International Journal of Information Technology and Computer Science @ijitcs
Journal articles - International Journal of Information Technology and Computer Science
All articles: 1317
Early Stage Disease Diagnosis System Using Human Nail Image Processing
Scientific article
Human's hand nail is analyzed to identify many diseases at early stage of diagnosis. Study of person hand nail color helps in identification of particular disease in healthcare domain. The proposed system guides in such scenario to take decision in disease diagnosis. The input to the proposed system is person nail image. The system will process an image of nail and extract features of nail which is used for disease diagnosis. Human nail consist of various features, out of which proposed system uses nail color changes for disease diagnosis. Here, first training set data is prepared using Weka tool from nail images of patients of specific diseases. A feature extracted from input nail image is compared with the training data set to get result. In this experiment we found that using color feature of nail image average 65% results are correctly matched with training set data during three tests conducted.
Free
Early and Accurate Diagnosis of a Neurological Disorder Epilepsy Using Machine Learning Techniques
Scientific article
An epileptic seizure is a type of seizure induced by aberrant brain activity caused by an epileptic condition, which is a brain Central Nervous System disorder (CNS). CNSs are relatively prevalent and include a wide range of symptoms, including loss of awareness, and strange behaviour. These symptoms frequently result in injuries as a result of walking imbalance, tongue biting, and hearing loss. For many researchers, detecting a prospective seizure in advance has been a difficult undertaking. In this research work we have used non-imaging data and applied supervised learning algorithms to determine the classification of epilepsy and try to improve the efficiency of the model, compared to the existing ones. Random Forest algorithm was found to have highest accuracy compared to other machine learning models. The paper can be helpful in diagnosing high-risk brain diseases and predicting diseases such as Alzheimer's with symptoms challenging to predict and diseases with overlapping symptoms and overlapping symptoms and attribute values. The scope of the research work can be further extended to determine at which stage the epilepsy is present in a patient, in order to provide a correct diagnosis and medical treatment.
Free
Scientific article
In this rapidly progressing technological age, the likelihood of transmitting inadequately secured data in the cloud is high. Over the past several decades, experts in data and information security have tested and experimented with numerous hashing combinations. However, these have proven to be insufficient in preventing the interception and decoding of confidential text during transmission. Therefore, methodologically, in this current research, cryptography and steganography is diversified into using three different encryption algorithms of RSA, AES and LSB with further compressing of the to-be-communicated data, to enable the use of limited space in the cloud, as well as permit fast and quick embedded message transmission. The proposed architecture, EdSri has been implemented and tested against few existing models and found to show improved performance in terms of measured security metrics such as password strength, time between login attempts, login attempt rate, failed login attempt rate, device and browser fingerprinting, and also, measuring compression parameters like structural similar index, compression time, compression ratio, compression speed, bit per pixel, saving percentage, mean squared error, and peak to noise signal ratio, EdSri would hopefully become viable platform for exchanging secured information among the cloud communicators when hosted.
Free
Scientific article
This paper presents a fully integrated, real-time assistive system that combines voice-based object recognition with a generative conversational interface, specifically designed to enhance elderly care through edge AI deployment. The proposed framework enables intuitive human–robot interaction in domestic environments by fusing natural language understanding, optimized visual detection, and local generative response. Voice commands are processed through a speech-to-text pipeline using the Google Web Speech API, with keyword extraction triggering object detection via a quantized YOLOv8n model accelerated through TensorRT with FP16 inference on an NVIDIA Jetson Nano. In parallel, a locally deployed generative AI assistant, executed entirely on-device, provides empathetic dialogue to support social engagement and emotional well-being. The proposed system adopts a hybrid edge architecture in which object detection, robot control, and LLM-based dialogue generation are executed on-device, while speech-to-text transcription relies on a cloud-based service. This generative interface is implemented as an LLM-based Emotional Assistant. The system achieves 13 FPS with an inference latency of 70 ms for object detection, 94.3% speech recognition accuracy, and an F1-score of 0.69 at a 0.5 confidence threshold. All AI components are executed on-board, preserving privacy for on- device processing while maintaining real-time responsiveness. Experimental validation confirms the effectiveness of deploying multimodal AI, including generative models, on resource-constrained hardware. This work lays the foundation for autonomous, voice-guided care robots that not only assist in locating objects but also engage users socially, promoting greater autonomy and quality of life for older adults.
Free
Educational data mining: a case study perspectives from primary to university education in Australia
Scientific article
At present there is an increasing emphasis on both data mining and educational systems, making educational data mining a novel emerging field of research. Educational data mining (EDM) is an attractive interdisciplinary research domain that deals with the development of methods to utilise data originating in an educational context. EDM uses computational methodologies to evaluate educational data in order to study educational questions. The first part of this paper introduces EDM, describes the different types of educational data environments, diverse phases of EDM, the applications and goals of EDM, and some of the most promising future lines of research. Using EDM, the second part of this paper tracks students in Australia from primary school Year 1 through to successful completion of high school, and, thereafter, enrolment in university. The paper makes an assessment of the role of student gender on successive rates of educational completion in Australia. Implications for future lines of enquiry are discussed.
