International Journal of Information Technology and Computer Science @ijitcs
Journal articles - International Journal of Information Technology and Computer Science
All articles: 1304
Scientific article
This paper focuses on an empirical hand gesture recognition system in the domain of image processing and machine learning. The hand gesture is probably the most intuitive and frequently used mode of nonverbal communication in human society. The paper analyzes the efficiency of the Histogram of Oriented Gradients (HOG) as the feature descriptor and Support Vector Machine (SVM) as the classification model in case of gesture recognition. There are three stages of the recognition procedure namely image binarization, feature extraction, and classification. The findings of the paper show that the model classifies hand gestures for the given dataset with satisfactory efficiency. The outcome of this work can be further utilized in practical fields of real-world applications dealing with non-verbal communication.
Free
An Efficient Graph-Coloring Algorithm for Processor Allocation
Scientific article
This paper develops an efficient exact graph-coloring algorithm based on Maximum Independent Set (MIS) for allocating processors in distributed systems. This technique represents the allocated processors in specific time in a fully connected graph and prevents each processor in multiprocessor system to be assigned to more than one process at a time. This research uses a sequential technique to distribute processes among processors. Moreover, the proposed method has been constructed by modifying the FMIS algorithm. The proposed algorithm has been programmed in Visual C++ and implemented on an Intel core i7. The experiments show that the proposed algorithm gets better performance in terms of CPU utilization, and minimum time for of graph coloring, comparing with the latest FMIS algorithm. The proposed algorithm can be developed to detect defected processor in the system.
Free
An Efficient IBE Scheme using IFP and DDLP
Scientific article
In 1984, Shamir introduced the concept of an identity-based encryption. In this system, each user needs to visit a private key generation (PKG) and identify him- self before joining a communication network. Once a user is accepted, the PKG will provide him with a secret key. In this way, if a user wants to communicate with others, he only needs to know the “identity” of his communication partner and the public key of the PKG. There is no public file required in this system. However, Shamir did not succeed in constructing an identity based encryption, but only in constructing an identity-based signature (IBS) scheme. In this paper, we propose an identity based encryption (IBE) based on the factorization problem (IFP) and double discrete logarithm problem (DDLP) and we consider the security against a conspiracy of some entities in the proposed system and show the possibility of establishing a more secure system.
Free
Scientific article
In recent days, the smart city project has been emerging concept all over the world. In this process, the proper communication between the sensors and the smart devices, and identification of optimal path between sensors and mutation sensors in large geographical area is very difficult. The main objective has been considered to overcome the drawbacks as mentioned above. The proposed algorithm is efficient to provide integrated communication of IoT-based ubiquitous networking (UBN) devices to improve in large geographically distributed area. The data storage capacity and accuracy of sensors and smart devices are enhanced using the proposed algorithm. The communication latency and data pre-processing of IoT-based UBN nodes deployed in smart cities are reduced. The proposed algorithm also analyses the performance of IoT-based UBN nodes by considering geographical testbeds that represent a smart city scenario. The analysis and comparison are carried out by considering the heuristic parameters. The proposed algorithm will also optimize the communication latency and data pre-processing time by analyzing various sensitivity levels by considering the heuristic parameters in different probability of nodes in smart cities. The proposed IoT-based UBN computing devices improve the objective function due to proper integrated communication between the sensors using a machine learning based regression algorithm. The proposed algorithm also identifies the probability sensitivity of optimal path between smart devices in a smart city thereby enhancing the connectivity of mutated sensor nodes. The proposed algorithm also enhances the probability of smart device connectivity to improve the accuracy, flexibility and large geographical coverage using machine learning based regression algorithm.
Free
An Efficient String Matching Technique for Desktop Search to Detect Duplicate Files
Scientific article
Information retrieval is used to identify the relevant documents in a document collection, which is matching a user's query. It also refers to the automatic retrieval of documents from the large document corpus. The most important application of information retrieval system is search engine like Google, which identify those documents on the World Wide Web that are relevant to user queries. In most situations, users may download the files that are already downloaded and stored in their computer. Then, there is a chance of multiple copies of the files that are already stored in different drives and folders on the system, which in turn reduces the performance of the system and these files occupy a lot of memory space. Analyzing the contents of the file and finding their similarity is one of the major problems in text mining and information retrieval. The main objective of this research work is to analyze the file contents and deletes the duplicate files in the system. In order to perform this task, this research work proposes a new tool named Duplicate File Detector Tool i.e. DFDT. DFDT helps the user to search and delete duplicate files in the system at a minimum time. It also helps to delete the duplicate files not only with the same file category, but also with different file categories. Boyer Moore Horspool and Knuth Morris Pratt string searching algorithms are existing algorithms and these algorithms are used to compare the file contents for finding their similarity. This work also proposes a new string matching algorithm named as W2COM (Word to Word COMparison). From the experimental results it is observed that the newly proposed W2COM string matching algorithm performance is better than Boyer Moore Horspool and Knuth Morris Pratt algorithms.
