Visual Preference Modeling and Optimization in Graphic Design via Feature Encoding and Apriori Rule Mining

In this paper, we propose a new mining task: mining top-k frequent closed graph patterns without minimum support. Most previous frequent graph pattern mining works require the specification of a minimum support threshold. However it is difficult for users to set a suitable value sometimes. We develop an efficient algorithm, called TGP, to mine patterns without minimum support. A new structure called Lexicographic Pattern Net is designed to store graph patterns, which makes the closed pattern verification more efficient and speeds up raising support threshold dynamically. In addition, Lexicographic Pattern Net can be stored in the file through serialization, so it doesn't need generate candidate patterns again in the next mining. It is found in the preliminary experiments that TGP can find top-k frequent closed graph patterns completely and accurately. Furthermore, TGP can be extended to mine other kinds of graphs or dynamic graph streams easily.

Downtimes in manufacturing significantly influence productivity, and their analysis is necessary for successful and flexible production. Although some classification and regression studies have been performed on the machine downtime in the manufacturing area, the rare itemset mining (RIM) technique has never been implemented in the existing downtime studies until now. Besides, anomaly detection for gear manufacturing downtime in the automotive sector using RIM is yet to be explored. To bridge this gap, this study proposes the application of the RIM method for detecting anomalies in gear manufacturing downtime of earth moving machinery for the first time. In this study, the Rare Pattern Growth (RP-Growth) algorithm was executed on a real-world dataset consisting of downtimes in gear manufacturing of earth moving machinery to discover rare itemsets that indicate anomalies in downtimes. In the experiments, the rare itemsets (anomalies) in the downtime data were detected using different minimum support (minsup) and minimum rare support (minraresup) threshold values. The obtained results were also evaluated in terms of the number of itemsets, execution time, and maximum memory usage. The experimental results show that the proposed approach, called Anomaly Detection with Rare Itemset Mining (ADRIM), is an effective method for detecting anomalies in machine downtimes and can be successfully used in the manufacturing area, especially in the automotive sector.

A natural language collaborative consultation system must take user preferences into account. A model of user preferences allows a system to appropriately evaluate alternatives using criteria of importance to the user. Additionally, decision research suggests both that an accurate model of user preferences could enable the system to improve a user's decision‐making by ensuring that all important alternatives are considered, and that such a model of user preferences must be built dynamically by observing the user's actions during the decision‐making process. This paper presents two strategies: one for dynamically recognizing user preferences during the course of a collaborative planning dialogue and the other for exploiting the model of user preferences to detect suboptimal solutions and suggest better alternatives. Our recognition strategy utilizes not only the utterances themselves but also characteristics of the dialogue in developing a model of user preferences. Our generation strategy takes into account both the strength of a preference and the closeness of a potential match in evaluating actions in the user's plan and suggesting better alternatives. By modeling and utilizing user preferences, our system is able to fulfill its role as a collaborative agent.

Assessing landscape perception of urban rocky habitats

Waste management companies are one of the major contributors in emission of greenhouse gases. In order to reduce this, we need to integrate renewable energy resources with these waste management companies. These waste management companies have a very high energy consumption processes involved in their operations. But most of these companies also rely on local power generation and hence making it a beneficial field to study micro grids. Our main aim through this research is to make sure that these waste management companies work with their best efficiency by processing the waste and to enable it dominance on micro grids without elimination user interference. This is done through a very unique machine learning approach. In this approach we first predict the amount of waste that can be brought to these companies with the help of ANN (artificial neural network). Then this waste is processed and optimized through Lagrangian Algorithm on the energy requirements that are dependent upon renewable energy. Also, this approach caters to user interference and preferences. This user preference is fed to the model with the help of user feedbacks and then processed through support vector machine. In order to include user feedback, we have used an active learning paradigm. This method is tested on a waste management company of district Warendorf. The results hence prove that the energy requirements can be managed and controlled in a micro grid with giving importance to user feedback.

