and their enzymes are associated with poultry feather degradation. In the present study feathers of Gallus gallus domesticus (chicken) and surrounding dry soil was collected from a private poultry sheds located in Jahman village near Lahore. Bacteria were isolated by using enrichment techniques and screened for their proteolytic activity on skim agar. Isolated Bacteria were colonially, morphologically and biochemically characterized and named as SNC1, SNC2, SNC3, SNC4, SCH1, SCH2, SCH3 and SCH4. Results showed closed similarity of bacterial isolates with bacillus species. Effect of various media (LB-broth and Nutrient broth), pHs (7 and 8) and temperatures (4, 37, and 50℃) were recorded on bacterial growth and feather degradation. Bacterial cell densities and amount of keratin produced per gram feather weight were high at temperature 50℃ and pH 8.0. The feather degradation by bacterial isolates was confirmed at different time intervals using stereomicroscopes. The protein analysis of G. gallus domesticus feathers showed protein contents of 3.125g/100 ml. It was concluded high temperature and alkaline pH favored keratin production by bacterial consortia. Moreover, the bacterial isolates used in the current study have the potential to degrade poultry feather waste and extracted keratin is found to be promising for further exploitation of poultry waste.
Full Tex
Global Temperature Variations Since Pre Industrial Era
The global temperature trends are being changed due to anthropogenic activities. The natural ecosystems and human societies are affected by this rapid climate change. These changes are caused by the increasing concentration of carbon dioxide and other green house gases including methane and oxides of nitrogen and sulphur. These changes can be identified using accurate data related to variations in temperature and precipitation. We used MODIS GLOVIS LST V6 global datasets to compute pixel-based temperature and mapped the trends. The considerable warming trends are exhibited by Arctic regions which are warming twice as compared to other parts of world. The largest increase in precipitation occurs in Northern Europe at the rate of 12.9mm per decade. The concentration of carbon dioxide has been raised up to 4.14 ppm in atmosphere by December 2020. This increased concentration has raised the global temperature up to 1.2°C since pre industrial era. Remotely sensed datasets provided promising results.
Full Tex
Bioaccumulation Efficacy of Heavy Metals In Body Organs of Rainbow (Oncorhynchus Mykiss) and Brown (Salmo Trutta Fairo) Trouts of Gilgit-Baltistan
Heavy metals are chemical elements that are poisonous and toxic comprising of both necessary and unnecessary trace metals. All aquatic organisms require very low amount of these metals yet in case where these values exceed to certain range, threshold harmful effects are levied upon the ecosystem. The aim of this study was to estimate the bioaccumulation of heavy and trace metals (Cr, Mn, Ni, Fe, Pb, Cu, Cd, Zn) in fish using Atomic Absorption Spectrophotometer (AAS). Samples of fish were procured from Ghizer and Astore districts of Gilgit-Baltistan region of Pakistan. The concentration of Cr, Pb, Cu and Cd were almost same and depicted low tendency of bioaccumulation as per WHO guidelines. The fish from Ghizer was having high concentration of Zn and Fe in intestine. While the concentration of Fe in muscles and intestine from the Astore species was slightly high. The highest concentration of Ni (10.09 ppm) was found in liver tissues of rainbow trout, while the lowest concentration (6.74 ppm) was in the fins of fish from Astore. In case of Cr, the highest concentration (3.8 ppm) was found in liver from both sampling sites, but the lowest concentration (0.24 ppm) was in the muscles of Ghizer Rainbow trout. The highest concentration of cu (6.09 ppm) was in the muscles of fish from Astore, but the lowest concentration (2.32 ppm) was found in many organs of fish from both study sites. Although the concentration of Zn, Mn and Fe were within the limits, however, the highest concentration of Pb (0.79 ppm) was in the muscles and the highest concentration of Cd (0.38 ppm) was in the skin of Ghizer rainbow trout. Concentration of Lead exceeded the limits of FAO/WHO in every organ of fish in both study areas, while all the other metals were in the maximum limits.
Full tex
Estimation of relation between moisture content of soil and reflectivity index using GPS signals
The irrigation system throughout the world is affected by the variations in water content due to different soil structure, textures and climate change. The irrigation system supplies sufficient water to the agricultural fields in order to fulfill the prerequisites. The measurement of soil moisture content (62%) is crucial for precision irrigation and sustainable agricultural system. Site specific agricultural system was utilized to overcome all issues related to soil water moisture contents in the paddock. Smart technology was utilized to record GPS signals utilizing the signals reflected on the Earth’s surface. The GPS was utilized to analyze dielectric soil properties and moisture content in proposed areas. The main objective of this study was to determine water content with stimulus soil type, ground cover and compaction on the irrigation system by utilizing the GPS-based techniques. The result indicated positive relation between soil moisture content and the signals reflected on the earth surface. All factors affecting the irrigation system were not related to the reflected signals and did not affect the soil moisture content. The reflectivity was not reduced by ground cover. Whereas, comparative relationship was found between soil moisture content and reflectivity index i.e. soil moisture contents were increased with reflectivity index up to 0.02 %. The results showed that GPS signals system have significant impact on estimation of soil moisture content in precise irrigation system.
