International Journal of Intelligent Engineering and Systems

1

Authors: Kumbala Pradeep Reddy, Gullipalli Apparao Naidu, Bulusu Vishnu Vardhan

Robust Action Recognition under multiple views has gained a significant research interest recently. To enhance the performance of Multi-view Action Recognition, we propose a novel Feature extraction and Feature Selection mechanism that allows building a mutual relationship between the actions sequences of multiple views. The feature extraction considered multiple features which are invariant to scale and orientation. Three different features such as Intensity Features, Orientational Features and Contour Features are used to represent every action. Further, the feature selection is accomplished through self-similarity matrix and is very much helpful in the provision of a perfect discrimination between actions sequences of different views. The proposed method is validated over the standard multi-view IXMAS dataset and experimental results confirm that the proposed method outperforms the conventional approaches with respect to Recognition Accuracy.

25

Authors: Eman K. Elsayed, Naglaa E. Ghannam

Ontology is the core of the semantic applications, so the quality of it has a direct proportion with Ontology. It impacts directly on the long life of the semantic applications. There are different negative effects in the design of Ontology' classes as Blob, Lazy Class, Large Class, and Singleton. These negative effects called bad smells. However, detecting smells is not supported in any Ontology editors. This paper proposes a metric method called ONTOPYTHO. It can detect classes’ smells automatically from Ontology models even if it is a Big Ontology. We programed ONTOPYTHO via Python and SPARQL languages. We evaluated the proposed method ONTOPYTHO by applying it on twelve publicly OWL Ontology projects. The detected smells appeared 117495 times in the twelve projects. The results showed that both the size and the number of classes of OWL Ontology has no effect in the presence of the smells. The results also showed that 69.24% of the classes are lazy classes. This means that big OWL Ontologies are not big in their nature, but because of theses lazy classes. The proposed method is the first method that detects Lazy class smell in the design of big OWL Ontology. In our random sample of big Ontologies, Lazy class smell appears approximately 99.8% of the smells.

47

Authors: Farza Nurifan, Riyanarto Sarno, Kelly Rossa Sungkono

Many restaurant review analysis have been done, however only few analysis have been done for specific aspects of a restaurant. In this context this paper proposes aspect based restaurant analysis which includes Physical environment, Food quality, Service quality and Price fairness. The analysis steps include Aspect Term Extraction (ATE), Aspect Keyword Extraction (AKE), Aspect Categorization (AC) and Sentiment Analysis (SA). ATE employs the modification of Double Propagation method and several Topic Modelling methods, AKE utilizes Term Frequency-Inverse Cluster Frequency (TF-ICF), in AC we propose Hybrid ELMo-Wikipedia (HEW), and in SA we propose Hybrid Expanded Opinion Lexicon-SentiCircle (HEOLS). The results show that our modification of the methods used in ATE could increase the f1measure of the AC by average 2%, then the HEW that we proposed had better f1measure compared to other similar methods by average 6%. Other than that, our proposed HEOLS can expand and redetermine the Opinion Lexicon polarity and can increase f1measure of SA by 6%.

71

Authors: Agus Zainal Arifin, Safri Adam, Avin Maulana Mohammad, Fatoni Anggris, Rarasmaya Indraswari, Dini Adni Navastara

Segmentation of single tooth in dental panoramic images is an important process to extract its features and information. However, it might be challenging when the segmentation process faces an overlapping teeth image. In this research, we introduce a new strategy for detecting overlapping area on dental panoramic radiographs automatically. This research proposes automatic thresholding to obtain marking points for the overlapping area and an automatic selection of overlapping area candidates by using the area orientation and the similarity of neighborhood intensity. The experimental results on 44 images show that our proposed strategy can detect overlapping teeth on the dental panoramic radiograph with accuracy, sensitivity, and specificity of 75%, 66.67%, and 85%, respectively. The evaluation conducted on 24 overlapping teeth images shows that the segmentation results of overlapping teeth area have an average misclassification error of 0.31%.

91

Authors: Youssef Barradi, Naoufel Khaldi, Khalida Zazi, Malika Zazi

This paper presents a network reconfiguration which is a vital analysis process for optimizing and controlling distribution systems. The method is based on genetic algorithm by changing the status of the switches to improve the operational performance. The main objective is to minimize the system power losses and to keep bus voltage profile into limits with radial distribution to provide the consumers with quality electrical energy while minimizing the cost. For this optimization problem, an objective function is developed from an electrical branch to sort the fittest solution. Selection, Crossover and mutation are the necessary three operators in which some improvements are made for the effectiveness of the genetic approach. The method can be successfully applied for loss minimum problem. Numerical example simulated with MATLAB/GUI is demonstrated by 33-bus distribution network and tested using a default mode network. As results, premature convergence is avoided, it shows the validity of the proposed methodology while respecting all the constraints.

