Search results for: Jinan Fiaidhi

Authors: Hang Wang, Xiaoming Gao

Abstract:

The rapid development of e-commerce has significantly transformed consumer behavior and urban consumption patterns worldwide. This study explores the impact of e-commerce on the development and spatial distribution of consumption centers, with a particular focus on Jinan City, China. Traditionally, urban consumption centers are defined by physical commercial spaces, such as shopping malls and markets. However, the rise of e-commerce has introduced a shift towards virtual consumption hubs, with a corresponding impact on physical retail locations. Utilizing Gaode POI (Point of Interest) data, this research aims to provide a comprehensive analysis of the spatial distribution of consumption centers in Jinan, comparing e-commerce-driven virtual consumption hubs with traditional physical consumption centers. The study methodology involves gathering and analyzing POI data, focusing on logistics distribution for e-commerce activities and mobile charging point locations to represent offline consumption behavior. A spatial clustering technique is applied to examine the concentration of commercial activities and to identify emerging trends in consumption patterns. The findings reveal a clear differentiation between e-commerce and physical consumption centers in Jinan. E-commerce activities are dispersed across a wider geographic area, correlating closely with residential zones and logistics centers, while traditional consumption hubs remain concentrated around historical and commercial areas such as Honglou and the old city center. Additionally, the research identifies an ongoing transition within Jinan’s consumption landscape, with online and offline retail coexisting, though at different spatial and functional levels. This study contributes to urban planning by providing insights into how e-commerce is reshaping consumption behaviors and spatial structures in cities like Jinan. By leveraging big data analytics, the research offers a valuable tool for urban designers and planners to adapt to the evolving demands of digital commerce and to optimize the spatial layout of city infrastructure to better serve the needs of modern consumers.

Keywords: big data, consumption centers, e-commerce, urban planning, jinan

Procedia PDF Downloads 21

Authors: Jinan Fiaidhi, Sabah Mohammed

Abstract:

Cross-domain learning in the medical field is a research challenge as many conditions, like in oncology imaging, use different imaging modalities. Moreover, in most of the medical learning applications, the sample training size is relatively small. Although few-shot learning (FSL) through the use of a Siamese neural network was able to be trained on a small sample with remarkable accuracy, FSL fails to be effective for use in multiple domains as their convolution weights are set for task-specific applications. In this paper, we are addressing this problem by enabling FSL to possess the ability to shift across domains by designing a two-layer FSL network that can learn individually from each domain and produce a shared features map with extra modulation to be used at the second layer that can recognize important targets from mix domains. Our initial experimentations based on mixed medical datasets like the Medical-MNIST reveal promising results. We aim to continue this research to perform full-scale analytics for testing our cross-domain FSL learning.

Keywords: Siamese neural network, few-shot learning, meta-learning, metric-based learning, thick data transformation and analytics

Procedia PDF Downloads 57

Authors: Sabah Mohammed, Jinan Fiaidhi, Darien Sawyer

Abstract:

Describing clinical cases according to a clinical charting standard that enforces interoperability and enables connected care services can save lives in the event of a medical emergency or provide efficient and effective interventions for the benefit of the patients through the integration of bedside and bench side clinical research. This article presented a multi-tenant extension to the problem-oriented medical record that we have prototyped previously upon using the GraphQL Application Programming Interface to represent the notion of a problem list. Our implemented extension enables physicians and patients to collaboratively describe the patient case via using multi chatbots to collaboratively describe the patient case using the SOAP charting standard. Our extension also connects the described SOAP patient case with the HL7 FHIR (Health Interoperability Resources) medical record for connecting the patient case to the bench data.

Keywords: problem-oriented medical record, graphQL, chatbots, SOAP

Procedia PDF Downloads 91

Authors: Jinan Fiaidhi, Sabah Mohammed

Abstract:

Diagnosing cataract severity is an important factor in deciding to undertake surgery. It is usually conducted by an ophthalmologist or through taking a variety of fundus photography that needs to be examined by the ophthalmologist. This paper carries out an investigation using a Siamese neural net that can be trained with small anchor samples to score cataract severity. The model used in this paper is based on a triplet loss function that takes the ophthalmologist best experience in rating positive and negative anchors to a specific cataract scaling system. This approach that takes the heuristics of the ophthalmologist is generally called the thick data approach, which is a kind of machine learning approach that learn from a few shots. Clinical Relevance: The lens of the eye is mostly made up of water and proteins. A cataract occurs when these proteins at the eye lens start to clump together and block lights causing impair vision. This research aims at employing thick data machine learning techniques to rate the severity of the cataract using Siamese neural network.

