This paper looks at how AI and machine learning have been applied over the last ten years to the development of anti-cancer drugs. By speeding up the synthesis of more desirable compounds and the identification of new ones, artificial intelligence (AI) hasdemonstrated substantial contributions to the research and therapy of anti-cancer therapies. Methods: This work is a narrative review that examines numerous uses of AI-based techniques in the development of anti-cancer medications. Results:Future developments in human cancer research and treatment are anticipated to be significantly influenced by AI. Protein-interaction network analysis, drug target prediction, binding site prediction, and virtual screening are examples of innovative techniques. Drug design and screening are enhanced by machine learning, and the use of multitarget drug development approaches has made it possible to develop cancer treatments with fewer side effects. AI does, however, have several drawbacks, such as a heavy reliance on data and a narrow scope of explanation. Interpretable AI models, which combine data and computation in AI-assisted cancer treatment research, will be the new development path in the future.Conclusion:For more than thirty years, computer-aided drug design techniques have been a key component in the advancement of cancer therapies. Artificial intelligence is a new and powerful technology that has the potential to speed up, lower the cost, and improve the efficacy of anti-cancer therapy development.

---

Journal: Journal of Ayub Medical College, Abbottabad, Pakistan, Volume 36 , Issue 1, Feb 2024.

The global impact of the COVID-19 pandemic has reached virtually every part of the world, significantly impacting people's health and daily routines. It has disrupted physical activities and necessitates early identification of infected individualsfor proper care. Identifying the disease through radiography and radiology images stands out as one of the quickest approaches. Previous research indicates that COVID-19 patients often exhibit distinct abnormalities in chest radiographs. Radiologists have the ability to detect the existence of COVID-19 by analyzing these images. This study employs a deep learning model that utilizes CT scan images to identify COVID-19 disease in patients. In the beginning, a dataset comprising 746 CT scan images from openly accessible sources is compiled, and then same dataset had been applied for augmentation which creates total 2984 images. Transfer learning is employed to train Convolutional Neural Networks (CNN) using VGG19, enabling the recognition of COVID-19 disease in the examined CT scan images. Additionally, it integrates an IoT-based application and validates the framework. The model undergoes assessment using 521 images for training, 112 images for validation, and the remaining 113 for testing, and then same images created a new dataset using the concept of augmentation and total 2984 images were spitted into 2088 images for training, 449 images for testing and remaining 447 images for validation. The model's efficiency is evaluated by assessing parameters such as precision, recall, FScore, and the confusion matrix. The implementation and validation of the study have been successful.

---

Journal: Journal of Electrical Systems, Volume 20 , Issue 3, Jan 2024.

Phishing, an Internet fraudwhere individuals are deceived into revealing critical personal and account information, poses a significant risk to both consumers and web-based institutions. Data indicates a persistent rise in phishing attacks. Moreover, these fraudulent schemes are progressively becoming more intricate, thereby rendering them more challenging to identify.Hence, it is imperative to utilize sophisticated algorithms to address this issue.Machine learning is a highly effective approach for identifying and uncovering these harmful behaviors. Machine learning (ML) approaches can identify common characteristics in most phishing assaults. In this paper, we propose an ensemble approach and compare it with six machine learning techniques to determine the type of website and whether it is normal or not based on two phishing datasets. After that, we used the normalization technique on the dataset to transform the range of all the features into the same range. The findings of this paper for all algorithms are as follows in the first dataset based on accuracy, precision, recall, and F1-score, respectively:Decision Tree (DT) (0.964, 0.961, 0.976, 0.968), Random Forest (RF) (0.970, 0.964, 0.984, 0.974), Gradient Boosting (GB) (0.960, 0.959, 0.971, 0.965), XGBoost (XGB) (0.973, 0.976, 0.976, 0.976), AdaBoost (0.934, 0.934, 0.950, 0.942), Multi Layer Perceptron (MLP) (0.970, 0.971, 0.976, 0.974) and Voting (0.978, 0.975, 0.987, 0.981). So, the Voting classifier gave the best results.While inthe seconddataset, all the algorithms gave the same results in four evaluation metrics, which indicates that each of them can effectively accomplish the prediction process. Also, this approach outperformed the previous work in detecting phishing websites with high accuracy, a lower false negative rate, a shorter prediction time, and a lower false positive rate.

---

Journal: CMES-Computer Modeling in Engineering & Sciences, Volume 80 , Issue 1, Jul 2024.