114

Authors: Ari Endang Jayati, Wirawan Wirawan, Titiek Suryani, Endroyono Endroyono

Generalized Frequency Division Multiplexing (GFDM) is one of the 5G candidates to overcome the shortcomings of Orthogonal Frequency Division Multiplexing (OFDM), high peak rating power ratio (PAPR), and high Out of Band (OOB) radiation. GFDM has a low PAPR due to the use of a number of subcarriers. The purpose of this paper is to compare the two algorithms to reduce PAPR if applied to the non-linear distortion-affected GFDM system. Partial Transmit Sequence (PTS) and Selected Mapping (SLM) are selected because these techniques do not distort the signal, so they do not change the spectrum of the signal. The simulation result shows PAPR GFDM is not significantly affected by nonlinear distortion. After being given the PTS technique, the PAPR value on GFDM dropped to 5 dB. Meanwhile, after being given a selective mapping technique, the PAPR value in GFDM dropped to 6.2 dB.. However, for a 5G application with thousands of devices, this value should still be reduced. After being given a PTS, the PAPR value drops to the value according to the 5G criterion. Better PTS performance decreases PAPR for GFDM systems that are given nonlinear distortion when compared to SLM.

133

Authors: Osama Sayed Abdelrahman, Hesham Ahmed Hefny

The term "Big Data" is a buzzword which describes new technologies that manipulate very large data sets which are massively generated by heterogonous sources. This new term encourages data scientists to extend their work and modify their techniques to overcome the new challenges come with big data concepts. Granular computing has emerged as a new rapidly growing information processing paradigm inside the community of Computational Intelligence. Theories of Fuzzy sets and Rough sets theory are considered powerful examples of granular computing that can be applied to data mining techniques to extract nontrivial knowledge from huge data. The aim of this paper is to introduce a data mining approach for big data based on integrating fuzzy sets and rough sets theories. The proposed approach provides a novel granular data mining for big data that allow extracting useful knowledge and rules from huge data to enhance the decision making process. The proposed approach has been applied on different types of datasets. The experimental results show that our proposed approach is more efficient and robust when dealing with very big datasets and obtained consistent classification rules with classification accuracy 100%.

157

Authors: Il Bae, Jaeyoung Moon, Shiho Kim

One of crucial concern of autonomous vehicles is that driver may experience discomfort, if the driving pattern of the vehicle is quite different from her/his personal driving style. This study focuses on an autonomous vehicle control based on user’s driving preference adopted to provide a personalized and a familiar driving experience to autonomous vehicle users. For this purpose, we defined a driver’s driving preference metric (DPM) to reflect their own driving style by specifying a preferred lateral and longitudinal acceleration region. Moreover, we also proposed a time optimal speed planning that utilize the DPM control parameters extracted from a GG diagram to provide a DPM-aware maneuvering for a personalized autonomous driving. The performance of the proposed planning strategy and a combined vehicle controller were verified using on-road experimental tests. The experimental result shows that the proposed DPM-aware system can control the lateral and longitudinal acceleration of autonomous vehicle within 28.7% of peak error tolerance from the specified criterion of DPM.

177

Authors: Karima Boudaraia, Hassane Mahmoudi, Ahmed Abbou

This paper presents a novel hybrid technique for tracking the maximum power point of the photovoltaic panel. This approach includes two loops: The first one is the ANN (Artificial neural network) loop that is used to estimate and generate the reference of optimal voltage. While, the second loop consists of the BSM (Backstepping Sliding Mode) controller. Effectively, the proposed controller is designed to track the signal of the desired voltage, which is generated using the first loop, by adjusting the duty cycle of the boost converter. Thus, this loop allows the DC/DC converter to product the maximum power at the terminals of the PV module and the load. Indeed, in contrary to the traditional backstepping, the proposed ANN-BSM technique guarantee zero steady-state error. On the one hand, by using the ANN, the system can quickly predict the desired optimal voltage, also it allows the system to avoid the unnecessary calculations and research of the maximum point of power. On the other hand, the sliding mode and the backstepping controller are used to provide the good performances and robustness against the rapid changes of insolation. In addition, the asymptotic stability of this system is made by applying the Lyapunov approach. To show the effectiveness and the tracking performances of the proposed ANN-BSM technique, a comparative study with the classical methods, P&O and incremental conductance algorithms, and hybrid approaches such as the ANN-Backstepping controllers and the ANN-Integral Sliding mode, is investigated in MATLAB/Simulink software.

