International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Comparison of Machine Learning Algorithms for Sepsis Detection
Get PDFSepsis is a very fatal disease, causing a lot of causalities all over the world, about 2, 70,000 die of Sepsis annually, thus early detection of Sepsis disease would be a remedy to prevent this disease and it would be a big relief to the family of sepsis patients. Different researchers have worked on sepsis disease detection and its prediction but still the need to have an improved model for Sepsis detection remains. We compared various machine learning algorithms for Sepsis detection and used the dataset publicly available for all the researchers at Physionet.org, the dataset contains many empty or Null values, we applied backward filling and forward filling techniques, and we calculated missing values of MAP using equation (1) which gives more precise results, we divided the 40,336 files of datasets A and B into 80% training set and 20% testing set. We applied the algorithms twice one time using vital signs and clinical values of patients and the second time using only vital signs of the patients; using vital signs only the training accuracy of KNN, Logistic Regression, Random Forest, MLP, and Decision Trees was 0.992, 0.999, 0.981, 0.981, and 0.981 respectively, while the testing accuracy of KNN, Logistic Regression, Random Forest, MLP, and Decision Trees was 0.987, 0.980, 0.983, 0.981, and 0.981 respectively, for Sepsis Label 0, the value of precision for KNN, Random Forest, Decision Trees, Logistic Regression, and MLP was 0.99, 0.98, 0.98, 0.98, and 0.98 respectively, while the value of recall for KNN, Random Forest, Decision Trees, Logistic Regression, and MLP was 1.00, 1.00, 1.00, 1.00, and 1.00 respectively; the comparison of all the above-mentioned algorithms showed that KNN leads over all the competitors regarding the accuracy, precision, and recall.
Full Tex
Detecting Aphid Concentration in Wheat Leaf Using Remote Sensing and GIS
Get PDFWheat lies among the most prominent cereal crop of Pakistan which has a significant role in the stability of Pakistan’s economy. Certain biotic and a biotic factors including agro-climatic conditions, rainfall, lack of irrigation infrastructure and conventional agricultural methods are raising the risk of aphid attacks. The current study utilized satellite imagery for obtaining thermal datasets of complete wheat growth. Results revealed that rainfall is a significant parameter for the determination of aphid growth on wheat plant. A region receiving 0-10 mm rainfall, supported the growth of aphid. Moreover, the aphid survival was highly supported at a moderate temperature ranging between 20-25 oC with relative humidity ranging from 70-75 %. The study also revealed the production of weed in wheat crop acted as a moistrizing agent which consequently provided favorable conditions to the aphid population for growth. Inapropriate usage of fertilizers increased the nitrogen content in soil which turned to be favourable for the aphid attack. Thus, the study concludes that agro-climatic conditions must be considered before the aplication of pesticides.
Full Tex
Analysis of Code Vulnerabilities in Repositories of GitHub and Rosettacode: A comparative Study
Get PDFOpen-source code hosted online at programming portals is present in 99% of commercial software and is common practice among developers for rapid prototyping and cost-effective development. However, research reports the presence of vulnerabilities, which result in catastrophic security compromise, and the individual, organization, and even national secrecy are all victims of this circumstance. One of the frustrating aspects of vulnerabilities is that vulnerabilities manifest themselves in hidden ways that software developers are unaware of. One of the most critical tasks in ensuring software security is vulnerability detection, which jeopardizes core security concepts like integrity, authenticity, and availability. This study aims to explore security-related vulnerabilities in programming languages such as C, C++, and Java and present the disparities between them hosted at popular code repositories. To attain this purpose, 708 programs were examined by severity-based guidelines. A total of 1371 vulnerable codes were identified, of which 327 in C, 51 in C++, and 993 in Java. Statistical analysis also indicated a substantial difference between them, as there is ample evidence that the Kruskal-Wallis H-test p-value (.000) is below the 0.05 significance level. The Mann-Whitney Test mean rank for GitHub (Mean-rank=676.05) and Rosettacode (Mean-rank=608.64) are also different. The novelty of this article is to identify security vulnerabilities and grasp the nature severity of vulnerability in popular code repositories. This study eventually manifests a guideline for choosing a secure programming language as a successful testing technique that targets vulnerabilities more liable to breaching security.
Full Tex
Empirical Assessment for the Domestic Worker Housing: A Case Study of Lahore
Get PDFA house is considered a basic human need. It provides identity, security, belonging, and privacy. Regrettably, Pakistan is facing a housing backlog of almost 10 million units. This research aims to diagnose the problems related to accommodation that domestic workers are facing and to assess the pragmatic options for housing the labor class groups. Data for this research was collected from the residents, domestic workers, and relevant authorities through a structured questionnaire survey in selected case study areas. The dependent variable in the study is the provision of accommodation to the domestic workers, which needs to be calculated. The predictors or independent variables are affordability of domestic workers’ residence, salary, housing provision, financial status, and role of government. The results reveal that when “provision of housing allowance” to the domestic workers will help in overcoming the problem of housing available to the workers Its value goes up by 1, “provision of residence to domestic workers at nearby places” increases by 0.518 Similarly, “provision of nearby residence increases the work efficiency” goes up to 1, “provision of residence to domestic workers at nearby places” goes up by the value 0.118.
Analysis revealed that workers’ work efficiency depends upon, Government and financial support from the people. The findings of the study/research analysis revealed that most domestic workers are being deprived of livable housing and have to bear significant travel expenses to reach their workplaces. There is a dire need to form a government-based strong association for the domestic worker which would work for the betterment of domestic workers to improve their quality of life. The government and private developers should increase the supply of low-income housing in the form of vertical growth development. It can be pertinent to propose that housing opportunities have to be placed close to the vicinity of workplaces to reduce the travel cost bear by domestic workers
Assessment of Water Stress in Rice Fields Incorporating Environmental Parameters
Get PDFRice is considered as a major crop due to its demand globally. Pakistan is famous throughout the world to produce export quality rice which have healthy contribution in boosting the regional economy. Rice plant require plenty of water for its proper growth and development therefore, water conservation is significant to maintain water reserves for a sustainable future. The main objective of this study was to identify day-to-day availability of water in rice fields from Germination to Ripening (GTR) using Carnegie Ames Stanford Approach (CASA) model. CASA model incorporates real-time parameter e.g., temperature, pressure, extraterrestrial radiations, Leaf Area Index (LAI), vapor pressure and sunshine hours to compute net-shortwave radiations (Rns), net-longwave radiations (Rnl), net-radiations (Rn), actual incoming radiations (Rso), sensible heat flux (H), ground heat flux (Go) and finally the water stress (W). The averaged values of Rn, Rso, Rns, Rnl and H were computed as 206, 319, 178, 34 and 124 (wm-2) respectively for GTR. Total expected sunshine hours were 1584h but we could receive only 874 h during GTR due to “off and on” cloud activity. LAI and Go were observed in inverse relation to each other.
Full Tex
Natural Language to SQL Queries: A Review
Get PDFThe relational database is the way of maintaining, storing, and accessing structured data but in order to access the data in that database the queries need to be translated in the format of SQL queries. Using natural language rather than SQL has introduced the advancement of a new kind of handling strategy called Natural Language Interface to Database frameworks (NLIDB). NLIDB is a stage towards the turn of events of clever data set frameworks (IDBS) to upgrade the clients in performing adaptable questioning in data sets. A model that can deduce relational database queries from natural language. Advanced neural algorithms synthesize the end-to-end SQL to text relation which results in the accuracy of 80% on the publicly available datasets. In this paper, we reviewed the existing framework and compared them based on the aggregation classifier, select column pointer, and the clause pointer. Furthermore, we discussed the role of semantic parsing and neural algorithm’s contribution in predicting the aggregation, column pointer, and clause pointer. In particular, people with limited background knowledge are unable to access databases with ease. Using natural language interfaces for relational databases is the solution to make natural language to SQL queries. This paper presents a review of the existing framework to process natural language to SQL queries and we will also cover some of the speech to SQL model in discussion section, in order to understand their framework and to highlight the limitations in the existing models
Report Generation of Lungs Diseases From Chest X-ray using NLP
Get PDFPulmonary diseases are very severe health complications in the world that impose a massive worldwide health burden. These diseases comprise of pneumonia, asthma, tuberculosis, Covid-19, cancer, etc. The evidences show that around 65 million people undergo the chronic obstructive pulmonary disease and nearly 3 million people pass away from it each year that make it the third prominent reason of death worldwide. To decrease the burden of lungs diseases timely diagnosis is very essential. Computer-aided diagnostic, are systems that support doctors in the analysis of medical images. This study showcases that Report Generation System has automated the Chest X-Ray interpretation procedure and lessen human effort, consequently helped the people for timely diagnoses of chronic lungs diseases to decrease the death rate. This system provides great relief for people in rural areas where the doctor-to-patient ratio is only 1 doctor per 1300 people. As a result, after utilizing this application, the affected individual can seek further therapy for the ailment they have been diagnosed with. The proposed system is supposed to be used in the distinct architecture of deep learning (Deep Convolution Neural Network), this is fine tuned to CNN-RNN trainable end-to-end architecture. By using the patient-wise official split of the OpenI dataset we have trained a CNN-RNN model with attention. Our model achieved an accuracy of 94%, which is the highest performance.
Full Tex
Computer Malware Classification, Factors, and Detection Techniques: A Systematic Literature Review (SLR)
Get PDFA Systematic Literature Review (SLR) was conducted using tailored searches based on our study topic. We completed all SLR processes, including periodic reviews as SLR. Researchers may find out about the justification, the review procedure, and the research question by using search keywords. This paper describes the trial approach to elaborate the search keywords, resources, restrictions, and validations that were, and explores search strategies made. The reviews are carried out by assessing the publication\u27s quality, devising a data extraction approach, and synthesizing the results. All four research questions were used to analyze the papers concerning the findings. Finally, reports on the categorization of computer malware were analyzed for their detection methods, factors, and how they infiltrate computer systems have been published. SLR identifies the element, characteristics, and detection techniques that are explained in this research paper. Computer malware infects the computer system. This comprehensive literature review\u27s is mainly based on recommendations by earlier studies
Development of Autism Spectrum Disorder Scale and its Psychometric Properties
Get PDFAutism spectrum disorder scale was developed for the use of diagnoses purpose of autism. This scale is consisting of 15 items in Pakistan’s indigenous language Urdu. Most autism assessment tools are available in English and were developed by Western cultures; however, when those tools are used in different cultures, biased results can be evident. So, a culture-friendly tool was dire need to be developed. A scale was developed and administered to individuals (N=143) with autism using standard procedures from item pooling to standardization of scale. The sample was selected from different cities in Pakistan through a convenient sampling technique. Rotated component matrix analysis, factors loading, sample adequacy KMO and CFI tests were performed using SPSS and AMOS. The convergent validity test demonstrated that there is a significant correlation (r=0.81, p=.00) at the 0.01 alpha level with CARS on the sample of n=50. The indigenous scale also confirmed good test-retest reliability (r=0. 950, p=.000) at a 0.01 alpha level, which indicated that the scale is a valid and reliable measure for diagnosing individuals with an autism spectrum disorder. This scale can be used by researchers, psychologists, and psychiatrists for the general population to measure the prevalence and for diagnosis
Development and Psychometric Properties of Harassment Tendency Scale
Get PDFThe aim of this research was to construct a native scale for harassment tendency and psychometric properties for the assessment of the Harassment tendency scale according to the cultural perspective of the Urdu language used. This indigenous scale can be used by psychologists, psychiatrists and even researchers for the general population to measure the tendency of harassment among males and females as well. Utilizing existent content and information from the literature research, the initial item pool of 150 items were created. Following the pilot research, 12 of the 138 expert-evaluated items were kept, including the eight aspects of harassment. Additionally, data from the sample of (N=340) people who completed this scale\u27s final administration were gathered. Participants from educational institutions and local communities from different areas of Pakistan by using a self-reported questionnaire through convenient sampling. Rotated component matrix analysis shows, factors loading ranges from 0.402 to 0.641 of 97 items. The sample adequacy showed KMO=0.866 on 27 items (N=340) and factor loading loaded 8 factors. CFI value 0.909 with the significant model fit p<0.05 with appropriate model fit indices. HTS also conformed to good test-retest reliability (r=0.954, p=.000) at a 0.01 alpha level which is indicated the scale is a reliable measure for harassment tendency. A scale to measure Harassment tendency in the Urdu language is competently established with 27 questions and eight factors. Statistical Package for the Social Science volume 24 used for EFA (Exploratory Factor Analysis). AMOS (Analysis of a Moment structure) version 24 was used for CFA (Confirmatory Factor Analysis)