International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Novel Technique to Investigate Glacio-Fluvial Hypsometry in Hunza Using Local Indicator of Spatial Autocorrelation (LISA)
Get PDFHypsometric Integral (HI) displays the effect of active tectonics and sensitivity on geomorphic structures. In this study we calculated HI values for Hunza valley to investigate neotectonics, development of topographic structures and process of erosion using SRTM DEM 90m. ArcGIS and MATLAB is used to generate HI and hypsometric curve (HC). We generated HI and HC values by using D8 algorithm in MATLAB to extract drainage basins for 5 and 6 Strahler orders. HI and HC values show the stages of erosion for instance high values of HI and convex HC displays young and tectonically active stage. We used different grid sizes in ArcGIS to calculate maximum, mean and minimum elevation utilizing different statistical techniques. We used Local Indicator of Spatial Autocorrelation (LISA) instead of Global Moran Index to determine the extent of distribution of clustered, dispersed and randomized HI values. This technique indicates high positive z score for auto correlated data. Regions with high HI value indicate relative uplift, undissected and young structures while low HI values indicate sediment accumulation and shallow earthquakes.
Full Tex
LSM: A Lightweight Security Mechanism for IoT Based Smart City Management Systems using Blockchain
Get PDFSmart cities utilize digital technologies for the improvement of its services’ quality and performance by reducing resources’ cost and consumption, with a commitment of action and efficiency to its citizens. The increased urban migration has led to many problems in cities, such as traffic congestion, waste management, noise pollution, energy consumption, air pollution, etc., as nowadays COVID-19 pandemic has seized the whole world. So, it is necessary to carry out its standard operating procedures (SOPs), including less human interaction. Thus, technology plays a vital role via Internet-of-Things (IoT) based systems. In this paper, a lightweight security mechanism (LSM) is proposed to enrich the IoT based systems. Blockchain technology is integrated, and its completely decentralized peer-to-peer (P2P) technology enables the users’ authentication and authorizes legitimate procedures. The IoT based management system is developed to monitor some of the aforementioned problems and solve solid waste, air, and noise monitoring systems. The Ethereum blockchain is used to implement a smart contract based framework for the system’s security and access control. The evaluation of performance of the LSM demonstrates that it is an efficient and lightweight tool in terms of cost, resources, and computation and superior over related security studies.
Full tex
Estimated Zones of Saint-Venant Equations for Flood Routing with Over Bank Unsteady Flow in Open Channel
Get PDFIn this paper, we learn about the control of open channel water glide under the flood routing conditions. Generally, for flood routing in rivers, the Saint-Venant equations will be used which can be solved by finite distinction method. Saint-Venant equations will be converted into nonlinear equations and will be solved using the Preissmann scheme in the finite difference method. Using the Newton Raphson method, the set of equations will be changed into linear equations and will be solved by the space method. Our aims are to the estimated zones of Saint-Venant equations for flood routing by using the finite difference method with over bank unsteady flow in an open channel. The effectiveness of this method to optimize the choice of finite difference method is more accurate than other methods having adequate space and time steps.
Full Tex
Identifying the Causes and Protective Measures of Road Traffic Accidents (RTAs) in Bahawalpur City, Pakistan
Get PDFRoad Traffic Accident (RTA) is a growing public issue and fall among the four top causes of mortality and morbidity globally. The main objective of this study was to identify the causes and protective measures of road traffic accidents in Bahawalpur City. Primary data was gathered through a structured questionnaire during a field survey in selected five public places as sample sites i.e. Larry Ada, University Chowk, Bahawal Victoria Hospital (BVH), One Unit Chowk, and Melad Chowk. Secondary data of road accidents was gathered form National Highway and Motor Way Police (NH&MP) while primary data was gathered from 150 respondents (30 from each study site) and analyzed in SPSS software by applying descriptive statistics and road accident risk index (RARI). Findings revealed that the main causes of these accidents include increase in population (62.66%), increase in demand for vehicles (22%), bike drivers (69.33%), overtaking of the vehicles (51.33%), over speed and hustle to reach the destination (34.66%). One wheeling is also a major reason, which results in the death of teenage drivers (52%), violation of the traffic rules (25.33%). RARI results also suggest the relationship between the affected persons and the road traffic accidents. Lastly, few suggestions were proposed to overcome the ratio and severity of road traffic accidents because these accidents are predictable and largely preventable through multi-disciplinary coherent strategies.
