The rapid spread of misinformation on social media threatens public discourse, trust, and decision-making. Existing rumor detection methods—ranging from multimodal fusion to graph-based reasoning—have achieved promising results but often struggle to capture the multiview, heterogeneous, evolving, and adversarial nature of real-world rumor propagation. Common limitations include oversimplified graph structures, shallow temporal modeling (TM), and limited semantic grounding or robustness. To address these challenges, we propose temporal reasoning and detection of emerging network threats (TRIDENT), a unified and interpretable framework that represents rumor events as multiview heterogeneous temporal graphs enriched with external knowledge. TRIDENT integrates a novel partial differential equation–graph convolutional network (PDE-GCN) module for continuous-time temporal encoding, cross-view attention for joint reasoning over user interactions, content semantics, and propagation structure, and multimodal adversarial training to defend against label-preserving manipulations in both text and graph domains. Comprehensive evaluations on four benchmark datasets,Twitter15,Twitter16,Weibo, andPHEME, show that TRIDENT consistently outperforms state-of-the-art baselines, with especially strong gains on challenging rumor types such asfalseandunverifiedclaims. These results highlight the importance of unifying TM, semantic grounding, and adaptive multiview graph reasoning for robust and explainable rumor detection in dynamic social ecosystems.

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues to grow, fully fine-tuning these models has become highly parameter-intensive. Although Parameter-Efficient Fine-Tuning (PEFT) methods have been introduced to reduce the number of tunable parameters, a significant performance gap remains compared to full fine-tuning. Furthermore, existing PEFT approaches are often highly parameterized, making them difficult to interpret and control. In light of this, we introduce Multimodal Representation Tuning (MRT), a novel approach that focuses on directly editing semantically rich multimodal representations to achieve strong performance and provide intuitive control over LMMs. Empirical results show that our method surpasses current state-of-the-art baselines with significant performance gains (e.g., 1580.40 MME score) while requiring substantially fewer tunable parameters (e.g., 0.03% parameters). Additionally, we conduct experiments on editing instrumental tokens within multimodal representations, demonstrating that direct manipulation of these representations enables simple yet effective control over network behavior.

As large language models (LLMs) evolve into autonomous agents equipped with tools and communication capabilities, they are increasingly deployed in multi-agent systems (MASs) to perform complex tasks. While these systems offer new levels of functionality and efficiency, their security risks remain underexplored. In this paper, we present a focused security analysis of LLM agents by implementing six representative attacks on two real-world MASs. These attacks expose structural and behavioral vulnerabilities unique to agent-based systems. We also introduce and evaluate defensive mechanisms such as fine-tuned agent behaviors, access control via the NGAC (Next Generation Access Control) standard, and a novel "sanity checker" agent for validating agent outputs. Our findings highlight the urgent need for robust, standardized security frameworks for LLM-based MASs and suggest promising directions for future research in agent-level threat modeling and mitigation.

This paper presents a novel framework for constructing a diabetes-specific knowledge graph (KG) using a streamlined multi-agent system powered by Gemini-based Large Language Models (LLMs). Leveraging insights from the 2016 National Diabetes Survey (NNDS) conducted by the National Diabetes Education Program (NDEP), the framework extracts critical variables related to diagnosis, risk perception, medical advice, and self-management practices across diverse U.S. populations. By processing data from the NNDS’s extensive 94-question survey, the methodology performs adaptive ontology mapping using APIs for six major medical standards (e.g., SNOMED CT, ICD-11), ensuring semantic interoperability. Relationships between variables are identified and structured using RDF, RDFS, and OWL standards. The integration of LLMs with ontology tools like Protégé enhances automation and scalability. Results demonstrate the framework’s effectiveness in generating contextually rich and clinically relevant knowledge graphs, providing a robust foundation for advancing healthcare informatics and personalized diabetes management.

Medical imaging has been a crucial component of COVID-19 clinical procedures. However, CT scans for lung and COVID-19 infection diagnosis are time-consuming and require specific knowledge. In addition, diverse imaging modalities, such as regions of interest (organs or lesions) and picture quality, make the automated segmentation of these infectious fragments difficult. In this paper, we proposed TLU-Net based on an optimized design of U-Net architectures to facilitate successful transfer learning for the segmentation of medical images from a source domain, such as lungs, to a target domain, such as COVID-19 infection. We have investigated the effective transfer learning methodologies for U-Net topologies, hyperparameters, freezing, and multiple models/datasets in the lungs and COVID-19 domains. Due to our improved and lightweight U-Net design, experiments with TLU-Net employing three lung and COVID-19 infection domain datasets increased segmentation accuracy and reduced training time.

Deep learning (DL) has recently achieved a massive response for medical image analysis, especially in semantic image segmentation. Semantic neural architectures are pivotal in extracting anatomical structures from provided input data. The conventional models, inspired by U-Net architecture with encoder-decoder structure, encounter irreversible intensity loss. It is due to continuous stride and pooling operations that prevent them from precisely extracting vascular tree structure and impact the efficacy of degenerative retinal disease detection. In this work, we proposed a Cascaded Neural Architecture (CNA) that uses a generative adversarial concept with two generators and discriminators to localize coarse and fine features. The network helps in preserving vessels by classifying input at pixel-level. In generators, we introduced residual blocks with a densely connected residual block used only in the bottleneck part of a fine-generator for maximum feature reuse and to restrain redundant feature sharing. We also designed customized lightweight discriminators with encoder-decoder structures to reduce computable parameters. Our network is compared with prominent architectures and evaluated on publicly available fundus image datasets (DRIVE, STARE, and CHASE-DB1) with variations in dimensions and focal points. Our network has achieved promising results by reporting the highest area under the ROC curve and structural similarity index score.

Communities have first-hand knowledge about community issues. This study aims to improve the efficiency of social-technical problem-solving by proposing the concept of "artificial process intelligence," based on the theories of socio-technical decision-making. The technical challenges addressed were channeling the communication between the internal-facing and external-facing 311 categorizations. Accordingly, deep learning models were trained on data from Kansas City's 311 system: (1) Bidirectional Encoder Representations from Transformers (BERT) based classification models that can predict the internal-facing 311 service categories and the city departments that handle the issue; (2) the Balanced Latent Dirichlet Allocation (LDA) and BERT clustering (BLBC) model that inductively summarizes residents' complaints and maps the main themes to the internal-facing 311 service categories; (3) a regression time series model that can predict response and completion time. Our case study demonstrated that these models could provide the information needed for reciprocal communication, city service planning, and community envisioning. Future studies should explore interface design like a chatbot and conduct more research on the acceptance and diffusion of AI-assisted 311 systems.

