Predicting movie success with machine learning techniques: ways to improve accuracy

Previous studies on predicting the box-office performance of a movie using machine learning techniques have shown practical levels of predictive accuracy. Their works are technically- and methodologically-oriented, focusing mainly on what algorithms are better at predicting the movie performance. However, the accuracy of prediction model can also be elevated by taking other perspectives such as introducing unexplored features that might be related to the prediction of the outcomes. In this paper, we examine multiple approaches to improve the performance of the prediction model. First, we develop and add a new feature derived from the theory of transmedia storytelling. Such theory-driven feature selection not only increases the forecast accuracy, but also enhances the interpretability of a prediction model. Second, we use an ensemble approach, which has rarely been adopted in the research on predicting box-office performance. As a result, the proposed model, Cinema Ensemble Model (CEM), outperforms the prediction models from the past studies that use machine learning algorithms. We suggest that CEM can be extensively used for industrial experts as a powerful tool for improving decision-making process.     

Application of machine learning techniques to the flexible assessment and improvement of requirements quality

It is already common to compute quantitative metrics of requirements to assess their quality. However, the risk is to build assessment methods and tools that are both arbitrary and rigid in the parameterization and combination of metrics. Specifically, we show that a linear combination of metrics is insufficient to adequately compute a global measure of quality. In this work, we propose to develop a flexible method to assess and improve the quality of requirements that can be adapted to different contexts, projects, organizations, and quality standards, with a high degree of automation. The domain experts contribute with an initial set of requirements that they have classified according to their quality, and we extract their quality metrics. We then use machine learning techniques to emulate the implicit expert’s quality function. We provide also a procedure to suggest improvements in bad requirements. We compare the obtained rule-based classifiers with different machine learning algorithms, obtaining measurements of effectiveness around 85%. We show as well the appearance of the generated rules and how to interpret them. The method is tailorable to different contexts, different styles to write requirements, and different demands in quality. The whole process of inferring and applying the quality rules adapted to each organization is highly automated.

     

Energy inefficiency diagnosis in industrial process through one-class machine learning techniques

In the era of Industry 4.0, the ease of access to precise measurements in real-time and the existence of machine-learning (ML) techniques will play a vital role in building practical tools to isolate inefficiencies in energy-intensive processes. This paper aims at developing an abnormal event diagnosis (AED) tool based on ML techniques for monitoring the operation of industrial processes. This tool makes it easier for operators to accomplish their tasks and to make quick and accurate decisions to ensure highly efficient processes. One of the most popular ML techniques for AED is the multivariate statistical control (MSC) method; it only requires the dataset of the normal operating conditions (NOC) to detect and identify the variables that contribute to abnormal events (AEs). Despite the popularity of MSC, it is challenging to select the appropriate method for detecting and isolating all possible abnormalities a complex industrial process can experience. To address this limitation and improve efficiency, we have developed a generic methodology that integrates different ML techniques into a unified multiagent based approach, the selected ML techniques are supposed to be built using only the normal operating condition. For the sake of demonstration, we chose a combination of two ML methods: principal component analysis and k-nearest neighbors (k-NN). The k-NN was integrated into the proposed multiagent to take into account the nonlinearity and multimodality that frequently occur in industrial processes. In addition, we modified a k-NN method proposed in the literature to reduce computation time during real-time detection and isolation. Finally, the proposed methodology was successfully validated to monitor the energy efficiency of a reboiler located in a thermomechanical pulp mill.

     

Modeling and assessing an intelligent system for safety in human-robot collaboration using deep and machine learning techniques

Multimedia Tools and Applications - The introduction of technological innovations is essential for accident mitigation in work environments. In a human-robot collaboration scenario, the current...     

Correction to: Semi-automation of gesture annotation by machine learning and human collaboration

Language Resources and Evaluation -     

Semi-automation of gesture annotation by machine learning and human collaboration

Language Resources and Evaluation - Gesture and multimodal communication researchers typically annotate video data manually, even though this can be a very time-consuming task. In the present work,...     

Utilizing learning process to improve recommender system for group learning support

With the rapid increasing of learning materials and learning objects in e-learning, the need for recommender system has also become more and more imperative. Although, the traditional recommendation system has achieved great success in many domains, it is not suitable to support e-learning recommender system because the approach in e-learning is hybrid and it is obtained mainly by two mechanisms: the learners’ learning processes and the analysis of social interaction. Therefore, this study proposes a flexible recommendation approach to satisfy this demand. The recommendation is designed based on a multidimensional recommendation model. Furthermore, we use Markov Chain Model to divide the group learners into advanced learners and beginner learners by using the learners’ learning activities and learning processes so that we can correctly estimate the rating which also include learners’ social interaction. The experimental result shows that the proposed system can give a more satisfying and qualified recommendation.     