Keywords: thick data analytics, siamese neural network, triplet-loss model, few shot learning

Procedia PDF Downloads 111

Authors: Jinyan Li, Simon Fong, Raymond Wong, Mohammed Sabah, Fiaidhi Jinan

Abstract:

Clinical data analysis and forecasting have make great contributions to disease control, prevention and detection. However, such data usually suffer from highly unbalanced samples in class distributions. In this paper, we target at the binary imbalanced dataset, where the positive samples take up only the minority. We investigate two different meta-heuristic algorithms, particle swarm optimization and bat-inspired algorithm, and combine both of them with the synthetic minority over-sampling technique (SMOTE) for processing the datasets. One approach is to process the full dataset as a whole. The other is to split up the dataset and adaptively process it one segment at a time. The experimental results reveal that while the performance improvements obtained by the former methods are not scalable to larger data scales, the later one, which we call Adaptive Swarm Balancing Algorithms, leads to significant efficiency and effectiveness improvements on large datasets. We also find it more consistent with the practice of the typical large imbalanced medical datasets. We further use the meta-heuristic algorithms to optimize two key parameters of SMOTE. Leading to more credible performances of the classifier, and shortening the running time compared with the brute-force method.

Keywords: Imbalanced dataset, meta-heuristic algorithm, SMOTE, big data

Procedia PDF Downloads 443

Authors: Sabah Mohammed, Jinan Fiaidhi, Darien Sawyer

Abstract:

Data integration of health through connected services can save lives in the event of a medical emergency or provide efficient and effective interventions for the benefit of the patients through the integration of bedside and bench side clinical research. Such integration will support all wind of change in healthcare by being predictive, pre-emptive, personalized, problem-oriented and participatory. Prototyping a healthcare system that enables data integration has been a big challenge for healthcare for a long time. However, an innovative solution started to emerge by focusing on problem lists where everything can connect the problem list forming a growing graph. This notion was introduced by Dr. Lawrence Weed in early 70’s, but the enabling technologies weren’t mature enough to provide a successful implementation prototype. In this article, we are describing our efforts in prototyping Dr. Lawrence Weed's problem-oriented medical record (POMR) and his patient case schema (SOAP) to shape a prototype for connected health. For this, we are using the TypeGraphQL API and our enterprise-based QL4POMR to describe a Web-Based gateway for healthcare services connectivity. Our prototype has reported success in connecting to the HL7 FHIR medical record and the OpenTarget biomedical repositories.

Keywords: connected health, problem-oriented healthcare record, SOAP, QL4POMR, typegraphQL

Procedia PDF Downloads 97

Authors: Jinan Fiaidhi, Hashmath Shaik

Abstract:

Breaking the barrier for practicing evidence-based medicine relies on effective methods for rapidly identifying relevant evidence from the body of biomedical literature. An important challenge confronted by medical practitioners is the long time needed to browse, filter, summarize and compile information from different medical resources. Deep learning can help in solving this based on automatic question answering (Q&A) and transformers. However, Q&A and transformer technologies are not trained to answer clinical queries that can be used for evidence-based practice, nor can they respond to structured clinical questioning protocols like PICO (Patient/Problem, Intervention, Comparison and Outcome). This article describes the use of deep learning techniques for Q&A that are based on transformer models like BERT and GPT to answer PICO clinical questions that can be used for evidence-based practice extracted from sound medical research resources like PubMed. We are reporting acceptable clinical answers that are supported by findings from PubMed. Our transformer methods are reaching an acceptable state-of-the-art performance based on two staged bootstrapping processes involving filtering relevant articles followed by identifying articles that support the requested outcome expressed by the PICO question. Moreover, we are also reporting experimentations to empower our bootstrapping techniques with patch attention to the most important keywords in the clinical case and the PICO questions. Our bootstrapped patched with attention is showing relevancy of the evidence collected based on entropy metrics.

Keywords: automatic question answering, PICO questions, evidence-based medicine, generative models, LLM transformers

Procedia PDF Downloads 47

Authors: Jinan Fiaidhi, Sabah Mohammed, Petros Zezos

Abstract:

Capsule endoscopy (CE) is an established noninvasive diagnostic modality in investigating small bowel disease. CE has a pivotal role in assessing patients with suspected bleeding or identifying evidence of active Crohn's disease in the small bowel. However, CE produces lengthy videos with at least eighty thousand frames, with a frequency rate of 2 frames per second. Gastroenterologists cannot dedicate 8 to 15 hours to reading the CE video frames to arrive at a diagnosis. This is why the issue of analyzing CE videos based on modern artificial intelligence techniques becomes a necessity. However, machine learning, including deep learning, has failed to report robust results because of the lack of large samples to train its neural nets. In this paper, we are describing a thick data approach that learns from a few anchor images. We are using sound datasets like KVASIR and CrohnIPI to filter candidate frames that include interesting anomalies in any CE video. We are identifying candidate frames based on feature extraction to provide representative measures of the anomaly, like the size of the anomaly and the color contrast compared to the image background, and later feed these features to a decision tree that can classify the candidate frames as having a condition like the Crohn's Disease. Our thick data approach reported accuracy of detecting Crohn's Disease based on the availability of ulcer areas at the candidate frames for KVASIR was 89.9% and for the CrohnIPI was 83.3%. We are continuing our research to fine-tune our approach by adding more thick data methods for enhancing diagnosis accuracy.

