@dcrlab.org
Dig Connectivity Research Laboratory (DCRLab)
DCRLab
Wasswa Shafik (IEEE member, P.Eng ) received a B.Sc. degree with honor rank in Mathematics and Computer Science in 2016 from Ndejje University, and an M.Sc. degree in Information Technology Engineering (MIT) in 2020, from the Computer Engineering Department, Yazd University, Islamic Republic of Iran. Prior to that, he was an associate researcher at the Computer Science Department and Network Interconnectivity Lab at Yazd University, Islamic Republic of Iran. He has authored and co-authored more than 60+ papers, refereed IEEE/ACM/Springer/Elsevier journals, conference papers, books, and book chapters. He is a founder and lead investigator of the Dig Connectivity Research Laboratory.
2021, MSc. In Information Technology Engineering, Computer and Communication Networks Option, Computer Engineering Department, Yazd University, Iran.
2016, BSc. Information Mathematics and Computer Science, Faculty of Science and Information Technology, Ndejje University, Uganda.
2012, Uganda Advanced Certificate of Education, Mulusa Academy, Luweero, Uganda East Africa.
Ecological Informatics, Computer Vision, AI-enabled IoT/IoMTs/IIoTs, Cyber Security, and Privacy, Smart Cities.
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Wasswa Shafik, Ali Tufail, Chandratilak De Silva Liyanage, and Rosyzie Anna Awg Haji Mohd Apong
BMC Plant Biology Springer Science and Business Media LLC
AbstractSubsistence farmers and global food security depend on sufficient food production, which aligns with the UN's “Zero Hunger,” “Climate Action,” and “Responsible Consumption and Production” sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.
Kassim Kalinaki, Wasswa Shafik, Sarah Namuwaya, and Sumaya Namuwaya
IGI Global
The emergence of the internet of things (IoT) has revolutionized many sectors of the economy, including logistics and supply chain management. By seamlessly integrating IoT into logistics operations, real-time tracking and monitoring of shipments becomes a reality, and optimizing routes and equipment performance becomes a breeze. Accordingly, supply chain operations have become streamlined like never before. This study delves into the various perspectives, applications, and challenges of deploying IoT in the logistics industry, offering a comprehensive overview for stakeholders, researchers, and students alike. With the potential for improved efficiency, effectiveness, and sustainability, the benefits of IoT in logistics are undeniable. The authors highlight future directions of this exciting field and learn how IoT shapes how we do business.
Wasswa Shafik
IGI Global
Examining the ethical aspects of artificial intelligence (AI) and data science (DS) recognizes their impressive progress in innovation while emphasizing the pressing necessity to tackle intricate ethical dilemmas. The chapter provides a detailed framework for navigating the changing environment, beginning with an examination of the increasing ethical challenges. The study highlights transparency, fairness, and responsibility as crucial for cultivating confidence in AI systems. The chapter emphasizes the urgent requirement to address problems such as algorithmic bias and privacy breaches with strong mitigation techniques. Furthermore, it promotes flexible policies that strike a balance between innovation and ethical safeguards. The examination of societal effects, particularly on various socioeconomic groups, economies, and cultures, is conducted thoroughly, with a focus on equity and the protection of individual rights. Finally, to proactively tackle future ethical challenges in technology, it is advisable to employ proactive solutions such as implementing AI ethics by design.
Wasswa Shafik
IGI Global
Artificial intelligence (AI) and robotics are becoming more popular globally, which makes Africa a potential hub for innovation and development in these fields. However, for the full benefits of these technologies to be realized, it is vital to understand and deal with the unique challenges and barriers that make it hard for them to be used and integrated in Africa. This chapter presents an overview of the current state of robotics and AI in Africa and explores the challenges associated with their adoption, including infrastructure limitations, inadequate technical expertise, and ethical considerations. It further discusses potential strategies for overcoming these challenges, such as investment in infrastructure and education, international collaboration, and the development of ethical frameworks for AI. Finally, the chapter suggests some future directions for continued attention and investment in the responsible and equitable development of AI and robotics in Africa to benefit stagnant and slow-growing African economies.
Yan Wang, Wasswa Shafik, Jin-Taek Seong, Aned Al Mutairi, Manahil SidAhmed Mustafa, and Mourad R. Mouhamed
Elsevier BV
Wasswa Shafik
IGI Global
The more technology advances, the extra benefits to the public and devices that connect to the internet have increased as well, commonly known as internet of things (IoT). The battery lifespan of these devices rises with technical concerns where an alternative to traditional energy attainment is needed. As the way forward, wireless sensor networks (WSNs) and IoT are tested to be used as novel energy alternatives through energy harvesting (EH). This study identifies the availability of energy by location. Similarly, it focuses on the sensor node's architecture with EH capabilities expanding to the classification of five EH techniques. It evaluates the EH developments in search of minimal resource utilization associated with WSNs. Its extensive distribution of interconnected devices is connected via the internet and other related high-tech innovations. Finally, it discusses the feasibility of energy storage and its potential for WSNs, paving the way for future trends and motivations.