Full Tex
Towards Skin Cancer Classification Using Machine Learning and Deep Learning Algorithms: A Comparison
Get PDFSkin cancer is an uncontrolled development of abnormal skin cells potentially due to excessive exposure to sun, history of sunburns, less melanin, Precancerous skin lesions, moles, etc. This occur when unrepaired DNA damages the cells of the skin. It is one of the diseases that are viewed on its quick evolution and the most common type of cancer that endangers life. Researchers have implemented several machine learning and deep learning techniques for classification of skin cancer. In this research paper, different cancer categories are classified using significant attributes. We have used International Skin Imaging Collaboration (ISIC) dataset for classification purposes. This dermoscopic attributes dataset includes 1000 images and 10016 instances, seven categories, 5 features and 2 Meta attributes. We implemented K-Nearest Neighbor, Logistic Regression, Convolutional Neural Network, Naïve Bayes, and Decision Tree for classification and compared their performance. In order to implement classification algorithm, we used Orange which is an open-source machine learning, data mining, and data visualization toolkit. The models are evaluated based on matrices that include Accuracy, C. Automation, F1 score, Precision, Recall, and AUC. Furthermore, frequency of features is visualized using graphical method and the ROC analysis is also performed for the classifiers. It is observed that CNN technique provided the highest accuracy of 89% and the mentioned results are the highest results of classification with the state of the art techniques. For future, the improved and recent dataset and ensemble modelling techniques based on deep learning can used to enhance classification results. The research can also be extended for other cancer types using CNN.
Full Tex
Effects of COVID-19 Pandemic on Food Chain and Poverty in Pakistan
Get PDFCOVID-19 pandemic has severely affected the food supply throughout the world. Pandemics affect the economy of nations badly but a number of countries were facing food insecurity even before COVID-19 pandemic. In this paper yearly data of food security is collected from the year 2015 to 2020 to inspect the consequences of poverty and COVID-19 pandemic through spatial regression analysis. The analysis shows that the food insecurity index has increased up to 33.5% by the year 2020 due to prevailing COVID- 19 pandemic. The Asian residents which are already living in developing countries have faced higher food insecurity between the years 2015 and 2018. The spatial regression analysis babbled that the discriminations like race, religion and creed doesn’t play any significant role in poverty and food insecurity. The primary factor of food insecurity is poverty. The poverty affected strongly during the years 2015 and 2018, the condition was worsened by the arrival of COVID-19 pandemic in 2020.
Full Tex
Evaluation of Catastrophic Global Warming due to Coal Combustion, Paradigm of South Asia
Get PDFCoal is a carbon containing non-renewable fossil fuel and one of the major contributors of climate change and global warming. We used TANSO FTS instrument in order to obtain the level of atmospheric carbon dioxide through datasets obtained from GOSAT satellite. GIOVANNI was also used to obtain atmospheric concentration of various gases. Burning of coal causes emission of greenhouse gases (GHG) and black carbon (BC) in atmosphere which are responsible for nearly 0.3°C of 1°C rise in temperature. The annual average value of carbon emission for the year 2010 and 2019 is 388.4 ppm and 409 ppm respectively. Since the pre-industrial times CO2 concentrations have increased up to100 PPM (36%) in the last two and a half centuries (250 years).In South Asia Dhaka has the worst quality of air as CO2 concentration (6.7%) is higher than the country’s GDP (5.25%) and energy consumption (4.77%). While an increasing trend GHG has been observed in Lahore up to 5.5 %. This study concludes that the high concentration of carbon dioxide in atmosphere is responsible for average rise of 1.2 °C temperature annually. This temperature rise can lead to adverse climatic conditions i.e., melting of glaciers which will consequently rise the sea level various landmasses may disappear by 2050.
