Search

Visual observation and dermoscopic analysis are the most common methods of diagnosing skin cancer. In advanced stages, melanomas spread faster and are less responsive to treatment. Because different lesions in the skin appear similar to one another and sometimes errors in identification occur, the accuracy of diagnosis will decrease significantly when the amount of received images is large. However, the proposed methods for estimating skin lesions and their separation from melanoma have uncertainties and are not generalizable. This paper proposes an optimal decision tree (DT)-based approach, including fuzzy-ID3-pValue and Bayes learning algorithms, which overcomes these challenges. When classifying images, DTs employ a multi-stage procedure to partition the feature space, which enhances their ease of use, precision, and speed. Inference engines are used in fuzzy logic to derive logical deductions about knowledge, which facilitates learning DT and Bayesian learning. Taking advantage of the DT dependency structure, we present a novel fuzzy DT for extracting precise and collaborative fuzzy rules. Furthermore, to emphasize the cohesive nature of the laws, a weighted method is employed. Besides, the inference engine system is constructed through deductive and inductive inference engines. The proposed method is verified using the ISIC-2019 dataset as well as the PH2 images, both of which contain dermoscopic images of multiple lesions. The proposed method provides efficient results with 96% and 88% accuracy for ISIC-2019 and PH2 data, respectively. [ABSTRACT FROM AUTHOR]

Autonomous Vehicles (AVs) and driverless cars which are equipped with communication capabilities, advanced sensing, and Intelligent Control Systems (ICS), aim to modernize the transportation system. It increases user satisfaction by enhancing personal safety, reducing infrastructure costs, decreasing environmental interruption, and saving time for passengers. On the other hand, in emergency cases when AVs require maintenance, their generated sensitive information (e.g., AV location, low brake fluid amount of an AV) should be shared with Road Side Units (RSUs) and other vehicles to address their problems and provide quality services. Despite its appealing benefits, sensitive data sharing carries security and privacy issues that trigger serious risks like unintentional physical accidents. If the privacy of the AV is breached and its sensitive data is unintentionally disclosed during data transmission, adversaries can misuse them and cause artificial accidents. Current studies in this area lack efficiency and cost-effectiveness. To fill this gap and reduce the number of potential accidents, this article proposes a new Context-Aware Privacy-Preserving method for Autonomous Driving (CAPPAD). In particular, the Software-Defined Networking (SDN) paradigm is employed to bring flexibility to AVs' privacy management while its SDN controller runs a novel algorithm for privacy preservation. Depending on whether the data generated is sensitive or not and whether there is an emergency, the AV applies Differential Privacy (DP) or Data Aggregation (DA) as its privacy-preserving method. Finally, extensive simulations are performed through MININET-WIFI to show the performance of CAPPAD in terms of privacy-preserving degree, computational cost overhead, computational complexity overhead, and latency. We also compare it with other relevant well-known studies to show its superior effectiveness. [ABSTRACT FROM AUTHOR]

The method of indeterminate monitoring of household appliances involves analyzing voltage and current signals detected at the power supply. Each electrical appliance exhibits a distinct consumption pattern (e.g., vacuum cleaners, ovens, etc.), including their switch-on and switch-off timings. The monitoring system determines these consumption patterns of electric appliances. This study introduces a wireless sensor network designed for subtle monitoring of household appliance consumption. This study addresses the challenges and issues concerning wireless sensor networks, alongside the notable advantages and capabilities in the areas mentioned above, such as network structure, performance methods, monitoring types, and energy consumption factor analysis. Through empirical investigation and scientific discourse, the study's findings indicate that a higher number of nodes and windows in a building correlates with a reduced rate of energy transfer. Conversely, employing fewer nodes and windows increases the speed at which energy is transferred. [ABSTRACT FROM AUTHOR]

In this paper, a new chaotic image encryption and authentication model based on Elliptic Curves is proposed. The Elliptic Curve Diffie-Hellman (ECDH) is used to generate a reliable session key prior to encryption. The scheme uses the Henon map for the initial shuffling of the pixels and the Hopfield chaotic neural network to compute random chaotic values. The chaotic matrix is XORed with henon shuffled image. The model encrypts the scrambled image using improved ElGamal encoding to obtain the cipher image. The model employs a low computational cost digital signature to check for the authenticity of the received encrypted images before decryption. The proposed model makes use of a large key space to resist brute force attacks, and produces randomized cipher images with high average Shannon's entropies, 7.9994 for grayscale and 7.9993 for color images, and lower adjacent pixel correlation to resist statistical attacks and ensure a good quality encryption. The model can withstand the chosen-plaintext and known-plaintext attacks, and attains average Number of Pixel Change Rate (NPCR) and Unified Average Change Intensity (UACI) values of (99.63%, 33.345%) for grayscale and (99.625%, 33.34%) for color images signifying its effectiveness against differential attacks. The ability to recover decipherable images after masking up to 75% of cipher image indicates the robustness of the proposed scheme against the occlusion attacks. [ABSTRACT FROM AUTHOR]

