Human activity recognition is an important area of machine learning research as it has many utilization in different areas such as sports training, security, entertainment, ambientassisted living, and health monitoring and management. Studying human activity recognition shows that researchers are interested mostly in the daily activities of the human. Therefore, the general architecture of HAR system is presented in this paper, along with the description of its main components. The state of the art in human activity recognition based on accelerometer is surveyed. According to this survey, Most of the researches recently used deep learning for recognizing HAR, but they focused on CNN even though there are other deep learning types achieved a satisfied accuracy. The paper displays a two-level taxonomy in accordance with machine learning approach (either traditional or deep learning) and the processing mode (either online or offline). Forty eight studies are compared in terms of recognition accuracy, classifier, activities types, and used devices. Finally, the paper concludes different challenges and issues online versus offline also using deep learning versus traditional machine learning for human activity recognition based on accelerometer sensors.

Nowadays, more and more human activity recognition (HAR) tasks are being solved with deep learning techniques because it's high recognition rate. The architectural design of deep learning is a challenge because it has multiple parameters which effect on the result. In this work, we propose a novel method to enhance deep learning architecture by using genetic algorithm and adding new statistical features. Genetic algorithm is utilized as an enhancing method to get the optimal value parameters of deep learning. Also new statistical features are appended to the features that are extracted automatically from CNN technique. Because the spread of the internet and its significance in our life, we developed Internet of Things (IoT) system. Therefore, we evaluated the performance of the proposed method in its system and found satisfactory results. Moreover, the proposed method was trained on two benchmark datasets (WISDM and UCI) and tested on the dataset, which was collected from IoT system. The results showed that the proposed model improved the accuracy up to 93.8% and 86.1% for user-dependent and independent.

Variability of semantic expression is a fundamental phenomenon of a natural language where same meaning can be expressed by different texts. The process of inferring a text from another is called textual entailment. Textual Entailment is useful in a wide range of applications, including question answering, summarization, text generation, and machine translation. The recognition of textual entailment is one of the recent challenges of the Natural Language Processing (NLP) domain. This paper summarizes key ideas from the area of textual entailment recognition by considering in turn the different recognition models. The paper points to prominent testing data, training data, resources and Performance Evaluation for each model. Also this paper compares between textual entailment models according to the method which used, the result of each method and the strong and weakness of each method.

Measuring Text similarity problem still one of opened fields for research area in natural language processing and text related research such as text mining, Web page retrieval, information retrieval and textual entailment. Several measures have been developed for measuring similarity between two texts: such as Wu and Palmer, Leacock and Chodorow measure and others . But these measures do not take into consideration the contextual information of the text .This paper introduces new model for measuring semantic similarity between two text segments. This model is based on building new contextual structure for extracting semantic similarity. This approach can contribute in solving many NLP problems such as te xt entailment and information retrieval fields.

No abstract