Full Tex
SRTM DEM Based Neotectonics From Non-Linear Analysis: A Paradigm Through Fractal Analysis
Get PDFNeotectonics amend the river base and causes landscape erosion. This study explores the DEM based differentiation of neotectonics in the northern regions of Pakistan. This method involves vertical and non-linear dissection base on digital evaluation method. This study uses Gliding Box Technique (GBM and GBT) and Box Counting method to evaluate Lacunarity (LA), Succolarity (SA) or 3-Fractals, and Fractal Dimensions (FD). 3-fractals are an attribute used for the recognition of spatial patterns, specifically to compute and differentiate natural textures including natural patterns. This study also investigates vertical dissection using DEM SRTM having spatial resolution of 90m. DEM SRTM measures surface area, plane area as well as the surface ratio. The vertical areas are investigated to make dissection maps and to identify the affects of neotectonics on the roughness of surface. Low value of surface roughness indicates flattened drainage basins and inclination of slope. The Raikot Fault shows higher values of surface roughness towards NE- SW. The surface roughness is mapped to recognize relative uplifts, uneven regions, depressions and pits. Analysis through non-linear method identifies the regions affected by neotectonics activity. Tectonics activity causes deformation and instability in drainage networks.
Full Tex
Monitoring of Mangrove Cover of Western Indus Delta Karachi Pakistan
Get PDFThe coastline of Pakistan comprises of five significant sites comprising of mangroves including Indus Delta which contains extensive mangroves zones and termed as the largest arid mangrove found globally. This study evaluate the current extent of mangroves along the Western edge of Indus Delta and provide the most recent forest cover assessment of mangroves. Moreover, this study identifies the changes occurred in forest cover from the years 2000 to 2020. Landsat 5 Thematic Mapper (TM), 8 Operational Land Imager (OLI) and Landsat 7 ETM data were used for mangroves mapping through supervised classification method. The results displayed that total area of mangrove forest cover was nearly 279.094km², 395.77km², 306.58km² in the years 2000, 2010 and 2020 respectively. This study indicates an increase in area of mangrove cover from 29% to 41% from the year 2000 to 2010. Regeneration of mangrove mostly took place around the southern region of the Indus Delta. The mangrove specie has decreased from 41% to 31% from the year 2010 to 2020. The major causes of this reduction were urban water and industrial pollution, over-fishing in Indus delta, freshwater diversion for agriculture, and overharvesting of mangroves by the local communities, coastal erosion and sedimentation.
Full Tex
Heart Attack Risk Prediction with Duke Treadmill Score with Symptoms using Data Mining
Get PDFThe healthcare industry has a huge volume of patients’ health records but the discovery of hidden information using data mining techniques is missing. Data mining and its algorithm can help in this situation. This study aims to discover the hidden pattern from symptoms to detect early Stress Echocardiography before using Exercise Tolerance Test (ETT). During this study, raw ETT data of 776 patients are obtained from private heart clinic “The Heart Center Bahawalpur”, Bahawalpur, South Punjab, Pakistan. Duke treadmill score (DTS) is an output of ETT which classifies a patient’s heart is working normally or abnormally. In this work multiple machine learning algorithms like Support Vector Machine (SVM), Logistic Regression (LR), J.48, and Random Forest (RF) are used to classify patients’ hearts working normally or not using general information about a patient like a gender, age, body surface area (BSA), body mass index (BMI), blood pressure (BP) Systolic, BP Diastolic, etc. along with risk factors information like Diabetes Mellitus, Family History, Hypertension, Obesity, Old Age, Post-Menopausal, Smoker, Chest Pain and Shortness Of Breath (SOB). During this study, it is observed that the best accuracy of 85.16% is achieved using the Logistic Regression algorithm using the split percentage of 60-40.
Full Tex