2023-06

International Conference on Interactive Collaborative Robotics

Deep Learning prediction techniques are widely studied and researched for their implementation in Human Age Prediction (HAP) to prevent, treat and extend life expectancy. So far most of the algorithms are based on facial images, MRI scans, and DNA methylation which is used for training and testing in the domain but rarely practiced. The lack of real-world-age HAP application is caused by several factors: no significant validation and devaluation of the system in the real-world scenario, low performance, and technical complications. This paper presents the Data, Classification technique, Prediction, and View (DCPV) taxonomy which specifies the major components of the system required for the implementation of a deep learning model to predict human age. These components are to be considered and used as validation and evaluation criteria for the introduction of the deep learning HAP model. A taxonomy of the HAP system is a step towards the development of a common baseline that will help the end users and researchers to have a clear view of the constituents of deep learning prediction approaches, providing better scope for future development of similar systems in the health domain. We assess the DCPV taxonomy by considering the performance, accuracy, robustness, and model comparisons. We demonstrate the value of the DCPV taxonomy by exploring state-of-the-art research within the domain of the HAP system.

2022-09

5th International Conference on Engineering Technology and its Applications (IICETA)

The Internet’s continued growth has resulted in a significant rise in the amount of electronic text documents. Grouping these materials into meaningful collections has become crucial. The old approach of document compilation based on statistical characteristics and categorization relied on syntactic rather than semantic information. This article introduces a unique approach for classifying texts based on their semantic similarity. The graph-based approach is depended an efficient technique been utilized for clustering. This is performed by extracting document summaries called synopses from the Wikipedia and IMDB databases and grouping thus downloaded documents, then utilizing the NLTK dictionary to generate them by making some important preprocessing to make it more convenient to use. Following that, a vector space is modelled using TFIDF and converted to TFIDF matrix as numeric form, and clustering is accomplished using Spectral methods. The results are compared with previews work.

2022-08

International Conference on Advanced Science and Engineering (2nd ICOASE)

The continuing success of the Internet has led to an enormous rise in the volume of electronic text records. The strategies for grouping these records into coherent groups are increasingly important. Traditional text clustering methods are focused on statistical characteristics, with a syntactic rather than semantical concept used to do clustering. A new approach for collecting documentation based on textual similarities is presented in this paper. The method is accomplished by defining, tokenizing, and stopping text synopses from Wikipedia and IMDB datasets using the NLTK dictionary. Then, a vector space is created using TFIDF with the K-mean algorithm to carry out clustering. The results were shown as an interactive website.

2022-08

ICR’22 International Conference on Innovations in Computing Research

In the era of digitalization, the number of electronic text documents has been rapidly increasing on the Internet. Organizing these documents into meaningful clusters is becoming a necessity by using several methods (i.e., TF-IDF, Word Embedding) and based on documents clustering. Document clustering is the process of dynamically arranging documents into clusters such that the documents contained within a cluster are very similar to those contained inside other clusters. Due to the fact that traditional clustering algorithms do not take semantic relationships between words into account and therefore do not accurately represent the meaning of documents. Semantic information has been widely used to improve the quality of document clusters by grouping documents according to their meaning rather than their keywords. In this paper, twenty-five papers have been systematically reviewed that are published in the last seven years (from 2016 to 2022) linked to semantic similarities which are based on document clustering. Algorithms, similarity measures, tools, and evaluation methods usage have been discussed as well. As result, the survey shows that researchers used different datasets for applying semantic similarity-based clustering regarding the text similarity. Hereby, this paper proposes methods of semantic similarity approach-based clustering that can be used for short text semantic similarity included in online laboratories repository.

2021-05

International Conference on Advanced Science and Engineering (2nd ICOASE)

Nowadays, cybersecurity threat is a big challenge to all organizations that present their services over the Internet. Distributed Denial of Service (DDoS) attack is the most effective and used attack and seriously affects the quality of service of each E-organization. Hence, mitigation this type of attack is considered a persistent need. In this paper, we used Network Load Balancing (NLB) and High Availability Proxy (HAProxy) as mitigation techniques. The NLB is used in the Windows platform and HAProxy in the Linux platform. Moreover, Internet Information Service (IIS) 10.0 is implemented on Windows server 2016 and Apache 2 on Linux Ubuntu 16.04 as web servers. We evaluated each load balancer efficiency in mitigating synchronize (SYN) DDoS attack on each platform separately. The evaluation process is accomplished in a real network and average response time and average CPU are utilized as metrics. The results illustrated that the NLB in the Windows platform achieved better performance in mitigation SYN DDOS compared to HAProxy in the Linux platform. Whereas, the average response time of the Window webservers is reduced with NLB. However, the impact of the SYN DDoS on the average CPU usage of the IIS 10.0 webservers was more than those of the Apache 2 webservers.

