International Journal of Information Technology最新文献

This paper aims to explore the image data augmentation application on the cloud platform utilizing state-of-the-art generative machine learning techniques. This paper further highlights these techniques’ significance in addressing the challenge of data generation and emphasizes the need for further research in this area. This research adopts an in-depth exploration approach to examine the burgeoning domain of generative machine learning techniques. It discusses the evolution of these techniques and their integration with cloud services powered by Graphical Processing Unit (GPU)-enabled computational engines. Practical experimentation involving Modified National Institute of Standards and Technology (MNIST) data is conducted to showcase the capabilities of generative models, with a focus on the core Generative Adversarial Network (GAN). The findings reveal the potential of generative machine learning techniques in generating new data images, as demonstrated through practical experimentation with MNIST data. It also highlights the ongoing evolution of these techniques and their challenges, particularly in terms of computational requirements and integration with cloud computing services. This research originally contributes to the existing literature by providing insights into recent advancements and challenges in GANs and their synergies with cloud computing. It presents results from experimentation and emphasizes the importance of cost-effective development environments for implementing generative machine learning techniques.

For some people in the region, Jakarta is considered a business and economic center so many people come there. Every year the number of people coming to Jakarta increases, which makes Jakarta increasingly dense. This condition inevitably makes Jakarta one of the most congested cities, not only in Indonesia but also in the world. The high cost of living and housing ultimately makes some residents choose to live in supporting areas such as Bogor, Depok, Tangerang, or Bekasi, even though their main activities are in Jakarta. On the one hand, the relationship between buffer areas and the capital city has made Jakarta, Bogor, Depok, Tangerang, and Bekasi (Jabodetabek) agglomerated areas that are mutually dependent on each other. On the other hand, this condition creates complicated problems in the transportation sector. This is because more people use private vehicles for transportation to carry out daily activities. The majority of trips are made by private vehicles, causing traffic jams. Not only in Jakarta, traffic jams also occur in the areas where residents come to the capital. Therefore, the government is trying to create an integrated p in Jabodetabek will be much better. Public transportation (PT) needs to account for 72.8% of all people’s movements. This article aims to analyze the implementation of an integrated PT system. The target is that by 2029 transportation and system policies in Jabodetabek. In 2018, the government introduced presidential regulation number 55, addressing the Jabodetabek Transportation Master Plan. This article will provide policy implications in the form of transportation development that pays attention to integrated transportation systems, road-based transportation systems, integration of transportation and spatial planning, engineering management and traffic supervision, transportation safety and security, infrastructure networks, rail-based transportation systems, environmentally friendly transportation, and financing systems.

Key frame selection serves as a c bridge between raw video data and meaningful retrieval results. Effective key frame selection enhances the performance of content-based video retrieval systems by reducing computational complexity, improving search accuracy, and enabling faster browsing through large video databases. Additionally, fixed keyframe sampling techniques do not address information optimization, which might lead to information redundancy or loss. For effective video retrieval, a keyframe selection method based on opposition-based learning has been developed. The outcomes show that the method performs better than numerous benchmark sampling strategies.

A surveillance camera is one of the most important tools for observing people's movements and stopping unauthorized or unplanned activity. Security management experts now significantly rely on video surveillance to combat crime and avert incidents that have a detrimental influence on human civilization. To monitor public activities, the installation of numerous surveillance cameras has drastically increased in both the public and private sectors. Security may be ensured most effectively through video surveillance. Installing a surveillance camera merely provides security personnel with the recorded video. However, integrating intelligent technology to analyze the videos is the only way to spot irregular actions. As a result, the goal of this study is to construct an Intelligent Video Analytics Model (IVAM), also known as a Human Object Detection (HOD) approach, for analyzing and spotting unusual human activity and abundant objects in videos. The proposed IVAM is designed based on Multi-level glowworm swarm convolution neural networks (ML-GSCNN). The proposed approach consists of two stages namely, frame conversion, and abnormal event detection. The captured video is first divided into segments, and then each segment is changed into a frame. After that, abnormal event detection is performed. For abnormal event detection, a novel ML-GSCNN is designed. Here, the hyper-parameter of CNN and the architecture of CNN both are optimized by the glowworm swarm optimization (GSO) algorithm to improve the detection accuracy. The experimental results show that the proposed approach attained better results compared to existing works.

Occupancy detection is crucial in optimizing building energy efficiency and enhancing occupant comfort. This study introduces an innovative data-driven approach for accurate occupancy detection in an office room environment. Specifically, the methodology combines the advantages of Independent Component Analysis (ICA) to extract essential features from multivariate data and Kantorovitch distance (KD)-based schemes for detection sensitivity. The KD scheme’s detection threshold is computed nonparametrically using kernel density estimation to enhance the sensitivity of occupancy detection. The efficacy of this strategy is evaluated utilizing publicly available data recorded during winter in Mons, Belgium, capturing vital environmental parameters such as temperature, humidity, light, and CO(_{2}) levels through specialized sensors. Results demonstrate that the ICA-KD approach achieves an averaged accuracy of 98.355%, surpassing conventional approaches like Principal Component Analysis (PCA)-based, ICA-based, and other state-of-the-art methods. Additionally, the study uses Shapley Additive exPlanations (SHAP) with XGBoost to explore the impact of input variables on occupancy detection, highlighting the influence of various factors under different testing conditions.