Diagnosis of skin cancer using machine learning techniques

Generally, skin disease is a common one in human diseases. In computer vision application, the skin color is the powerful indication for this disease. This system identifies the skin cancer disease based on the images of skin. Initially, the skin is filtered using median filter and segmented using Mean shift segmentation. Segmented images are fed as input to feature extraction. GLCM, Moment Invariants and GLRLM features are extracted in this research work. The extracted features are classified by using classification techniques like Support vector machine, Probabilistic Neural Networks and Random forest and Combined SVM+ RF classifiers. Here combined SVM+RF classifier provided better results than other classifiers.     

Calling communities analysis and identification using machine learning techniques

The analysis of social communities related logs has recently received considerable attention for its importance in shedding light on social concerns by identifying different groups, and hence helps in resolving issues like predicting terrorist groups. In the customer analysis domain, identifying calling communities can be used for determining a particular customer’s value according to the general pattern behavior of the community that the customer belongs to; this helps the effective targeted marketing design, which is significantly important for increasing profitability. In telecommunication industry, machine learning techniques have been applied to the Call Detail Record (CDR) for predicting customer behavior such as churn prediction. In this paper, we pursue identifying the calling communities and demonstrate how cluster analysis can be used to effectively identify communities using information derived from the CDR data. We use the information extracted from the cluster analysis to identify customer calling patterns. Customers calling patterns are then given to a classification algorithm to generate a classifier model for predicting the calling communities of a customer. We apply different machine learning techniques to build classifier models and compare them in terms of classification accuracy and computational performance. The reported test results demonstrate the applicability and effectiveness of the proposed approach.     

Popularity prediction of movies: from statistical modeling to machine learning techniques

Multimedia Tools and Applications - Film industries all over the world are producing several hundred movies rapidly and grabbing the attraction of people of all ages. Every movie producer is of...     

Teacher regulation of cognitive activities during student collaboration: Effects of learning analytics

By collaboratively solving a task, students are challenged to share ideas, express their thoughts, and engage in discussion. Collaborating groups of students may encounter problems concerning cognitive activities (such as a misunderstanding of the task material). If these problems are not addressed and resolved in time, the collaborative process is hindered. The teacher plays an important role in monitoring and solving the occurrence of problems. To provide adaptive support, teachers continuously have to be aware of students' activities in order to identify relevant events, including those that require intervention. Because the amount of available information is high, teachers may be supported by learning analytics. The present experimental study (n = 40) explored the effect of two learning analytics tools (the Concept Trail and Progress Statistics) that give information about students' cognitive activities. The results showed that when teachers had access to learning analytics, they were not better at detecting problematic groups, but they did offer more support in general, and more specifically targeted groups that experienced problems. This could indicate that learning analytics increase teachers' confidence to act, which in turn means students could benefit more from the teacher's presence.     

机器学习算法在药物专利分类中的应用研究

为实现药物专利的自动分类,本文结合药物专利的特点,研究了机器学习算法如何应用于药物专利分类。将2000余份药物专利按疗效分类,选取其中五类作为训练样本,对每一类提取特征文本,利用向量空间模型将非结构化的文本数字化,用支持向量机、Naive Bayes、RBFNetwork三种机器学习算法,分别测试专利样本的分类,使用5重交叉验证比较了三种算法的查准率(precision)和召回率(recall),结果表明支持向量机的分类效果最好。将机器学习算法应用于药物化学专利分类,有助于提高药物化学专利信息检索的效率。     

A survey of visual analytics techniques for machine learning

Computational Visual Media - Visual analytics for machine learning has recently evolved as one of the most exciting areas in the field of visualization. To better identify which research topics are...     