Free
Scientific article
Project management information systems have their proven position as an effective tool for achieving project management success in terms of the successful realization of the project regarding time, cost and quality. Recent research results have indicated that quality of project management information system output information is positively and significantly related to project management information system application and project management factors and revealed the empirical support. However, getting the reporting quality of the project status report, monthly generated from the project management information system based on the information timely maintained by the project managers, responsible for ERP implementation up to the satisfactory level at any time, can be problematic without having a systematic approach implemented. This article is to discuss how the continuous quality improvement based on the plan-do-check-act cycle was conducted on the reporting quality of the project status report from project management information system generated by the project managers, for achieving project management success in ERP projects implemented by a solution provider for their customers in the various industries in Japan. The results of the study indicate that the continuous improvement on the reporting quality of project management information system was found to be effective in achieving quality of project management information system output information to help managers in decision making, planning, organizing and controlling the project. It was also found to be effective in positively influencing achievement of project management success in terms of respecting the time, cost and quality.
Free
Effective use of lessons learned to conduct the project review for ERP implementation
Scientific article
According to a recent study, it has been said that “lessons learned” is one of the most important and “value added” aspects of the project management lifecycle. However, it has been reported that it is often the most ignored part of finishing a project. Various reasons have been offered for this phenomenon. This article describes the systematic approach to initiate the project review on the specific project identified for requiring the formal quality audit based on the use of project management information system for having the execution date fixed by the independent quality reviewer with the project manager. Then, the project review process is started by retrieving the lessons learned data from the lessons learned repository, which were collected from the previous project reviews for the relevant ERP implementation projects, for the preparation of conducting the project document review and project stakeholder interviews. A case study methodology was applied to the historical lessons learned data of the ERP implementation projects conducted by the solution provider for their customers in the various industries in Japan, which were retrieved for a period of four years from 2014 to 2017 to analyze how the lessons learned collected from the project reviews of the earlier projects were reused in those of the succeeding projects conducted during the period. Use of lessons learned based on the past project review results was found to be effective in focusing on the specific areas projected for improvement during the processes of conducting the project document review and project stakeholder interviews, as well as putting together the practical recommendations for the findings to finalize the results of the project review, which were to be formally presented and submitted to the customer as the results of the quality audit.
Free
Efficient Algorithm for Destabilization of Terrorist Networks
Scientific article
The advisory feasibility of Social Network Analysis (SNA) to study social networks have encouraged the law enforcement and security agencies to investigate the terrorist network and its behavior along with key players hidden in the web. The study of the terrorist network, utilizing SNA approach and Graph Theory where the network is visualized as a graph, is termed as Investigative Data Mining or in general Terrorist Network Mining. The SNA defined centrality measures have been successfully incorporated in the destabilization of terrorist network by deterring the dominating role(s) from the network. The destabilizing of the terrorist group involves uncovering of network behavior through the defined hierarchy of algorithms. This paper concerning the destabilization of terrorist network proposes a pioneer algorithm which seems to replace the already available hierarchy of algorithms. This paper also suggests use of the two influential centralities, PageRank Centrality and Katz Centrality, for effectively neutralizing of the network.
Free
Efficient Analysis of Pattern and Association Rule Mining Approaches
Scientific article
The process of data mining produces various patterns from a given data source. The most recognized data mining tasks are the process of discovering frequent itemsets, frequent sequential patterns, frequent sequential rules and frequent association rules. Numerous efficient algorithms have been proposed to do the above processes. Frequent pattern mining has been a focused topic in data mining research with a good number of references in literature and for that reason an important progress has been made, varying from performant algorithms for frequent itemset mining in transaction databases to complex algorithms, such as sequential pattern mining, structured pattern mining, correlation mining. Association Rule mining (ARM) is one of the utmost current data mining techniques designed to group objects together from large databases aiming to extract the interesting correlation and relation among huge amount of data. In this article, we provide a brief review and analysis of the current status of frequent pattern mining and discuss some promising research directions. Additionally, this paper includes a comparative study between the performance of the described approaches.
