Design of a Commercial Hybrid VTOL UAV System

For the last four decades Unmanned Air Vehicles (UAVs) have been extensively used for military operations that include tracking, surveillance, active engagement with weapons and airborne data acquisition. UAVs are also in demand commercially due to their advantages in comparison to manned vehicles. These advantages include lower manufacturing and operating costs, flexibility in configuration depending on customer request and not risking the pilot on demanding missions. Even though civilian UAVs currently constitute 3 % of the UAV market, it is estimated that their numbers will reach up to 10 % of the UAV market within the next 5 years. Most of the civilian UAV applications require UAVs that are capable of doing a wide range of different and complementary operations within a composite mission. These operations include taking off and landing from limited runway space, while traversing the operation region in considerable cruise speed for mobile tracking applications. This is in addition to being able traverse in low cruise speeds or being able to hover for stationary measurement and tracking. All of these complementary and but different operational capabilities point to a hybrid unmanned vehicle concept, namely the Vertical Take-Off and Landing (VTOL) UAVs. In addition, the desired UAV system needs to be cost-efficient while providing easy payload conversion for different civilian applications. In this paper, we review the preliminary design process of such a capable civilian UAV system, namely the TURAC VTOL UAV. TURAC UAV is aimed to have both vertical take-off and landing and Conventional Take-off and Landing (CTOL) capability. TURAC interchangeable payload pod and detachable wing (with potential different size variants) provides capability to perform different mission types, including long endurance and high cruise speed operations. In addition, the TURAC concept is to have two different variants. The TURAC A variant is an eco-friendly and low-noise fully electrical platform which includes 2 tilt electric motors in the front, and a fixed electric motor and ducted fan in the rear, where as the TURAC B variant is envisioned to use high energy density fuel cells for extended hovering time. In this paper, we provide the TURAC UAV’s iterative design and trade-off studies which also include detailed aerodynamic and structural configuration analysis. For the aerodynamic analysis, an in-house software including graphical user interface has been developed to calculate the aerodynamic forces and moments by using the Vortex Lattice Method (VLM). Computational Fluid Dynamics (CFD) studies are performed to determine the aerodynamic effects for various configurations For structural analysis, a Finite Element Model (FEM) of the TURAC has been prepared and its modal analysis is carried out. Maximum displacements and maximal principal stresses are calculated and used for streamlining a weight efficient fuselage design. Prototypes have been built to show success of the design at both hover and forward flight regime. In this paper, we also provide the flight management and autopilot architecture of the TURAC. The testing of the controller performance has been initiated with the prototype of TURAC. Current work focuses on the building of the full fight test prototype of the TURAC UAV and aerodynamic modeling of the transition flight.     

Large-scale SRAM-based IP lookup architectures using compact trie search structures

SRAM-based pipelined architectures for high-speed IP lookup using Field Programmable Gate Arrays (FPGAs) has recently attracted a great deal of attention from researchers. Due to the limited amount of on-chip memory and the number of I/O pins of FPGAs, compact data structures providing high memory efficiency are in great demand.     

Inferring Phylogenetic Trees Using Answer Set Programming

We describe the reconstruction of a phylogeny for a set of taxa, with a character-based cladistics approach, in a declarative knowledge representation formalism, and show how to use computational methods of answer set programming to generate conjectures about the evolution of the given taxa. We have applied this computational method in two domains: historical analysis of languages and historical analysis of parasite-host systems. In particular, using this method, we have computed some plausible phylogenies for Chinese dialects, for Indo-European language groups, and for Alcataenia species. Some of these plausible phylogenies are different from the ones computed by other software. Using this method, we can easily describe domain-specific information (e.g., temporal and geographical constraints), and thus prevent the reconstruction of some phylogenies that are not plausible. This paper is a revised and extended version of [3].     

Detection of COVID-19 and its pulmonary stage using Bayesian hyperparameter optimization and deep feature selection methods

Since the first case of COVID-19 was reported in December 2019, many studies have been carried out on artificial intelligence for the rapid diagnosis of the disease to support health services. Therefore, in this study, we present a powerful approach to detect COVID-19 and COVID-19 findings from computed tomography images using pre-trained models using two different datasets. COVID-19, influenza A (H1N1) pneumonia, bacterial pneumonia and healthy lung image classes were used in the first dataset. Consolidation, crazy-paving pattern, ground-glass opacity, ground-glass opacity and consolidation, ground-glass opacity and nodule classes were used in the second dataset. The study consists of four steps. In the first two steps, distinctive features were extracted from the final layers of the pre-trained ShuffleNet, GoogLeNet and MobileNetV2 models trained with the datasets. In the next steps, the most relevant features were selected from the models using the Sine–Cosine optimization algorithm. Then, the hyperparameters of the Support Vector Machines were optimized with the Bayesian optimization algorithm and used to reclassify the feature subset that achieved the highest accuracy in the third step. The overall accuracy obtained for the first and second datasets is 99.46% and 99.82%, respectively. Finally, the performance of the results visualized with Occlusion Sensitivity Maps was compared with Gradient-weighted class activation mapping. The approach proposed in this paper outperformed other methods in detecting COVID-19 from multiclass viral pneumonia. Moreover, detecting the stages of COVID-19 in the lungs was an innovative and successful approach.     