In an era characterized by the relentless evolution of Internet of Things (IoT) technologies, marked by the pervasive adoption of smart devices and the ever-expanding realm of Internet connectivity, the IoT has seamlessly integrated itself into our daily lives. This integration has ushered in a new era for manufacturing companies, enabling them to conduct real-time monitoring of their machinery, supervise product quality, and closely monitor environmental variables within their facilities. In addition to the immediate benefits of risk mitigation and loss prevention, this multifaceted approach has provided decision-makers with a comprehensive perspective for making informed decisions. People are now more dependent than ever in IoT devices and services. However, anomalies within IoT networks pose a critical concern despite the IoT's immense potential. These anomalies can pose significant security and safety risks if they go undetected. Identifying and alerting users of these anomalies on time has become crucial for preventing potential damages and losses. In response to this imperative, our research endeavors to utilize the power of Machine Learning and Deep Learning techniques to detect anomalies in IoT networks. We undertake exhaustive experiments with the IoT-23 dataset to validate our methodology empirically. Our research examines an exhaustive comparison of numerous models, assessing their performance and time efficiency to determine the optimal algorithm for achieving high detection accuracy under strict time constraints. This research represents an important step towards enhancing the security of Industrial IoT environments, thereby protecting vital infrastructure and ensuring the integrity of industrial operations in our increasingly interconnected world.

---

Journal: International Journal of Intelligent Systems and Applications in Engineering (IJISAE), ISSN 1247-6799, Volume 12, Issue 2, Jan 2024

The Internet of Things (IoT) technology has recently emerged as a potential global communication medium that efficiently facilitates human-to-human, human-to-machine, and machine-tomachine communications. Most importantly, unlike the traditional Internet, it supports machine-to-machine communication without human intervention. However, billions of devices connected to the IoT environment are mostly wireless, small, hand-held, and resourced-constrained devices with limited storage capacities. Such devices are highly prone to external attacks. These days, cybercriminals often attempt to launch attacks on these devices, which imposes the major challenge of efficiently implementing communications across the IoT environment. In this paper, the issue of cyber-attacks in the IoT environment is addressed. An end-to-end encryption scheme was proposed to protect IoT devices from cyber-attacks.

---

Journal: Tikrit Journal of Engineering Sciences, ISSN 2312-7589, Volume 30, NO. 4, Dec 2023

In normal pharmacological effect screening protocols, natural substances that were thoroughly diluted and without their active components separated are employed. Over the last two decades, strong active isomeric compounds have been identified and isolated. The notion of multitarget treatment was novel in the mid-2000s, but it will be one of the most significant advancements in drug development by 2021. Instead, then relying on organically generated mixtures, researchers are looking at target-based drug development based on precisely specified fragments for effective organic anticancer medicines. This study emphasizes the breakdown of structures utilizing computer aids or fragments, as well as a process for applying natural anticancer medications. The use of computer-assisted drug development (CADD) is becoming more frequent. The major areas of this study were the development of computer-aided pharmaceuticals and anticancer agents. The discovery of effective all-natural cancer treatments will be accelerated. Multitarget drug development methodologies have enabled the development of cancer medicines with fewer negative side effects. Cutting-edge analytical and bioinformatics approaches, particularly machine learning, will be employed to uncover natural anticancer therapies

---

Journal: “,Journal of Ayub Medical College, Abbottabad, Pakistan, ISSN 1025-9589 , Volume 36 , Issue 1, Feb 2024

Mobile learning applications utilise the advantages of mobile technologies to increase learning opportunities, mainly on an anytime, anywhere basis. The advancement of mobile technology has facilitated the development of numerous applications to improve students’ learning experience and performance. Successful implementation of m-learning is highly dependent on learning context and environment awareness. This work presents a multiphase exploration of early phases responsible for defining and validating the m-learning context, and later phases based on context validation results achieved from the previous phases, involving the development and evaluation of a new m-learning context prototype. This new prototype proved to provide context-aware and ubiquitous learning services fulfilling several diverse user interaction levels and requirements.

---

Journal: International Journal of Computer applications in Technology. 58 (4), 296- 307.

This paper delves into the capacity of enhanced Big Bang-Big Crunch (EBB-BC) metaheuristic to handle data clustering problems. BB-BC is a product of an evolution theory of the universe in physics and astronomy. Two main phases of BB-BC are big bang and big crunch. The big bang phase involves a creation of a population of random initial solutions, while in the big crunch phase these solutions are shrunk into one elite solution exhibited by a mass center. This study looks into enhancing the BB-BC’s effectiveness in clustering data. Where, the inclusion of an elite pool alongside implicit solution recombination and local search method, contribute to such enhancement. Such strategies resulted in a balanced search of good quality population that is also diverse. The proposed elite pool-based BB-BC was compared with the original BB-BC and other identical metaheuristics. Fourteen different clustering datasets were used to test BB-BC and the elite pool-based BB-BC showed better performance compared to the original BB-BC. BB-BC was impacted more by the incorporated strategies. The experiments outcomes demonstrate the high quality solutions generated by elite pool-based BB-BC. Its performance in fact supersedes that of identical metaheuristics such as swarm intelligence and evolutionary algorithms.

---

Journal: Journal of Computer Science. 14 (12), 1611-1626.

---

Journal: 20th International Congress on Modelling and Simulation, Adelaide, Australia

---

Journal: 19th International Congress on Modelling and Simulation, Perth, Australia