Search

Amount social media active users are always increasing and come from various backgrounds. An active user habit in social media is to use their local or national language to express their thoughts, social conditions, socialize, ideas, perspectives, and publish their opinions. Karonese is a non-English language prevalent mostly in North Sumatra, Indonesia, with unique morphology and phonology. Sentiment analysis has been frequently used in the study of local or national languages to obtain an overview of the broader public opinion behind a particular topic. Good quality Karonese resources are needed to provide good Karonese sentiment analysis (KSA). Limitation resources become an obstacle in KSA research. This work provides Karonese Dataset from multi-domain social media. To complete the dataset for sentiment analysis, sentiment label annotated by Karonese transcribers, three kinds of experiments were applied: KSA using machine learning, KSA using machine learning with two variants of feature extraction methods. Machine learning algorithms include Logistic Regression, Naïve Bayes, Support Vector Machine and K-Nearest Neighbor. Feature extraction improves model performance in the range of 0.1 – 7.4 percent. Overall, TF-IDF as feature extraction on machine learning has a better contribution than BoW. The combination of the SVM algorithm with TF-IDF is the combination with the highest performance. The value of accuracy is 58.1 percent, precision is 58.5 percent, recall is 57.2, and F1 score is 57.84 percent

Meta-heuristic algorithms have emerged as a powerful optimization tool for handling non-smooth complex optimization problems and also to address engineering and medical issues. However, the traditional methods face difficulty in tackling the multimodal non-linear optimization problems within the vast search space. In this paper, the Flower Pollination Algorithm has been improved using Dynamic switch probability to enhance the balance between exploitation and exploration for increasing its search ability, and the swap operator is used to diversify the population, which will increase the exploitation in getting the optimum solution. The performance of the improved algorithm has investigated on benchmark mathematical functions, and the results have been compared with the Standard Flower pollination Algorithm (SFPA), Genetic Algorithm, Bat Algorithm, Simulated annealing, Firefly Algorithm and Modified flower pollination algorithm. The ranking of the algorithms proves that our proposed algorithm IFPDSO has outperformed the above-discussed nature-inspired heuristic algorithms.

The texture is the object’s appearance with different surfaces and sizes. It is mainly helpful for different applications, including object recognition, fingerprinting, and surface analysis. The goal of this research is to investigate the best classification models among the Naive Bayes (NB), Random Forest (DF), and k-Nearest Neighbor (k-NN) algorithms in performing texture classification. The algorithms classify the leaves and urban land cover of texture using several evaluation criteria. This research project aims to prove that the accuracy can be used on data of texture that have turned in a group of different types of data target based on the texture’s characteristic and find out which classification algorithm has better performance when analyzing texture patterns. The test results show that the NB algorithm has the best overall accuracy of 78.67% for the leaves dataset and 93.60% overall accuracy for the urban land cover dataset.

Phishing is a serious web security problem, and the internet fraud technique involves mirroring genuine websites to trick online users into stealing their sensitive information and taking out their personal information, such as bank account information, usernames, credit card, and passwords. Early detection can prevent phishing behavior makes quick protection of personal information. Classification methods can be used to predict this phishing behavior. This paper presents an intelligent classification model for detecting Phishing by redefining a fuzzy soft set (FSS) theory for better computational performance. There are four types of similarity measures: (1) Comparison table, (2) Matching function, (3) Similarity measure, and (4) Distance measure. The experiment showed that the Similarity measure has better performance than the others in accuracy and recall, reached 95.45 % and 99.77 %, respectively. It concludes that FSS similarity measured is more precise than others, and FSS could be a promising approach to avoid phishing activities. This novel method can be implemented in social media software to warn the users as an early warning system. This model can be used for personal or commercial purposes on social media applications to protect sensitive data.

Robotics technology is very useful for the lives of many people today. Almost all aspects of his life utilize robotics technology according to the required field. The development of robotics technology has become a higher quality of human life. Perhaps robotics are still less popular among the general public who still thinks robotics are humanoid robots (robots or human machines). Robotics has been widely implemented in the real world ranging from the fields of industry, medicine, entertainment, security, to household appliances. In the field of security, robotics has an important role. As the robot principle itself is tireless and has little tolerance, the product in robotics in the security field can be a very useful tool. In addition to facilitate human insecurity, robotics products can also facilitate human in various jobs, such as in the locking doors or walls of anyone who already exists. The development of robotics is in line with the development of computer vision which is increasing its application in everyday life. With this research, is expected to improve security and comfort in the security room. The design of this system using electronic door locks, open source OpenCV and webcam as a unit component.

The recent progress in the digital multimedia technologies has offered many facilities in the transmission, reproduction and manipulation of data. However, this advance has brought the problem such as copyright protection for content providers. Watermarking is one of the proposed solutions for copyright protection of multimedia. Most of the content provider use Photoshop to create a watermark photo, but Photoshop involve many procedures to complete a watermarked image. In addition, watermark image using Photoshop easily destroy by attacker where attacker can modifies the image to remove the watermark from the image. Hence, it has become a tough task to protect copyright of an individual’s creation. Thus, i-Mark is developed to solve the problem to protect the watermarked image. An invisible watermark embeds an imperceptible signal into data such as image, which indicates whether or not the content is copyrighted. By using i-Mark, invisible watermarking was provided where steganography method was implemented for users to encrypt message into an image. Hence, the image is protected from been easily modifies or copy by others. Meanwhile, i-Mark allow user to store their invisible watermarked image in database and can be view later. In addition, i-Mark also can made a visible watermark where user can adding text on the cover of image more convenient than Photoshop. In conclusion, i-Mark provides users to watermark their image either visible watermark or invisible watermark. Hence, throughout the project, user may use the system user friendly compare to Photoshop

UTHM Student Planner is an application which includes web version and mobile version. It is a system that is use to help student to manage the time. The purpose of developing this application is to solve the time management problem and increase the awareness on the importance of time management. Object Oriented Software Development (OOSD) Model is being use as a guideline and standard along the process of system development. Overall, this system includes calendar, reminder, notes and a function to find people. It is capable to improve student’s time management which will leads to the betterment of student performance in academics.

Teaching performance evaluation process in higher learning institutions (HLI) is of the most importance in building a higher education policy which purposes for teaching improvement and administrative decision making. Several issues have been raised such as 1) instrument characteristic used to detect values is not sufficient to handle subjective evaluation criteria’s and, 2) the most techniques used in handling survey data is statistical method. In conventional practice, ordinal Likert scales used for marking schema and statistical techniques are implemented for analyzing the data. In order to manage the issues, this research presents a multi-criteria decision making methodology, called analytic hierarchical process (AHP) to evaluate HLI instructors teaching performance. As a well known decision making approach, AHP can systematically cope with highly subjective problems in social system. An AHP implementation framework for teaching performance evaluation will use the possible internal factors; preparation, organization, delivery and effectiveness that are evaluated as teaching evaluation weight. The future work is also suggested, this evaluation system should be implemented in real time situations. It becomes the best platform to evaluate teaching performance and categorize instructors into appropriate bands.

Web Based Management System of Enactus Malaysia National Cup (E-EMNC) is event management system that specially designed for the uses of Enactus Malaysia National Cup. Without a proper event management system, Enactus Malaysia National Cup cannot be perfect enough due to several outburst issues such as miss update of payment, long queue at registration counter, misunderstand of information and others. Thus, this event management system was developed to overcome most of the problem that occurs before, during and after the events. Related objectives are stated to solve the problem. System Development Life Cycle Waterfall model is used as the methodology to develop this system. This system is developed by using PHP as server-side scripting and Bootstrap as front end framework. The prototype of the system was considered success because it could navigate student leader to complete submit the report by shown the flow of system. This system is expected to lighten the burden of event committees and educated team leader on filing document through internet.

Content adaptation is a potential solution for tailoring multimedia web content according to the users’ preferences and heterogeneous devices’ constraints. Content adaptation can be done as third party service over the Internet. Users may pay for the service thus demand quality. The quality should include the human psychological factors. One of these factors is the maximum time a user can wait for the output to be displayed. Thus, response time is one of the qualities of service (QoS) to be considered in assessing the deliverability of content adaptation services. However, the advertised response time may not be deliverable accordingly during the actual service execution due to heavy load. Practically, the service provider should able to determine a current deliverable response time before the service level agreement (SLA) is settled with the users. In this paper, we propose a strategy for service providers to evaluate incoming requests and capable of offering the new response time. The proposed strategy takes into account the current server load and enables a mechanism for the user to evaluate whether the new response time can be accepted or not. We analyzed the performance of the proposed strategy in terms of SLA settlement under various conditions. The results indicate that the proposed strategy performs well.

Many small online retailers and new entrants to the online retail sector are keen to practice data mining and consumer-centric marketing in their businesses yet technically lack the necessary knowledge and expertise to do so. In this article a case study of using data mining techniques in customer-centric business intelligence for an online retailer is presented. The main purpose of this analysis is to help the business better understand its customers and therefore conduct customer-centric marketing more effectively. On the basis of the Recency, Frequency, and Monetary model, customers of the business have been segmented into various meaningful groups using the classification and naïve bayes algorithm, and the main characteristics of the consumers in each segment have been clearly identify ed. Accordingly a set of recommendations is further provided to the business on consumer-centric marketing.

Measuring semantic similarity between terms is an important step in information retrieval and information integration which requires semantic content matching. Semantic similarity has attracted great concern for a long time in artificial intelligence, psychology and cognitive science. This paper contains a review of the state of art approaches including structure based approach, information content based approach, and feature based approach and hybrid approach. We also discussed similarity according to their advantages, disadvantages and issues related to multiple ontology especially on method in features based approach.

This paper reports an ongoing research to develop a theoretical model for sustainable green information systems (green IS) design. The model is intended to be used as a reference model in designing a green IS by taking into account consideration, the environmental, economic, social and cultural sustainability dimensions so that they are fit for sustainability. For each dimension, the related non-functional attributes are specified.

MBJB Claim Management System is developed to provide an online platform for MBJB staff to manage the claim activities. By changing the current manual claim method to computerised system, the effectiveness and efficiency of claim process have been improved, for instances this system can quicken the approval process as well as allow applicants to check the status of claim application, minimizes human errors in calculation and provides several type of claim report. By putting the system online, there is no more problems of time and distance. Iterative Model which each iterative are mini-waterfall is applied to develop this project. Furthermore, Model-View-Controller (MVC) architecture is also used for developing this project. Hence, laravel framework is used. Data dictionary is produced for better understanding on system database. Several user interfaces are created to visualise the actual system environment. Last but not least, Hypertext pre-processor (PHP), Javascript, jQuery and MySQL are used during system development. As a conclusion, MBJB Claim Management system can replace the existing manual claim management as well as bring benefits to staff MBJB.