Wasswa Shafik and Kassim Kalinaki
IGI Global
This chapter explores the growing use of technology in various aspects of people's lives and focuses on smart cities. First, it provides a comprehensive survey that examines the need for smart cities, their architectural elements, and the characteristics and purposes of different architectural layers. The chapter also offers an overview of notable smart cities such as London, New York, Singapore, Busan, Amsterdam, and Sunshine Coast Regions, highlighting their unique features. Next, privacy and security concerns associated with smart cities are addressed, emphasizing the importance of privacy issues and suggesting potential solutions. The chapter discusses future research directions, including the integration of blockchains, security considerations, collaborative filtering, and infrastructure upgrades in smart city applications. The analysis of privacy and security concerns is organized into three subsections: smart city security traits, leveraging issues, and privacy challenges and solutions. Finally, the chapter concludes by presenting future research trends in this field.
Wasswa Shafik, Ali Tufail, Chandratilak De Silva Liyanage, and Rosyzie Anna Awg Haji Mohd Apong
Wiley
BACKGROUND
Early plant diseases and pests identification reduces social, economic, and environmental deficiencies entailing toxic chemical utilization on agricultural farms, thus posing a threat to global food security.
METHODOLOGY
An enhanced convolutional neural network (CNN) along with long short-term memory (LSTM) using a majority voting (MVE) ensemble classifier has been proposed to tackle plant pest and disease identification and classification. Within pre-trained models, deep feature extractions have been obtained from connected layers. Deep features have been extracted and are sent to the LSTM layer to build a robust, enhanced LSTM-CNN model for detecting plant pests and diseases. Experiments were carried out using Turkey Dataset, with 4,447 apple pests and diseases categorized into 15 different classes.
RESULTS
The study has been evaluated in different CNNs using logistic regression (LR), LSTM, and extreme learning machine (ELM), focusing on plant disease detection problems. The ensemble majority voting (EMV) classifier was used at the LSTM layer to detect and classify plant disease labels. Furthermore, an autonomous selection of the optimal LSTM layer network parameters was applied. Finally, the performance was validated based on sensitivity, F1-score, accuracy, and specificity using LSTM, ELM, and LR classifiers.
CONCLUSION
The presented model attained 99.2% accuracy in comparison to the cutting-edge models on different classifiers like LSTM, LR, and ELM, and performed better in comparison to transfer learning (TL). Pre-trained models, like VGG-19, VGG-18, and AlexNet, demonstrated better accuracy when the fc6 layer was compared to other layers. This article is protected by copyright. All rights reserved.
Wasswa Shafik
IGI Global
As the public use drones (aircraft that can operate semi or autonomous), sometimes referred to as unmanned aerial vehicles or automotive aircrafts, to ease daily people's lifestyles, there are cyber security threats and cyber-attacks that hinder public safety and privacy during the moments when these drones are used. Cyber threats are analyzed based on the commonly known approaches to evaluate the cyber perspective and its effect on the public. Public drones' cyber security hazards are well tested using the STRIDE approach connected with the considered threats. The evaluation is highly dependent on the accuracy of drone mission definition, potential intruders, social, and other human-related cases. This chapter therefore encompasses the most current studies focusing on possible intruders portrayed as critical when carrying out a cyber security assessment. A brief future direction to mitigate cyber-related threats as it entails the public are conclusively depicted.
Sundus Naji Alaziz, Bakr Albayati, Abd al-Aziz H. El-Bagoury, and Wasswa Shafik
IGI Global
The COVID-19 pandemic is one of the current universal threats to humanity. The entire world is cooperating persistently to find some ways to decrease its effect. The time series is one of the basic criteria that play a fundamental part in developing an accurate prediction model for future estimations regarding the expansion of this virus with its infective nature. The authors discuss in this paper the goals of the study, problems, definitions, and previous studies. Also they deal with the theoretical aspect of multi-time series clusters using both the K-means and the time series cluster. In the end, they apply the topics, and ARIMA is used to introduce a prototype to give specific predictions about the impact of the COVID-19 pandemic from 90 to 140 days. The modeling and prediction process is done using the available data set from the Saudi Ministry of Health for Riyadh, Jeddah, Makkah, and Dammam during the previous four months, and the model is evaluated using the Python program. Based on this proposed method, the authors address the conclusions.