The retina manifests a vital role in tracing chronic retinal disorders. It is located near the optic nerve that transforms the captured light into neural signals. The most prominent chronic eye diseases exhibit themselves in the retina. The analysis of a retina for detecting disease symptoms is quite challenging. Most of the prior methods developed using shallow and deep learning algorithms primarily emphasized single feature extraction for disease diagnosis. The underlying article has designed an ensemble network for extracting multiple retinal features using a single comprehensive platform. It includes a set of models that reflect feature-based needs to prevent intensity loss, micro-vessels overlap, and data redundancy. The proposed method has experimented with prominent benchmark datasets developed for vessels tree, optic disc/cup, and arteries/veins extraction. It is also compared with other methods and achieved promising results. Our platform is helpful for physicians to trace the variations in the retina of subjects facing chronic retinal disorders.

The retinal vasculature has a vital role in predicting chronic diabetic and hypertensive retinopathy. Recently, the advent of deep learning algorithms has brought a revolution in ocular disease prediction. The researchers frequently design complex and intricate techniques to efficiently segment vessels, micro-vessels and achieve better response on publicly available benchmark datasets. This article has designed an attention-guided neural system to extract vascular tree and distinguish it in arteries and veins. The proposed learning protocol with a minimalist approach can compete with state-of-the-art work without a performance compromise. Our method has achieved a promising response on numerous retinal image datasets. The pitfall of previously proposed work is also addressed through the self-defined assessment criteria. The in-depth analysis highlights that the underlying problem is unsolved for unseen data with different distribution than training. Our method is cross-validated to report the performance loss by keeping diversity in data selection. The technique is further applied for the arteries and veins extraction. Our effort can be adapted as an efficient vision-critical platform to scan and localize retinal damage and diagnose the disease symptoms early to prevent vision impairment.

Training a neural network model from scratch is a computationally intensive operation. To alleviate this issue, researchers often employ "transfer learning" that transfers knowledge from a source data distribution to a target data distribution, instead of training the whole model from scratch. Typically, the last few layers of a pretrained convolutional neural network (CNN) are chosen for many transfer learning tasks where the outputs of those selected layers are combined to construct a feature space based on which a task-specific classification n etwork i s t rained o r fi ne-tuned. Th is arbitrary way of selecting layers, however, often fails to achieve the desired accuracy for the target task. What we need is an intelligent way of selecting layers from a pretrained model for a given task so that the additional overhead of successive training remains low. To this end, we propose a novel method, called TransJury, to find t he m ost s ignificant la yers from a pretrained mo del for transfer learning along with preserving the knowledge for the source domain. Through extensive experimentation on several target domain datasets, we show the supremacy of our approach in terms of lower training overhead and improved accuracy. By deploying MobileNet-v2, a lightweight CNN model pretrained on the ImageNet dataset on an edge device, we also discuss the future direction of this research.

There are increasingly leveraging public data with cities increasingly interested in driving both responsiveness to citizen demands and cost savings through data analytics. As public managers seek to augment existing data sources, such as 311 complaints, with existing secondary data, such as US Census products, severe challenges exist. This paper considers the problems inherent in data being collected at divergent geographic levels over different time horizons. An inductive analytical methodology is developed to create units of analysis that are both useful and analytically appropriate for public managers and policy leaders in urban areas. A big data analytics framework for public data, called BDAP, was presented predictive analytics for community need considering data the spatial and temporal location while addressing the data issues such as missing values, privacy-preserving, and predictive modeling. The findings illustrate the power of inductive data curation and privacy-preserving leading to benefits to the big data community. An application for the Open Data Platform was developed using KCMO’s 311 data, crime data and census data.

Many people around the world suffer from neurological impairments and face many difficulties in performing their routine daily tasks. Caregiver services can become exhausted, expensive, and depressing for the patient over time. In the last few decades, numerous research is conducted on developing BCIs that can help a neurological impaired individual to communicate and functionally rehabilitate. Advances in the field of the Internet of Things (IoT) has opened the door for new opportunities in smart assistive technologies, like smart home, elderly care, or robotic applications. In this paper, we present an IoT-based non-invasive brain-computer interface (BCI) system. This system uses electroencephalography (EEG) signals to help severely paralyzed and locked-in patients regain the ability to do a simple daily task, such as locking/unlocking the door, turning on/off the lights or TV, and communicate with others, caregivers or healthcare providers, by sending text notifications. For our BCI, we have also built a deep learning classifier to understand the patient intent and trigger the corresponding workflow on connected IoT devices. This model has achieved a global accuracy of 72.82% for 103 subjects and 93.33% subject specific transfer learning for 10 subjects on the EEG Motor Movement/Imagery (MI) dataset [1] for MI tasks for 2 classes. Our BCI is also integrable with EEG headsets (like Emotiv) and IoT devices like Google Home and Alexa.

Program comprehension is a fundamental prerequisite for software maintenance and evolution. In order to understand a software structure, developers often read its codebase or documentation—if available and not outdated. Both approaches are tedious, time-consuming, and inefficient. Recent methods and tools have emerged to facilitate program comprehension, such as static call graphs, which depict the structure of the software system as a directed graph. However, the usage of call graphs still faces two main challenges: (1) large call graphs can be difficult to understand, and (2) they are limited to a single level of granularity, such as function calls. In this paper, we introduce a coarsening technique to create multi-level, hierarchical representations of the call graph. Specifically, we propose a hierarchical clustering approach of the execution paths to visualize the call graph at different granularity levels and for different software units, including packages, classes, and functions. Our overarching goal is to assist software developers in understanding the software system from a high-level of abstraction to the low-level of implementation with the ability to focus on particular parts of the system individually. To validate our approach and tool support, we conducted a user study of 18 software engineers from more than 11 industries who carried out several tasks using our system and then answered a survey. The results demonstrate that our approach is feasible to automatically construct multi-level abstractions of the call graph and hierarchically cluster them into meaningful abstractions. A video demo of the tool is available at https://rakanalanazi.github.io/CodEx/.

Lung disease is the most common cause of severe illness and death in the World. The early diagnosis and treatment of the disease are of great importance in the medical field. The computer-assisted systems for lung disease recognition are effective methods to help physicians diagnose the diseases effectively. Therefore, this paper studies the multimodal recognition of lung sound using spectrograms. Based on the classification of lung diseases by deep convolutional neural networks, an integrated network Multimodal Lung Disease Classification (MLDC) model was used with advanced pre-processing techniques to assess the classification accuracy acceptable in the medical field. The research has three main contributions. First, we have performed data pre-processing using two techniques Data Normalization and Data Augmentation. The data were normalized by removing the unwanted noise and adjusting the peak values in a sound signal. For training purposes, the publicly available data was insufficient. Hence we applied advanced data augmentation techniques to generate some additional data without affecting the categories. Secondly, we have extracted the spectrograms from lung sound and used them as features and images for signal and image processing. Finally, we created an integrated model for the high-performance classification of lung diseases. We have compared the audio and spectrogram image-based results where we found the image-based approach is cost-effective, efficient, and reliable.