Performance prediction of roadheaders using ensemble machine learning techniques

Mechanical excavators are widely used in mining, tunneling and civil engineering projects. There are several types of mechanical excavators, such as a roadheader, tunnel boring machine and impact hammer. This is because these tools can bring productivity to the project quickly, accurately and safely. Among these, roadheaders have some advantages like selective mining, mobility, less over excavation, minimal ground disturbances, elimination of blast vibration, reduced ventilation requirements and initial investment cost. A critical issue in successful roadheader application is the ability to evaluate and predict the machine performance named instantaneous (net) cutting rate. Although there are several prediction methods in the literature, for the prediction of roadheader performance, only a few of them have been developed via artificial neural network techniques. In this study, for this purpose, 333 data sets including uniaxial compressive strength and power on cutting boom, 103 data set including RQD, and 125 data sets including machine weight are accumulated from the literature. This paper focuses on roadheader performance prediction using six different machine learning algorithms and a combination of various machine learning algorithms via ensemble techniques. Algorithms are ZeroR, random forest (RF), Gaussian process, linear regression, logistic regression and multi-layer perceptron (MLP). As a result, MLP and RF give better results than the other algorithms also the best solution achieved was bagging technique on RF and principle component analysis (PCA). The best success rate obtained in this study is 90.2% successful prediction, and it is relatively better than contemporary research.

     

Application of machine learning to predict the recurrence-proneness for cervical cancer

This study applied advanced machine learning techniques, widely considered as the most successful method to produce objective to an inferential problem of recurrent cervical cancer. Traditionally, clinical diagnosis of recurrent cervical cancer was based on physician’s clinical experience with various risk factors. Since the risk factors are broad categories, years of clinical study and experience have tried to identify key risk factors for recurrence. In this study, three machine learning approaches including support vector machine, C5.0 and extreme learning machine were considered to find important risk factors to predict the recurrence-proneness for cervical cancer. The medical records and pathology were accessible by the Chung Shan Medical University Hospital Tumor Registry. Experimental results illustrate that C5.0 model is the most useful approach to the discovery of recurrence-proneness factors. Our findings suggest that four most important recurrence-proneness factors were Pathologic Stage, Pathologic T, Cell Type and RT Target Summary. In particular, Pathologic Stage and Pathologic T were important and independent prognostic factor. To study the benefit of adjuvant therapy, clinical trials should randomize patients stratified by these prognostic factors, and to improve surveillance after treatment might lead to earlier detection of relapse, and precise assessment of recurrent status could improve outcome.     

Object recognition using laser range finder and machine learning techniques

In recent years, computer vision has been widely used on industrial environments, allowing robots to perform important tasks like quality control, inspection and recognition. Vision systems are typically used to determine the position and orientation of objects in the workstation, enabling them to be transported and assembled by a robotic cell (e.g. industrial manipulator). These systems commonly resort to CCD (Charge-Coupled Device) Cameras fixed and located in a particular work area or attached directly to the robotic arm (eye-in-hand vision system). Although it is a valid approach, the performance of these vision systems is directly influenced by the industrial environment lighting. Taking all these into consideration, a new approach is proposed for eye-on-hand systems, where the use of cameras will be replaced by the 2D Laser Range Finder (LRF). The LRF will be attached to a robotic manipulator, which executes a pre-defined path to produce grayscale images of the workstation. With this technique the environment lighting interference is minimized resulting in a more reliable and robust computer vision system. After the grayscale image is created, this work focuses on the recognition and classification of different objects using inherent features (based on the invariant moments of Hu) with the most well-known machine learning models: k-Nearest Neighbor (kNN), Neural Networks (NNs) and Support Vector Machines (SVMs). In order to achieve a good performance for each classification model, a wrapper method is used to select one good subset of features, as well as an assessment model technique called K-fold cross-validation to adjust the parameters of the classifiers. The performance of the models is also compared, achieving performances of 83.5% for kNN, 95.5% for the NN and 98.9% for the SVM (generalized accuracy). These high performances are related with the feature selection algorithm based on the simulated annealing heuristic, and the model assessment (k-fold cross-validation). It makes possible to identify the most important features in the recognition process, as well as the adjustment of the best parameters for the machine learning models, increasing the classification ratio of the work objects present in the robot's environment.     

Comparing and experimenting machine learning techniques for code smell detection

Several code smell detection tools have been developed providing different results, because smells can be subjectively interpreted, and hence detected, in different ways. In this paper, we perform the largest experiment of applying machine learning algorithms to code smells to the best of our knowledge. We experiment 16 different machine-learning algorithms on four code smells (Data Class, Large Class, Feature Envy, Long Method) and 74 software systems, with 1986 manually validated code smell samples. We found that all algorithms achieved high performances in the cross-validation data set, yet the highest performances were obtained by J48 and Random Forest, while the worst performance were achieved by support vector machines. However, the lower prevalence of code smells, i.e., imbalanced data, in the entire data set caused varying performances that need to be addressed in the future studies. We conclude that the application of machine learning to the detection of these code smells can provide high accuracy (>96 %), and only a hundred training examples are needed to reach at least 95 % accuracy.