Free
Efficient Networks Communication Routing Using Swarm Intelligence
Scientific article
As demonstrated by natural biological swarm’s collective intelligence has an abundance of desirable properties for problem-solving like in network routing. The focus of this paper is in the applications of swarm based intelligence in information routing for communication networks. As we know networks are growing and adopting new platforms as new technologies comes. Also according to new demands and requirements networks topologies and its complexity is increasing with time. Thus it is becoming very difficult to maintain the quality of services and reliability of the networks using current Networks routing algorithms. Thus Swarm intelligence (SI) is the collective behavior of decentralized self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. A new class of algorithms, inspired by swarm intelligence is currently being developed that can potentially solve numerous problems of modern communications networks. These algorithms rely on the interaction of a multitude of simultaneously interacting agents. In this paper we give disadvantages of previously used network routing algorithms and how we can apply swarm intelligence to overcome these problems.
Free
Efficient Sensor-Cloud Communication using Data Classification and Compression
Scientific article
Wireless Sensor Network, a group of specialized sensors with a communication infrastructure for monitoring and controlling conditions at diverse locations, is a recent technology which is getting popularity day by day. Besides, cloud computing is a type of high-performance computing that uses a network of remote servers which simultaneously provides the service to store, manage and process data rather than a local server or personal computer. An architecture called sensor-cloud is also providing good services by combining the capabilities from both ends. In order to provide such services, a large volume of sensor network data needs to be transported to cloud gateway with a high amount of bandwidth and time requirement. In this paper, we have proposed an efficient sensor-cloud communication approach that minimizes the enormous bandwidth and time requirement by using statistical classification based on machine learning as well as compression using deflate algorithm with a minimal loss of information. Experimental results describe the overall efficiency of the proposed method over the traditional and related research.
Free
Electronic police ambush system via vehicles/drivers safety authentication system
Scientific article
The suggested system aims to develop the level of security for the Egyptian police ambushes and to decrease the overcrowding because the traditional police ambushes was depressing in the last decade in Egypt due to the actions of terrorism and the threatening of our nation security, which was causing a waste of human casualties and will decrease the income of the tourism and reputation of our nations. The direct interaction with the vehicles inside the police ambushes may cause an unnecessary overcrowding. The introduced system try to minimize the human element in the police ambush through utilizing RFID technology by specifying an RFID card for each vehicle and vehicle driver which will be like the electronic passport at the RFID Sensing check point before the ambush. After checking for the information saved on the RFID card supposed inside the vehicle and also registered previously on the system server results in giving the vehicle the “PASS” signal or “ARRESSTED” signal which required a capture photo shot for the vehicle. So that system aims to increase the security level and reduce casualties of police ambushes anywhere even if it is fixed or non-fixed.
Free
Empirical Estimation of Hybrid Model: A Controlled Case Study
Scientific article
Scrum and Extreme Programming (XP) are frequently used models among all agile models whereas Rational Unified Process (RUP) is one of the widely used conventional plan driven software development models. The agile and plan driven approaches both have their own strengths and weaknesses. Although RUP model has certain drawbacks, such as tendency to be over budgeted, slow in adaptation to rapidly changing requirements and reputation of being impractical for small and fast paced projects. XP model has certain drawbacks such as weak documentation and poor performance for medium and large development projects. XP has a concrete set of engineering practices that emphasizes on team work where managers, customers and developers are all equal partners in collaborative teams. Scrum is more concerned with the project management. It has seven practices namely Scrum Master, Scrum teams, Product Backlog, Sprint, Sprint Planning Meeting, Daily Scrum Meeting and Sprint Review. Keeping above mentioned context in view, this paper intends to propose a hybrid model naming SPRUP model by combining strengths of Scrum, XP and RUP by eliminating their weaknesses to produce high quality software. The proposed SPRUP model is validated through a controlled case study.
Free
Scientific article
IT industry in the present market situation faces high demand for performance and burgeoning user expectations; with the pressure manifesting itself in three forms – Development Cost, Time-to-market and Product Quality. Researchers have proposed several techniques to effectively deal with these conflicting scenarios and draw optimized output. One of the relevant techniques in this context is Component Based Software Development (CBSD) with a targeted and discriminative approach influencing all phases of development. Although, CBSD proposes a multi-faceted approach in complex scenarios, its prime focus lies in “write once and reuse multiple times” methodology with either no or minor modifications. The model has been markedly successful in large enterprise applications with companies deriving benefits from shorter development time, increased productivity and better quality product. This research paper focuses and discusses Empirical Study of an Improved Component Based Software Development (ICBD) Model using Expert Opinion Technique which covers both component based software development as well as Component development phases. ICBD Model tries to overcome some of the issues in the contemporary CBD Models. A case study was conducted to investigate and evaluate our model by experienced professionals working in the IT industry. Results have shown that our improved model registers significant improvement over previous models suggested by other researchers.