2021-05

International Conference on Advanced Science and Engineering (2nd ICOASE)

The continuing success of the Internet has greatly increased the number of text documents in electronic formats. The techniques for grouping these documents into meaningful collections have become mission-critical. The traditional method of compiling documents based on statistical features and grouping did use syntactic rather than semantic. This article introduces a new method for grouping documents based on semantic similarity. This process is accomplished by identifying document summaries from Wikipedia and IMDB datasets, then deriving them using the NLTK dictionary. A vector space afterward is modeled with TFIDF, and the clustering is performed using the HAC and K-mean algorithms. The results are compared and visualized as an interactive webpage.

2021-05

International Conference on Advanced Science and Engineering (2nd ICOASE)

Nowadays in the age of technology, textual documents are rapidly growing over the internet. Offline and online documents, websites, e-mails, social network and blog posts, are archived in electronic structured databases. It is very hard to maintain and reach these documents without acceptable ranking and provide demand clustering while there is classification without any details. This paper presents an approach based on semantic similarity for clustering documents using the NLTK dictionary. The procedure is done by defining synopses from IMDB and Wikipedia datasets, tokenizing and stemming them. Next, a vector space is constructed using TFIDF, and the clustering is done using the ward's method and K-mean algorithm. WordNet is also used to semantically cluster documents. The results are visualized and presented as an interactive website describing the relationship between all clusters. For each algorithm three scenarios are considered for the implementations: 1) without preprocessing, 2) preprocessing without stemming, and 3) preprocessing with stemming. The Silhouette metric and seven other metrics are used to measure the similarity with the five different datasets. Using the K-means algorithm, the best similarity ratio acquired from the Silhouette metric with (nltk-Reuters) dataset for all clusters, and the highest ratio is when k=10. Similarly, with Ward's algorithm, the highest similarity ratio of the Silhouette metric obtained using (IMDB and Wiki top 100 movies, and nltk-brown) datasets together for all clusters, and best similarity ratio is obtained when k=5 using the (IMDB and Wiki top 100 movies) dataset. The results are compared with the literature, and the outcome exposed that the Ward's method outperforms the results of K-means for small datasets.

2021-05

International Conference on Advanced Science and Engineering (2nd ICOASE)

In the recently developed document clustering, word embedding has the primary role in constructing semantics, considering and measuring the times a specific word appears in its context. Word2vect and Glove word embedding are the two most used word embeddings in document clustering. Previous works do not consider the use of glove word embedding with DBSCAN clustering algorithm in document clustering. In this work, a preprocessing with and without stemming of Wikipedia and IMDB datasets applied to glove word embedding algorithm, then word vectors as a result are applied to the DBSCAN clustering algorithm. For the evaluation of experiments, seven metrics have been used: Silhouette average, purity, accuracy, F1, completeness, homogeneity, and NMI score. The experimental results are compared with the results of TFIDF and K-means algorithms on six datasets. The results of this work outperform the results of the TFIDF and K-means approach using the four main evaluation metrics and CPU time consuming.

2021-05

International Conference on Advanced Science and Engineering (2nd ICOASE)

The steady success of the Internet has led to an enormous rise in the volume of electronic text records. Sensitive tasks are increasingly being used to organize these materials in meaningful bundles. The standard clustering approach of documents was focused on statistical characteristics and clustering using the syntactic rather than semantic notion. This paper provides a new way to group documents based on textual similarities. Text synopses are found, identified, and stopped using the NLTK dictionary from Wikipedia and IMDB datasets. The next step is to build a vector space with TFIDF and cluster it using an algorithm K-mean. The results were obtained based on three proposed scenarios: 1) no treatment. 2) preprocessing without derivation, and 3) Derivative processing. The results showed that good similarity ratios were obtained for the internal evaluation when using (txt-sentoken data set) for all K values. In contrast, the best ratio was obtained with K = 20. In addition, as an external evaluation, purity measures were obtained and presented V measure of (txt). -sentoken) and the accuracy scale of (nltk-Reuter) gave the best results in three scenarios for K = 20 as subjective evaluation, the maximum time consumed with the first scenario (no preprocessing), and the minimum time recorded with the second scenario (excluding derivation).

2018-11

2018 International Conference on Advanced Science and Engineering (ICOASE)

In this paper, we present a discussion panel of two of the hottest topics in this area namely distributed parallel processing and distributed cloud computing. Various aspects have been discussed in this review paper such as concentrating on whether these topics are discussed simultaneously in any previous works. Other aspects that have been reviewed in this paper include the algorithms, which simulated in both distributed parallel computing and distributed cloud computing. The goal is to process the tasks over resources then readjusted the calculation among the servers for the sake of optimization. These help us to improve the system performance with the desired rates. During our review, we presented some articles which explain the designing of applications in distributed cloud computing while some others introduced the concept of decreasing the response time in distributed parallel computing.

2018-10

2018 International Conference on Advanced Science and Engineering (ICOASE)

In this paper, we present a discussion panel of two of the hottest topics in this area namely distributed parallel processing and distributed cloud computing. Various aspects have been discussed in this review paper such as concentrating on whether these topics are discussed simultaneously in any previous works. Other aspects that have been reviewed in this paper include the algorithms, which simulated in both distributed parallel computing and distributed cloud computing. The goal is to process the tasks over resources then readjusted the calculation among the servers for the sake of optimization. These help us to improve the system performance with the desired rates. During our review, we presented some articles which explain the designing of applications in distributed cloud computing while some others introduced the concept of decreasing the response time in distributed parallel computing.

2018-10

2018 International Conference on Advanced Science and Engineering (ICOASE)

Nowadays, continuously accessing Internet services is vital for the most of people. However, due to Denial of Service (DoS) and its severe type ‘Distributed Denial of Service (DDoS), online services becomes unavailable to users in sometimes. Rather than DDoS is dangerous and has serious impact on the Internet consumers, there are multiple types of that attack such Slowrise, ping of death and UDP, ICMP, SYN flood, etc. In this paper, the effect of HTTP and SYN flood attack on the most recent and widely used web servers is studied and evaluated. Systematic performance analysis is performed on Internet Information Service 10.0 (IIS 10.0) on Windows server 2016 and Apache 2 on Linux Ubuntu 16.04 Long Term Support (LTS) server. Furthermore, the key metrics of the performance are average response time, average CPU usage and standard deviation as a responsiveness, efficiency and stability of the web …

2018-10

2018 International Conference on Advanced Science and Engineering (ICOASE)

Internet of Things (IoT) is a huge number of objects which communicate over a network or the Internet. These objects are a combination of electronics, sensors, and a software to control the way of working other parts of the object. Each object generates and collects data from its environment using sensors and transfers them to other objects or a central database through a channel. Keeping this generated data and its transformation is one of the biggest challenges in IoT today and it is one of the biggest concerns of all organizations that they use the IoT technology. In this paper, the most crucial researches related to security in the IoT field have been reviewed and discussed while taking account of the great power of the Quantum Computers. Significant attributes of these studies are compared. IoT security ranges from the software layer security, board and chip, vulnerable cryptography algorithm, protocol and network …

2015-08

Proceedings of the 5th International Conference on Computing and Informatics

The fact that the existing Web allows people to effortlessly share data over the Internet has resulted in the accumulation of vast amounts of information available on the Web. Therefore, a powerful search technology that will allow retrieval of relevant information is one of the main requirements for the success of the Web which is complicated further due to use of many different formats for storing information. Semantic Web technology plays a major role in resolving this problem by permitting the search engines to retrieve meaningful information. Exploratory search system, a special information seeking and exploration approach, supports users who are unfamiliar with a topic or whose search goals are vague and unfocused to learn and investigate a topic through a set of activities. In order to achieve exploratory search goals Linked Open Data (LOD) can be used to help search systems in retrieving related data, so the investigation task runs smoothly. This paper provides an overview of the Semantic Web Technology , Linked Data and search strategies, followed by a survey of the state of the art Exploratory Search Systems based on LOD. Finally the systems are compared in various aspects such as algorithms, result rankings and explanations .