Dissimilarity between two skeletal trees in a context

Skeletal trees are commonly used in order to express geometric properties of the shape. Accordingly, tree-edit distance is used to compute a dissimilarity between two given shapes. We present a new tree-edit based shape matching method which uses a recent coarse skeleton representation. The coarse skeleton representation allows us to represent both shapes and shape categories in the form of depth-1 trees. Consequently, we can easily integrate the influence of the categories into shape dissimilarity measurements. The new dissimilarity measure gives a better within group versus between group separation, and it mimics the asymmetric nature of human similarity judgements.     

Mumford-Shah Regularizer with Contextual Feedback

We present a simple and robust feature preserving image regularization by letting local region measures modulate the diffusivity. The purpose of this modulation is to disambiguate low level cues in early vision. We interpret the Ambrosio-Tortorelli approximation of the Mumford-Shah model as a system with modulatory feedback and utilize this interpretation to integrate high level information into the regularization process. The method does not require any prior model or learning; the high level information is extracted from local regions and fed back to the regularization step. An important characteristic of the method is that both negative and positive feedback can be simultaneously used without creating oscillations. Experiments performed with both gray and color natural images demonstrate the potential of the method under difficult noise types, non-uniform contrast, existence of multi-scale patterns and textures.

Approximate probabilistic optimization using exact-capacity-approximate-response-distribution (ECARD)

Probabilistic structural design deals with uncertainties in response (e.g. stresses) and capacity (e.g. failure stresses). The calculation of the structural response is typically expensive (e.g., finite element simulations), while the capacity is usually available from tests. Furthermore, the random variables that influence response and capacity are often disjoint. In previous work we have shown that this disjoint property can be used to reduce the cost of obtaining the probability of failure via Monte Carlo simulations. In this paper we propose to use this property for an approximate probabilistic optimization based on exact capacity and approximate response distributions (ECARD). In Approximate Probabilistic Optimization Using ECARD, the change in response distribution is approximated as the structure is re-designed while the capacity distribution is kept exact, thus significantly reducing the number of expensive response simulations. ECARD may be viewed as an extension of SORA (Sequential Optimization and Reliability Assessment), which proceeds with deterministic optimization iterations. In contrast, ECARD has probabilistic optimization iterations, but in each iteration, the response distribution is approximated so as not to require additional response calculations. The use of inexpensive probabilistic optimization allows easy incorporation of system reliability constraints and optimal allocation of risk between failure modes. The method is demonstrated using a beam problem and a ten-bar truss problem. The former allocates risk between two different failure modes, while the latter allocates risk between members. It is shown that ECARD provides most of the improvement from risk re-allocation that can be obtained from full probabilistic optimization.     

Colon segmentation and colonic polyp detection using cellular neural networks and three-dimensional template matching

Abstract: In this study, an automatic three-dimensional computer-aided detection system for colonic polyps was developed. Computer-aided detection for computed tomography colonography aims at facilitating the detection of colonic polyps. First, the colon regions of whole computed tomography images were carefully segmented to reduce computational burden and prevent false positive detection. In this process, the colon regions were extracted by using a cellular neural network and then the regions of interest were determined. In order to improve the segmentation performance of the study, weights in the cellular neural network were calculated by three heuristic optimization techniques, namely genetic algorithm, differential evaluation and artificial immune system. Afterwards, a three-dimensional polyp template model was constructed to detect polyps on the segmented regions of interest. At the end of the template matching process, the volumes geometrically similar to the template were emhanced.     

Laser-induced fluorescence visualization of ion transport in a pseudo-porous capacitive deionization microstructure

In this paper, a microfluidic experimental set-up is introduced to study the ionic transport in an artificial capacitive deionization (CDI) cell. CDI is a promising desalination technique, which relies on the application of an external electric field and high surface area porous electrodes for ion separation and storage. Photolithography and deep reactive ion etching were used to fabricate a micro-CDI channel with pseudo-porous electrodes on a silicon-on-insulator substrate. Laser-induced fluorescence was performed using cationic Sulforhodamine B (SRB) fluorescent dye to measure ion concentration within the bulk solution and more importantly, within the porous electrodes during the desalination process, with an average normalized root mean square deviation of 8.2 %. Using this set-up, electromigration of ions within the electrode was visualized and the effect of applied electric potential on bulk solution concentration distribution is quantified. In addition, SRB and Fluorescein were used together to visualize anion and cation concentrations simultaneously. The method presented in this study can be used for solution concentrations up to approximately 0.7 mM. The ionic concentration profiles obtained by this approach can be used to test and validate the existing electrosorption models, and pseudo-porous electrodes can be modified to observe the effects of pore size, shape and distribution on electrosorption performance. Furthermore, with proper modifications, the microfabricated structure and experimental set-up can be used for CDI-on-a-chip applications and bio-separation devices.     

Dynamical system parameter identification using deep recurrent cell networks

Neural Computing and Applications - In this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear...