The trend of bicycle exercise during the pandemic has resulted in increased sales and even scarcity of bicycle stock in some shops. The phenomenon has raised attention from both the bicycle industry and government to provide necessary responses toward the trends. Even though it is a trend, many prospective buyers are still confused about their choices. The types of bicycles that sell the most on the market are folding bikes, mountain bikes, and racing bikes. The research data were collected from 242 bicycle users who came from various bicycle communities in major cities of Java Island, Indonesia. Some of the predictors used were age, gender, height, weight, and cycling speed. The target variable is the type of bicycle whose data is categorical. Predictor variables consist of nominal and ordinal variables, so preprocessing needs to be done using Python's Sklearn library. To test the accuracy of the model, the data was broken down into training data and test data with a test size of 20%. Several methods are used to form a classification model, including K-NN, Naive Bayes, Support Vector Machine, Decision Tree, and Random Forest. The results of the classification model evaluation show that the Support Vector Machine and Decision Tree have the highest accuracy of 90%, while Naive Bayes has the lowest accuracy of 73%. The model formed can be a predictive tool for potential bicycle buyers in order to be able to choose the right type of bicycle.

This paper presents an intelligent tutoring system as seen to be successful in assisting in the instruction of basic skill, particularly, reading comprehension. The goal of the study is to develop an Intelligent Tutoring System that will greatly help the Grade 7. The system adapted considerable instructional needs of learners from early development to advanced reading comprehension skills. The developed system provided an immediate feedback to learners upon completion of an activity without requiring intervention from a Teacher. To improve the system, learners and teachers filled out survey questionnaires. The result reveals that teachers and students want the system to be user-friendly, have a user log-in, lesson content with text, audio and video as well as various types of questions in quizzes. They also perceived that the developed ITS is useful and the content is valid thus is very acceptable to be utilized by the learners. In addition, result reveals that student’s reading comprehension could be improved and developed by the proposed ITS.

An election is a formal procedure through which a group of individuals decides on an individual or multiple individual to be in a position of authority using mechanical, paper-based and electronic methods. Despite the measures to secure the voting systems from fraudulent activities among corrupt politicians and election officers, attackers have been compromising the security measures thereby, providing illegitimate opportunities for unwanted contestants to win elections. This research was on the development of an electronic voting system using fingerprint and visual semagram techniques. The proposed e-voting model had six modules for effectiveness in the e-voting system. It was implemented using Java in Android Studio and C-Sharp (C#) in Microsoft Visual Studio, and was tested in an official deanship election of five faculties in a tertiary institution. Every illegible staff was enrolled and presented with a voter identification number (VIN) card. The voter's fingerprint and VIN were the fundamental credentials required for authentication and to poll a legitimate vote to a preferred contestant at a designated polling centre. The sensitive results were firstly encrypted and secondly concealed in an image to produce "Vimago" using the visual semagram technique. The "Vimago" was subjected to steganalysis and concealed results were not detected. An Equal Error Rate of 0.0019, a sensitivity of 0.9962 and an accuracy of 99.81% were obtained from the experiment. Based on the experimental results, the proposed e-voting model is highly recommended for use by various electoral commissions for voting and security agencies for the dissemination of sensitive information through the public network, the manufacturers of electronic voting machines are hereby offered a model for use in the development and securing of a fingerprint-based platform for a voting system were made among other recommendations.

The internet was basically designed for the static nodes, but with the development of mobile nodes such as smart phones, that have wireless capabilities, the first design was insufficient. MNs change their point of attachment while they are roaming (traveling) in the internet, to maintain the survival of ongoing sessions for these mobile nodes, the internet requires techniques for managing mobility.. Currently, there are two types of mobility management protocols, host-based protocols and network-based protocols, the involvement of MN in the mobility process is must in the first type, while is unnecessary in the second type. The IETF standardized the Proxy Mobile IPv6 (PMIPv6) protocol in 2004, to overcome the limitations experienced by the host-based protocol, Mobile IPv6 (MIPv6) such as sub-optimal routing, handover latency, packet loss and single point of failure, however, the biggest drawback of PMIPv6 is the lack of inter-domain handover. This paper provides an efficient scheme based on standard PMIPv6 called (E-PMIPv6) to support inter-domain handover by introducing a new entity called (GLMA) which enables MN to traverse different domains while keeping the ongoing sessions, additionally; we use buffering techniques to preemptively lighten packet losses. The ultimate goal for the suggested scheme is to solve the scalability problem for the PMIPv6 and it is extensions to encourage network operators to deploy E-PMIPv6 for large networks. Results of preliminary analysis of handover latencies and related packet losses favored (E-PMIPv6) over two of the leading contenders.

Named Entity Recognizer (NER) is a widely used method of Information extraction (IE) in Natural language processing (NLP) and Information Retrieval (IR) aimed at predicting and categorizing words of a given text into predefined classes of Named Entities like a person, date/time, organization, location, etc. This paper adopts boosting NER for Afaan Oromo by using multiple methods. Combinations of approaches such as machine learning, the stored rules, and pattern matching make a system more efficient and accurate to recognize candidates name entities (NEs). It takes the strongest points from each method to boost the system performance by voting a candidate NE which is detected in more than 1 entity category or out of context because of word ambiguity, it penalized by Word senses disambiguation. Subsequent NEs tagged with identical tags merged as a single tag before the final output. The evaluation shows the system is outperformed. Finally, the future direction is forwarded a hybrid approach of rule-based with unsupervised zero-resource cross-lingual to enhance more.