Free
Empirical and theoretical validation of a use case diagram complexity metric
Scientific article
A key artifact produced during object oriented requirements analysis is Use Case Diagram. Functional requirements of the system under development and relationship of the system and the external world are displayed with the help of Use Case Diagram. Therefore, the quality aspect of the artifact Use Case Diagram must be assured in order to build good quality software. Use Case Diagram quality is assessed by metrics that have been proposed in the past by researchers, based on Use Case Diagram countable features such as the number of actors, number of scenarios per Use Case etc., but they have not considered Use Case dependency relations for metric calculation. In our previous paper, we had proposed a complexity metric. This metric was defined considering association relationships and dependency prevailing in the Use Case Diagram. The key objective in this paper is to validate this complexity metric theoretically by using Briand’s Framework and empirically by performing a Controlled experiment. The results show that we are able to perform the theoretical and empirical validation successfully.
Free
Energy Detection Performance of Spectrum Sensing in Cognitive Radio
Scientific article
Spectrum sensing is a challenging task for cognitive radio. Energy detection is one of the popular spectrum sensing technique for cognitive radio. In this paper we analyze the performance of energy detection technique to detect primary user (PU). Simulation results show that the probability of detection increases significantly when signal to noise ratio increases. It is also observed that the detection probability decreases when the bandwidth factor increases.
Free
Energy efficiency analysis by fine grained modification in link state routing protocol
Scientific article
A major concern in modern explosive development of information and communication technology, especially in wired networking is to reduce of unnecessary energy consumption. It is needed because of expected environmental impact and potential economic benefits. These issues are usually referred as “Green networking”. It is related to increase the awareness of energy consuming in routing protocols, in the devices, including the structure of the whole networking system. Here different issues will be described which is topically related and the possible impact in green networking field. Also, special attention will be monitored in the routing protocol and algorithm especially link state routing protocol which is generally used for calculating the shortest path. This research paper tries to find out a new technique or modified routing technique that will be more effective for every router in terms of energy efficiency.
Free
Energy efficient routing protocol for maximum lifetime in wireless sensor networks
Scientific article
Wireless sensor networks (WSNs) have become a popular research area that is widely gaining the attraction from both the researchers and the practitioner communities due to their wide area of applications. These include real time sensing for audio delivery, imaging, video streaming, environmental monitoring, industrial applications and remote monitoring. WSNs are constrained with limited energy due to their physical size. In order to maximize network lifetime, efficient use of limited sensor nodes energy resources is important. Energy efficient routing protocol for maximum lifetime in wireless sensor networks (EERPM) is proposed. Sensor nodes lifetime optimization models are formulated subject to energy consumption constraint, data flow conservation constraint, maximum data rate constraint and link capacity constraint. The models are used to solve mathematical models for the maximum lifetime routing problems. Sensor nodes transmit their data packets based on the link capacity that is inference free among the sets of links. Moreover, algorithms are developed for coverage of sensor nodes and maximization of lifetime for sensor nodes. Simulation results show that EERPM performs better than MLCS, MLCAL and AEEC protocols. It can reduce data gathering latency and achieve load balancing. Finally, the proposed method extends network lifetime compared to the related selected protocols.
Free
Energy-Efficient PSO and Latency Based Group Discovery Algorithm in Cloud Scheduling
Scientific article
Cloud computing is a large model change of computing system. It provides high scalability and flexibility among an assortment of on-demand services. To imporve the performance of the multi-cloud environment in distributed application might require less energy efficiency and minimal inter-node latency correspondingly. The major problem is that the energy efficiency of the cloud computing data center is less if the number of server is low, else it increases. To overcome the energy efficiency and network latency problem a novel energy-efficient particle swarm optimization representation for multi-job scheduling and Latency representation for the grouping of nodes with respect to network latency is proposed. The scheduling procedure is through on the basis of network latency and energy efficiency. Scheduling schema is the main part of Cloud Scheduler component, which helps the scheduler in scheduling decision on the base of dissimilar criterion. It also works well with incomplete latency information and performs intelligent grouping on the basis of both network latency and energy efficiency. Design a realistic particle swarm optimization algorithm for the cloud servers and construct an overall energy competence based on the purpose of the servers and calculation of fitness value for each cloud servers. Also, in order to speed up the convergent speed and improve the probing aptitude of our algorithm, a local search operative is introduced. Finally, the experiment demonstrates that the proposed algorithm is effectual and well-organized.
Free
Energy-efficient Secure Directed Diffusion Protocol for Wireless Sensor Networks
Scientific article
In wireless sensor networks, it is crucial to design and employ energy-efficient communication protocols, since nodes are battery-powered and thus their lifetimes are limited. Such constraints combined with a great number of applications used in these networks, pose many challenges (limited energy, low security…) to the design and management of wireless sensor networks. These challenges necessitate a great attention. In this paper, we present a new version of Directed Diffusion routing protocol which provides both security and energy efficiency together in wireless sensor networks.
Free
