IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
An ensemble framework augmenting surveillance cameras for detecting intruder clusters as potential mobs
Get PDFMany developing nations around the world curtail crimes through video surveillance technology, but the crime rate is still high. This is compounded by short-staffed security operatives and a deficiency of security infrastructure to assist security operatives with knowledge-driven decision support systems in the low-resource constraint environment. In a public environment, it is challenging to detect intruder clusters accurately as potential mobs for early warning. Previous research investigated some classical techniques, but their recommendations were insufficient. This research develops a machine learning 3-tiers ensemble framework, which integrates gray level co-occurrence matrices (GLCM) principles to enhance the capabilities of surveillance cameras and security operatives to effectively discern and respond to potential mob formations. The University of California San Diego (UCSD) pedestrian datasets that are publicly available were used for the experiments. With an improved overall average precision of 0.98, recall of 0.98, and accuracy of 98.52% on the UCSD dataset, the suggested framework outperforms the widely used methods for the detection of intruder clusters. The reduction in computational time on processors showcases the framework's significant advancements as a promising solution for robust real-time threat assessment applications
The integrated smart system to assist elderly at home
Get PDFSome elders prefer to live independently rather than in a nursing home. However, they need to be assisted because of health and safety reasons. We developed an integrated system consisting of a smart home, a mobile robot, and a wearable device, using message queuing telemetry transport (MQTT) protocol to communicate with each other. The smart home can be monitored and controlled via a mobile application. We use the telepresence robot equipped with a light detection and ranging (LIDAR) sensor to perform simultaneous localization and mapping (SLAM) and autonomous navigation. The wearable device application is used to detect older adults' heart rate, the steps taken, and the burnt calories. We also add pose detection and location estimation using a depth camera powered by an efficient deep-learning algorithm. We also developed an Android application as a dashboard that monitors and controls all system components. Our system can facilitate communication between its various components
Application of artificial intelligence in music generation: a systematic review
Get PDFOur analysis explores the benefits of artificial intelligence (AI) in music generation, showcasing progress in electronic music, automatic music generation, evolution in music, contributions to music-related disciplines, specific studies, contributions to the renewal of western music, and hardware development and educational applications. The identified methods encompass neural networks, automation and simulation, neuroscience techniques, optimization algorithms, data analysis, and Bayesian models, computational algorithms, and music processing and audio analysis. These approaches signify the complexity and versatility of AI in music creation. The interdisciplinary impact is evident, extending into sound engineering, music therapy, and cognitive neuroscience. Robust frameworks for evaluation include Bayesian models, fractal metrics, and the statistical creator-evaluator. The global reach of this research underscores AI's transformative role in contemporary music, opening avenues for future interdisciplinary exploration and algorithmic enhancements
Optimizing the long short-term memory algorithm to improve the accuracy of infectious diseases prediction
Get PDFThis study discusses the implementation of the proposed optimizedlong short-term memory (LSTM) to predict the number of infectious disease cases that spread in Central Java, Indonesia. The proposed model is developed by optimizing the output layer, which affects the output value of the cell state. This study used cases of four infectious diseases in Indonesia's Central Java Province, namely COVID-19, dengue, diarrhea, and hepatitis A. This model was compared to basic LSTM and MinMax schaler LSTM improvement to see the difference in the accuracy of each disease. The results showed a significant difference in the average prediction results with real cases between the three models. The main objectives of this study were: modifying the LSTM algorithm to predict the number of infectious disease cases to get a smaller residual value, comparing the results of the optimization accuracy of the LSTM algorithm with the LSTM algorithm in previous studies, and evaluating the use of spatial variables in applying infectious disease prediction models using the LSTM algorithm. The results found that the performance difference between the proposed optimization algorithm and the model in the previous study was obtained. The proposed LSTM optimization algorithm had an accuracy improvement of about 2% over the previous model
Deep learning based biometric authentication using electrocardiogram and iris
Get PDFAuthentication systems play an important role in wide range of applications. The traditional token certificate and password-based authentication systems are now replaced by biometric authentication systems. Generally, these authentication systems are based on the data obtained from face, iris, electrocardiogram (ECG), fingerprint and palm print. But these types of models are unimodal authentication, which suffer from accuracy and reliability issues. In this regard, multimodal biometric authentication systems have gained huge attention to develop the robust authentication systems. Moreover, the current development in deep learning schemes have proliferated to develop more robust architecture to overcome the issues of tradition machine learning based authentication systems. In this work, we have adopted ECG and iris data and trained the obtained features with the help of hybrid convolutional neural network- long short-term memory (CNN-LSTM) model. In ECG, R peak detection is considered as an important aspect for feature extraction and morphological features are extracted. Similarly, gabor-wavelet, gray level co-occurrence matrix (GLCM), gray level difference matrix (GLDM) and principal component analysis (PCA) based feature extraction methods are applied on iris data. The final feature vector is obtained from MIT-BIH and IIT Delhi Iris dataset which is trained and tested by using CNN-LSTM. The experimental analysis shows that the proposed approach achieves average accuracy, precision, and F1-core as 0.985, 0.962 and 0.975, respectively
