Real-Time Classification of Diesel Marine Engine Loads Using Machine Learning.

An engine control system is responsible for controlling the combustion parameters of an internal combustion engine to increase the efficiency of the engine. An optimized parameter setting of an engine control system is highly influenced by the engine load. Therefore, with a change in engine load, the parameter settings need to be updated for higher engine efficiency. Hence, to optimize parameter settings during operation, engine load information is necessary. In this paper, we propose a real-time engine load classification from sensed signals. For the classification, an artificial neural network is used and trained using processed, real, measured data. To that end, a magnetic pickup sensor extracts the rotational speed of the prime mover of a four-stroke V12 marine diesel engine. The measured signal is then converted into a crank angle degree (CAD) signal that shows the behavior of the combustion strokes of firing cylinders at a particular engine load. The CAD signals are considered an input feature to the designed network for classification of engine loads. For verification, we considered five classes of engine load, and the trained network classifies these classes with an accuracy of 99.4%.

An emergency packet forwarding scheme for V2V communication networks.

This paper proposes an effective warning message forwarding scheme for cooperative collision avoidance. In an emergency situation, an emergency-detecting vehicle warns the neighbor vehicles via an emergency warning message. Since the transmission range is limited, the warning message is broadcast in a multihop manner. Broadcast packets lead two challenges to forward the warning message in the vehicular network: redundancy of warning messages and competition with nonemergency transmissions. In this paper, we study and address the two major challenges to achieve low latency in delivery of the warning message. To reduce the intervehicle latency and end-to-end latency, which cause chain collisions, we propose a two-way intelligent broadcasting method with an adaptable distance-dependent backoff algorithm. Considering locations of vehicles, the proposed algorithm controls the broadcast of a warning message to reduce redundant EWM messages and adaptively chooses the contention window to compete with nonemergency transmission. Via simulations, we show that our proposed algorithm reduces the probability of rear-end crashes by 70% compared to previous algorithms by reducing the intervehicle delay. We also show that the end-to-end propagation delay of the warning message is reduced by 55%.

Mobility-assisted on-demand routing algorithm for MANETs in the presence of location errors.

We propose a mobility-assisted on-demand routing algorithm for mobile ad hoc networks in the presence of location errors. Location awareness enables mobile nodes to predict their mobility and enhances routing performance by estimating link duration and selecting reliable routes. However, measured locations intrinsically include errors in measurement. Such errors degrade mobility prediction and have been ignored in previous work. To mitigate the impact of location errors on routing, we propose an on-demand routing algorithm taking into account location errors. To that end, we adopt the Kalman filter to estimate accurate locations and consider route confidence in discovering routes. Via simulations, we compare our algorithm and previous algorithms in various environments. Our proposed mobility prediction is robust to the location errors.

Effects of the material properties and thickness on the minimum formable radius in the subtle feature forming process.

The subtle feature geometry also called a feature line, is considered an important geometric characteristic of automotive outer panels. The influences of material properties and thickness on the radius of curvature of subtle features were investigated in this study. First, the stamping process was simplified to a combined forming process between tensile and bending deformation. Subsequently, test materials, namely, 180B2, 210B2, CR2, CR3, and CR4, with various thickness values were adopted in the finite element analysis and experiments. In addition, the radius of curvature with respect to the material, thickness, punch radius, and punch angle was studied. The simulation results were compared with the experimental results for verification. From this comparison, it was found that the simulation results were in good agreement with the experimental data. Finally, the forming characteristics of the subtle feature-forming process were investigated to determine the effects of the material properties and thickness on the radius of curvature. The reason for the minimum formable radius when the radius of the punch was zero was studied. The results showed that, as the material thickness increased, more concentrated deformation occurred in the central region. In contrast, the radius of curvature of the subtle features increased as the thickness of the central region decreased. Similarly, decreased n-value results were identified for the same reason as the increased radius of curvature.

Differential expression and cellular localization of doublecortin in the developing rat retina.

Doublecortin is 40 kDa microtubule-associated phosphoprotein required for neuronal migration and differentiation in various regions of the developing central nervous system. We have investigated the expression and cellular localization of doublecortin in the developing rat retina using immunocytochemistry and Western blot analysis. The expression of doublecortin was high from embryonic day 18 (E18) until E20 and was low during the postnatal period. The doublecortin immunoreactivity first appeared in a few radially orientated cells in the mantle zone of the primitive retina at E15. From E16 onward, the immunoreactivity appeared in two different regions: the inner part of the retina and middle of the neuroblastic layer. In the inner part, the somata of cells in the ganglion cell layer, in the distal row of the neuroblastic layer and profiles in the inner plexiform layer showed doublecortin immunoreactivity up to postnatal day 1 (P1). Afterwards, the doublecortin immunoreactivity persisted in the inner plexiform layer until P15, although the intensity decreased gradually with the maturation of the retina. In the middle of the neuroblastic layer, doublecortin immunoreactivity appeared in the radially orientated cells. These cells transformed into horizontal cells. The doublecortin immunoreactivity persisted in these cells up to P21. Given these results, doublecortin may play an important role in the migration and differentiation of specific neuronal populations in developmental stages of the rat retina.

Localization of CD15 immunoreactivity in the rat retina.

Using immunocytochemistry, we have investigated the localization of CD15 in the rat retina. In the present study, two types of amacrine cell in the inner nuclear layer (INL) and some cells in the ganglion cell layer were labeled with anti-CD15 antisera. Type 1 amacrine cells have large somata located in the INL, with long and branched processes ramifying mainly in stratum 3 of the inner plexiform layer (IPL). Type 2 cells have a smaller soma and processes branching in stratum 1 of the IPL. A third population showing CD15 immunoreactivity was a class of displaced amacrine cells in the ganglion cell layer. The densities of type 1 and type 2 amacrine cells were 166/mm(2) and 190/mm(2) in the central retina, respectively. The density of displaced amacrine cells was 195/mm(2). Colocalization experiments demonstrated that these CD15-immunoreactive cells exhibit gamma-aminobutyric acid and neuronal nitric oxide synthase (nNOS) immunoreactivities. Thus, the same cells of the rat retina are labeled by anti-CD15 and anti-nNOS antisera and these cells constitute a subpopulation of GABAergic amacrine cells.