Preferred mental models for direct manipulation and command-based interfaces

In computer-aided drafting and designing area, interactive graphics are used for designing components, systems, layouts, and structures. There are currently several approaches using for automated graphical layout tools in designing the graphic. Our research aims to reduce design-working time, to learn user preferences, and to generate 3D graphical layout design automatically. An attempt to enable computers to generate 3D graphical layout design and presentation automatically by using the genetic algorithm (GA) has been discussed for a decade. An effective use of GA in automated graphical layout design relies on how closely it is possible to define a fitness function that can reflect the user preferences. In this paper, we introduce methods to define chromosome structures and fitness functions of the selected objects. A learning mechanism is employed to adjust the fitness values of the objects in the selected layout chosen by the users. By this approach, the fitness functions can be changed adaptively reflecting the selection and user preferences.

Techniques for mining rare patterns have been researched in the association rule mining area because traditional frequent pattern mining methods have to generate a large amount of unnecessary patterns in order to find rare patterns from large databases. One such technique, the multiple minimum support threshold framework was devised to extract rare patterns by using a different minimum item support threshold for each item in a database. Nevertheless, this framework cannot sufficiently reflect environments of the real world. The reason is that it does not consider weights of items, such as market prices of products and fatality rates of diseases, in its mining process. Therefore, an algorithm has been proposed to mine rare patterns with utilities exceeding a user-specified minimum utility by considering rarity and utility information of items. However, since this algorithm employs the concept of traditional high utility pattern mining, patterns' lengths are not considered for determining utilities of the patterns. If the length of a pattern is sufficiently long, the pattern is more likely to have an enough utility to become a high utility pattern regardless of item utilities within the pattern. Therefore, the algorithm cannot guarantee that all items in a mined pattern have high utilities. In this paper, we propose a novel algorithm that effectively reduces such dependency of patterns on their lengths by considering their lengths in the mining process in order to mine more meaningful rare patterns compared to patterns mined by previous algorithms. Experimental results demonstrate that our algorithm extracts a lesser number of more meaningful patterns and consumes less computational resources compared to state-of-the-art algorithms.

Based on analysis of mobile tourism users' multi-dimensional feature, the concept of context is introduced into user model modeling of mobile tourism. From the perspective of user and context, context theory and machine learning is used to accomplish user modeling in terms of tourism activities recommendation. The dimension of this model includes history behavior, current context, historical context and demographic factor. The problems of new user and similar recommendation and lack of weight are settled in this paper. According to the impact of multi dimension to user preference, user preference interfering is used to acquire user preference to accomplish multi-dimensional user model based on context model to contribute to improvement of traditional e-tourism recommendation and personalization and adaptability of platform.

Social media has become a central part of daily life in Indonesia, yet the rapid growth of digital platforms presents challenges in analyzing large, unstructured user data. Responding to this issue, this study aims to cluster the behavioral patterns of Indonesian social media users using the K-Means Clustering algorithm, a data mining technique for unsupervised segmentation. Employing a quantitative approach, data were collected through an online questionnaire from 553 respondents aged 15–80 years. After data cleaning, normalization, and feature encoding, the optimal number of clusters was determined using the Elbow method and Silhouette Coefficient, resulting in two clusters with a Silhouette score of 0.177. Cluster 0 (303 respondents) represents highly interactive multi-platform users active on Instagram, TikTok, and YouTube for 3–6 hours daily, showing strong interest in entertainment and motivational content. Cluster 1 (250 respondents) includes more passive users, mainly on Instagram and TikTok, spending 3–4 hours per day with moderate engagement and a preference for motivational and self-development content. The findings demonstrate that K-Means Clustering effectively maps user behavior based on platform use, content preferences, motivations, and interaction patterns. The implications of these findings suggest that digital communication strategies need to be tailored to the characteristics of each user cluster so that the messages and content conveyed are more effective.