Free
An Empirical Study on Testing of SOA based Services
Scientific article
Service-Oriented Architecture (SOA) removed the gap between software and business. Today, there is a business transformation among enterprises and they adopt a service based information technology (IT) model. So, testing is necessary for SOA based applications. This paper investigates different type of approaches and techniques that address the testing problems of SOA based services. Here we also investigate the differences between SOA and web services and traditional testing and SOA testing. Various testing levels are also discussed in detail. This paper also expresses various testing perspectives, challenges of SOA testing and review the many testing approaches and identify the problems that improve the testability of SOA based services.
Free
An Energy Effective WBAN Architecture for Athletes Efforts Analysis under a Common Activity
Scientific article
Wireless Body Area Network (WBAN) is one of the most critical real time networks. In order to increase network lifetime, several protocols have been proposed in the Literature. Majority of these protocols are based on either coverage or residual energy of the network. However, none of the protocols is based on node criticality, communication count, coverage and residual energy. In this paper, we have taken into consideration all the above stated parameters to determine the optimal path for transmission of message. In particular, we are implementing this scenario for Athlete Activity Monitoring to identify the athlete with maximum physical stamina. As per best of our knowledge, only intra-BAN routing protocols are proposed till date. However, in this paper we have simulated Athlete Activity Monitoring scenario for intra-WBAN and inter-WBAN architecture. It is clear from the simulation results that our scheme performs much better in terms of energy consumption than earlier routing schemes.
Free
Scientific article
Consolidation of storage into IP SANs (Internet protocol storage area network) has led to a combination of multiple workloads of varying demands and importance. To ensure that users get their Service level objective (SLO) a technique for isolating workloads is required. Solutions that exist include cache partitioning and throttling of workloads. However, all these techniques require workloads to be classified in order to be isolated. Previous works on performance isolation overlooked the classification process as a source of overhead in implementing performance isolation. However, it’s known that linear search based classifiers search linearly for rules that match packets in order to classify flows which results in delays among other problems especially when rules are many. This paper looks at the various limitation of list based classifiers. In addition, the paper proposes a technique that includes rule sorting, rule partitioning and building a tree rule firewall to reduce the cost of matching packets to rules during classification. Experiments were used to evaluate the proposed solution against the existing solutions and proved that the linear search based classification process could result in performance degradation if not optimized. The results of the experiments showed that the proposed solution when implemented would considerably reduce the time required for matching packets to their classes during classification as evident in the throughput and latency experienced.
Free
An Experimental Analysis on Performance and Energy Saving in Mobile Cloud Computing
Scientific article
Mobile Cloud Computing is a combination of mobile, cloud and wireless network where data storage and processing happens outside the mobile device. The storage capacity, processing power and battery life can be improved by moving resource intensive applications onto the cloud. In this paper, the performance of the mobile device is measured by using four different sorting techniques. Two different strategies were used for execution. In the first strategy, the input, execution and the output happens on the mobile device. In the other strategy, the input and output happens on the mobile device while the execution of the sorting techniques is offloaded to the server. The parameters considered for measurement are the execution time and mobile device’s energy consumption. The results show that offloading the task to the server reduces the execution time and energy consumption on the mobile device.
