Heba M. El-Hoseny^1,*, Heba F. Elsepae², Wael A. Mohamed², Ayman S. Selmy²

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 1855-1872, 2023, DOI:10.32604/cmc.2023.042107

Abstract Diabetic retinopathy is a critical eye condition that, if not treated, can lead to vision loss. Traditional methods of diagnosing and treating the disease are time-consuming and expensive. However, machine learning and deep transfer learning (DTL) techniques have shown promise in medical applications, including detecting, classifying, and segmenting diabetic retinopathy. These advanced techniques offer higher accuracy and performance. Computer-Aided Diagnosis (CAD) is crucial in speeding up classification and providing accurate disease diagnoses. Overall, these technological advancements hold great potential for improving the management of diabetic retinopathy. The study’s objective was to differentiate between different classes of diabetes and verify the… More >

Abid Mahboob¹, Muhammad Asif², Rana Muhammad Zulqarnain^3,*, Imran Saddique⁴, Hijaz Ahmad⁵, Sameh Askar⁶

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2565-2578, 2023, DOI:10.32604/cmc.2023.040371

Abstract Nowadays, one of the most important difficulties is the protection and privacy of confidential data. To address these problems, numerous organizations rely on the use of cryptographic techniques to secure data from illegal activities and assaults. Modern cryptographic ciphers use the non-linear component of block cipher to ensure the robust encryption process and lawful decoding of plain data during the decryption phase. For the designing of a secure substitution box (S-box), non-linearity (NL) which is an algebraic property of the S-box has great importance. Consequently, the main focus of cryptographers is to achieve the S-box with a high value of… More >

Yonghao Tang¹, Zhiping Cai^1,*, Qiang Liu¹, Tongqing Zhou¹, Qiang Ni²

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2645-2656, 2023, DOI:10.32604/cmc.2023.032307

Abstract As an emerging discipline, machine learning has been widely used in artificial intelligence, education, meteorology and other fields. In the training of machine learning models, trainers need to use a large amount of practical data, which inevitably involves user privacy. Besides, by polluting the training data, a malicious adversary can poison the model, thus compromising model security. The data provider hopes that the model trainer can prove to them the confidentiality of the model. Trainer will be required to withdraw data when the trust collapses. In the meantime, trainers hope to forget the injected data to regain security when finding… More >

Muhammad Tahir^1,2,*, Mingchu Li^1,2, Irfan Khan^1,2, Salman A. Al Qahtani³, Rubia Fatima⁴, Javed Ali Khan⁵, Muhammad Shahid Anwar⁶

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2529-2544, 2023, DOI:10.32604/cmc.2023.042403

Abstract Real-time health data monitoring is pivotal for bolstering road services’ safety, intelligence, and efficiency within the Internet of Health Things (IoHT) framework. Yet, delays in data retrieval can markedly hinder the efficacy of big data awareness detection systems. We advocate for a collaborative caching approach involving edge devices and cloud networks to combat this. This strategy is devised to streamline the data retrieval path, subsequently diminishing network strain. Crafting an adept cache processing scheme poses its own set of challenges, especially given the transient nature of monitoring data and the imperative for swift data transmission, intertwined with resource allocation tactics.… More >

Arif Hussain Magsi^1,*, Ali Ghulam², Saifullah Memon¹, Khalid Javeed³, Musaed Alhussein⁴, Imad Rida⁵

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 1445-1465, 2023, DOI:10.32604/cmc.2023.040290

Abstract Named Data Networking (NDN) is gaining a significant attention in Vehicular Ad-hoc Networks (VANET) due to its in-network content caching, name-based routing, and mobility-supporting characteristics. Nevertheless, existing NDN faces three significant challenges, including security, privacy, and routing. In particular, security attacks, such as Content Poisoning Attacks (CPA), can jeopardize legitimate vehicles with malicious content. For instance, attacker host vehicles can serve consumers with invalid information, which has dire consequences, including road accidents. In such a situation, trust in the content-providing vehicles brings a new challenge. On the other hand, ensuring privacy and preventing unauthorized access in vehicular (VNDN) is another… More >

