Today, smart cities are turning to electric transport, carpooling and zero emission zones. The growing number of electric vehicles on the roads makes it increasingly necessary to have a public charging infrastructure. On the other hand, the main limitations of electric vehicles are the limited range of their batteries and their relatively long charging times. To avoid having problems to recharge, electric vehicle drivers must plan their journeys more thoroughly than others. At the goal of optimizing trip time, drivers need to automate their travel plans based on a smart charging solution, which will require the development of new Vehicle-to-Grid applications that will allow at the charging stations to dynamically interact with the vehicles. In this paper, we propose an architecture based on an algorithm allowing the management of charging plans for electric vehicles traveling on the road to their destination, in order to minimize the duration of the drivers’ journey including waiting and charging times. The decision taken by the algorithm based on the exploration of the data of each public supply station according to its location, number of vehicles in the queue, number of charging sockets, and rates of service.

This paper proposes a hybrid method for skin lesion classification combining deep learning features with conventional descriptors such as HOG, Gabor, SIFT, and LBP. Feature extraction was performed by extracting features of interest within the tumor area using suggested fusion methods. We tested and compared features obtained from different deep learning models coupled to HOG-based features. Dimensionality reduction and performance improvement were achieved by Principal Component Analysis, after which SVM was used for classification. The compared methods were tested on the reference database skin cancer-malignant-vs-benign. The results show a significant improvement in terms of accuracy due to complementarity between the conventional and deep learning-based methods. Specifically, the addition of HOG descriptors led to an accuracy increase of 5% for EfficientNetB0, 7% for ResNet50, 5% for ResNet101, 1% for NASNetMobile, 1% for DenseNet201, and 1% for MobileNetV2. These findings confirm that feature fusion significantly enhances performance compared to the individual application of each method.

The electric vehicle (EV) is considered an attractive alternative to a conventional vehicle, due to its potential beneficiation in decreasing carbon emission. But the battery range anxiety is a key challenge to its wide adoption and also the EV drivers spend so much time in public charging stations (CS) to charge especially during peak times. In this paper, we propose a charging station selected system (C3S) to control and manage EVs charging plans. Moreover, the C3S system proposed consists of a set of algorithms that are proposed to recommend a suitable CS for EV charging requests. The CS selection is based on minimizing travel time and takes into account in real-time the queuing time at CS, EVs' charging reservations, and the predicted time of EVs' future charging requests. Besides, we proposed three different strategies for predicting the EVs incoming and controlling the uncertainty matter of the dynamic arrival of EV charging requests. As part of the Helsinki City scenario, the evaluation results demonstrate the performance, especially at peak times, of our proposed C3S with regard to the CS recommendation which has the minimum total trip duration.

This paper examines the issue of 3D object indexing and retrieval and tries to solve this problem using partial indexing approach. The hypothesis in this context is that similar 3D objects will be composed of similar 2D slices. The proposed partial 3D object indexing and retrieval method is applicable on both complete and incomplete 3D objects, which is based on a similarity measuring between 2D slices of 3D objects. The main idea behind our approach is to extract an initial set of 2D slices corresponding to determined axes, and then use the Apriori algorithm to select the most representative ones, transforming the issue of shapematching between 3D objects into evaluating the similarities between their 2D slices. Experiments on the Princeton Shape Benchmark (PSB) indicate that our approach outperforms evaluated retrieval approaches.

Deep reinforcement learning (DRL) is widely assumed to outperform simpler rule-based and tabular baselines for sequential decision problems. We test this assumption for electric vehicle (EV) charging assignment using Simulation of Urban MObility (SUMO) simulations of real Rabat and Tangier road networks, with a protocol-amended, trained-vs-untrained diagnostic of Deep Q-Network (DQN) and Double DQN (DDQN) agents against untrained controls and an adaptive heuristic under a corrected pipeline and a not-yet-field-validated station-power regime. The primary endpoint, mean queue waiting time, is an assignment-to-arrival access delay. Trained policies are classified against a pre-specified 60 s rule using multiplicity-adjusted bootstrap intervals: of 12 pre-defined contrasts, none reaches the rule, two show a small detectable advantage, one is detrimental (softening to inconclusive with ten seeds), and nine are inconclusive. A legacy 210-run campaign predating the pipeline corrections is exploratory and shows no Holm-corrected difference. A reward/Markov decision process (MDP) audit identifies four structural defects and one replay sampling limitation; of the five audit-derived interventions, three were already active, one was structurally inert although enabled, and one showed no improvement. Exact per-contrast tests of the isolated ablations cannot reject at seven seeds; restoring R2 yields a small DDQN effect in one scenario that does not reproduce in a second. Two post hoc exploratory comparators, a deterministic minimum expected completion time dispatcher (MECT) and a discrete action proximal policy optimization (PPO) agent, are reported descriptively. The diagnostic does not separate under-training from a non-discriminative environment. The broader contribution is a reusable audit workflow for applied reinforcement learning benchmarks: endpoint semantic validation, trained-vs-untrained controls, multiplicity-adjusted inference and reward specification inspection.