Free
Scientific article
Lung cancer is a main reason of death globally, and reducing death rates and enhancing treatment results depend heavily on quick identification. However, medical image diagnosis, including Computed Tomography (CT) scans, is difficult and demands a high level of experience. This research proposes a comprehensive and interpretable Computer-Aided Diagnosis (CAD) structure to identify lung cancer from medical images. The workflow initiates with an Adaptive Savitzky-Golay Filter, effectively enhancing image quality by smoothing while preserving critical structural edges. Hierarchical Adaptive Cluster Refinement (HACR) is then used for precise segmentation, adaptively identifying abnormal lung regions with high accuracy. For feature extraction, the proposed system utilizes the Deep Statistical Gray-Level Co-occurrence Matrix (DS-GLCM) approach, which captures deep spatial and statistical texture features essential for distinguishing cancerous tissue. At last stage, classification is performed using a novel Deep Learning (DL) model Crested Porcupine Optimized (CPO) Channel-Attention (CA) InceptionResNet. The CPO algorithm is exploited to tune the CA- InceptionResNet model's hyperparameters. To ensure transparency and reliability in clinical use, Explainable AI (XAI) technique- Local Interpretable Model-Agnostic Explanations (LIME) is used for visual interpretability, highlighting regions in CT images that contribute the most to model forecasts, thus boosting clinician trust and decision-making. The entire framework is implemented in Python, and experimental results on benchmark lung cancer imaging datasets demonstrate its superior performance in terms of performance metrics with an accuracy of 98.18% with sensitivity of 95.94 % and specificity of 99.10%. The combination of advanced DL and explainable AI makes the proposed framework a promising solution for lung cancer diagnosis.
Free
An Exploratory Analysis between the Feature Selection Algorithms IGMBD and IGChiMerge
Scientific article
Most of the data mining and machine learning algorithms will work better with discrete data rather than continuous. But the real time data need not be always discrete and thus it is necessary to discretize the continuous features. There are several discretization methods available in the literature. This paper compares the two methods Median Based Discretization and ChiMerge discretization. The discretized values obtained using both methods are used to find the feature relevance using Information Gain. Using the feature relevance, the original features are ranked by both methods and the top ranked attributes are selected as the more relevant ones. The selected attributes are then fed into the Naive Bayesian Classifier to determine the predictive accuracy. The experimental results clearly show that the performance of the Naive Bayesian Classifier has improved significantly for the features selected using Information Gain with Median Based Discretization than Information Gain with ChiMerge discretization.
Free
Scientific article
A mathematical model and a solving strategy for the Pickup and Delivery Problem with three-dimensional loading constraints regarding a combinatorial configuration instead of a traditional approach that utilizes Boolean variables is proposed. A traditional one-to-one Pickup and Delivery Problem in a combination with a problem of packing transported items into vehicles by means of the proposed combinatorial generation algorithm is solved.
Free
An ICT based solution for virtual garment fitting for online market place
Scientific article
In this paper, we describe various technologies that are being used in virtual garment fitting and simulation. There, we have focused on the usage of anthropometry in the clothing industry and avatar generation of virtual garment fitting. Most commonly used technologies for avatar generation in virtual environment have been discussed in this paper such as generic body model method and laser scanning technologies. Moreover, this paper includes the usage of real-time tracking technologies used in virtual garment fitting like markers and depth cameras. Apart from these, virtual clothing methods such as geometrical, physical and hybrid-based models were also discussed in this paper. As ease allowance has a major impact on virtual cloth fitting, it is also considered in this paper relating to similar research studies. As the final stage, our proposed design has been explained including the steps of the experiment that has been conducted to generate a two-dimensional model of the garment item. Within this paper, all the above-mentioned areas were described thoroughly while stating the existing gap of the virtual garment fitting in online marketplaces and our proposed solution to bridge that gap.
Free
An Image Encryption Scheme Based on Bit Circular Shift and Bi-directional Diffusion
Scientific article
A novel image encryption scheme based on chaotic system is proposed. The proposed encryption scheme utilizes one tent map to generate a pseudo-random sequence and then shift the bits of the expanding 0-1 image circularly so as to shuffle the image gray values. To make the encryption scheme resist differential attack efficiently, generalized Arnold maps and Bernoulli shift maps are applied to produce two pseudo-random gray value sequences and then diffuse the gray values bi-directionally. The bit circular shift process and diffusion processes greatly confuse the statistical nature between plain-images and cipher-images. Security analyses including key sensitivity analysis, key space analysis, statistical analysis, differential attack analysis and information entropy analysis are performed. All the experimental results demonstrate that the proposed image encryption scheme possesses large key space to frustrate brute-force attack efficiently and can resist statistical attack, differential attack, etc.
Free
An Improved Active Shape Model Application onFacial Feature Localization
Scientific article
An improved active shape model is proposed in this paper. The proposed algorithm includes the following four aspects. Firstly, this paper adopts a semi-automatic facial feature points marking tool. Secondly, this paper proposes to extract 2D gradient feature on the highest level and the higher level of multi-resolution pyramid images, and use Gabor wavelet transformation to extract the lowest level’s 2D texture feature. Thirdly, this paper adopts a new method of decomposition of multi-resolution pyramid. Pyramid images are got by wavelet transformation. Finally, this paper uses an improved searching scheme of multiresolution pyramid. The length of 2D profile searching rectangle is changed according to different pyramid levels. Experimental results demonstrate that the proposed algorithm exhibits better performance than the original ASM.