In metropolitan cities, outdoor air pollution and ambient outdoor noise transmission are significant environmental hazards, degrading indoor environmental quality. Natural ventilation is often a viable option for diluting indoor air pollutants, but transportation noise transmission is a crucial ecological conflict. Therefore, personal control over the concentration of outdoor/indoor air pollutants and noise levels is a significant threshold for natural ventilation availability. This study proposes real-time data detection and notification solutions using sensors and artificial intelligence (AI) to improve indoor air quality and outdoor air quality and outdoor noise transmission. An intelligent real-time detection and notification system was implemented in a distributed computing framework with cloud and edge computing. The objective of this study is placed on three facets: (1) development of sensors and NVIDIA Jetson Nano prototype for air quality and noise level detection, (2) application of machine learning for air quality and noise level prediction and classification, and (3) web interface for real-time monitoring and prediction for air quality and noise level detection. The results showed that the proposed user interface provides building occupants with real-time data of outdoor/indoor Air Quality Index (AQI) and noise levels for the optimized occupant control over Indoor Air Quality (IAQ). The personal control over indoor environmental quality (IEQ) enables occupants to promote natural ventilation behaviors and integrate with the existing building system on optimized IEQ by interacting with AI-based real-time data.

Heart diseases are considered the leading cause of death globally. Early diagnosis of disease may help give appropriate prescribing medicines, which may help control and reduce conditions. The current clinical diagnosis methods such as Electrocardiograms, computed tomography, echocardiogram, Magnetic Resonance Imaging, etc. provide valuable information for diagnosis and treatment. However, these techniques are time-intensive, operator-dependent, and expensive. In this paper, we propose a low-cost solution real-time solution to diagnose heart diseases. We suggest an integrated automatic multimodal heart disease classification (AMHDC) system using the Phonocardiogram (PCG) signal. For this purpose, first, we have developed an advanced fusion method using pre-processing techniques such as Data Normalization and Data Augmentation. Secondly, we have extracted the spectrograms from heart sound and used them as features and images for signal and image processing. Finally, we created a real-time integrated Convolutional Neural Network (CNN) model for high-performance heart disease classification. The results show our model outperformed the state-of-art research, whose accuracy is 89.7%., while our model reported accuracy of 93% for audio and 96% for image-based approach.

Human-in-the-Loop has been receiving special attention from the data science and machine learning community. It is essential to realize the advantages of human feedback and the pressing need for manual annotation to improve machine learning performance. Recent advancements in natural language processing (NLP) and machine learning have created unique challenges and opportunities for digital humanities research. In particular, there are ample opportunities for NLP and machine learning researchers to analyze data from literary texts and use these complex source texts to broaden our understanding of human sentiment using the human-in-the-loop approach. This paper presents our understanding of how human annotators differ from machine annotators in sentiment analysis tasks and how these differences can contribute to designing systems for the "human in the loop" sentiment analysis in complex, unstructured texts. We further explore the challenges and benefits of the human-machine collaboration for sentiment analysis using a case study in Greek tragedy and address some open questions about collaborative annotation for sentiments in literary texts. We focus primarily on (i) an analysis of the challenges in sentiment analysis tasks for humans and machines, and (ii) whether consistent annotation results are generated from multiple human annotators and multiple machine annotators. For human annotators, we have used a survey-based approach with about 60 college students. We have selected six popular sentiment analysis tools for machine annotators, including VADER, CoreNLP's sentiment annotator, TextBlob, LIME, Glove+LSTM, and RoBERTa. We have conducted a qualitative and quantitative evaluation with the human-in-the-loop approach and confirmed our observations on sentiment tasks using the Greek tragedy case study.

One of the leading causes of cancer death is liver cancer. The most common type of primary liver cancer in adults is Hepatocellular carcinoma (HCC), and it is also the most common cause of death among people suffering from chronic liver diseases. In clinical practices, accurate and automated liver and tumor segmentation mechanisms are highly desired to help oncologists with early diagnosis and treatment of HCC. Manual segmentation of tumor and liaisons, from abdominal computerized tomography (CT) scans, is time-consuming, requires domain expertise, and is prone to inaccuracies in many cases. Automated segmentation, on the other hand, is a challenging task due to the nature of medical images such as heterogeneous modalities and formats, the minimal labeled training data, and the high-class imbalance in the labeled data. To solve these problems, we propose a 2-dimensional network consists of two CNN models, called CU-Net. To perform double segmentation, the first model segments the liver from the CT scan of the abdominal cavity and second detects the tumor on the liver. Our model also goes one step further and provides useful information for interpretation purposes and reports on the number of tumors, size of each tumor, size of the liver, and percentage of the liver that is tumorous, which is not provided by any other liver-lesion segmentation model. We have used the Liver Tumor Segmentation (LiTS) challenge data for training and validation purposes, and with this data, we have achieved a Dice score of 0.894 for liver segmentation and 0.595 for tumor detection.

The advanced technologies are essential to achieving the improvement of medicine. More specifically, an extensive investigation in a partnership among researchers, health care providers, and patients is integral to bringing precise and customized treatment strategies in taking care of various diseases. This paper aims to assess the degree of accuracy acceptable in the medical field by utilizing deep learning to publicly available data. First, we extracted spectrogram features and labels of the annotated lung sound samples and used them as an input to our 2D Convolutional Neural Network (CNN) model. Secondly, we normalized the lung sounds to remove the peak values and noise from them. For deep learning classification, publicly available data was not sufficient to conduct the learning process. Finally, we have created a deep learning model called Lung Disease Classification (LDC), combined with advanced data normalization and data augmentation techniques, for high-performance classification in lung disease diagnosis. The final accuracy obtained after the normalization and augmentation was approximately 97%. The proposed model paves the way for adequate assessment of the degree of accuracy acceptable in the medical field and guarantees better performance than other previously reported approaches.