Ahmad Fathan Hidayatullah, Kassim Kalinaki, Muhammad Muzamil Aslam, Rufai Yusuf Zakari, and Wasswa Shafik
IEEE
Social media platforms like Twitter have become substantial sources of user-generated content, enabling people to easily express their emotions and opinions. However, this freedom has increased the spread of harmful content, such as abusive language, sexually explicit content, and hate speech. This poses challenges for content moderation and user safety. In order to guarantee a safer, more receptive, and more pleasurable online environment for users of all ages, it is essential to develop a system capable of recognizing abusive and sexually explicit material on Twitter. Despite the growing importance of content moderation, a research gap exists in Indonesian tweets, with limited comprehensive studies on negative content identification. This research addresses this gap by evaluating the effectiveness of Bidirectional Encoder Representations from Transformers (BERT) models in the Indonesian context, which were primarily developed for English and other languages. This research aims to identify abusive, adult, and neutral content in Indonesian tweets by examining and fine-tuning BERT-based models to maintain a healthy online environment for optimal tweet classification. Based on our experiments, the BERT-based models showed promising results in detecting negative tweets. Among the BERT-based models, IndoBERTweet achieved the best precision, recall, and macro F1 scores with 97.03, 96.88, and 96.94, respectively.
Wasswa Shafik, S. Mojtaba Matinkhah, and Fawad Shokoor
Walter de Gruyter GmbH
Abstract Context With the rapid advancement of unmanned aerial vehicle (UAV) technology, ensuring these autonomous systems’ security and integrity is paramount. UAVs are susceptible to cyberattacks, including unauthorized access, control, or manipulation of their systems, leading to potential safety risks or unauthorized data retrieval. Moreover, UAVs encounter limited computing resources, wireless communication and physical vulnerabilities, evolving threats and techniques, necessity for compliance with regulations, and human factors. Methods This review explores the potential cyberthreats faced by UAVs, including hacking, spoofing, and data breaches, and highlights the critical need for robust security measures. It examines various strategies and techniques used to protect UAVs from cyberattacks, e.g., encryption, authentication, and intrusion detection systems using cyberthreat analysis and assessment algorithms. The approach to assess the UAVs’ cybersecurity hazards included STRIDE (a model for identifying computer security-related threats) connected with the threats considered. Findings Emphasis was laid on the evaluation highly depending on the accuracy of UAV mission definition, potential intruders, and social and other human-related situations. The review discovered that most studies focused on possible intruders’ portraits, which can be crucial when conducting a cybersecurity assessment. Based on a review, future research directions to mitigate cybersecurity risks are presented. Significance Protecting UAVs from cyberthreats ensures safe operations and data integrity and preserves public trust in autonomous systems.
Wasswa Shafik
IGI Global
This chapter examines how education, technology, national and international regulations contribute to a comprehensive cybersecurity framework for present and future global IT companies. IT-driven enterprises may utilize the following security recommendations. Businesses who seek to examine their external and internal security with security upload and establish settings for success regardless of location must solve these issues. To produce more effective legislation, education efforts, and technologies that are resistant to cyberattacks, this work explores fundamental research gaps in cybersecurity and demonstrates how cybersecurity may be divided into these three fundamental categories and integrated to tackle problems such as the creation of training environments for authentic cybersecurity situations. It will explain links between technology and certification and discuss legislative standards and instructional frameworks for merging criteria for system accreditation and cybersecurity. The study finishes with wireless network security recommendations.
Wasswa Shafik
IGI Global
The internet of things (IoT) entails all devices that can get onto the internet. This is mainly because of the technological advancement. This exponential growth of IoT increases on the dense nodes with a huge data volume on the network that affect the collision and network congestion probabilities. This chapter presents a comprehensive description of the central and supporting innovations that are used to make cities smarter, focusing on the fifth generation (5G) IoT paradigm from a software-based network viewpoint. Furthermore, the main initiatives of international significance are discussed. Also, the chapter presents software-defined networking (SDN), IoT, and network function virtualization (NFV) challenges as it relates to the user privacy and security, IoT security, energy consumption, integration of IoT with subsystems, and architecture design. A segment of the top five future trends that are made and will make cities smarter is conclusively included.