Free
An Improved Classification Model for Fake News Detection in Social Media
Scientific article
Fake news dissemination is a critical issue in today’s fast-changing network environment. Existing classification models for fake news detection have not completely stopped the spread because of their inability to accurately classify news, thus leading to a high false alarm rate. This study proposed a model that can accurately identify and classify deceptive news articles content infused on social media by malicious users. The news content, social-context features and the respective classification of reported news was extracted from the PHEME dataset using entropy-based feature selection. The selected features were normalized using Min-Max Normalization techniques. A predictive fake news detection model was formulated as a stacked ensemble of three algorithms. The model was simulated and its performance was evaluated by benchmarking with an existing model using detection accuracy, sensitivity, and precision as metrics. The result of the evaluation showed a higher 17.25% detection accuracy, 15.78% sensitivity, but lesser 0.2% precision than the existing model. Thus, the proposed model detects more fake news instances accurately based on news content and social content perspectives. This indicates that the proposed classification model has a better detection rate, reduces the false alarm rate of news instances and thus detects fake news more accurately.
Free
An Improved Kerberos Scheme Based on Dynamic Password
Scientific article
By studying the Kerberos authentication scheme, an improved authentication scheme is raised, which is based on Dynamic Password Method. In the improved scheme, user’s password can be effectively protected, and the authentication is double between users and severs. Also, the scheme can resist jacking connection attack. The improved scheme is more secure and more practical than the original one.
Free
An Improved Trust-based and Energy Efficient Secure Routing Protocol for 5g-Wsn
Scientific article
The 5G-enabled Wireless Sensor Networks (WSN) use the increased capabilities of 5G technology to represent the next version of conventional WSN environments. WSN performance may be affected by interference from high-density 5 G networks. The novel Hummingbird-based Graph Bernoulli Binomial Trust Management Network (HBbGBBTMN) proposed in this research is to enhance smart, secure, and energy-saving routing in 5G-enabled wireless networks. Python is initially used to simulate and model the network under consideration, accounting for fluctuating network conditions and dynamic node dynamics. An improved Hummingbird algorithm is used to detect and remove nodes with high energy consumption, thereby minimizing routing inefficiencies and avoiding suspicious behavior. To protect data integrity and prevent route disruption, malicious nodes are continuously detected and removed. The trust of the remaining nodes is calculated using the Bernoulli-Binomial distribution, which estimates each node's trust based on its previous packet-forwarding history. Such trust mechanisms are combined with node energy levels as well as network dynamics to form a fitness function that identifies optimal routing patterns. The suggested system is validated through extensive performance analysis, including measurements of packet delivery ratio, throughput, packet drop rate, delay, and malicious node prediction accuracy. The findings indicate that in decentralized wireless environments, HBbGBBTMN significantly enhances network efficiency, security, and dependability.
Free
An Improved Wavelet Filtering Algorithm and Its FPGA Implementation
Scientific article
The de-noising of sensor data has become an important to research. Since the traditional de-noising method can’t achieve successful de-noising effect and the software-only method never meets a high real time capability. In this paper, we illustrate a novel threshold function based on the wavelet hard and soft threshold function. It is unlike ordinary function, which has overcome the defect such as the discontinuity of hard threshold function and an invariable dispersion between the estimated wavelet coefficients and the decomposed coefficients of soft threshold function. Moreover, we consider the hardware implementation of wavelet threshold filter on FPGA which adopt the pleated sheet structure of multiplier and fit to frame data. A detailed description of the simulation and implementation is given. Finally, the experiment result on-board is shown that our hardware implementation can meet the requirement of real-time signal processing.
Free
An Improvement over AODV Routing Protocol by Limiting Visited Hop Count
Scientific article
The AODV protocol is based on the minimum delay path as its route selection criteria, regardless of the paths load. This issue leads to unbalanced load dissemination in the network and the energy of the nodes on the shortest path deplete earlier than others. We proposed an improved AODV protocol with limited TTL (Time to Live) of RREP packet in which the route reply (RREP) packet of AODV is modified to limite TTL information of nodes. Experiments have been carried out using network simulator software (NS2). Simulation results show that our proposed routing protocol outperforms regular AODV in terms of packet delivery rate, good put, throughput, and jitter.
Free