Alzheimer's Disease is an irreversible, progressive brain disorder that slowly destroys cognitive abilities. In recent years, the relationship between the prodromal Mild Cognitive Impairment (MCI) stage and the Alzheimer's Disease (AD) stage has been extensively researched in hopes of finding a path towards early diagnosis. Early detection at the MCI stage can help determine appropriate treatment plans as well as assist in clinical trial enrollment as 32% of individuals with MCI will develop AD within 5 years. Computer vision studies leveraging Magnetic Resonance Imaging (sMRI, fMRI), Diffusion Tensor Imaging (DTI), and Positron Emission Tomography (PET) have led to encouraging results in classifying the different stages of AD. Studies around DTI specifically have shown that structural differences in white matter are prevalent between these stages. Rather than classification between stages, we propose a recurrent neural network model (RNN) based on the DTI modality for identifying the subset (32%) of individuals with Early Mild Cognitive Impairment (EMCI) that will develop AD. Our results are state-of-the-art and demonstrate high accuracy in determining which individuals will develop AD within the next 5-7 years. Additionally, we propose our augmentation methods for DTI data as well as our classification accuracy across the traditional AD stage categories.

In this paper, we propose a new framework, DeepLite, for real-time deep learning on the edge. In DeepLite, a network of multiple deep learning models is designed to conduct the context-aware inferencing using real-time deep learning technologies. Comprehensively, DeepLite has several innovative concepts as follows: 1) an inference network of deep learning models/containers, 2) invocation of a new model based on the output of the previous model's inferencing, 3) intelligent containers for models, 4) plug-and-play model/container, and 5) microservice architecture on the edge. DeepLite has been evaluated via a case study, NeighborNets which was based on an inference network of several deep learning models deployed to edge devices for computer vision, e.g., object detection algorithms to compute a diverse range of aspects, such as house types, level of greenery, house age, traffic conditions, and the types of recreational facilities.

In this paper, we propose a new Internet of things (IoT) solution, called the Urban Noise Monitoring (UNM) system, which can classify real-time environmental audio sound using an embedded system such as Raspberry pi 4 and log the data in the Google Cloud. The reported events will be available for future usage, i.e., selection of the safe area for living. The real-time audio classification has been a big challenge for deep learning in environmental sounds due to the high noisy nature of sound. We have implemented a real-time IoT system for urban sound classification and monitored the historical reports generated. We have developed an advanced fusion method using normalization techniques such as peak, RMS, and EBU and an efficient data augmentation method using various factors, including time stretch, pitch shifting, and dynamic range compression. Further, we have integrated the normalization and the augmentation methods into 2D Convolutional Neural Network (CNN) with the TensorFlow framework on Raspberry pi 4 for urban sound classification. Our classification model outperformed the state of the art performance: 95% accuracy with the Urban sound dataset. The outstanding performance confirmed the effectiveness of the proposed method on the IoT system for urban noise monitoring.

Human emotions are essential to recognize the behavior and state of mind of a person. Emotion detection through speech signals has started to receive more attention lately. This paper proposes the method for detecting human emotions using speech signals and its implementation in real-time using the Internet of Things (IoT) based deep learning for the care of older adults in nursing homes. The research has two main contributions. First, we have implemented a real-time system based on audio IoT, where we have recorded human voice and predicted emotions via deep learning. Secondly, for advance classification, we have designed a model using data normalization and data augmentation techniques. Finally, we have created an integrated deep learning model, called Speech Emotion Detection (SED), using a 2D convolutional neural networks (CNN). The best accuracy that was reported by our method was approximately 95%, which outperformed all state-of-the-art approaches. We have further extended to apply the SED model to a live audio sentiment analysis system with IoT technologies for the care of older adults in nursing homes.

Understanding software evolution is an imperative prerequisite for software related activities such as testing, debugging, and maintenance. As a software system evolves, it increases in size and complexity, introducing new challenges of understating the inner system interactions and subsequently hinders the overall system comprehension. While tools that construct and visualize call graphs have been used to facilitate software comprehension, they are still limited to capturing the functionality of a single software system at a time. However, understanding the similarities and differences across multiple releases becomes an imperative and challenging task during software evolution. To this end, we present a tool, named GraphEvo, that focuses on automating the process of quantifying and visualizing the changes across multiple releases of a software system based on an information-theoretic approach to compare the call graphs. Specifically, GraphEvo can automatically (1) construct and visualize the call graph for one or more software releases, (2) calculate and display a set of graph-based metrics, and (3) construct color-coded call graphs to visualize system evolution. The main goal of GraphEvo is to assist software developers and testers in exploring and tracking software changes over time. We demonstrate the functionality of GraphEvo by analyzing and studying five real software systems throughout their entire lifespan. The tool, evaluation results, and a video demo are available at https://goo.gl/8edZ64.

Customer Relationship Management (CRM) systems play an important role in helping companies identify and keep sales and service prospects. CRM service providers offer a range of tools and techniques that will help find, sell to and keep customers. To be effective, CRM users usually require extensive training. Predictive CRM using machine learning expands the capabilities of traditional CRM through the provision of predictive insights for CRM users by combining internal and external data. In this paper, we will explore a novel idea of computationally learning salesmanship, its patterns and success factors to drive industry intuitions for a more predictable road to a vehicle sale. The newly discovered patterns and insights are used to act as a virtual guide or trainer for the general CRM user population.

A parallel and distributed machine learning framework are in need to deal with a large amount of data. We have seen unsatisfactory classification performance especially with increasing the number of classes. In this paper, we propose a distributed deep learning framework, called Multi-Class Discriminative Distribution (MCDD) that aims to distribute classes while improving the accuracy performance of the deep learning models with large scale datasets. The MCDD framework works on an evidence-based learning model for the optimal distribution of classes by computing a misclassification cost (i.e., confusion factor). These observations about learning attempts have been used to extend a classifier into a classification model hierarchy by learning an optimal distribution of classes. As a result, a distributed deep neural network model with multi-class classifiers (MCDD) was built to optimize the accuracy and performance of the learning process. The MCDD model runs on parallel environments, such as Apache Spark and Tensor Flow using large real-world datasets (Caltech-101, CIFAR-100, ImageNet-1K) showing that MCDD can build a class distribution model with higher accuracy compared to existing models.

Program comprehension is an imperative and indispensable prerequisite for several software tasks, including testing, maintenance, and evolution. In practice, understanding the software system requires investigating the high-level system functionality and mapping it to its low-level implementation, i. e. source code. The implementation of a software system can be captured using a call graph. A call graph represents the system's functions and their interactions at a single level of granularity. While call graphs can facilitate understanding the inner system functionality, developers are still required to manually map the high-level system functionality to its call graph. This manual mapping process is expensive, time-consuming and creates a cognitive gap between the system's highly-level functionality and its implementation. In this paper, we present an innovative approach that can automatically (1) construct and visualize the static call graph for a system written in Python, (2) cluster the execution paths of the call graph into hierarchal abstractions, and (3) label the clusters according to their major functional behaviors. The goal is to bridge the cognitive gap between the high-level system functionality and its call graph, which can further facilitate system comprehension. To validate our approach, we conducted four case studies including code2graph, Detectron, Flask, and Keras. The results demonstrated that our approach is feasible to construct call graphs and hierarchically cluster them into abstraction levels with proper labels.