Full Tex
Analysis of Pesticides Residues in Breast Milk of primiparous and multiparous women in Gilgit
Milk contains all the essential nutrients like fats, proteins, and minerals. The utilization of contaminated food can induce a proportion of pesticides in the body. The main purpose of the study was to determine the pesticide residues and current status of breast milk in primiparous and multiparous mothers. In a current study, a total of 50 samples were collected from different areas of District Gilgit and Astore. The pesticides cypermethrin, deltamethrin, and chlorpyrifos were analyzed using gas chromatography. The presence of cypermethrin in 10 samples was in a range 0.00 – 0.012 mg/kg, while the detection of Deltamethrin in 07 with variation from 0.000.12mg/kg. Whereas chlorpyrifos was found in 05 samples with the ranges of 0.00-0.0062 mg/kg. Residue level was quite higher in urban areas than rural areas. The multiparous women had prominent residues level than primiparas and the concentration of Deltamethrin was higher than other pesticides. All the pesticides residues levels in the breast milk of primiparous and multiparous mothers were within the permissible limits of WHO. Yet the women of these areas are not vulnerable but prolong exposure may pose a serious threat to neonatal and maternal health and other relevant reproductive issues. To manage the risk of milk contamination in the future, the demand for public awareness campaigns and the adoption of alternative clean approaches to control pests and other disease-spreading vectors in the best interests of public health seems reasonable.
Full tex
Activity Detection of Elderly People Using Smartphone Accelerometer and Machine Learning Methods
Elderly activity detection is one of the significant applications in machine learning. A supportive lifestyle can help older people with their daily activities to live their lives easier. But the current system is ineffective, expensive, and impossible to implement. Efficient and cost-effective modern systems are needed to address the problems of aged people and enable them to adopt effective strategies. Though smartphones are easily accessible nowadays, thus a portable and energy-efficient system can be developed using the available resources. This paper is supposed to establish elderly people\u27s activity detection based on available resources in terms of robustness, privacy, and cost-effectiveness. We formulated a private dataset by capturing seven activities, including working, standing, walking, and talking, etc. Furthermore, we performed various preprocessing techniques such as activity labeling, class balancing, and concerning the number of instances. The proposed system describes how to identify and classify the daily activities of older people using a smartphone accelerometer to predict future activities. Experimental results indicate that the highest accuracy rate of 93.16% has been achieved by using the J48 Decision Tree algorithm. Apart from the proposed method, we analyzed the results by using various classifiers such as Naïve Bays (NB), Random Forest (RF), and Multilayer Perceptron (MLP). In the future, various other human activities like opening and closing the door, watching TV, and sleeping can also be considered for the evaluation of the proposed model.
Full Tex
A Study of Awareness and Practices in Pakistan’s Software Industry towards DevOps Readiness
There are regular conflicts between the traditionally divided software organization i.e. dev and ops teams during the software development process for delivering the software to the end-user. DevOps overcome these conflicts by automating the processes between the development and operations team in such a way that they can build, test, and release the software successfully and efficiently to the end-user. Globally, more and more organizations are adopting DevOps. As Pakistan’s software industry is progressively growing while DevOps is a relatively new concept, there is a need for DevOps awareness and understanding towards its adoption and practices. This paper evaluated DevOps awareness and identified the practices adopted in Pakistan’s software organizations and suggested generic guidelines for DevOps transition. A questionnaire-based survey is conducted to collect data and various DevOps sub-activities being practiced. The survey analysis and results depicted that Pakistan’s Software Industry is making efforts towards the adoption of DevOps but due to lack of its awareness, most of the DevOps practices are not fully adopted yet. According to the DevOps evolution model, only one-eighth of Pakistan’s software organizations are at the self-service stage, while the rest of them are still struggling at the normalization and standardization stage.
Full Tex
Riverbank Erosion & Consequent Land Settlement Issues: A Case of River Chenab, District Hafizabad
When calamity strikes, it causes damage but it also provides opportunities for newer learnings opportunities and better preparedness to combat menace. Pakistan is agrarian economy and comprises fertile plains. According to Pakistan Bureau of Statistics, agriculture contributes to 24 percent of national Gross Domestic Product. Agriculture is dependent on water needs, met through water channels fed by rivers originating mostly from glacial sources existing in northern part of the country. The country hosts five major rivers, namely Indus Jhelum, Chenab, Ravi, and Sutlej. The dendritic river patterns follow gravity flow causing frequent morphological changes and riverbank erosion is the most significant phenomenon which acts as hazard for farming communities in terms of loss of shelter, livelihood, and landholdings. An in-time identification of the issue is the real concern nowadays. Presently, different tools are available for instant interpretation of riverbank erosion like Remote Sensing (RS) and Geographical Information System (GIS), which are not only good for instant identification but also helpful for precise estimation of historical losses. Landsat images for years 2009, 2013, and 2017 have used to make an initial assessment of erosion hotspots. High-resolution satellite imagery from Google Earth is also used for meticulous analysis. The analysis shows that beyond other factors, average riverbank displacement rate due to erosion directly depends on rise in water levels. The study provides systematic bases to estimate the losses precisely. The study is useful for damages assessment of land and livelihood to device relief packages for the affected communities. The study also builds the capacity in resolving land settlement issues consequent to the riverbank erosion phenomenon.
Full Tex