International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Sentiment Classification Using Multinomial Logistic Regression on Roman Urdu Text
Get PDFSentiment analysis seeks to reveal textual knowledge of literary documents in which people communicate their thoughts and views on shared platforms, such as social blogs. On social blogs, users detail is available as short comments. A question of sentiment analysis has been raised by information across large dimensions published on these blogs. Although, some language libraries are established to address the problem of emotional analysis but limited work is available on Roman Urdu language because most of the comments or opinions available online are published in text-free style. The present study evaluates emotions in the comments of Roman Urdu by using a machine learning technique. This analysis was done in different stages of data collection, labeling, pre-processing, and feature extraction. In the final phase, we used the pipeline method along with Multinomial Logistic Regression for the classification of the dataset into four categories (Politics, Sports, Education and Religion). The whole dataset was divided into training and test sets. We evaluated our test set and achieved results by using Precision, Recall, Accuracy, F1 Score and Confusion Matrix and found the accuracy ranging to 94%.
Full Tex
Marek’s Disease and Its Outbreak in Asia: Python-Based Approach for Detection of Marek’s Virus
Get PDFMarek\u27s disease is an infectious disease that manifests in tumors of the nervous system and organs in chickens. Computer programming languages have enough potential to detect various viral diseases. An effort has been made to detect and evaluate the intensity of viruses. Despite the widespread use of effective vaccines designed to halt its spread, recent data reveal that their efficacy is declining as a result of the virus\u27s adaptability. We analyzed 53 reports documenting 157 viral strains in Asian countries during the last decade of Marek\u27s disease outbreaks and correlated meq sequences. The visceral variety of Marek\u27s disease is the most common (18 out of 28 investigations), although there may be other, unrecognized brain alterations as well. Most commonly, MD causes tumors in the liver (16 out of 26 studies), however, other organs such as the spleen, kidney, heart, gizzard, skin, gut, lung, and sciatic nerve have also been affected. Using amino acid alignment, we found numerous point alterations in 28 strains that may be associated with its virulence. More research is needed on the virulence of the Marek strain, as well as the structural modifications to the Meq protein, and we recommend that this research take place in disease-endemic areas
Impact Assessment of Commercialization of Main Roads in Planned Housing Schemes: A Case Study of PIA Housing Scheme
Get PDFThe phenomenon of commercialization of residential properties is taking place rapidly. Although conversion of landuse from residential to commercial in built-up areas is not new in developing countries but planned housing schemes also start experiencing this land-use conversion, and now are no more predominantly residential. Furthermore, declaring a road commercial by the competent authorities, even without taking necessary improvements in infrastructure and consent of the community, further exaggerate the problem. The negative consequences of this phenomenon have a severe effects on residential areas and include environmental problems, traffic congestion, noise, and air pollution, and affect the residential character of the area in negative manner for which they were initially developed. The aim of the study is to describe briefly about remits of commercialization polices in Lahore and then to assess the functionality of commercialized residential roads through assessment criteria based upon the indicators established to assess capacity of road infrastructure before declaring it commercial. This includes road management plan, details of road network with condition of road, its width, Pedestrian and Public transport facilities, structure, including the primary, mixed-use, and secondary nodes. Perception of the users and residents regarding the change in the use of land is also weighed up. The findings of this research will draw the attention of responsible authorities to improve the design guidelines, which are essential to consider before commercializing the residential roads
Sales Prediction of Cardiac Products by Time Series and Deep Learning
Get PDFMaintaining inventory level to avoid high inventory costs is an issue for Cardiac Product Distribution Companies (CPDCs) because of the shortage of their products which affect their sale and causes loss of the customer. This research aims to provide a method for predicting the upcoming demand of the Balloon and Stents by using time series analysis (Auto Regression Integrated Moving Average) and Deep learning (Long-Short Term Memory). To conduct this research, data was collected from Pakistan’s leading cardiac product distributors to determine the method\u27s performance. The findings were compared using Mean absolute error (MAE) and Root Mean Square Error (RMSE). Resulst conclude that the ARIMA algorithm successfully forecasts cardiac products sale
Role of Geospatial Technology in Crime Mapping & Analysis: A Case Study of District Kasur, Punjab, Pakistan
Get PDFCrime is a social stigma that needs to be addressed beyond talks. The use of geospatial information technology has become well recognized within the fields of forensic sciences and criminology, especially in the developed world. The current study is an attempt to analyze the distribution and trends of various crime types, including rape, murder, baby kidnapping, vehicle theft, and dacoity in district of Kasur Punjab, Pakistan during the year 2021. (Police station wise crime data) was collected from the District Police Office (DPO), Kasur and interpolation technique was applied and several maps were generated, including crime type, crime rate, and crime density with in study area and statistical illustrations were down users Microsoft Excel software suite. Murder crimes were found highest in the vicinity of Sadar Kasur police station whereas lowest in the vicinity of City Pattoki police station. Alla abad police station reported the highest rape crimes, whereas the lowest crime rate was found in the jurisdiction of Theh Sheikham. Kidnapping were highest in Sadar Kasur and Kot Radhakishen police stations’ vicinity, while it was found to be the lowest in the The Sheikham police station’s jurisdiction. Ganda Singh Wala, Kangan Pur, and Sadar Chunian had the lowest number of vehicle theft, whereas the city Pattoki and Sadar Kasur police stations recorded the highest dacoity crime. The present study suggests that the use of geospatial technology within the study area and beyond by the law enforcement departments can effectively enhance crime control and can help to maintain law and order situations
Charging Stations Distribution Optimization using Drones Fleet for Disaster Prone Areas
Get PDFA disaster is an unforeseen calamity that causes damage to property or brings about a loss of human life. Quick response and rapid distribution of vital relief items into the affected region could save precious lives. In this regard, disaster management comes into play, which is highly dependent on the topography of the disaster-hit area. If the disaster-hit area has little or no road connectivity, the use of drones in such areas becomes essential for the delivery of health packages. Since the battery capacity of the drone is limited, there is a need of charging stations that should be transported using road infrastructure and pre-installed in disaster-prone areas, as access to these areas may be denied once the disaster hits. In this article, a simulation model was used to optimize the number and location of drone charging stations for deployment in a disaster-prone area in the pre-disaster scenario, aiming at the distribution of relief items to disaster-hit areas in the post-disaster scenario. We consider the relative priority of locations where a preference is given to the locations that have higher priority levels. An optimal number of charging stations and optimal routes have also been determined by using our optimization model. To illustrate the use of our model, numerical examples have been simulated for different sizes of the disaster-hit area and the number of targets. In our numerical simulation, it was observed that the drone\u27s maximum distance capacity is the key factor in determining the optimal grid size, which directly correlates to the number of charging stations.