Kassim Kalinaki, Wasswa Shafik, Tar J. L. Gutu, and Owais Ahmed Malik
IGI Global
The advent of cutting-edge techniques such as Computer Vision (CV) and Artificial Intelligence (AI) have sparked a revolution in the agricultural industry, with applications ranging from crop and livestock monitoring to yield optimization, crop grading and sorting, pest and disease identification, and pesticide spraying among others. By leveraging these innovative techniques, sustainable farming practices are being adopted to ensure future food security. With the help of CV, AI, and related methods, such as Machine Learning (ML) together with Deep Learning (DL), key stakeholders can gain invaluable insights into the performance of agricultural and farm initiatives, enabling them to make data-driven decisions without the need for direct interaction. This chapter presents a comprehensive overview of the requirements, techniques, applications, and future directions for smart farming and agriculture. Different vital stakeholders, researchers, and students who have a keen interest in this field would find the discussions in this chapter insightful.
Wasswa Shafik, Ali Tufail, Abdallah Namoun, Liyanage Chandratilak De Silva, and Rosyzie Anna Awg Haji Mohd Apong
Institute of Electrical and Electronics Engineers (IEEE)
Plant pests and diseases are a significant threat to almost all major types of plants and global food security. Traditional inspection across different plant fields is time-consuming and impractical for a wider plantation size, thus reducing crop production. Therefore, many smart agricultural practices are deployed to control plant diseases and pests. Most of these approaches, for example, use vision-based artificial intelligence (AI), machine learning (ML), or deep learning (DL) methods and models to provide disease detection solutions. However, existing open issues must be considered and addressed before AI methods can be used. In this study, we conduct a systematic literature review (SLR) and present a detailed survey of the studies employing data collection techniques and publicly available datasets. To begin the review, 1349 papers were chosen from five major academic databases, namely Springer, IEEE Xplore, Scopus, Google Scholar, and ACM library. After deploying a comprehensive screening process, the review considered 176 final studies based on the importance of the method. Several crops, including grapes, rice, apples, cucumbers, maize, tomatoes, wheat, and potatoes, have tested mainly on the hyperspectral imagery and vision-centered approaches. Support Vector Machines (SVMs) and Logistic regression (LR) classifiers demonstrated an increased accuracy in experiments compared to traditional classifiers. Besides the image taxonomy, disease localization is depicted in these approaches as a bottle neck to disease detection. Cognitive CNNs with attention mechanisms and transfer learning are showing an increasing trend. There is no standard model performance assessment though the majority use accuracy, recall, precision, F1 Score, and confusion matrix. The available 11 datasets are laboratory and in-field based, and 9 are publicly available. Some laboratory-based datasets are considerably small, making them impractical in experiments. Finally, there is a need to avail models with fewer parameters, implementable on small devices and large datasets accommodating several crops and diseases to have robust models.
Wasswa Shafik and Ali Tufail
Springer International Publishing
Liguo Zhao, Derong Zhu, Wasswa Shafik, S Mojtaba Matinkhah, Zubair Ahmad, Lule Sharif, and Alisa Craig
SAGE Publications
The application of Big Data Analytics is identified through the Cyber Research Alliance for cybersecurity as the foremost preference for future studies and advancement in the field of cybersecurity. In this study, we develop a repeatable procedure for detecting cyber-attacks in an accurate, scalable, and timely manner. An in-depth learning algorithm is utilized for training a neural network for detecting suspicious user activities. The proposed system architecture was implemented with the help of Splunk Enterprise Edition 6.42. A data set of average feature counts has been executed through a Splunk search command in 1-min intervals. All the data sets consisted of a minute trait total derived from a sparkling file. The attack patterns that were not anonymized or were indicative of the vulnerability of cyber-attack were denoted with yellow. The rule-based method dispensed a low quantity of irregular illustrations in contrast with the Partitioning Around Medoids method. The results in this study demonstrated that using a proportional collection of instances trained with the deep learning algorithm, a classified data set can accurately detect suspicious behavior. This method permits for the allocation of multiple log source types through a sliding time window and provides a scalable solution, which is a much-needed function.