The aim of the paper is to perform audio analytics based on the audio sensor data that is continuously monitoring the home environment automatically through an audio Internet of Things (IoT) system. Domestic violence is one of the major problems in many cities nowadays. We have proposed a home automation system where IoT sensors records the audio in home environment continuously and the audio is sent to machine learning server where the audio is split into small clips and classified into different categories. The need of an automatic detection system is urgent for enforcing home safety and safe neighborhood. If IoT system detects any suspicious sound, it generates an emergency notification to nearest emergency services for possible action to be taken. The classification of audio such as gunshots, explosion, glass breaking, screaming and siren is based on shallow learning (Support vector machine, Decision tree, Random forest and Naïve Bayes) and deep learning (Convolutional neural network and Long short-term memory). Our experiments validated that Convolutional Neural Network shows the best performance (89% accuracy) compared to other machine learning algorithms.

A static call graph is an imperative prerequisite used in most interprocedural analyses and software comprehension tools. However, there is a lack of software tools that can automatically analyze the Python source-code and construct its static call graph. In this paper, we introduce a prototype Python tool, named code2graph, which automates the tasks of (1) analyzing the Python source-code and extracting its structure, (2) constructing static call graphs from the source code, and (3) generating a similarity matrix of all possible execution paths in the system. Our goal is twofold: First, assist the developers in understanding the overall structure of the system. Second, provide a stepping stone for further research that can utilize the tool in software searching and similarity detection applications. For example, clustering the execution paths into a logical workflow of the system would be applied to automate specific software tasks. Code2graph has been successfully used to generate static call graphs and similarity matrices of the paths for three popular open-source Deep Learning projects (TensorFlow, Keras, PyTorch). A tool demo is available at https://youtu.be/ecctePpcAKU.

We have developed a fast, scalable, and purely geometric structure search combining techniques from information retrieval and big data with a novel approach to encoding sequences of torsion angles. Along the way, we introduce a new torsion angle plot without breaks in continuity while still maintaining traditional torsion angle ranges, to assist in identifying separable regions of torsion angles. Subsequently, we introduce a new heuristic we call run position encoding, for handling the lack of specificity of items within character sequences containing runs of repeats. Comparing our results to the output of the CATH structural scan, response times are measured in seconds as opposed to minutes and average RMSDs and TM-scores are better. Our approach is a step towards a comprehensive indexing of protein structures scalable to millions of entries. Code and data are available at https://github.com/rayoub/rupee.

In recent years, there has been explosive growth in the amount of biomedical publications. In this paper, we propose a semantic framework that aims to automatically generate an ontology by extracting assertions and topics from multiple free-text scientific publications in PubMed. The pipeline approach for knowledge discovery and ontology generation in the proposed framework has been implemented on the Spark parallel engine based on the Stanford CoreNLP for Natural Language Processing, TF-IDF (Term Frequency Inverse Document Frequency) for feature extraction, OpenIE (Open Information Extraction) for relation extraction, K-Means clustering for topic discovery and OWL API for ontology generation. We have shown that the ontology generated may be very effective in biomedical applications (such as paper search and summarization) with scientific publications.

Studies on visual attention of patients with Alzheimer's disease and dementia are a promising way for keeping track of an individual patients image recognition ability over time. This research seeks to expand upon the current applications of combining the Android operating system with TensorFlow by providing QA diagnostics alongside a visual question answering (VQA) platform for image analysis. This framework, Cognitive Visual Recognition Tracker (CVRT), provides an entry point by which the user can ask symptom-related inquiries or visual questions concerning any image of their choosing, and then receive cumulative metrics over time to better assess any diminishing cognitive ability (i.e. Alzheimer's patients). In this work, recurrent neural networks alongside semantic analysis and knowledge graphs are leveraged to provide an interactive VQA experience. One of the main objectives of CVRT is for physicians to be able to determine trends from patient data that could either be applicable to the individual patient, or to many patients if an aggregate is formed from many individual datasets. On an individual level, these metrics would provide a way for the physician to monitor daily cognitive capability, whereas on a grander scale, these joint datasets could be used to provide better overall treatment for the disease with the future inclusion of Predictive Analytics. The final contribution is an interactive metrics platform by which other users can assess the primary users cognitive capacity based on features of their questioning, and to then provide them with accurate trending or possible remediation plans based on their condition.

An alarming proportion of the US population is overweight: 2/3 of US adults are overweight, and 1/3 of those overweight are obese. Obesity increases the risk of illnesses such as diabetes and cardiovascular diseases. This epidemic can be attributed to the combination of cheap, high-calorie food and lack of physical activity. In this paper, we propose a Big Data Analytics framework, called BiDAF, that aims to explore social contextual influences on healthy eating. For this purpose, we classified food tweets and social media images into as either healthy or unhealthy as well as food sentiments into either positive or negative, and further mapped them to an obesity prevalence map. The classification outcomes would be useful to reveal the social food trends and sentiments of the Centers for Disease and Control Prevention (CDC) USA obesity regions. The BiDAF framework has been implemented on Apache Spark and TensorFlow platforms. We have evaluated the BiDAF framework in terms of the accuracy on the food tweet classification and sentiment analysis. The experimental results indicated that the BiDAF framework is effective in classification and sentiment analysis of food tweet messages and also showed its potential in exploring social contextual influences that may contribute to healthy eating.

In this paper, we present an energy efficient motion sensing platform for wireless body area networks that supports real-time, persistent gesture recognition through motion tracking sensors. The platform consists of multiple heterogeneous wearable sensors. The custom-built body sensors include inertial sensors, a low-power microcontroller and a 2.4 GHz radio transceiver. Signal classifiers such as Fishers linear discriminant classifiers, static neural networks, and focused time delay neural networks (fTDNN) are employed to classify the signals obtained from the wearable sensors. It was found that at a sampling rate of 10 Hz and just 4 bits/sample, the fTDNN classifier achieves 88% classification rate. Our results show that reducing the sampling and quantization rates could be used in energy constrained sensor networks for gesture recognition.

A large number of structured and unstructured data (e.g., EHRs, ontologies, reports) have been introduced by the biomedical community. Cross-domain data integration is identified as an important research problem for translational research. From an application perspective, identifying related concepts among medical ontologies is an important goal of life science research. It is essential to analyze how relations are specified to connect concepts in a single ontology or across multiple ontologies. With the explosion of cross domain datasets, it is extremely hard for researchers to discover knowledge from current infrastructures of ontologies. It is mainly a lack of the connectivity between the ontologies' cross domains and ontologies to unstructured data; even if they have specific biomedical knowledge in a more general and comprehensive level. Therefore, there is a need for a mechanism to do semantic partition and query generation for cross domain biomedical knowledge discovery. In this paper, we present such a model that clusters integrated data based on semantic closeness of predicates into different groups and produces meaningful queries to fully discover knowledge over a set of interlinked data sources. We have implemented a prototype of the BmQGen system and evaluated the proposed query model based on the predicate oriented clustering with colorectal surgical cohort from the Mayo Clinic.