Multi-granularity tooth analysis via YOLO-based object detection models for effective tooth detection and classification
Get PDFEffective and intelligent methods to classify medical images, especially in dentistry, can assist in building automated intra-oral healthcare systems. Accurate detection and classification of teeth is the first step in this direction. However, the same class of teeth exhibits significant variations in surface appearance. Moreover, the complex geometrical structure poses challenges in learning discriminative features among the tooth classes. Due to these complex features, tooth classification is one of the challenging research domains in deep learning. To address the aforementioned issues, the presented study proposes discriminative local feature extraction at different granular levels using you only look once (YOLO) models. However, this necessitates a granular intra-oral image dataset. To facilitate this requirement, a dataset at three granular levels (two, four, and seven teeth classes) is developed. YOLOv5, YOLOv6, and YOLOv7 models were trained using 2,790 images. The results indicate superior performance of YOLOv6 for two-class classification achieving a mean average precision (mAP) value of 94%. However, as the granularity level is increased, the performance of YOLO models decreases. For, four and seven-class classification problems, the highest mAP value of 87% and 79% was achieved by YOLOv5 respectively. The results indicate that different levels of granularity play an important role in tooth detection and classification
Review of image processing and artificial intelligence methodologies for apple leaf disease diagnosis
Get PDFApple leaf disease (ALD) potentially affects the apple tree's health by reducing fruit yield and its capability to grow healthy. The prime purpose of the proposed study is to review and assess the strengths and weaknesses associated with the frequently exercised methods of ALD diagnosis using image processing and artificial intelligence (AI). Although these are widely adopted in recent studies, the core notion is to find the pros and cons associated with the practical viability. A desk research methodology is undertaken to carry out proposed review work where a database of recent scientific manuscripts is collected and studied very closely. The existing approaches are reviewed concerning identified problems, adopted solutions, advantages, and limitations. Finally, the paper contributes towards offering insight into potential research gap which will guide the upcoming researchers to make wise decisions for planning their models. The results acquired from this review work show that generalized challenges of ALD are not addressed, less emphasis on illumination variability, reduced target to minimize complexity, lesser evidence towards real-time processing, no evidence towards interpretability, limitation of available dataset, and tradeoff-between image processing and AI
Congestion and throughput optimization protocol for providing better quality of service and experience
Get PDFMultimedia traffic in internet of things (IoT) applications is generated for various purposes and encompasses a wide range of multimedia data, including video streams, audio files, images, and sensor data. Network providers employ various strategies to handle multimedia traffic in IoT applications efficiently. But most of these methods have not considered optimizing the real-time streaming protocol (RTSP), real-time transport protocol (RTP), and real-time control protocol (RTCP) to improve the throughput and quality of service (QoS) of the IoT applications. Hence, in this congestion and throughput optimization protocol (CTOP) work, we present a model which optimizes the RTSP, RTP, and RTCP protocol to improve the throughput and QoS. The CTOP model outperforms the big packet protocol model in terms of average throughput, multimedia loss, delay, and energy consumption for both less and high-traffic scenarios. For less-level of traffic and high level of traffic, the CTOP model achieves a better average throughput, and average multimedia delay, reducing the average multimedia loss and average energy consumption in comparison to the existing big-packet-protocol (BBP) model. These results highlight the improved performance and efficiency of the CTOP model compared to the BBP model
Identifying liver cancer cells using cascaded convolutional neural network and gray level co-occurrence matrix techniques
Get PDFLiver cancer has a high mortality rate, especially in South Asia, East Asia, and Sub-Saharan Africa. Efforts to reduce these rates focus on detecting liver cancer at all stages. Early detection allows more treatment options, though symptoms may not always be apparent. The staging process evaluates tumor size, location, lymph node involvement, and spread to other organs. Our research used the CLD staging system, assessing tumor size (C), lymph nodes (L), and distant invasion (D). We applied a deep learning approach with a cascaded convolutional neural network (CNN) and gray level co-occurrence matrix (GLCM)-based texture features to distinguish benign from malignant tumors. The method validated with the cancer imaging archive (TCIA) dataset, demonstrating superior accuracy compared to existing techniques
Application of classification algorithms for smishing detection on mobile devices: literature review
Get PDFSmishing is a form of phishing carried out via mobile devices to steal confidential information from victims. The number of smishing attacks has increased in recent years due to the large number of users acquiring these easy-to-use and functional devices. This literature review objective is to examine the techniques and methods used in smishing attacks using classification algorithms. To do so, we conducted a manual search process and selected 155 articles from Scopus and 29 articles from access to research for development and innovation (ARDI). Of these, 36 articles met the inclusion criteria. In addition, the algorithms most commonly used by the studies were random forest classification techniques, decision trees, and neural networks. These studies analyzed various machine learning models for detecting phishing and smishing messages. The attack simulation scenarios included generating web pages, sending fake links (URLs), and installing malicious applications. The analysis evaluated web pages and SMS messages using a database containing legitimate as well as smishing messages. Based on the results, it is suggested to combine these methods to improve detection performance, making it more robust and promising