Aamir Saeed

Aamir Saeed

Auto-generated profile, based on publicly available information

Aamir Saeed

Department of Computer Science and IT, University of Engineering and Technology, Peshawar, Pakistan

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 October 2023 in IEEE Access
Verified
Journal Article
Open access
SAShahid Akbar
Shahid Akbar
ARAli Raza
Ali Raza
TSTamara Al Shloul
Tamara Al Shloul
AAAshfaq Ahmad
Ashfaq Ahmad
ASAamir Saeed
Aamir Saeed
ETElsayed Tag-Eldin
Elsayed Tag-Eldin
Mycobacterium tuberculosis, a highly perilous pathogen in humans, serves as the causative agent of tuberculosis (TB), affecting nearly 33% of the global population. With the increasing prevalence of multidrug-resistant TB, there is a needs for novel and efficacious alternative therapies. Peptide therapies have emerged as a favorable alternative due to its remarkable specificity in targeting effected cells without effecting healthy cells. However, the experimental identification of anti-tubercular peptides (AtbPs) is labor-intensive and costly. Therefore, accurate prediction of AtbPs has become challenging due to the large number of peptide samples. In this paper, we propose an ensemble learning model to enhance the prediction outcomes by addressing the limitations of individual learning models. We formulate the training samples by utilizing four distinct representation methods: AAindex, Composition/Transition/Distribution, Dipeptide Deviation from Expected Mean, and Enhanced Grouped Amino Acid Composition to numerically encode peptide samples. The feature vectors extracted from these methods are fused to develop a compact vector. We evaluate the prediction rates using three different classification models, employing both individual and heterogeneous vectors. Furthermore, we enhance the prediction and training capabilities of the proposed model by using the predicted labels of the individual classifiers for implementing an ensemble deep model via genetic algorithm. Through evaluation on both the training datasets and independent datasets, our proposed ensemble learner achieves impressive accuracies of 97.80%, 95.13%, 93.91%, and 94.17%, using RD training, MD training, RD independent, and MD independent datasets, respectively. Our findings demonstrate that the proposed pAtbP-EnC model outperforms existing predictors by reporting approximately 11% higher training accuracy. We conclude that the pAtbP-EnC predictor will be a considerable tool in the field of pharmaceutical design and research academia. The used datasets and the source code are publicly available at https://github.com/Intelligent-models/pAtbP-EnC2023.

25 December 2023 in IEEE Access
Verified
Journal Article
Open access
HJHamza Javed
Hamza Javed
ZAZainab Abaid
Zainab Abaid
SAShahid Akbar
Shahid Akbar
KUKifayat Ullah
Kifayat Ullah
AAAshfaq Ahmad
Ashfaq Ahmad
ARAli Raza
Ali Raza
IoT-based remote health monitoring is a promising technology to support patients who are unable to travel to medical facilities. Due to the sensitivity of health data, it is important to secure it against all possible threats. While a great deal of work has been done to secure IoT device-cloud communication and health records on the cloud, insider attacks remain a significant challenge. Malicious insiders may tamper, steal or change patients’ health data, which results in a loss of patient trust in these systems. Audit logs in the cloud, which may point to illegal data access, may also be erased or forged by malicious insiders as they tend to have technical knowledge and privileged access to the system. Thus, in this work, we propose a Cloud Access Security Broker (CASB) model that (a) logs every action performed on user data and (b) secures those logs by placing them in a private blockchain that is viewable by the data owners (i.e., patients). Patients can query the blockchain, track their data’s movement, and be alerted if their data has been accessed by an administrator or moved outside the cloud storage. In this work, we practically implement a web application that receives health data from patients, a CASB that securely stores the records in the cloud, and integrate a private blockchain that immediately logs all actions happening in the backend of the web application and CASB. We evaluate the system’s security and performance under varying numbers of patients and actions.

12 May 2023
Verified
Conference Paper
Closed access
ASAamir Saeed
Aamir Saeed
LGLiu Guibai
Liu Guibai
YDYang Danxia
Yang Danxia
ZWZhou Wei
Zhou Wei
DMDelidana Mansuer
Delidana Mansuer
LQLv Quan
Lv Quan
In order to effectively evaluate the maximum hosting capacity of distributed photovoltaic with battery energy storage systems in the distribution network under the premise of allowing rational photovoltaic curtailment, this paper constructs an evaluation model of the maximum hosting capacity of photovoltaic with battery energy storage systems in the distribution network, considering the constraints of photovoltaic curtailment rate. By linearizing power flow constraints and line capacity constraints, this model is constructed into a large-scale linear programming model with the scale of year and the granularity of hour as the scale. In order to effectively improve the solution efficiency, a scenario reduction strategy was proposed according to the model characteristics and the operation law of battery energy storage, which effectively reduced the size of the optimization model, and further ensured the optimality of understanding through the iterative update of the optimized scenario set. The numerical results show that the solution time can be reduced by 80% by using the proposed scenario reduction strategy, and the accuracy is basically unchanged.

6 February 2026 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
AAAmal Alrasheed
Amal Alrasheed
RKRahim Khan
Rahim Khan
AAAftab Ahmed
Aftab Ahmed
ASAamir Saeed
Aamir Saeed
FAFahad Alturise
Fahad Alturise
Salem AlkhalafSalem Alkhalaf
Salem Alkhalaf
The Internet of Things (IoT) consists of smart devices equipped with embedded sensors and actuators that interact with their surrounding environment, collect data, and share refined information with nearby server modules for informed decision-making. In most IoT networks, devices communicate over shared channels, making them highly vulnerable to intruder attacks aimed at eavesdropping on or hijacking communication sessions. Consequently, verifying the trustworthiness and legitimacy of both communicating entities—the source and destination devices—is essential before initiating any communication session. Although numerous authentication algorithms have been proposed in the literature to safeguard IoT devices from potential adversaries, existing approaches often suffer from limitations such as application specificity, high complexity, poor scalability, and limited robustness. To address these challenges, this paper introduces a hybrid authentication algorithm in which the source module verifies the trustworthiness of the destination through an encrypted challenge. This challenge is generated using a hybrid mechanism that combines Elliptic Curve Cryptography (ECC) with a pre-shared secret key. A legitimate destination device must successfully resolve the challenge and generate a timely response—an encrypted counter-challenge for the source device. The proposed hybrid authentication model ensures privacy preservation and message integrity for both communicating IoT devices. Its security and resilience against various intruder attacks are validated using OMNET++. Moreover, the model achieves significantly lower resource consumption compared to existing schemes, demonstrating approximately 17%, 21%, and 12% reductions in communication, processing, and storage costs, respectively, as illustrated through both textual and graphical evaluations.