Rizwan Iqbal^1,*, Rashid Hussain², Sheeraz Arif³, Nadia Mustaqim Ansari⁴, Tayyab Ahmed Shaikh²

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 1575-1598, 2023, DOI:10.32604/cmc.2023.042432

Abstract Software-Defined Networking (SDN) is a new network technology that uses programming to complement the data plane with a control plane. To enable safe connection, however, numerous security challenges must be addressed. Flooding attacks have been one of the most prominent risks on the internet for decades, and they are now becoming challenging difficulties in SDN networks. To solve these challenges, we proposed a unique firewall application built on multiple levels of packet filtering to provide a flooding attack prevention system and a layer-based packet detection system. This study offers a systematic strategy for wrapping up the examination of SDN operations.… More >

Lingyu Liang¹, Xiangyu Zhao^1,*, Wenqi Huang¹, Liming Sun^2,3, Ziyao Wang³, Yaosen Zhan²

Energy Engineering, Vol.120, No.12, pp. 2839-2856, 2023, DOI:10.32604/ee.2023.042042

Abstract The N-1 criterion is a critical factor for ensuring the reliable and resilient operation of electric power distribution networks. However, the increasing complexity of distribution networks and the associated growth in data size have created a significant challenge for distribution network planners. To address this issue, we propose a fast N-1 verification procedure for urban distribution networks that combines CIM file data analysis with MILP-based mathematical modeling. Our proposed method leverages the principles of CIM file analysis for distribution network N-1 analysis. We develop a mathematical model of distribution networks based on CIM data and transfer it into MILP. We… More >

Peng Cheng^1,2,*

Journal on Big Data, Vol.5, pp. 69-84, 2023, DOI:10.32604/jbd.2023.046294

Abstract To serve as a reference for future foreign tourism study, relevant tourist sectors have done in-depth investigations on foreign tourism both domestically and internationally. A study of outbound tourism activities from the viewpoint of tourists can examine its development law and create successful marketing tactics based on the rise in the number of foreign tourists. Based on this, this study suggests a data mining technique to examine the variations in travel needs and marketing tactics among various consumer groups. The combined example analysis demonstrates how logical and useful our data mining analysis is. Our data tests demonstrate that the tourism… More >

Shaocheng Wu¹, Honghao Liang¹, Xiaowei Chen¹, Tao Liu¹, Junpeng Ru^2,3, Qianhong Gong^2,3, Jin Li^2,3,*

Journal on Big Data, Vol.5, pp. 57-67, 2023, DOI:10.32604/jbd.2023.044257

Abstract Enabling data sharing among smart grid power suppliers is a pressing challenge due to technical hurdles in verifying, storing, and synchronizing energy metering data. Access and sharing limitations are stringent for users, power companies, and researchers, demanding significant resources and time for permissions and verification. This paper proposes a blockchain-based architecture for secure and efficient sharing of electric energy metering data. Further, we propose a data sharing model based on evolutionary game theory. Based on the Lyapunov stability theory, the model’s evolutionary stable strategy (ESS) is analyzed. Numerical results verify the correctness and practicability of the scheme proposed in this… More >

Sanxiu Jiao¹, Lecai Cai^2,*, Xinjie Wang¹, Kui Cheng², Xiang Gao³

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.2, pp. 1679-1694, 2024, DOI:10.32604/cmes.2023.030512

Abstract As a distributed machine learning method, federated learning (FL) has the advantage of naturally protecting data privacy. It keeps data locally and trains local models through local data to protect the privacy of local data. The federated learning method effectively solves the problem of artificial Smart data islands and privacy protection issues. However, existing research shows that attackers may still steal user information by analyzing the parameters in the federated learning training process and the aggregation parameters on the server side. To solve this problem, differential privacy (DP) techniques are widely used for privacy protection in federated learning. However, adding… More > Graphic Abstract