Sun Tracking and Control Design for PV Solar energy system
Get PDFIn this modern era of the rapid increase in population, a high rise in technology, and a large number of machinery installed, fuel demand has increased significantly. Non-renewable energies contribute a lot to producing energy worldwide, and that\u27s why they are decreasing at an alarming rate. As an alternative, renewable energies have a high potential to solve this upcoming issue. In this paper, sunlight is utilized for the location of Islamabad, and an active solar tracker is designed. The objective is to develop a cost-effective system with low maintenance requirements. The tracking mechanism is modeled by two sensors, LDR and PV sensor. LDR sensor generates high resistance when light is incident on them, thus reducing the voltage production. PV sensors produce a voltage when sunlight is incident on them, and a voltage drop occurs if a shadow occurs. A thin plate between two LDR sensors or two PV sensors will cast a shadow according to the sun\u27s position. It will create a voltage difference between the two sides, thus causing the system to track the sun. For smooth movement, a servomotor is an effective choice. The system is integrated with a microcontroller for a feedback system of output; Arduino Uno will regulate the uniform and accurate movement of the system. The research on azimuth and elevation angles for the location of an installment is also included in this paper. Different tests are performed for comparative study for both sensors to have performance analysis
Inventory and Altitudinal Distribution of Plant Biodiversity Along the Nalter Expressway in Nalter Valley Gilgit Baltistan
Get PDFThe present study was conducted in 2020-2021 to record the inventory and altitudinal distributions of plants and biodiversity in Nalter valley. The study area is situated at 36 N and 74 E, with 27,206 ha area in the Karakoram highlands. It is 40km away from Gilgit city. The purpose was to explore the natural floral inventory, life-form structure, and the biological spectrum of the plant biodiversity. This study recorded 126 species belonging to 106 genera and 48 families. The life forms of the collected species were 40 Hemicryptophytes (H), 8 Therophytes, 50 Chaemephyte, and geophytes 3 species, and 25 phanerophytes. While the habit categories of the recorded flora were analyzed with the help of Theophrastus classification. The categories of the recorded flora were 88 herbs, 113 shrubs,9 subshrubs, and 18 trees which contribute to the flora of the study area. The phytosociological studies were also carried out to recognize the dominant taxa, habit category, and the dominant life form in the study area. For this study, we divided the study area into three stands. In each stand, we placed 20 quartets to recognize the dominant taxa based on IVI. The phytosociological studies provided the required information from each stand like dominant habit categories, life forms, and dominant taxa along the Nalter expressway
Psychosocial Factors as the Determinants of Relapse in Individuals with Substance Use Disorder
Get PDFRelapse to substance abuse after withdrawal is one of the most perplexing and frustrating aspect of addiction. The word relapse defines as collapse/hindrance to the client’s prior substance dependence behavior after treatment due to many psychological, social, and other associated factors. This study is designed to find out the psychological and social factors which determine relapse behavior in individuals with substance use disorder. A cross-sectional study was conducted among 200 relapse patients from November 2020 to January 2021 in different rehabilitations in Wazirabad, Gujranwala, Lahore, Gujrat, and Sialkot cities of Pakistan. Data were collected by using a psychosocial functioning scale. Data analyzed using SPSS 21. A total of 200 individuals were taken ,of which 170 were males and 30 females. The results indicates that the most important predictor was risk-taking 0.148 (100% of normalized importance) followed by social conformity 0.130 (88% of normalized importance), decision making confidence 0.128 (86.2% of normalized importance), childhood problem 0.125 (84.4% of normalized importance), hostility 0.125 (84.0% of normalized importance), depression 0.119 (80.5% of normalized importance), self-esteem 0.114 (76.6% of normalized importance) and anxiety 0.111 (74.7% of normalized importance).Social factors were connected with a high relapse rate. These results may help clinicians to improve treatment and policy guidelines for the prevention of relapse to drug addiction
