International Journal of Computational Intelligence and Applications

Grey Wolf optimizer (GWO) has been used in several fields of research. The main advantages of this algorithm are its simplicity, little controlling parameter, and adaptive exploratory behavior. However, similar to other metaheuristic algorithms, the GWO algorithm has several limitations. The main drawback of the GWO algorithm is its low capability to handle a multimodal search landscape. This drawback occurs because the alpha, beta, and gamma wolves tend to converge to the same solution. This paper presents HDGM – a novel hybrid optimization model of dragonfly algorithm and grey wolf optimizer, aiming to overcome the disadvantages of GWO algorithm. Dragonfly algorithm (DA) is combined with GWO in this study because DA has superior exploration ability, which allows it to search in promising areas in the search space. To verify the solution quality and performance of the HDGM algorithm, we used twenty-three test functions to compare the proposed model’s performance with that of the GWO, DA, particle swam optimization (PSO) and ant lion optimization (ALO). The results show that the hybrid algorithm provides more competitive results than the other variants in terms of solution quality, stability, and capacity to discover the global optimum.

In recent years, the internet of services has been more responsive to access through the development of various application program interfaces (API). Accessing an HTTP uniform resource locator (URL) contains malicious software intended by the attacker to create security breaches through the use of APIs from various services on the internet. By default, the non-attentive URL downloads and installs malware in the background without the user’s knowledge. The host does not analyze the API-URL security certificate contract due to the feature access by the user. Therefore, the current Machine Learning (ML) techniques only check malware signatures and certificates rather than analyzing URL behaviour based on the impact of a URL accessed from the internet. To address this problem, we propose a novel intelligent malicious software based on URL-API intensity feature selection (IFS) and deep spectral neural classification (DSNC) for improving Host Security. Initially, the URL — successive certificate signing (SCS) of the user link accessibility is verified based on API download rate logs. This system identifies the best malware software. The Link Redirection Stability Rate (LRSR) is estimated based on the Redirection URL by accessing the direct link and redirect link. The domain transformation matrix (DTM) was created to create a pattern to access successive features. URL-API Intensity Feature Selection selects each estimated feature, and the selected features are based on soft-max logical activation with a recurrent neural network (RNN) optimized for deep learning. RNN is trained in the spectral domain for improving computation and efficiency. It predicts the class based on the risk of malicious weight to categorize class by reference. The proposed IFS-DSNC achieves accuracy of 95.6% than the other algorithms such as KNN, NB, CNN, LCS, GCRNC AGSCR. The experimental result shows that the proposed method provides better performance in finding malware software than the existing approaches, thereby improving the security against host breaching.

Indonesia is one of the archipelago countries located in Asia and it has diverse cultures. In modern society, Indonesian traditional houses have become rare and need to be preserved. This research is conducted to build a digital collection and to develop an image-based automatic recognition system for Indonesian traditional houses. In this paper, the traditional house images are collected in several ways: on-site image captures, receiving images from volunteers, and collecting public images from Google. The dataset is limited to the collection of building shape images, excluding the interior design. The authors implement Convolutional Neural Networks (ConvNets) to build a model for an automatic recognition system. The experiments run some deep network models: VGG, DenseNet, Inception, Xception, MobileNetV2, NasNetMobile, and EfficientNet. The experiments involve 1526 images of 16 classes. EfficientNet-Lite0 outperforms other models and produces the average F1-score and accuracy of 90.1% and 91.8%, respectively. ConvNets also outperform conventional classifiers.

Wireless video surveillance system is one of the cyber-physical security systems kinds, which transmits the signal of IP cameras through a wireless medium using a radio band. WVSSs are widely deployed with large systems for use in strategic places such as city centers, public transportation, public roads, airports, and play a significant role in critical infrastructure protection. WVSSs are vulnerable to jamming attacks creating an unwanted denial of service. Hence, it is essential to secure this system from jamming attacks. In this paper, three models of IoT-fuzzy inference system-based jamming detection system are proposed for detecting and countermeasure the presence of jamming by computing two jamming detection metrics; PDR and PLR, and based on the result, the system countermeasures this attack by storing the video feed locally in the subsystem nodes. FIS models are based on Mamdani, Tsukamoto, and Sugeno fuzzy logic which optimizes the jamming detection metrics for detecting the jamming attack. The efficiency of these proposed models is compared in detecting jamming signals. The experimental results show that the proposed Tsukamoto model detects jamming attacks with high accuracy and efficiency. Finally, the proposed IoT-Tsukamoto-based model was compared with the existing systems and proved to be superior to them in terms of central processing complexity, accuracy, and countermeasure for this attack.

Forecasting the motion of surrounding vehicles is necessary for a self-driving vehicle to plan a safe and efficient trajectory for the future. Like experienced human drivers, the self-driving vehicle needs to perceive the interaction of surrounding vehicles and decide the best trajectory from many choices. However, previous methods either lack modeling of interactions or ignore the multi-modal nature of this problem. In this paper, we focus on two important cues of trajectory prediction: interaction and maneuver, and propose Maneuver conditioned Attentional Network named MAN. MAN learns the interactions of all vehicles in a scenario in parallel by self-attention social pooling and the attentional decoder generates the future trajectory conditioned on the predicted maneuver among 3 classes: Lane Changing Left (LCL), Lane Changing Right (LCR) and Lane Keeping (LK). Experiments demonstrate the improvement of our model in prediction on the publicly available NGSIM and HighD datasets. We also present quantitative analysis to study the relationship between maneuver prediction accuracy and trajectory error.

Over the last decades, facing the blooming growth of technological progress, interest in digital devices such as computed tomography (CT) as well as magnetic resource imaging which emerged in the 1970s has continued to grow. Such medical data can be invested in numerous visual recognition applications. In this context, these data may be segmented to generate a precise 3D representation of an organ that may be visualized and manipulated to aid surgeons during surgical interventions. Notably, the segmentation process is performed manually through the use of image processing software. Within this framework, multiple outstanding approaches were elaborated. However, the latter proved to be inefficient and required human intervention to opt for the segmentation area appropriately. Over the last few years, automatic methods which are based on deep learning approaches have outperformed the state-of-the-art segmentation approaches due to the use of the relying on Convolutional Neural Networks. In this paper, a segmentation of preoperative patients CT scans based on deep learning architecture was carried out to determine the target organ’s shape. As a result, the segmented 2D CT images are used to generate the patient-specific biomechanical 3D model. To assess the efficiency and reliability of the proposed approach, the 3DIRCADb dataset was invested. The segmentation results were obtained through the implementation of a U-net architecture with good accuracy.

Group photo images are everywhere and vary greatly by the shooting scene. Compared with common images, the Image Aesthetic Quality Assessment (IAQI) of group photo pays more attention to the relevant characteristics of the main population. Still, the existing methods do not make further special research on group photos. Therefore, we propose a new concept of group photo styling based on analyzing group photos and photographic theory. Besides that, by comparing and analyzing many group photos, we classify the group photos into five categories. In this paper, the main factors of the head and pose are considered simultaneously, and the method of Group Photo Styling Classification (GPSC) can classify different group photos automatically. To verify the effectiveness of our method, we collected a Group Photo Styling Dataset (GPSD). The dataset contains 998 group photo images, and each image’s group photo styling category is marked. The experimental results on GPSD show that the fusion of head features and pose features can classify different group photos well. The accuracy of GPSC reaches 93.9%, much higher than the previous classification model.