Keywords: thick data analytics, capsule endoscopy, Crohn’s disease, siamese neural network, decision tree

Procedia PDF Downloads 156

Authors: Jinan Laurentia Woo

Abstract:

This paper explores the intersection of technology, music education, and social-emotional learning (SEL) with a focus on Latin America. It delves into the impact of music education on social-emotional skills development, highlighting the universal significance of music across various life stages. The integration of artificial intelligence (AI) in music education is discussed, emphasizing its potential to enhance learning experiences. The paper also examines the implementation of SEL strategies in Latin American public schools, emphasizing the importance of fostering social-emotional well-being in educational settings. Challenges such as unequal access to technology and education in the region are addressed, calling for further research and investment in tech-assisted music education.

Keywords: music education, social emotional learning, educational technology, Latin America, artificial intelligence, music

Procedia PDF Downloads 59

Authors: Jinan B. Al-Dabbagh, Rozman Mohd Tahar, Mahadzir Ishak

Abstract:

TiAl alloy nano-powder was successfully produced by a mechanical alloying (MA) technique in a planetary ball mill. The influence of milling parameters, such as the milling duration, rotation speed, and balls-to-powder mass ratio, on the characteristics of the Ti50%Al powder, including the microstructure, crystallite size refinement, and phase formation, were investigated. It was found that MA of elemental Ti and Al powders promotes the formation of TiAl alloys, as Ti (Al) solid solution was formed after 5h of milling. Milling without the addition of process control agents led to a dramatic decrease in the crystallite size to 17.8 nm after 2h of milling. Higher rotation energy and a higher ball-to-powder weight ratio also accelerated the reduction in crystallite size. Subsequent heating up to 850°C resulted in the formation of a new intermetallic phase with a dominant TiAl3 phase plus minor γ-TiAl or α2-Ti3Al phase or both. A longer milling duration also exhibited a better effect on the micro-hardness of Ti50%Al powders.

Keywords: TiAl alloys, nanocrystalline materials, mechanical alloying, materials science

Procedia PDF Downloads 358

Authors: Ghazi Faisal Najmuldeen, Wahida Amat-Fadzil, Zulkafli Hassan, Jinan B. Al-Dabbagh

Abstract:

The objective of this study was to evaluate the optimum fabrication process variables to produce particleboards from oil palm fronds (OPF) particles and empty fruit bunch fiber (EFB). Response surface methodology was employed to analyse the effect of hot press temperature (150–190°C); press time (3–7 minutes) and EFB blending ratio (0–40%) on particleboards modulus of rupture, modulus of elasticity, internal bonding, water absorption and thickness swelling. A Box-Behnken experimental design was carried out to develop statistical models used for the optimisation of the fabrication process variables. All factors were found to be statistically significant on particleboards properties. The statistical analysis indicated that all models showed significant fit with experimental results. The optimum particleboards properties were obtained at optimal fabrication process condition; press temperature; 186°C, press time; 5.7 min and EFB / OPF ratio; 30.4%. Incorporating of oil palm frond and empty fruit bunch to produce particleboards has improved the particleboards properties. The OPF–EFB particleboards fabricated at optimized conditions have satisfied the ANSI A208.1–1999 specification for general purpose particleboards.

Keywords: empty fruit bunch fiber, oil palm fronds, particleboards, response surface methodology

Procedia PDF Downloads 226

Authors: Zhaocheng Shang

Abstract:

In order to study the topic of cities crossing rivers, a Four-Dimensional Analysis Method consisting of timeline, X-axis, Y-axis, and Z-axis is proposed. Policies, plans, and their implications are summarized and researched along with the timeline. The X-axis is the direction which is parallel to the river. The research area was chosen because of its important connection function. It is proposed that more surface water network should be built because of the ecological orientation of the research area. And the analysis of groundwater makes it for sure that the proposal is feasible. After the blue water network is settled, the green landscape network which is surrounded by it could be planned. The direction which is transversal to the river (Y-axis) should run through the transportation axis so that the urban texture could stretch in an ecological way. Therefore, it is suggested that the work of the planning bureau and river bureau should be coordinated. The Z-axis research is on the section view of the river, especially on the Yellow River’s special feature of being a perched river. Based on water control safety demands, river parks could be constructed on the embankment buffer zone, whereas many kinds of ornamental trees could be used to build the buffer zone. City Crossing River is a typical case where we make use of landscaping to build a symbiotic relationship between the urban landscape architecture and the environment. The local environment should be respected in the process of city expansion. The planning order of "Benefit- Flood Control Safety" should be replaced by "Flood Control Safety - Landscape Architecture- People - Benefit".

Keywords: blue-green landscape network, city crossing river, four-dimensional analysis method, planning order

Procedia PDF Downloads 160