Dr. Ammar Mohammed

Recently, most companies market their products on the web to recognize their customers’ requirements and to improve their services’ quality according to the customers’ feedback and opinions. A huge amount of reviews and opinions are posted daily on products. Obtaining and quickly analyzing these opinions become a difficult task. These opinions might lead to a tendency or disinclination to a specific point of view. To represent the products’ opinions from customers’ perspectives, opinion retrieval becomes a demanding and essential task for automatically extracting, analyzing, and summarizing customers’ reviews. Usually, online products are offered by several suppliers in e-commerce. Therefore, to keep up the competitiveness among suppliers, the need for innovative requirements is required. This paper proposed an enhanced opinion retrieval approach depending on the explicit feature based opinion mining. The proposed approach expands the initial products’ requirements using extended heuristics and linguistic patterns of the Arabic opinions. Besides the relevant score, several factors, like features’ weight, the opinion importance, and the sentiment polarity are used to rank the retrieved results. The experimental results show the capability of the proposed approach to automatically extract more innovative features compared to the conditional random field (CRF) results.

With the growth rate of modern technologies, Computer-based learning environment receives attention for academic goals. In this environment, a computer provides learners with a set of learning contents divided into learning levels. Usually, Computer-based learning environment research efforts detect the next level of the learner automatically based on the correct responses of the learner on a test at the end of every learning level. Different efforts use fuzzy approaches to handle the uncertainly in the learning environment. In this paper, a machine learning approach is proposed to detect the current education level of the learner based on a recorded facial expressions of the learners as well as important features of the learning environment. Several classifiers are employed to recognize the education level. The evaluation of the proposed approach on a real dataset shows that Support Vector Machine (SVM) outperforms the other classifiers and achieves accuracy of 87%. The paper also presents a regression method to detect the learning level as a continuous value. The evaluation of the regression methods shows that the Linear Regression with mean squared error of 0.0048 outperform SVR.

Visually impaired people struggle to live without assistance or face any aspect of life alone especially with people that cannot afford extra assistance equipment. Usually impaired people receive assistance by either human or wearable devices. The first one bears the burden on the human, while the second adds financial burdens nevertheless the hassle of identifying an object is not decreased. Smartphones are almost accessible to everyone and equipped with accessibility features including sensors that can be utilized to help both visually impaired and sighted people. Thus, this paper proposes an approach using Convolutional Neural Network (CNN), speech recognition and smartphone camera calibration aiming at facilitating the process of indoor guidance for visually impaired people. A smartphone's camera acts as the user's eyes. A pre-trained CNN model is used for object detection and the distance to objects is calculated to guide the user toward the right directions and to warn them of obstacles. The speech recognition part is used as a communication channel between visually impaired people and the smartphone. Also, the proposed approach supports object personalising that helps to distinguish user's item from other items found in the room. To evaluate the personalized objected detection, a customized dataset is created for two objects. The experimental results indicate that the accuracy is 92% and 87% for both objects respectively. Also, we experiment the detect distance of two objects against their real distances. The results achieve 0.05 and 0.08 error ratio.

Recently, there has been an enormous increase in the number of reviews of popular products. Therefore, opinion analysis has become a tedious task for customers when making decisions. As a result, opinion retrieval systems have emerged as an effective tool to analyze and represent customers’ feelings toward offered services. Conventional opinion retrieval systems retrieve and rank products according to both relevance and the overall polarity scores of the opinions. However, customer reviews are usually more detailed, including multiple features with different polarities. Consequently, feature-based opinion retrieval is necessary to extract and analyze each feature separately. Customers’ opinions are usually written with a short and unclear structure and contain many implicit linguistic features that cannot be identified by retrieval systems. As a result, the recall results are negatively affected. Few studies have focused on implicit features, as most examined explicit features. Also, implicit features extraction is a challenging task in some languages like Arabic due to difficulties with morphology. This paper proposes an enhanced retrieval approach based on feature-based opinion mining to enhance retrieval performance. In addition to explicit feature extraction, a metaheuristic optimization method with several similarity measures is utilized to identify implicit features and measure its effect on the retrieval results. The experimental results on Arabic and English datasets revealed the effectiveness of the proposed approach, whereby more features were extracted compared to the explicit feature results. Furthermore, the ranking results were improved by identifying both implicit and explicit features compared to the results obtained by the conditional random field method and association rule mining.

n/a

Numerous endeavors have been made to improve the retrieval procedure in Textual Case-Based Reasoning (TCBR) utilizing clustering and feature selection strategies. SOPHisticated Information Analysis (SOPHIA) approach is one of the most successful efforts which is characterized by its ability to work without the domain of knowledge or language dependency. SOPHIA is based on the conditional probability, which facilitates an advanced Knowledge Discovery (KD) framework for case-based retrieval. SOPHIA attracts clusters by themes which contain only one word in each. However, using one word is not sufficient to construct cluster attractors because the exclusion of the other words associated with that word in the same context could not give a full picture of the theme. The main contribution of this chapter is to introduce an enhanced clustering approach called GloSOPHIA (GloVe SOPHIA) that extends SOPHIA by integrating word embedding technique to enhance KD in TCBR. A new algorithm is proposed to feed SOPHIA with similar terms vector space gained from Global Vector (GloVe) embedding technique. The proposed approach is evaluated on two different language corpora and the results are compared with SOPHIA, K-means, and Self- Organizing Map (SOM) in several evaluation criteria. The results indicate that GloSOPHIA outperforms the other clustering methods in most of the evaluation criteria.

Deep learning, one of the most remarkable techniques of machine learning, has been a major success in many fields, including image processing, speech recognition, and text understanding. It is powerful engines capable of learning arbitrary mapping functions, not require a scaled or stationary time series as input, support multivariate inputs, and support multi-step outputs. All of these features together make deep learning useful tools when dealing with more complex time series prediction problems involving large amounts of data, and multiple variables with complex relationships. This paper provides an overview of the most common Deep Learning types for time series forecasting, Explain the relationships between deep learning models and classical approaches to time series forecasting. A brief background of the particular challenges presents in time-series data and the most common deep learning techniques that are often used for time series forecasting is provided. Previous studies that applied deep learning to time series are reviewed.