BACKGROUND: The cascade computer model (CCM) was designed as a machine-learning feature platform for prediction of drug diffusivity from the mucoadhesive formulations. Three basic models (the statistical regression model, the K nearest neighbor model and the modified version of the back propagation neural network) in CCM operate sequentially in close collaboration with each other, employing the estimated value obtained from the afore-positioned base model as an input value to the next-positioned base model in the cascade. The effects of various parameters on the pharmacological efficacy of a female controlled drug delivery system (FcDDS) intended for prevention of women from HIV-1 infection were evaluated using an in vitro apparatus "Simulant Vaginal System" (SVS). We used computer simulations to explicitly examine the changes in drug diffusivity from FcDDS and determine the prognostic potency of each variable for in vivo prediction of formulation efficacy. The results obtained using the CCM approach were compared with those from individual multiple regression model. RESULTS: CCM significantly lowered the percentage mean error (PME) and enhanced r(2) values as compared with those from the multiple regression models. It was noted that CCM generated the PME value of 21.82 at 48169 epoch iterations, which is significantly improved from the PME value of 29.91% at 118344 epochs by the back propagation network model. The results of this study indicated that the sequential ensemble of the classifiers allowed for an accurate prediction of the domain with significantly lowered variance and considerably reduces the time required for training phase. CONCLUSION: CCM is accurate, easy to operate, time and cost-effective, and thus, can serve as a valuable tool for prediction of drug diffusivity from mucoadhesive formulations. CCM may yield new insights into understanding how drugs are diffused from the carrier systems and exert their efficacies under various clinical conditions.

Service discovery is an integral issue in the area of service oriented computing (SOC). A centralized platform based service discovery suffers from major drawbacks such as scalability and a single point of failure. A P2P based design incurs high maintenance overhead for a distributed service registry and querying task. In this paper, we have proposed SMARTSPACE-a hybrid multiagent based distributed platform for efficient semantic service discovery. By utilizing reactive agents in modeling services, users' requests, and registry management middleware, the proposed service discovery algorithm, SmartDiscover, is able to achieve fast, scalable, parallel, and concurrent service finding within a systemic environment that can be highly dynamic, asynchronous, and concurrent. We have conducted the SmartDiscover experiments within the JADE 3.7 agent framework on top of both IBM Cloud Cluster and NetLogo simulation environments. The results showed promising positive outcomes in terms of average query response time and the number of message exchanges to maintain the distributed registry. The accuracy of SmartDiscover was measured and compared with the widely accepted benchmark OWL-S MX approach.

An integral step in the discovery of new treatments for medical conditions is the matching of potential subjects with appropriate clinical trials. Eligibility criteria for clinical trials are typically specified as inclusion and exclusion criteria for each study in freetext form. While this is sufficient for a human to guide a recruitment interview, it cannot be reliably and computationally construed to identify potential subjects. Standardization of the representation of eligibility criteria can enhance the efficiency and accuracy of this process. This article presents a semantic framework that facilitates intelligent matchmaking by identifying a minimal set of eligibility criteria with maximal coverage of clinical trials. In contrast to existing top-down manual standardization efforts, a bottom-up data driven approach is presented to find a canonical nonredundant representation of an arbitrary collection of clinical trial criteria. The methodology has been validated with a corpus of 709 clinical trials related to Generalized Anxiety Disorder containing 2,760 inclusion and 4,871 exclusion eligibility criteria. This corpus is well represented by a relatively small number of 126 inclusion clusters and 175 exclusion clusters, each of which corresponds to a semantically distinct criterion. Internal and external validation measures provide an objective evaluation of the method. An eligibility criteria ontology has been constructed based on the clustering. The resulting model has been incorporated into the development of the MindTrial clinical trial recruiting system. The prototype for clinical trial recruitment illustrates the effectiveness of the methodology in characterizing clinical trials and subjects and accurate matching between them.

The Smart Grid holds promise for transforming the behavior of individuals and communities towards a more efficient and greener use of electric power. There is a growing demand for non-intrusive monitoring of energy consumption behavior at multiple scales and also for autonomous energy saving opportunities for both individuals and communities. In this demo, we present a sentient service framework for a smart application, named E-SAVE that aims to monitor activities by a user or community and configure the environment of devices for a smarter energy usage. The key building block to the smart application capability is context aware activity monitoring and energy usage optimization by recognizing appropriate energy-usage patterns pertaining to various activities, areas, and devices. We have developed the E-SAVE prototype system to monitor the usage of energy by a user or community and configure the environment of devices for smart usage of energy.

Service discovery is one of the key problems that have been widely researched in the area of Service Oriented Architecture (SOA) based systems. Web Service clustering is a technique for efficiently facilitating service discovery. Most Web Service clustering approaches are based on suitable semantic similarity distance measure and a threshold. Threshold selection is essentially difficult and often leads to unsatisfactory accuracy. In this paper, we have proposed a self-organizing based clustering algorithm called Taxonomic clustering for taxonomically organizing semantic Web Service advertisements. We have tested the algorithm on both simulation based randomly generated test data and the standard OWL-S TC test data set. We have observed promising results both in terms of accuracy and performance.

The World Wide Web (WWW) has become a major platform for hosting, discovering, and composing web services. Web service clustering is a technique for efficiently facilitating web service discovery. Most web service clustering approaches are based on suitable semantic similarity distance measure and a threshold. Threshold selection is essentially difficult and often leads to unsatisfactory accuracy. In this paper we propose a taxonomic clustering algorithm for grouping functionally similar web services. We have tested the algorithm on both simulation based randomly generated test data and the standard OWL-S TC test data set. We have observed promising results both in terms of accuracy and performance.

With the multi-fold development in communication technology, there has been a rapid growth in consumption of multimedia services using mobile devices. In particular, lots of research has been done to provide multimedia services using a 3G/WLAN dual mode to mobile device users. All users download contents from content providers through cellular networks and can share their contents with their neighbors. This may lead to a situation where the cost of receiving multimedia contents is reduced owing to contents sharing. In other words, users effectively reduce the cost of receiving contents as they share some contents with neighbors. However, we believe that selfish users (or users with limited resources) are not willing to cooperate or share their contents with other users. In this paper, we propose an incentive scheme that gives the benefit of contents sharing to users in a 3G/WLAN dual mode supporting network. There are two types of users; premium users and ordinary users. Premium users can get high quality contents at the expense of spending their own money and resources of power and bandwidth, while ordinary users receive plain quality contents freely or with paying little amount of money. Our incentive mechanism designs the content provider to offer each premium user a discounted price for downloading high quality contents. Through our approach, each premium user will receive some incentive of a discounted price for receiving high quality contents in proportion to the contribution to the content provider. By doing so, the content provider can increase its total utility too. Our simulation results confirm that our proposed incentive scheme performs well.

