Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology
Short name
PAF IAST
Country, city
Pakistan, Haripur
Publications
429
Citations
5 333
h-index
35
Top-3 journals
IEEE Access
IEEE Access (27 publications)
Frontiers in Public Health
Frontiers in Public Health (7 publications)
Top-3 foreign organizations
King Saud University
King Saud University (21 publications)
King Abdulaziz University
King Abdulaziz University (15 publications)
Taif University
Taif University (15 publications)

Most cited in 5 years

Madni A., Kousar R., Naeem N., Wahid F.
2021-02-01 citations by CoLab: 234 Abstract  
The use of polymer based composites in the treatment of skin tissue damages, has got huge attention in clinical demand, which enforced the scientists to improve the methods of biopolymer designing in order to obtain highly efficient system for complete restoration of damaged tissue. In last few decades, chitosan-based biomaterials have major applications in skin tissue engineering due to its biocompatible, hemostatic, antimicrobial and biodegradable capabilities. This article overviewed the promising biological properties of chitosan and further discussed the various preparation methods involved in chitosan-based biomaterials. In addition, this review also gave a comprehensive discussion of different forms of chitosan-based biomaterials including membrane, sponge, nanofiber and hydrogel that were extensively employed in skin tissue engineering. This review will help to form a base for the advanced applications of chitosan-based biomaterials in treatment of skin tissue damages.
Subhan F., Hussain Z., Tauseef I., Shehzad A., Wahid F.
2020-04-29 citations by CoLab: 139 Abstract  
During the processing of the fishery resources, the significant portion is either discarded or used to produce low-value fish meal and oil. However, the discarded portion is the rich source of valuable proteins such as collagen, vitamins, minerals, and other bioactive compounds. Collagen is a vital protein in the living body as a component of a fibrous structural protein in the extracellular matrix, connective tissue and building block of bones, tendons, skin, hair, nails, cartilage and joints. In recent years, the use of fish collagen as an increasingly valuable biomaterial has drawn considerable attention from biomedical researchers, owing to its enhanced physicochemical properties, stability and mechanical strength, biocompatibility and biodegradability. This review focuses on summarizing the growing role of fish collagen for biomedical applications. Similarly, the recent advances in various biomedical applications of fish collagen, including wound healing, tissue engineering and regeneration, drug delivery, cell culture and other therapeutic applications, are discussed in detail. These applications signify the commercial importance of fish collagen for the fishing industry, food processors and biomedical sector.
Haghniaz R., Rabbani A., Vajhadin F., Khan T., Kousar R., Khan A.R., Montazerian H., Iqbal J., Libanori A., Kim H., Wahid F.
Journal of Nanobiotechnology scimago Q1 wos Q1 Open Access
2021-02-05 citations by CoLab: 125 PDF Abstract  
Increasing antibiotic resistance continues to focus on research into the discovery of novel antimicrobial agents. Due to its antimicrobial and wound healing-promoting activity, metal nanoparticles have attracted attention for dermatological applications. This study is designed to investigate the scope and bactericidal potential of zinc ferrite nanoparticles (ZnFe2O4 NPs), and the mechanism of anti-bacterial action along with cytocompatibility, hemocompatibility, and wound healing properties. ZnFe2O4 NPs were synthesized via a modified co-precipitation method. Structure, size, morphology, and elemental compositions of ZnFe2O4 NPs were analyzed using X-ray diffraction pattern, Fourier transform infrared spectroscopy, and field emission scanning electron microscopy coupled with energy-dispersive X-ray spectroscopy. In PrestoBlue and live/dead assays, ZnFe2O4 NPs exhibited dose-dependent cytotoxic effects on human dermal fibroblasts. In addition, the hemocompatibility assay revealed that the NPs do not significantly rupture red blood cells up to a dose of 1000 µg/mL. Bacterial live/dead imaging and zone of inhibition analysis demonstrated that ZnFe2O4 NPs showed dose-dependent bactericidal activities in various strains of Gram-negative and Gram-positive bacteria. Interestingly, NPs showed antimicrobial activity through multiple mechanisms, such as cell membrane damage, protein leakage, and reactive oxygen species generation, and were more effective against gram-positive bacteria. Furthermore, in vitro scratch assay revealed that ZnFe2O4 NPs improved cell migration and proliferation of cells, with noticeable shrinkage of the artificial wound model. This study indicated that ZnFe2O4 NPs have the potential to be used as a future antimicrobial and wound healing drug.
Ahmad K., Maabreh M., Ghaly M., Khan K., Qadir J., Al-Fuqaha A.
Computer Science Review scimago Q1 wos Q1
2022-02-01 citations by CoLab: 124 Abstract  
As the globally increasing population drives rapid urbanization in various parts of the world, there is a great need to deliberate on the future of the cities worth living. In particular, as modern smart cities embrace more and more data-driven artificial intelligence services, it is worth remembering that (1) technology can facilitate prosperity, wellbeing, urban livability, or social justice, but only when it has the right analog complements (such as well-thought out policies, mature institutions, responsible governance); and (2) the ultimate objective of these smart cities is to facilitate and enhance human welfare and social flourishing. Researchers have shown that various technological business models and features can in fact contribute to social problems such as extremism, polarization, misinformation, and Internet addiction. In the light of these observations, addressing the philosophical and ethical questions involved in ensuring the security, safety, and interpretability of such AI algorithms that will form the technological bedrock of future cities assumes paramount importance. Globally there are calls for technology to be made more humane and human-centered. In this paper, we analyze and explore key challenges including security, robustness, interpretability, and ethical (data and algorithmic) challenges to a successful deployment of AI in human-centric applications, with a particular emphasis on the convergence of these concepts/challenges. We provide a detailed review of existing literature on these key challenges and analyze how one of these challenges may lead to others or help in solving other challenges. The paper also advises on the current limitations, pitfalls, and future directions of research in these domains, and how it can fill the current gaps and lead to better solutions. We believe such rigorous analysis will provide a baseline for future research in the domain.
Ali A., Shaukat H., Bibi S., Altabey W.A., Noori M., Kouritem S.A.
Energy Strategy Reviews scimago Q1 wos Q1 Open Access
2023-09-01 citations by CoLab: 100 Abstract  
This paper provides a comprehensive review of the recent progress made in energy harvesting systems for wearable technology. An energy-harvesting system would be a useful strategy to address the issue of powering wearable electronic devices. This review presents different wearable energy harvesting methods based on the human body's heat and mechanical energy. To achieve continuous operation and high performance, reduce the requirement for external sources of energy, and enhance the lifespan of wearable devices, the invention of a sustainable and compatible power supply is required. In the human body, heat and mechanical motions are the two reliable and readily available energy sources. This study highlights the most recent research and advancements in energy harvesting from the human's mechanical motion and heat source. This article provides a detailed overview of the different wearable energy harvesters, their fabrication, working, and output results, which include piezoelectric, electrostatic, triboelectric, electromagnetic, thermoelectric, solar and hybrid wearable energy harvesters. The second part defines wearable energy harvesting using smart systems and artificial intelligence technology. Then the comparison of these energy harvesters is analyzed. Hybrid wearable energy harvesters provide the maximum power densities because they use two combined energy conversions. The advantages, limitations, and future perspectives of wearable energy harvesting technology are also discussed. Lastly, the wearable energy harvesters' market, and general developing and manufacturing cost of each wearable device is also presented functioning as a point of reference to comprehend the cost factors that are taken into account during the development and manufacturing processes.
Rehman E., Rehman S.
Energy Reports scimago Q2 wos Q2 Open Access
2022-11-01 citations by CoLab: 89 Abstract  
Environmental degradation has been identified as a major worldwide concern in recent decades, with CO 2 emissions considered as one of the primary drivers of this catastrophe. This study creatively analyzes the underlying impact of urbanization, population growth, Gross domestic product (GDP) per capita, energy use on CO 2 emissions to mitigate the environmental degradation from the five most populated regions of Asia i.e., China, India, Indonesia, Pakistan, and Bangladesh. To investigate the integrated impact of CO 2 emission and associated factors, a grey relational analysis (GRA) based weights and ranking were estimated for the year 2001 to 2014. Then, utilizing the Conservative minimax approach, we sought to determine which country contributes the most to CO 2 emissions based on weights acquired by Second Synthetic Grey Relational Analysis (SSGRA). The Grey technique for order of preference by similarity to ideal solution (G-TOPSIS) technique was employed for further optimization by prioritizing the explanatory factors that have the greatest influence on CO 2 emissions. The outcomes through GRA techniques discovered that India is a major contributor of carbon emission caused by population growth and economic development. Whereas the use of energy and urbanization are grounded factors of emission for China and Pakistan respectively. The outcomes of the Conservative minimax criterion indicate that India is a leading contributor to carbon emissions in Asia. Also, the unsustainable growth of population and CO 2 emissions indicates a direct causative relationship for environmental damage based on the G-TOPSIS. The findings of the study potentially aid governments and policymakers in making better decisions and investments to mitigate CO 2 emissions while fostering a more environmentally friendly atmosphere. • This paper investigates CO 2 emissions convergence in the Asian region. • Grey relation analysis and G-TOPSIS are utilized as the MCDM approach. • More evidence against India as a major contributor of emissions. • Population growth appeared as the most intensifying factor of the CO 2 emissions.
Haider J., Saeed S., Qyyum M.A., Kazmi B., Ahmad R., Muhammad A., Lee M.
2020-05-01 citations by CoLab: 85 Abstract  
The impurities CO2 and H2S in natural gas (NG) are recognized as major contaminants that exacerbate economic, operational, and environmental losses. Generally, these undesirable impurities are removed using well-established amine-based absorption methods. However, typical methods in this category are cost-intensive, primarily due to their high operating and maintenance costs. The ionic liquids (ILs) are emerging as alternative solvents owing to their lower regeneration costs and non-flammable nature. However, ILs could not attain a significant attention from practitioners due to the lack of effective communication between industry and academia. In this context, a comprehensive review and analysis of specific ILs that can simultaneously remove H2S and CO2 is proposed. This article highlights the major challenges and issues associated with various acid gases removal approaches, particularly IL-based absorption techniques. Recent developments toward solving the major issues associated with absorption using ILs are assessed to highlight areas for further improvement. The acid gas solubility data for ILs are analyzed to evaluate the feasibility and associated major constraints for large-scale process designs using commercial process simulators. Furthermore, the fundamentals for the process systems engineering-based investigations using ILs are also highlighted and evaluated. This study concludes that ILs have the potential to completely replace conventional solvents, have synergistic effects in terms of energy savings, and provide feasible solutions to maintenance-related issues.
Khan B., Naseem R., Muhammad F., Abbas G., Kim S.
IEEE Access scimago Q1 wos Q2 Open Access
2020-03-18 citations by CoLab: 82 Abstract  
Chronic Kidney Disease (CKD) implies that the human kidneys are harmed and unable to blood filter in the manner which they should. The disease is designated “chronic” in light of the fact that harm to human kidneys happen gradually over a significant time. This harm can make wastes to build up in your body. Many techniques and models have been developed to diagnos the CKD in early-stage. Among all techniques, Machine Learning (ML) techniques play a significant role in the early forecasting of different kinds ailments. ML techniques have been used for achieving analytical results which is one of the instruments utilize in medical analysis and prediction. In this paper, we employ experiential analysis of ML techniques for classifying the kidney patient dataset as CKD or NOTCKD. Seven ML techniques together with NBTree, J48, Support Vector Machine, Logistic Regression, Multi-layer Perceptron, Naïve Bayes, and Composite Hypercube on Iterated Random Projection (CHIRP) are utilized and assessed using distinctive evaluation measures such as mean absolute error (MAE), root mean squared error (RMSE), relative absolute error (RAE), root relative squared error (RRSE), recall, precision, F-measure and accuracy.The experimental outcomes accomplished of MAE are 0.0419 for NB, 0.035 for LR, 0.265 for MLP, 0.0229 for J48, 0.015 for SVM, 0.0158 for NBTree and 0.0025 for CHIRP. Moreover, experimental results using accuracy revealed 95.75% for NB, 96.50% for LR, 97.25% for MLP, 97.75% for J48, 98.25% for SVM, 98.75% for NBTree, and 99.75% for CHIRP. The overall outcomes show that CHIRP performs well in terms of diminishing error rates and improving accuracy.
Sajjad W., He F., Ullah M.W., Ikram M., Shah S.M., Khan R., Khan T., Khalid A., Yang G., Wahid F.
2020-09-15 citations by CoLab: 76 PDF Abstract  
The current study aimed to fabricate curcumin-loaded bacterial cellulose (BC-Cur) nanocomposite as a potential wound dressing for partial thickness burns by utilizing the therapeutic features of curcumin and unique structural, physico-chemical, and biological features of BC. Characterization analyses confirmed the successful impregnation of curcumin into the BC matrix. Biocompatibility studies showed the better attachment and proliferation of fibroblast cells on the BC-Cur nanocomposite. The antibacterial potential of curcumin was tested against Escherichia coli (E. coli), Pseudomonas aeruginosa (P. aeruginosa), Salmonella typhimurium (S. typhimurium), and Staphylococcus aureus (S. aureus). Wound healing analysis of partial-thickness burns in Balbc mice showed an accelerated wound closure up to 64.25% after 15 days in the BC-Cur nanocomposite treated group. Histological studies showed healthy granulation tissues, fine re-epithelialization, vascularization, and resurfacing of wound bed in the BC-Cur nanocomposite group. These results indicate that combining BC with curcumin significantly improved the healing pattern. Thus, it can be concluded that the fabricated biomaterial could provide a base for the development of promising alternatives for the conventional dressing system in treating burns.
Al-Ammar E.A., Farzana K., Waqar A., Aamir M., Saifullah, Ul Haq A., Zahid M., Batool M.
Ain Shams Engineering Journal scimago Q1 wos Q1 Open Access
2021-03-01 citations by CoLab: 75 Abstract  
In recent years, due to increase in load demand, distribution networks have got substantial attention to get optimized. It is significant to optimally place the distributed generators (DGs) in distribution networks to minimize power losses and voltage drops. However, the DGs incur certain investment and operational costs, and their placement is only viable if these costs overcome energy losses. Therefore, current paper investigates the optimal sizing and placement of DGs in distribution networks with a novel concept to simultaneously minimize total energy cost along with total power loss and average voltage drop. Artificial bee colony (ABC) algorithm is proposed to solve the considered multi-objective problem. The performance of the proposed ABC algorithm is tested with standard algorithms. Newton Raphson load flow (NRLF) analysis is conducted on IEEE 33 and 69-bus radial networks and on CIGRE medium voltage (MV) benchmark grid. Two test cases have been formed and investigated. The results prove that proposed ABC algorithm mostly outperforms other algorithms.
Li Y., Duan Y., Wang Z., Maurice N.J., Claire M.J., Ali N., Giwa A.S.
Processes scimago Q2 wos Q2 Open Access
2025-01-24 citations by CoLab: 0 PDF Abstract  
The escalating challenges of municipal solid waste (MSW) management, exacerbated by the classification of MSW as hazardous waste due to the presence of heavy metals (HMs) and toxic compounds, necessitate innovative treatment strategies. Plasma pyrolysis has emerged as a promising technology for converting MSW into valuable energy byproducts, such as syngas, bio-oil, and slag, while significantly reducing waste volume. However, maintaining optimal operational parameters during the plasma pyrolysis process remains a complex challenge that can adversely affect both the efficiency and the quality and quantity of outputs. To address this issue, the integration of the Internet of Things (IoT) presents a transformative approach. By leveraging IoT technologies, real-time monitoring and advanced data analytics can be employed to optimize the operational conditions of plasma pyrolysis systems, ensuring consistent performance and maximizing resource recovery. This review explores the synergistic integration of plasma pyrolysis and IoT as a novel strategy for MSW management. The slag from plasma treatment can be efficiently channeled into anaerobic digestion (AD) systems, promoting resource recovery through biogas production and the generation of nutrient-rich digestate. This synergy not only mitigates the environmental impacts associated with traditional MSW disposal methods but also paves the way for sustainable energy recovery and resource management. Ultimately, this review presents a comprehensive framework for exploiting plasma pyrolysis and IoT in addressing the pressing issues of hazardous MSW, thereby fostering a circular economy through innovative waste-to-energy solutions.
Ullah R., Ullah S., Ali A., Jianxin R., Alwageed H.S., Yaya M., Qi Z., Yu Y., Imtiaz W.A., Khan M.
Journal of Lightwave Technology scimago Q1 wos Q2
2025-01-17 citations by CoLab: 0
Ijaz H., Mahmood A., Tayyab M., Sarfraz R.M., Akram M.R., Haroon B., Ayub S., Raza M., Menaa F., Albadi F.O., Alzahrani H.A.
Polymer Bulletin scimago Q2 wos Q2
2025-01-12 citations by CoLab: 0 Abstract  
5-Fluorouracil (5-FU) is a firstline chemotherapeutic agent used for treating colorectal cancer, but has short half-life, rapid metabolism which requires its continuous intravenous (IV) infusion, resulting in significant adverse events. synthesis as well as characterizations of 5-FU-loaded thiolated chitosan (TCS)-co-polymethacrylic acid (MAA)-based hydrogel for colon targeting to treat colorectal carcinoma. Free radical polymerization was employed for preparation of the 5-FU-loaded hydrogel. Potassium persulfate (KPS), methylene bis-acrylamide (MBA), and MAA were employed as initiator, crosslinker, and monomer, respectively. All the six 5-FU-TCS-co-poly (MAA) formulations (TCS1-TCS6) were subjected to in-vitro pH-dependent swelling and dissolution studies at pH 1.2 and 7.4 at 37 °C. TCS4 was selected for further in-vivo studies based upon swelling and release patterns evaluation. Reverse phase HPLC (RP-HPLC)-coupled with UV spectrophotometer was employed for estimation of 5-FU in plasma. In-vivo studies were performed to determine pharmacokinetics parameters (i.e., Cmax, tmax and area-under-curve (AUC)) among control and treated groups. Release profile of TCS4 was optimal at pH 7.4. Indeed, 5-FU showed twofold higher release at pH 7.4 than at pH 1.2. Cmax and tmax of TCS4 were found to be 300 ± 0.87 µg/mL and 4 ± 0.00 h, which are significantly higher than Cmax and tmax oral solution (250 ± 0.65 µg/mL and 2 ± 0.00 h) used as a reference. TCS4-treated group depicted AUC0-t of 2767 ± 0.54 ng/ml.hr which was remarkably higher as compared to controlled group. Toxicity studies were carried out on male albino rats and histological slides showed no signs of toxicity. TCS4 hydrogel could be effectively administered per os (orally) to improve the bioavailability of 5-FU.
Ali S., Ahmad Z., Mahmood A., Khan M.I., Siddique W., Latif R., Ijaz H., Sarfraz R.M., Haroon B.
BioNanoScience scimago Q3 wos Q3
2025-01-11 citations by CoLab: 0 Abstract  
Labetalol is an anti-hypertensive medication available in both tablet and liquid injectable forms. However, a transdermal delivery system may offer a more convenient option for patients requiring this medication. Due to its solubility in organic solvents and high molecular weight, a transdermal patch could face challenges in effectively delivering the drug through the stratum corneum, the outermost layer of the skin. To overcome this challenge, labetalol-loaded nanoparticles were prepared using a solvent evaporation method and incorporated into dissolvable microneedle patches. The nanoparticles ensured controlled drug release, while microneedles facilitated drug penetration through the stratum corneum. The patches were formulated with hydroxypropyl methylcellulose and carbopol polymers and evaluated for their mechanical properties, penetration efficacy, drug loading, in vitro drug release, and biological safety. Scanning electron microscopy confirmed uniform nanoparticle distribution, and drug loading efficiency reached 95.25 ± 1.68%. The optimized formulation achieved a sustained in vitro drug release of 89.27 ± 2.34% over 24 h, significantly improving release efficiency compared to conventional oral and injectable labetalol formulations. In contrast to the burst release observed with oral and injectable formulations, the microneedle patch offered controlled and sustained release, enhancing therapeutic outcomes and reducing side effects. Penetration studies demonstrated successful nanoparticle delivery into deeper skin layers, while irritation studies confirmed the safety of the patches. These findings suggest that nanoparticle-loaded dissolvable microneedle patches provide a promising strategy for the transdermal delivery of labetalol, offering controlled drug release and enhanced patient compliance.
Chiang P.F., Zhang T.L., Giwa A.S., Maurice N.J., Claire M.J., Ali N., Shafique E., Vakili M.
Molecules scimago Q1 wos Q2 Open Access
2025-01-07 citations by CoLab: 0 PDF Abstract  
The increasing global population and urbanization have led to significant challenges in waste management, particularly concerning vacuum blackwater (VBW), which is the wastewater generated from vacuum toilets. Traditional treatment methods, such as landfilling and composting, often fall short in terms of efficiency and sustainability. Anaerobic digestion (AD) has emerged as a promising alternative, offering benefits such as biogas production and digestate generation. However, the performance of AD can be influenced by various factors, including the composition of the feedstock, pH levels, and the presence of inhibitors. This review investigates the effects of calcium oxide (CaO)-modified biochar (BC) as an additive in AD of VBW. Modifying BC with CaO enhances its alkalinity, nutrient retention, and adsorption capacity, creating a more favorable environment for microorganisms and promoting biogas production, which serves as a valuable source of heat, fuel and electricity. Additionally, the digestate can be processed through plasma pyrolysis to ensure the complete destruction of pathogens while promoting resource utilization. Plasma pyrolysis operates at extremely high temperatures, effectively sterilizing the digestate and eliminating both pathogens and harmful contaminants. This process not only guarantees the safety of the end products, but also transforms organic materials into valuable outputs such as syngas and slag. The syngas produced is a versatile energy carrier that can be utilized as a source of hydrogen, electricity, and heat, making it a valuable resource for various applications, including fuel cells and power generation. Furthermore, the slag has potential for reuse as an additive in the AD process or as a biofertilizer to enhance soil properties. This study aims to provide insights into the benefits of using modified BC as a co-substrate in AD systems. The findings will contribute to the development of more sustainable and efficient waste management strategies, addressing the challenges associated with VBW treatment while promoting renewable energy production.
Naeem N., Butt S., Sumayya, Afzal Z., Waseem Akram M., Irfan M., Atiq Ur Rehman M., Baluch A.H., Rehman G.U., Farooq M.U.
RSC Advances scimago Q1 wos Q2 Open Access
2025-01-06 citations by CoLab: 1 PDF Abstract  
Development process of flexible thermoelectric using multiwalled carbon nanotubes (MWCNTs) film: vacuum filtration of CNTs using HNO3/H2SO4, followed by hot pressing to enhance alignment, leading to improved thermoelectric properties.
Malik M., Mehmood S., Hussain A., Hashmi A., Aslam U., Kow C.S., Jamshed S.
2024-12-28 citations by CoLab: 0 Abstract  
The National Medicine Policy (NMP) is crucial for setting the direction of a country’s action plan to achieve targeted healthcare goals. This study aimed to explore the perceptions of different stakeholders regarding the current NMP of Pakistan. A qualitative study design was employed using purposive sampling to identify respondents. Semi-structured interviews were conducted with regulators (n = 6), manufacturers (n = 8), healthcare professionals (n = 9), and academicians (n = 7) until saturation was reached. Interviews were conducted at convenient times and locations, recorded, transcribed verbatim, and subjected to thematic analysis. Most stakeholders demonstrated expertise in policy-making and understood the basic concepts, need, and importance of the NMP. Six key themes were identified: general understanding of the NMP, existing regulatory framework and NMP, essential medicines and the current healthcare system, comparison of NMP with international standards, focus of NMP for better provision of healthcare, and recommendations for an effective NMP for Pakistan. Stakeholders emphasized the need for policies to set Standard Operating Procedures and direction, and noted that some frameworks require revision. There was consensus that the availability of essential medicines needs improvement and that the current healthcare system requires revamping, as the National Essential Medicine List is not fully implemented. The study concludes that NMP is integral to a robust healthcare system. However, Pakistan lacks an effective NMP despite extensive efforts in recent years. This deficiency is attributed to scarce resources, lack of political will and ownership, and inadequate compliance with performance-based indicators.
Ali A., Iqbal A., Khan S., Ahmad N., Shah S.
PeerJ Computer Science scimago Q1 wos Q1 Open Access
2024-12-19 citations by CoLab: 0 Abstract  
Gastrointestinal (GI) disorders are common and often debilitating health issues that affect a significant portion of the population. Recent advancements in artificial intelligence, particularly computer vision algorithms, have shown great potential in detecting and classifying medical images. These algorithms utilize deep convolutional neural network architectures to learn complex spatial features in images and make predictions for similar unseen images. The proposed study aims to assist gastroenterologists in making more efficient and accurate diagnoses of GI patients by utilizing its two-phase transfer learning framework to identify GI diseases from endoscopic images. Three pre-trained image classification models, namely Xception, InceptionResNetV2, and VGG16, are fine-tuned on publicly available datasets of annotated endoscopic images of the GI tract. Additionally, two custom convolutional neural networks are constructed and fully trained for comparative analysis of their performance. Four different classification tasks are examined based on the endoscopic image categories. The proposed architecture employing InceptionResNetV2 achieves the most consistent and generalized performance across most classification tasks, yielding accuracy scores of 85.7% for general classification of GI tract (eight-category classification), 97.6% for three-diseases classification, 99.5% for polyp identification (binary classification), and 74.2% for binary classification of esophagitis severity on unseen endoscopic images. The results indicate the effectiveness of the two-phase transfer learning framework for clinical use to enhance the identification of GI diseases, aiding in their early diagnosis and treatment.
Xu X., Gu L., Bilal M., Khan M., Wen Y., Liu G., Yuan Y.
2024-12-18 citations by CoLab: 0 Abstract  
Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data management. The combination of Web3.0 and edge content caching holds promise in providing low-latency data access for CAVs’ real-time applications. Web3.0 enables the reliable pre-migration of frequently requested content from content providers to edge nodes. However, identifying optimal edge node peers for joint content caching and replacement remains challenging due to the dynamic nature of traffic flow in IoV. Addressing these challenges, this article introduces GAMA-Cache, an innovative edge content caching methodology leveraging Graph Attention Networks (GAT) and Multi-Agent Reinforcement Learning (MARL). GAMA-Cache conceptualizes the cooperative edge content caching issue as a constrained Markov decision process. It employs a MARL technique predicated on cooperation effectiveness to discern optimal caching decisions, with GAT augmenting information extracted from adjacent nodes. A distinct collaborator selection mechanism is also developed to streamline communication between agents, filtering out those with minimal correlations in the vector input to the policy network. Experimental results demonstrate that, in terms of service latency and delivery failure, the GAMA-Cache outperforms other state-of-the-art MARL solutions for edge content caching in IoV.
Syed S., Ahmed R., Iqbal A., Ahmed N., Alshara M.A.
Journal of Imaging scimago Q2 wos Q3 Open Access
2024-12-13 citations by CoLab: 0 PDF Abstract  
With technological advancements, remarkable progress has been made with the convergence of health sciences and Artificial Intelligence (AI). Modern health systems are proposed to ease patient diagnostics. However, the challenge is to provide AI-based precautions to patients and doctors for more accurate risk assessment. The proposed healthcare system aims to integrate patients, doctors, laboratories, pharmacies, and administrative personnel use cases and their primary functions onto a single platform. The proposed framework can also process microscopic images, CT scans, X-rays, and MRI to classify malignancy and give doctors a set of AI precautions for patient risk assessment. The proposed framework incorporates various DCNN models for identifying different forms of tumors and fractures in the human body i.e., brain, bones, lungs, kidneys, and skin, and generating precautions with the help of the Fined-Tuned Large Language Model (LLM) i.e., Generative Pretrained Transformer 4 (GPT-4). With enough training data, DCNN can learn highly representative, data-driven, hierarchical image features. The GPT-4 model is selected for generating precautions due to its explanation, reasoning, memory, and accuracy on prior medical assessments and research studies. Classification models are evaluated by classification report (i.e., Recall, Precision, F1 Score, Support, Accuracy, and Macro and Weighted Average) and confusion matrix and have shown robust performance compared to the conventional schemes.
Syed S., Talha S.M., Iqbal A., Ahmad N., Alshara M.A.
AI scimago Q2 wos Q2 Open Access
2024-12-08 citations by CoLab: 0 PDF Abstract  
Cryptocurrency is recognized as a leading digital currency by its peer-to-peer transfer capabilities and secure features. Accurately forecasting cryptocurrency price trends holds substantial significance for investors and traders, as they inform critical decisions regarding the acquisition, divestment, or retention of cryptocurrencies, guided by expectations of value, risk assessment, and potential returns. This study also aims to identify a resourceful technique to efficiently forecast prices of cryptocurrencies such as Bitcoin (BTC), Binance (BNB), Ripple (XRP), and Tether (USDT) using optimal data-driven models (LSTM, GRU, and BiLSTM models) using bias correction. The proposed methodology includes collecting cryptocurrency data and precious metal data from Coindesk and BullionVault, respectively, and then finding the optimal model input combination for each cryptocurrency by lag adjustment and correlating feature selection. Hyperparameter tuning was performed by trial-and-error technique, and an early stopping function was applied to minimize time and space complexity. Bias correction (BC) is applied to model-forecasted price trends to reduce errors in evaluation and to enhance accuracy by adjusting model outputs to reduce prediction bias, providing a refined alternative to traditional unadjusted deep learning methods. GRU-BC outperformed other models in forecasting Bitcoin (with MAE 25.291, RMSE 31.266, MAPE 2.999) and USDT (with MAE 0.0006, RMSE 0.0012, MAPE 0.0622) price trends, while BiLSTM-BC was superior in predicting XRP (with MAE 0.0129, RMSE 0.0171, MAPE 2.9013) and BNB (with MAE 2.2759, RMSE 2.8357, MAPE 1.9785) market price flow.

Since 2019

Total publications
429
Total citations
5333
Citations per publication
12.43
Average publications per year
71.5
Average authors per publication
6.87
h-index
35
Metrics description

Top-30

Fields of science

10
20
30
40
50
60
General Materials Science, 58, 13.52%
Electrical and Electronic Engineering, 57, 13.29%
General Computer Science, 39, 9.09%
General Engineering, 38, 8.86%
General Chemistry, 35, 8.16%
General Medicine, 30, 6.99%
Condensed Matter Physics, 28, 6.53%
Computer Networks and Communications, 27, 6.29%
General Chemical Engineering, 25, 5.83%
Renewable Energy, Sustainability and the Environment, 25, 5.83%
Hardware and Architecture, 20, 4.66%
Software, 20, 4.66%
Multidisciplinary, 19, 4.43%
Electronic, Optical and Magnetic Materials, 18, 4.2%
Biochemistry, 18, 4.2%
Computer Science Applications, 18, 4.2%
Energy Engineering and Power Technology, 18, 4.2%
Materials Chemistry, 17, 3.96%
Process Chemistry and Technology, 17, 3.96%
Instrumentation, 15, 3.5%
Information Systems, 15, 3.5%
Pharmaceutical Science, 14, 3.26%
Biomedical Engineering, 14, 3.26%
Physical and Theoretical Chemistry, 13, 3.03%
Analytical Chemistry, 13, 3.03%
Polymers and Plastics, 13, 3.03%
Public Health, Environmental and Occupational Health, 13, 3.03%
Control and Systems Engineering, 13, 3.03%
Mechanical Engineering, 12, 2.8%
Pollution, 12, 2.8%
10
20
30
40
50
60

Journals

5
10
15
20
25
30
5
10
15
20
25
30

Publishers

10
20
30
40
50
60
70
80
90
10
20
30
40
50
60
70
80
90

With other organizations

10
20
30
40
50
60
70
80
10
20
30
40
50
60
70
80

With foreign organizations

5
10
15
20
25
5
10
15
20
25

With other countries

20
40
60
80
100
120
140
China, 123, 28.67%
Saudi Arabia, 103, 24.01%
Republic of Korea, 52, 12.12%
USA, 39, 9.09%
Malaysia, 29, 6.76%
United Kingdom, 28, 6.53%
Australia, 25, 5.83%
Egypt, 24, 5.59%
Germany, 14, 3.26%
Italy, 13, 3.03%
UAE, 12, 2.8%
Canada, 10, 2.33%
Spain, 9, 2.1%
Turkey, 9, 2.1%
Iran, 8, 1.86%
Norway, 8, 1.86%
Oman, 8, 1.86%
Sweden, 8, 1.86%
Austria, 6, 1.4%
Algeria, 6, 1.4%
India, 6, 1.4%
Iraq, 6, 1.4%
Qatar, 6, 1.4%
Slovakia, 6, 1.4%
France, 5, 1.17%
Kazakhstan, 5, 1.17%
Poland, 5, 1.17%
Czech Republic, 5, 1.17%
Bangladesh, 4, 0.93%
20
40
60
80
100
120
140
  • We do not take into account publications without a DOI.
  • Statistics recalculated daily.
  • Publications published earlier than 2019 are ignored in the statistics.
  • The horizontal charts show the 30 top positions.
  • Journals quartiles values are relevant at the moment.