E-commerce is one of the most popular service applications in the world in the last decade. It has become a revolutionary model from traditional shopping transaction to entire internet commerce. E-commerce needs essential artificial intelligence (AI) to provide the customer with information about a product, called a recommendation machine. Collaborative filtering is a model of a recommendation algorithm that relies on rating as the fundamental calculation to make a recommendation. It has been successfully implemented in e-commerce. Even so, this model has a weakness in sparse product data in which the rating number is very low or sparse. Mostly, only less than 3% of the total user population rate a product, leading to the rise of sparse data. A text sentence document is a part of customers' feedback that can be converted into a product rating. According to a traditional approach, bag of word and lexicon model are ignored in a contextual approach. This experiment, it developed a new model to increase the contextuality of text sentences, leading to a more effective rating prediction. We employed a kind of convolutional neural network to generate item latent factor vectors that could be incorporated with probabilistic matrix factorization to make rating prediction. Our method outperformed several previous works based on a metric evaluation using the Root Mean Squared Error (RMSE). In this experiment, we analyzed MovieLens and IMDB datasets, which contained a movie product review.

In this paper, a new image encryption technique is proposed based on the integration of shifted image blocks and basic AES, where the shifted algorithm technique is used to divide the image into blocks. Each block consists of number of pixels, and these blocks are shuffled by using a shift technique that moves the rows and columns of the original image in such a way to produce a shifted image. This shifted image is then used as an input image to the AES algorithm to encrypt the pixels of the shifted image. In order to evaluate the performance, the proposed integration technique and AES algorithm were measured through a series of tests. These tests included a histogram analysis, information entropy, correlation analysis, differential analysis. Experimental results showed that the new integration technique has satisfactory security and is more efficient than using the AES algorithm alone without the shifting algorithm which makes it a good technique for the encryption of multimedia data. The results showed that the histogram of an encrypted image produced a uniform distribution, which is very different from the histogram of the plain image, and the correlation among image pixels was significantly decreased by using the integration technique and a higher entropy was achieved.

Background: This study aims to obtain criteria and indicator as parameters to determine the degree of injury from Visum et Repertum (VeR). The approach is done by adopting quantitative descriptive learning from VeR data. This study is conducted to retrieve the independent variable, either one variable or more. The techniques applied in this study are (Analytical Hierarchy Process) AHP and (Logistic Regession) LR to the opinion of experts according to the VeR data for a new knowledge discovery. Survey methods used in Bhayangkara Hospital Pekanbaru in the period from 2013 until 2016. The data sample used in this study is secondary data which are injury data from VeR. Result: The finding of this study reveals that the model developed using the AHP and LR has good ability to determine and analyze the parameters for the degree of injury from VeR based on experts' opinion. Conclusions: The LR results also showed the physical factors that influence the degree of injury. Which are Respiration Rate (RR) and Systolic Blood Pressure (SBP). The higher Respiration Rate (RR) indicated the degree of injury is lighter. On the contrary, the lower Respiration Rate (RR) indicated the degree of injury is rising. While, the higher Systolic Blood Pressure (SBP) explained the degree of injury is lighter, and the lower level of Systolic Blood Pressure (SBP) explained the degree of injury level increase.

No abstract

No abstract