Innovative Computing Review

Tree-Based Learning Models for Botnet Malware Classification in Real World Sub-Sample Dataset

2024-03-20T09:04:11+00:00

The use of machine learning techniques for botnet detection has been an active area of research in security field for some years now. Some of the past machine learning-based botnet detection studies used datasets that were generated synthetically. The release of a large and real-life botnet dataset, named CTU-13, allowed researchers to build machine learning-based models from real-world data. In fact, the real-life traces in the dataset makes it more promising for being used for botnet identification studies. The current study proposed the use of a single tree-based learning algorithm in the classification of botnet evidence from sub-sampled portion of three captures in CTU-13 dataset. Random sub-sampling was used to arrive at three different datasets that was used in the study. The first step in the methodology involved experimental analyses on three captures out of thethirteen in the whole dataset. The analyses revealed the basic characteristics of the datasets which further guided the study further. The missing values and categorical data types in the dataset were handled through mixed imputation and feature encoding, respectively. The big data nature of the dataset was handled through random sub-sampling technique with a view to building a botnet detection model that is less computationally intensive. The random sub-sampling technique was used without changing the data distributions in thedataset. The botnet detection models were built by using decision-tree algorithm from the three sub-sampled dataset captures. The performances of the models were evaluated by using accuracy, precision, recall, and f1-score, respectively. In all, the model built with scenario5 capture slightly performed better than the ones built using scenario 6 and scenario 7 captures, respectively.

Nourishing the Future: AI-Driven Optimization of Farm-to-Consumer Food Supply Chain for Enhanced Business Performance

2024-03-20T09:07:26+00:00

Efficiency and sustainability are upending the global food supply system. The current study examined the relationship between Artificial Intelligence (AI) and agriculture to optimize food supply chain from farm to consumer business model. The study examined how AI-driven solutions may boost efficiency, reduce waste, and promote environmental responsibility with an emphasis on sustainability. The food supply system faces resource depletion, climate change, and growing global food consumption. AI technologies, such as automation, data analytics, and machine learning may solve these issues. AI systems use real-time data, predictive analytics, and intelligent logistics to improve production, distribution, and consumption. This reduces food production and transportation of carbon emissions along with improving resource allocation. AI-powered precision agriculture helps the farmers to increase crop yields while lowering fertilizer and pesticide use along with supporting sustainable farming as well. IoT devices and sensor networks are helpful to improve livestock management and crop monitoring, enabling data-driven agriculture. The current study highlighted how AI ensures food quality and safety across supply chain. By identifying impurities, monitoring storage conditions, and forecasting shelf life, AI-powered quality control systems may decrease food wastage and ensure safe, high-quality goods. In conclusion, AI-agriculture integration is an innovative way to increase farm-to-consumer food supply chain efficiency and sustainability. AI technology may help the supply chain stakeholders to create resource-efficient, environmentally friendly food production that meets the needs of a growing population. The current study discussed food industry sustainability and AI uses in agriculture, as well as future possibilities and challenges.

E-Satisfaction of Pakistani e-NADRA Website Using System Usability Scale (SUS) Evaluation

2024-03-20T09:08:43+00:00

The current study attempted to evaluate how customers perceive and interact with the 'Pak identity service' offered by the “National Database and Registration Authority” (NADRA). The study specifically aimed to assess the citizens' opinions about the lately introduced e-government service, Pak-identity, in terms of its user-friendliness, adaptation, and artistry. A quantitative approach was employed by using a questionnaire-based survey in order to identify the factors that influence customer e-loyalty. This approach helps to gain insights into how citizens perceive and behave towards this service. The study collected responses from a sample of 25 individuals through random sampling technique to ensure that it aligns with the study's objectives. Additionally, certain measures were taken to ensure the credibility and validity of the scale used in this research. The current study holds a unique position in the context of evaluating e-services in the country. It focused on the attributes related to the quality of web services provided to citizens, with the ultimate goal of enhancing their adoption and acceptance within society.

Textual vs Visual Representation- Role of Aesthetics in Human Cognition and Perception

2024-03-20T09:09:42+00:00

Visual representation is better as compared to textual representation in every aspect, either for a code or for the design of a software product. Writing a code using different programming languages in textual form is quite difficult as compared to a visual representation of code. The current study proved this phenomenon by presenting different codes in three different representations. These representations include textual, algorithm,
and flow graph. On the basis of observation and analysis of the current study, these three representations were examined. It was concluded that visual representation is the best way to present a code according to many parameters. These results are helpful in the recent switch towards low programming from high programming. Moreover, further research can be conducted on how large enterprise applications code can be created by using visual programming languages.

Sentiment Analysis of Roman Urdu Text Using Machine Learning Techniques

2024-03-20T09:11:02+00:00

Social media has attained popularity during the last few decades due to the rapid growth of online businesses and social interaction. People can interact with one another and communicate their sentiments by expressing their ideas and points of view on social media. Businesses involved in manufacturing, sales, and marketing increasingly focus on social media to get feedback on their goods and services from people worldwide. Businesses must process and analyze this feedback in the form of sentiments to gain business insights. Every day, millions of Urdu and Roman Urdu sentences are posted on social media platforms. The critical loss of this massive amount of data results from ignoring the thoughts and opinions in language with limited resources, such as Urdu and Roman Urdu in the favor of resource-rich languages, such as English. The current study focused on sentiment analysis of Roman Urdu text. Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) word embedding techniques were deployed to conduct the current study. Support Vector Machine (SVM), Linear Support Vector Machine (LSVC), Logistic Regression (LR), and Random Forest (RF) classifiers were deployed. The experiments showed that SVM showed 94.74%, while RF showed 93.13% accuracy using BoW word embedding technique