Semantic web search involves retrieval of user-specific web artifacts by utilizing their semantic descriptions. A very specific web artifact that has evolved in recent times is web services. Web services can be semantically described in languages like OWL-S. However, such languages are limited with respect to their expressivity of context. They also lack a formal ontological framework where efficient web service retrieval can be conducted. In this paper we model a service request scenario within the web as an event-driven system. Services as well as user requests are modeled as events. We propose an ontological framework called Context-Aware Ontology Framework for Events and Services (CAOFES) where such event-driven web service retrieval can be efficiently executed by a novel reasoning technique.

In P2P live streaming, free-riders which do not upload data but only download them are still present. Since a greater number of viewers can generate more profit, the streaming server wants to serve the free-riders also. In this paper, we have proposed a novel P2P live streaming system, called super-peer assisted live streaming architecture (SALSA). In SALSA, super-peers, which have high upload bandwidth and serve many free-riders, are eligible to receive an incentive reward that is the ability to watch high quality videos. The server places high-quality-view-tickets at auction to make the super-peers serve free-riders more efficiently. We have proposed novel auction mechanisms and a heuristic algorithm. The simulation results showed that the proposed scheme has comparable performance to the optimal form and are able to differentiate the super-peers' video quality commensurate with their contribution level.

The three core problems that can be identified with any SOA based system are: (i) service discovery, (ii) service selection, and (iii) service composition. Most of the previous researches have considered these three problems separately. However, we argue that these three problems are intrinsically related and hence, cannot be treated separately. We propose a proactive event-driven model where user activities and services are treated as events. We then graphically model a SOA system into a network of activities called "activity network" (ANet). The nodes of such a network are the services and the edges their mutual causal dependency. We show how both functional as well as contextual information can be incorporated into the network and then justify why that is necessary for solving the three problems mentioned hereby. We then propose an abstraction technique that helps us to simplify the ANet and provide an architectural platform where the three problems can be solved in an efficient manner.

Pervasive Computing plays an integral role in our daily life. As pervasive services become increasingly important to be able to capture context, it is reasonable to speculate that dynamic representations for composition of services is very much needed. Such representations may typically include activities or functional modules that are not only temporal but also responsive to each other. Such actions may be associated with actors who execute them, spatial and temporal information, information-flow and background objects. Consequently, one may model an activity network that depicts causal relations between activities and has the capability of embedding the semantic relations of these activities with other contextual entities. In this paper we discuss a new way of representing such dynamic workflows with a novel data structure called activity logic graphs (ALGs). We introfduce a novel design of an architecture that grasps the semantics of activities (or events) in dynamic pervasive environments, maps that to a collaboration of services (as ALGs) in order to recognize specific situations (known as Situation Boundaries) that has risen out of the events, and implements the recognition process using an efficient indexing technique. We test the model with a set of ALGs and report experimental results on the queries that are essential for service composition.

Today's Web becomes a platform for services to be dynamically interconnected to produce a desired outcome. It is important to formalize the semantics of the contextual elements of web services. In this paper, we propose a novel technique called Semantic Genome Propagation Scheme (SGPS) for measuring similarity between semantic concepts. We show how SGPS is used to compute a multi-dimensional similarity between two services. We evaluate the SGPS similarity measurement in terms of the similarity performance and scalability.

OBJECTIVE: The idea of testing a hypothesis is central to the practice of biomedical research. However, the results of testing a hypothesis are published mainly in the form of prose articles. Encoding the results as scientific assertions that are both human and machine readable would greatly enhance the synergistic growth and dissemination of knowledge. DESIGN: We have developed MachineProse (MP), an ontological framework for the concise specification of scientific assertions. MP is based on the idea of an assertion constituting a fundamental unit of knowledge. This is in contrast to current approaches that use discrete concept terms from domain ontologies for annotation and assertions are only inferred heuristically. MEASUREMENTS: We use illustrative examples to highlight the advantages of MP over the use of the Medical Subject Headings (MeSH) system and keywords in indexing scientific articles. RESULTS: We show how MP makes it possible to carry out semantic annotation of publications that is machine readable and allows for precise search capabilities. In addition, when used by itself, MP serves as a knowledge repository for emerging discoveries. A prototype for proof of concept has been developed that demonstrates the feasibility and novel benefits of MP. As part of the MP framework, we have created an ontology of relationship types with about 100 terms optimized for the representation of scientific assertions. CONCLUSION: MachineProse is a novel semantic framework that we believe may be used to summarize research findings, annotate biomedical publications, and support sophisticated searches.

Recent advances in the distributed computing infrastructure like Web, grid, and pervasive computing environment accompany demands for a more powerful and autonomous service framework. We believe it is feasible to achieve service discovery and matching in an automated manner and perform the service execution not in restricted environments. For the purpose, we developed an autonomous service framework, called ASF, which allows autonomous service to be published, discovered and executed in distributed environments based on the autonomous service specification, extension of the Web service ontology (OWL-S) to incorporate physical/logical resources and resource policy.

The vision of the Semantic Web is to reduce manual discovery and usage of Web resources (documents and services) and to allow software agents to automatically identify these Web resources, integrate them and execute them for achieving the intended goals of the user. Such a composed Web service may be represented as a workflow, called service flow. Current studies of Web services are not sufficient for automatic composition. This paper presents different types of compositional knowledge required for Web service discovery and composition: syntactic, semantic and pragmatic knowledge. As a proof of concept, we have implemented our framework in a cardiovascular domain which requires advanced service discovery and composition across heterogeneous platforms of multiple organizations. Within this framework, we describe (1) How to represent the compositional knowledge, which plays a role in service discovery and composition, in DAML-S; (2) How heterogeneous medical services intemperate in a composed medical service flow. (3) To solve this knowledge level integration, we build on an ontology integration method called SEMIO (Semantic Interoperability).