Collaborative Filtering Recommender Systems are used to recommend items that may match each user preference on the basis of preferences of similar users in the system. Since different users have different patterns of preference, there is a problem when one user's preference is used to recommend another user's preference. A way of converting one user's preference pattern into another user's pattern is proposed. However, there are several problems with current methods: some methods take many users' patterns as a similar one, some rely on co-rated items data between user pairs which is hardly obtained, and some methods can't exactly convert a rating to a suitable one. This work proposes a new transpose function that can be utilized on any pair of users regardless of using co-rated items by applying latent model. The new transpose function is composed of an original value term and an adjustment term which transposes an original rating to an average of the target user's rating on the corresponding items. Moreover, for more accuracy, a distribution term and a confidence term are combined to the adjustment term. This new function provides better results than the current transpose function in terms of three evaluation metrics (MAE, F-measure, and coverage).

Reorganizing implicit feedback of users as a user-item interaction graph facilitates the applications of graph convolutional networks (GCNs) in recommendation tasks. In the interaction graph, edges between user and item nodes function as the main element of GCNs to perform information propagation and generate informative representations. Nevertheless, an underlying challenge lies in the quality of interaction graph, since observed interactions with less-interested items occur in implicit feedback (say, a user views micro-videos accidentally). This means that the neighborhoods involved with such false-positive edges will be influenced negatively and the signal on user preference can be severely contaminated. However, existing GCN-based recommender models leave such challenge under-explored, resulting in suboptimal representations and performance. In this work, we focus on adaptively refining the structure of interaction graph to discover and prune potential false-positive edges. Towards this end, we devise a new GCN-based recommender model, Graph-Refined Convolutional Network (GRCN), which adjusts the structure of interaction graph adaptively based on status of model training, instead of remaining the fixed structure. In particular, a graph refining layer is designed to identify the noisy edges with the high confidence of being false-positive interactions, and consequently prune them in a soft manner. We then apply a graph convolutional layer on the refined graph to distill informative signals on user preference. Through extensive experiments on three datasets for micro-video recommendation, we validate the rationality and effectiveness of our GRCN. Further in-depth analysis presents how the refined graph benefits the GCN-based recommender model.

As wireless communication advances, research on location-based services using mobile devices has attracted interest, which provides information and services related to user's physical location. As increasing information and services, it becomes difficult to find a proper service that reflects the individual preference at proper time. Due to the small screen of mobile devices and insufficiency of resources, personalized services and convenient user interface might be useful. In this paper, we propose a map-based personalized recommendation system which reflects user's preference modeled by Bayesian Networks (BN). The structure of BN is built by an expert while the parameter is learned from the dataset. The proposed system collects context information, location, time, weather, and user request from the mobile device and infers the most preferred item to provide an appropriate service by displaying onto the mini map.

Auditory preferences of young children with and without hearing loss for meaningful auditory–visual compound stimuli

Abstract. The packaging design’s important role as a means of marketing communication is growing. This research examines the effect of Monggo size 40 grams’ packaging design on impulsive buying in South Jakarta and also examines which one among the dimensions in packaging design (graphic design, structure design, and product information) has the biggest effect on impulsive buying. This research uses the quantitative approach to explain the connection between the two variables. The data was collected through questionnaires filled out by impulsive buyers of Monggo size 40 grams in South Jakarta. A total of 100 respondents are examined using the purposive sampling technique. The result of the research shows that the packaging design affects impulsive buying at a rate of 38.0% and the packaging design dimension that results in impulsive buying is graphic design. We may conclude that Monggo’s management needs to review the brand’s packaging design. As the management is yet to utilize other communicating tools such as advertisements to support marketing communication, the packaging design becomes more crucial in boosting sales. The research also finds that customers have a great liking for the brand name ‘Monggo’, as it is a very distinctly traditional name that is not only appealing but also noticeable among the current brands Keywords: packaging design, impulsive buying, marketing communication, product information