Solagbade Saheed Afolabi, Monsour Olawale Zakariyah, Mohammad Hashim Abedi, and Wasswa Shafik
Elsevier BV
Wasswa Shafik, S. Mojtaba Matinkhah, Mamman Nur Sanda, and Fawad Shokoor
Politeknik Negeri Padang
In recent years, the IoT) Internet of Things (IoT) allows devices to connect to the Internet that has become a promising research area mainly due to the constant emerging of the dynamic improvement of technologies and their associated challenges. In an approach to solve these challenges, fog computing came to play since it closely manages IoT connectivity. Fog-Enabled Smart Cities (IoT-ESC) portrays equitable energy consumption of a 7% reduction from 18.2% renewable energy contribution, which extends resource computation as a great advantage. The initialization of IoT-Enabled Smart Grids including (FESC) like fog nodes in fog computing, reduced workload in Terminal Nodes services (TNs) that are the sensors and actuators of the Internet of Things (IoT) set up. This paper proposes an integrated energy-efficiency model computation about the response time and delays service minimization delay in FESC. The FESC gives an impression of an auspicious computing model for location, time, and delay-sensitive applications supporting vertically -isolated, service delay, sensitive solicitations by providing abundant, ascendable, and scattered figuring stowage and system associativity. We first reviewed the persisting challenges in the proposed state-of-the models and based on them. We introduce a new model to address mainly energy efficiency about response time and the service delays in IoT-ESC. The iFogsim simulated results demonstrated that the proposed model minimized service delay and reduced energy consumption during computation. We employed IoT-ESC to decide autonomously or semi-autonomously whether the computation is to be made on Fog nodes or its transfer to the cloud.
Wasswa Shafik, S. Motjaba Matinkhah, Solagbade Saheed Afolabi, and Mamman Nur Sanda
Institute of Advanced Engineering and Science
<p>The 5G technology is predicted to achieve the unoptimized millimeter Wave (mmWave) of 30-300 GHz bands. This unoptimized band because of the loss of mm-Wave bands, like path attenuation and propagation losses. Nonetheless, because of: (i) directional transmission paving way for beamforming to recompense for the path attenuation, and (ii) sophisticated placement concreteness of the base stations (BS) is the best alternative for array wireless communications in mmWave bands (that is to say 100-150 m). The advance in technology and innovation of unmanned aerial vehicles (UAVs) necessitates many opportunities and uncertainties. UAVs are agile and can fly all complexities if the terrains making ground robots unsuitable. The UAV may be managed either independently through aboard computers or distant controlled of a flight attendant on pulverized wireless communication links in our case 5G. Although a fast algorithm solved the problematic aspect of beam selection for 2-dimensional scenarios. This paper presents 3-dimensional scenarios for UAV. We modeled beam selection with environmental responsiveness in millimeter Wave UAV to accomplish close optimum assessments on the regular period through learning from the available situation.</p>
Yao Jun, Alisa Craig, Wasswa Shafik, and Lule Sharif
Hindawi Limited
Devices are increasingly getting connected to the internet with the advances in technologies called the Internet of Things (IoT). The IoTs are the physical device in which are embedded with software, sensors, among other technologies. Linking and switching data resources with other devices, IoT has been recognized to be a trending research arena due to the world’s technological advancement. Every stage of technology avails several capacities, for instance, the IoT avails any device, anyone, any service, any technological path or any network, any place, and any context to be connected. The effective IoT applications permit public and private business organizations to regulate their assets, optimize the performance of the business, and develop new business models. In this study, we scrutinize the IoT progress as an approach to the technological upgrade through analyzing traits, architectures, applications, enabling technologies, and future challenges. To enable an aging society, and optimize different kinds of mobility and transportation, and helps to enhance the effectiveness of energy, along with the definition and characteristics of the IoT devices, the study examined the architecture of the IoT that includes the perception layer, transmission layer, application layer, and network management. It discusses the enabling technologies of the IoT that include application domain, middleware domain, network domain, and object domain. The study further evaluated the role of the IoT and its application in the everyday lives of the people by making smart cities, smart agriculture and waste management, retail and logistics, and smart environment. Besides the benefits, the IoT has demonstrated future technological challenges and is equally explained within the study.
Solagbade Saheed Afolabi, John Oluwafemi Oyeyode, Wasswa Shafik, Zubair. A. Sunusi, and Adegoke Abdullahi Adeyemi
Hindawi Limited
The purpose of this research was to demonstrate the proximate analysis of poultry-mix made using maize bran as a basis. Red beans, soya beans, and benny beans were the three samples utilised in this study. This work investigates the appropriate poultry mix for birds breed for meat and egg. Thirty grammes of proteinous feedstock were weighed and homogeneously combined with 70 grammes of maize bran. The following was revealed in a proximate analysis of the feeds: moisture ranged from 1.18% to 1.54%, unrefined lipids 0.99–3.08%, total carbohydrate 57% to 72%, ash content 38.48% to 38.92%, unrefined protein 18.38% to 22.53% and unrefined fiber 2.0% to 4.65% respectively for broilers and layers. In terms of nutritional concentrations, all feed samples showed a substantial variation. Based on the findings of the study, it can be stated that Soya bean-maize bran is an excellent poultry-mix formulation that has deep well-disposed benefits and meets nearly all nutritional needs for meat and egg-producing birds.