An accurate measure of the quality of the air in any given location is the air quality index(AQI). When calculating the AQI, important air pollutants such as SO2, NO2, ground-level O3, CO, and particle matter are taken into account. Numerous organizations worldwide compute these indices based on a range of parameters. In India, the Central Pollution Control Board(CPCBs) and State Pollution Control Board (SPCBs) monitor the air quality. Every pollutant is assigned a sub-index, and the aggregate of all these sub-indices is known as the AQI. Poor, fair, or acceptable air quality can be conveyed linguistically using the AQI, which is a numerical value. When the AQI rises, it is anticipated that a considerable segment of the population may have major health effects. The current research’s aims to calculate the levels of air pollutants in Raipur's four major parts of cities from December 21, 2023, to March 27, 2024. The traditional AQI is calculated using an equation. To determine the fuzzy air quality index, a fuzzy logic system is used, and membership functions are provided as input to the Noval Dual Mamdani fuzzy inference system (FIS). As a result, the research suggests a more dependable method for computing the fuzzy air quality index using fuzzy logic.

A key component of cognitive radio systems is spectrum sensing, which reduces coexistence problems and maximises spectrum efficiency. However, the introduction of multiple situations with distinct characteristics brought about by 5G communication presents problems for spectrum sensing to support a wide range of applications with high performance and flexible implementation. Inspired by these difficulties, a new method with a multi-layer extreme learning machine optimised for bats is presented in this study. This technique makes use of a variety of input vectors, such as channel ID, energy, distance, and received signal intensity, to enhance user categorization and sensing capabilities. Moreover, we compare the proposed method with the state-of-the-art spectrum sensing approaches in order to evaluate its effectiveness in 5G situations, especially in healthcare applications. Evaluation metrics including channel detection probability, sensitivity, and selectivity are carefully examined. The findings unequivocally prove the suggested spectrum sensing approach’s superiority over current methods and highlight its potential for smooth incorporation into a variety of 5G applications.

Progress in wisdom medicine has been driven by advancements in big data, cloud computing, and artificial intelligence, enabling the accumulation of valuable information and insights. However, the increasing reliance on cloud-based storage and transmission of medical images has raised significant concerns regarding information security. The risk of unauthorized access to patients' private data poses a considerable obstacle to medical research advancement. Thus, safeguarding patient data in cloud environments is imperative. Color space-based scrambling algorithms (CSSA) are gaining traction for multimedia data encryption due to their compatibility with JPEG and reduced processing requirements. However, traditional CSSA methods rely on colorful images to optimize security, limiting their applicability in fields like medical image processing where color images may be scarce. This study seeks to integrate CSSA image encryption with Multilayer Perceptron (MLP)-based techniques for securing medical images. Additionally, a noise-based data augmentation method is developed to address data scarcity in medical image analysis. Security analysis and temporal complexity assessments are employed to evaluate the effectiveness of the proposed MLP-CSSA deep learning model in encrypting medical images. Results demonstrate robust security in encrypting both grayscale and color medical images, with the proposed MLP-CSSA method outperforming existing encryption techniques.

The paper describes the application of the Accelerator Leg of Robot Driver (ALRD) which is applied to automotive tests to save time and cost and improve the accuracy of the tests. The accelerator leg of the robot driver is controlled by Proportional-Integral-Derivative (PID) controller technique. PID Control parameters are optimized using proposed Meta-heuristic Techniques such as Artificial Bee Colony (ABC) and Firefly Algorithm (FF) which overcome the limitations of conventional PID controllers. These ABC-PID and FF-PID are employed for automotive tests to obtain coordinated control of the driving test cycle and accurate speed tracking during all types of conditions. Simulation results are then presented to demonstrate improved performance of FF-PID in tracking accuracy compared to the ABC-PID and conventional technique namely Linear-Quadratic-Gaussian (LQG).

Internet of things (IoT) consists of nodes with constraints concerning size, battery life, storage, processing, etc. Many IoT applications such as health monitoring systems generate huge amount of data that must be transmitted to destinations without delay during critical situations. Since IoT nodes have very small storage capacity, to transfer big data there is a requirement for a high bandwidth wireless technology such as visible light communication (VLC) which is harmless. Also flows that carry critical data must not be affected during congestion and must be given priority. The existing Transmission Control Protocol (TCP) has good congestion control algorithms but none of them consider the priority of flows during flow control. A Priority Queue based Flow Control Protocol named FCP_PQ is developed by providing priority to flows that carry critical data in high bandwidth network. The protocol developed ensures that only the flows that carry critical data are given priority over other flows during congestion by exhibiting an increase of 210 Kbps in case of goodput, 1.94% towards packet delivery ratio (PDR) and 4 Mega Bits transmission over 100 s time period in error free context and similar outcome is achieved in error-prone context compared to other flows.