Web Services are emerging technologies that enable application-to-application communication and reuse of autonomous services over the Web. Recent efforts, OWLS, model the semantics of Web Services that includes the capabilities of the service, the service interaction protocol, and the actual messages for service exchanges. However, there is a need to automate discovery, selection and execution of OWL-S services. Further, a framework that meets the quality of service (QoS) requirements for ad hoc Internet based services is rarely provided. In this paper, we have proposed a rule-based framework, called SetnWebQ, which manages workflows composed of Semantic Web Services. SemWebQ is capable of conducting QoS-based adaptive selection as well as dynamic binding and execution of Web Services according to the semantics of workflow, thereby rendering a resilient and adaptive Web based service flow. A series of experiments performed on the SemWebQ with real Web Services have confirmed the effectiveness of proposed framework with respect to adaptive selection and execution of the Web Services in Web based workflows.

Peer-to-peer networks continue to gain popularity, but the problem of locating suitable peers still remains formidable. The lack of globally accepted standards and protocols is another problem that further creates the issue of a lack of global connectivity. This paper presents a hybrid P2P infrastructure, called PSI, which uses Web Services as registries to locate peers. We also formally define the set of basic operations that are performed during peer search to determine optimized connectivity. Heuristics for locating peers are based on preference values computed using historical data. The PSI model is compared to other models with respect to suitability for integrating a set of distributed and heterogeneous peers. The mechanism for locating files depends only on discovering and using Web Services. The greatest advantage of this is the possibility of global connectivity. The understanding gained by analysis and preliminary implementation confirms that the model is highly scalable.

Peer-to-peer (P2P) systems and Semantic Web are two novel technologies that face a lot of shortcomings if considered as isolated paradigms. We present an approach that utilizes ontologies to set up a peer profile containing all the data, necessary for peer-to-peer interoperability. Using this profile can help eliminate some major issues persistent in current P2P networks, such as security, resource aggregation, group management. We also consider applications of peer profiling for Semantic Web built on P2P networks, such as an improved semantic search for resources, not explicitly published on the Web, but available in a P2P system. We develop the ontology-based peer profile in RDF format and demonstrate its manifold benefits for peer communication and knowledge discovery in both P2P networks and Semantic Web.

Electronic distributed learning that overlooks the physical and geographic status of learners has become a reality. Moreover, its quality has been considerably improved by utilizing recent advances in web-based technology. Various electronic learning support systems such as Internet-based tutorials and Virtual Universities have appeared in different forms and reflect advances in technology. However, there remains a huge barrier to support the shareable and collaborative learning available through virtual communities. Our solution to these problems was to develop an educational middleware, called the Community-Based Learning (CoBL) framework whose goal is to: (a) adapt to the diverse requirements of learners; (b) support shareable and collaborative learning; and (c) be capable of facilitating distributed learning over the Internet. The CoBL framework is based on: (1) agents to manage individual learners and communities of learners; (2) a shared data model for integrating heterogeneous communities; and (3) a component-oriented development approach. We have implemented the CoBL prototype system and used it for community-based learning.

Emerging peer-to-peer computing provides new possibilities but also challenges for distributed applications. Despite their significant potential, current peer-to-peer networks lack efficient knowledge discovery and management. This paper addresses this deficiency and proposes the Intelligent File Sharing framework, which provides an effective and flexible query for P2P file sharing. The IFS is based on powerful schema and flexible inference, as well as efficiently integrated and extensible retrieval algorithms. Experimental results have provided evidence of the high performance and scalability of the Intelligent File Sharing (IFS) system in peer-to-peer environments.

We propose a software framework for non-repudiation service in e-commerce (electronic commerce) on the Internet. The proposed software framework is an explicit security framework for notary service. In the framework we propose a systematic design methodology that provides a security class concept. Our framework can be differentiated from others. First, unlike other frameworks, it is interested in a successful completion of e-commerce transactions by supporting non-repudiation of service. Second, the proposed framework is based on dynamic adaptive mechanism that improves the performance of e-commerce transactions.

Emerging peer-to-peer applications require efficient group communication. However, current techniques for group communication are not optimal for peer-to-peer networks, which do not have group communication methods themselves. This paper presents the novel multiring topology, which is designed to meet requirements of high performance group communication in peer-to-peer networks. It improves data communication by applying several concepts: building overlay networks for each topic, a topology consisting of multiple rings, backup links and dual mode links. Experimental results provide evidence for improving performance and scalability of peer group communication.

Dynamic and complex computation in the area of Geographic Information System (GIS) or Mobile Computing System involves huge amount of spatial objects such as points, boxes, polygons, etc and requires a scalable data structure and an efficient management tool for this information. In this paper, for a dynamic management of spatial objects, we construct a hierarchical dynamic data structure, called an IST/OPG hierarchy, which may overcome some limitations of existing Spatial Access Methods (SAMs). The hierarchy is constructed by combining three primary components: (1) Minimum Boundary Rectangle (MBR), which is the most widely used method among SAMs; (2) the population-based domain slicing, which is modified from the Grid File [14]; (3) extended optimal Integer Searching algorithm [4]. For dynamic management of spatial objects in the IST/OPG hierarchy, a number of primary and supplementary operations are introduced. This paper includes a comparative analysis of our approach with previous SAMs, such as R-Tree, R+-Tree and R*-Tree and QSF-Tree. The results of analysis show that our approach is better than other SAMs in construction and query time and space requirements. Specifically, for a given search domain with n objects, our query operations yield $O($ \scriptsize $\sqrt {\frac {\log n} {\log\log n}}$\normalsize $)$ compared to $O(\log n)$ of the fast SAM and an IST/OPG hierarchy containing $n$ objects can be constructed in $O(n$ \scriptsize $\sqrt {\frac {\log n}{\log\log n}}$\normalsize $)$ time and O(n) space.

As Internet business exponentially grows, the need for high security level categories to identify groups of connections or individual transactions is manifest. The development of an efficient and secure communication protocol seems to be highly demanding. We propose the adaptive secure protocol to support secure E-commerce transactions. Our adaptive secure protocol dynamically adapts the security level based on the nature and sensitivity of the interactions among participants. The security class incorporates the security level of cryptographic techniques with a degree of information sensitivity. We implement the adaptive secure protocol and measure its performance. The experimental results show that the adaptive secure protocol provides E-commerce transactions with high quality of security service.

As an increasing number of people communicate and collaborate computationally over the Internet, the need for a collaborative environment that facilitates secure and reliable access to large quantities of distributed resources has become manifest. However the breadth of resource distribution makes it difficult for Internet users to acquire the necessary resources for collaborative computing. We have developed a framework for an efficient infrastructure that provides a reasonable mapping between users and resources distributed over the Internet. The proposed framework contributes: an authority mechanism that can be applied to independent and widely distributed resource-providers; a resource hierarchy for partitioning global resource spaces into manageable subspaces; and systematic management of dynamic groups of users and resources running on different sites. This paper describes the schema and processes for resource partition, mapping, negotiation, and forming a resource domain in our framework.