Data is generated over time by each device in the Internet of Things (IoT) ecosphere. Recent years have seen a resurgence in interest in the IoT due to its positive impact on society. However, due to the automatic management of IoT devices, the possibility of disclosing sensitive information without user consent is high. A situation in which information should not be unintentionally disclosed to outside parties we do not trust, i.e., privacy-preservation. Additionally, IoT devices should share their data with others to perform data aggregation and provide high-level services. There is a trade-off between the amount of data utility and the amount of disclosure of data. This trade-off has been causing a big challenge in this field. To improve the efficiency of this trade-off rather than current studies, in this study, we propose a Privacy-Preserving Data Aggregation architecture, PPDMIT, that leverages Homomorphic Paillier Encryption (HPE), K-means, a One-way hash chain, and the Chinese Remainder Theorem (CRT). We have found that the proposed privacy-preserving architecture achieves more efficient data aggregation than current studies and improves privacy preservation by utilizing extensive simulations. Moreover, we found that our proposed architecture is highly applicable to IoT environments while preventing unauthorized data disclosure. Specifically, our solution depicted an 8.096% improvement over LPDA and 6.508% over PPIOT. [ABSTRACT FROM AUTHOR]

Artificial intelligence techniques are excessively used in computing for training, forecasting and evaluation purposes. Among these techniques, artificial neural network (ANN) is widely used for developing prediction models. ANNs use various Meta-heuristic algorithms including approximation methods for training the neural networks. ANN plays a significant role in this area and can be helpful in determining the neural network input coefficient. The main goal of presented study is to train the neural network using meta-heuristic approaches and to enhance the perceptron neural network precision. In this article, we used an integrated algorithm to determine the neural network input coefficients. Later, the proposed algorithm was compared with other algorithms such as ant colony and invasive weed optimization for performance evaluation. The results reveal that the proposed algorithm results in more convergence with neural network coefficient as compared to existing algorithms. However the proposed method resulted in reduction of prediction error in the neural network. [ABSTRACT FROM AUTHOR]

With the recent development and advancement of business growth models, information exchange has emerged as a critical component of computer communication technology. To serve dynamic business models with the latest data, most system architecture tends to retrieve data from back-end systems in real-time. Numerous leading organizations have started to think of or are implementing two different platforms: read cluster and write cluster. In this article, we propose a model that adopts a data streaming system and a data caching mechanism for faster access to real-time and non-real-time data. This system only focuses on providing the read data elements and reducing most of the load in the existing cluster(s). Our mathematical and simulation performance analysis shows a clear distinction and comparison between the current and proposed systems architecture. [ABSTRACT FROM AUTHOR]

A 33-year-old female presented with lethargy due to multidrug toxicity. At physical examination, both gluteal regions showed brown patchy scars. The atrophic scars surrounding necrotic lesions were round and brown in appearance, and gluteal mass had gradually been lost. The patient disclosed using intramuscular ketamine injections for 3.5 years along with smoking hashish, alcohol use, intranasal use of methamphetamine (sniffing), and oral use of methadone. Since recreational drug use can affect multiple organs, dermatologists should be familiar with the dermatologic features of intravenous or intramuscular injecting drug use. [ABSTRACT FROM AUTHOR]

Nowadays, wireless mesh networks are known as important parts of different commercial, scientific, and industrial processes. Their prevalence increases day-by-day and the future of the world is associated with such technologies for better communication. However, the issue of improving quality of service for dealing with more complex and intense flow of data has been always a remarkable research problem, as a result of improved wireless communication systems. In this sense, objective of this study is to provide a new algorithm for contributing to the associated literature. In the study, peer to peer wireless mesh networks and the concept of service quality were examined first and then an approach for improving service quality in such networks has been proposed accordingly. In detail, the proposed an approach allows profiting data transfer capability by data packet and using this information for routing and preventing overcrowd in network nodes and finally, distributing the load over it. When middle nodes overcrowd, they withhold to send control messages of route creating or do that by delay. The proposed approach has been evaluated and the findings revealed that at least 10% of undue delays through network can be prevented while permittivity does not reduce, thanks to the approach. Also energy consumption within network nodes partially increases due to adding table and the search which can be overlooked. [ABSTRACT FROM AUTHOR]

The original version of this article unfortunately contained an error in one of the co-author's name. The third author's name should read as "Xiaobo Zhang" instead of "Xioabo Zhang". [ABSTRACT FROM AUTHOR]