207

Authors: Wahyu Pamungkas, Titiek Suryani, Wirawan Wirawan, Achmad Affandi

A communication system of Vehicle to Vehicle (V2V) consists of a transmitter, a receiver, and scatterers which can move in random speeds and directions to generate the Doppler Effect that reduces communications system performance. The Doppler effect that occurs in V2V channel modeling is a combination of the Doppler effect on each of its constituent components. After being combined with the Orthogonal Frequency Division Multiplexing (OFDM) multi-carrier system, the signal received at the receiving end experiences attenuation due to the characteristics of the channel used. To analyze the attenuation factor received due to the influence of channel characteristics, the power spectral density parameter is used. Previous research was limited to modeling the V2V channel with moving scatterers, without knowing the effect of velocity on power spectral density. The purpose of this study was to examine the effects of velocity parameters of V2V’s components on power spectral density where scatterers moved randomly. Moving scatterers speed was classified into two categories, where the scatterers were faster or slower than the sender and receiver. The power spectral density was analyzed after combining Quadrature Phase Shift Keying (QPSK) modulation with multi-carrier OFDM. The results show that components with higher velocity yielded more damped power spectral density on the receiver that reached -0.7099 dB/Hz. Moreover, the number of scatterers that moved around the transmitter and receiver highly affected the magnitude of the Doppler effect. The largest Doppler Shift generated in this study was 13.5 kHz with attenuated power spectral density at -0.8646 dB/Hz.

225

Authors: Gehad Ismail Sayed, Ghada Khoriba, Mohamed H. Haggag

This paper proposes a new hybrid approach based on quantum computing and SSA to boost the performance of SSA through finding the optimal trade-off between exploitation and exploration. QSSA relies on embedding the integration of the quantum operators and interference in the optimization process of SSA and the quantum representation of the search space. QSSA is tested on 29 global benchmark functions of CEC2017 and 8 benchmark images. The simulation results showed that employing the principles of quantum can significantly boost the performance of SSA. The performance of QSSA is compared with SSA and other recent and well-known optimization algorithms. The results on CEC2017 demonstrated the capability of QSSA to find the global optima for most of unimodal and multimodal benchmark functions, especially with complex search space. Moreover, the results revealed that the proposed image enhancement based QSSA is robust and can distinctly enhance the contrast of the color images.

249

Authors: Maddali M.V.M. Kumar, Aparna Chaparala

A large number of small sensors in the Wireless Sensor Network (WSN) can be an efficient tool for data collection in a range of environments. Each sensor transfers the information to the basic unit that transmits the information to the end user. The objective of clustering is to separate the network into sectors with a cluster head (CH). The job is to collect, aggregate and transmit cluster heads to the base station. Energy Efficient Clustering has been used widely for energy conservation in wireless sensor networks (WSNs) and also preserves the restricted energy resources of their sensors. Cluster heads (CHs) perform a major part and exhaust power faster than other member nodes in a distributed WSN. Opposition-based Chaotic Whales Optimization algorithm (OBC-WOA) is meta-heuristic optimization algorithm which has recently been proposed in opposition. It simulates humpback whales ' social behaviour. OBC-WOA produces randomly its population during exploration and exploitation stages, like other population-based systems, which can produce values far from the optimal alternative or block the development of local optima. The revised algorithm known as Opposition-based Chaotic Whale Optimization Algorithm (OBC-WOA) is designed to increase solution precision and reliability. The OBC-WOA uses a technique based on opposition to improve the efficiency of OBC-WOA. The OBC-WOA is screened with the initial WOA algorithm and other meta-heuristic techniques. The performance of the proposed approach is evaluated in terms of energy consumption, throughput, packet delivery ratio and network life time. When compared with the existing method the proposed method is 12% better than Whale Optimization algorithm (WOA), 25% better than Gravitational Search Algorithm (GSA), 40% better than Particle Swarm Optimisation (PSO) and 8% better than Fuzzy K-Means and Centralized Mid-point Algorithm (FKM-CMA).