Cataract is a common eye condition that causes clouding of the eye's natural lens, resulting in blurry vision and it is very common in older ages people. However, it can also occur in younger aged people due to va...
Cataract is a common eye condition that causes clouding of the eye's natural lens, resulting in blurry vision and it is very common in older ages people. However, it can also occur in younger aged people due to various genetical effects, diabetes, smoking, and prolonged exposure to sunlight. Cataracts can be treated through surgery to remove the clouded lens and replaced by an artificial one, which can significantly improve the vision. This problem can be reduced through early detection, regular eye examinations etc. In this research, a Contrast Limited Histogram Equalization (CLAHE) of retinal fundus images is applied for a better presentation of the above cataract effects. These improved images are fed to a machine learning-based model for effective detection. Finally, the ensembling of the proposed machine learning-based classifiers is performed for the accurate detection of cataracts. The proposed model was tested experimentally on a real dataset and achieves excellent performance with accuracy, precision, and recall scores of 99.67%, 100%, and 99.25%, respectively which outperform the baseline methods. The robustness of the proposed ensemble model is evaluated through 5-fold cross-validation and achieved an average accuracy of 99.6%. The implementation code can be accessed from the GitHub repository: https://***/nahid-tech/cataract-detection.
The automotive industry is one of the lucrative markets in the world. With the advancement of the human lifestyle, everybody needs a car for their daily business. Before buying a used vehicle, the history of the vehic...
详细信息
To support massive random access trials of devices with diverse QoS is a major challenge for massive machine-type communications. Space-air-ground integrated network(SAGIN) can be a promising solution for the congesti...
详细信息
Two approaches are available for WSOD: MIL and CAM. MIL-based methods are capable of addressing multiple targets and multiple class problems. However, these methods require the input of region proposals. In contrast, ...
详细信息
ISBN:
(数字)9798331521165
ISBN:
(纸本)9798331521172
Two approaches are available for WSOD: MIL and CAM. MIL-based methods are capable of addressing multiple targets and multiple class problems. However, these methods require the input of region proposals. In contrast, CAM-based methods are straightforward and more efficient, yet they are constrained by limited localization accuracy and are likely to be applicable only to single target classes. This study proposes a CAM-based WSOD method that is capable of addressing multi-object, multi-class tasks with high efficiency, which could prove beneficial for the development of specific consumer electronic applications, such as smart cameras and smart home devices. The proposed method was evaluated on two public datasets, demonstrating that it is significantly more efficient than the baseline method.
Numerous technologies are constantly being created due to the rapid rise in the standardization and automation of operational and management systems. It simplifies procedures and allows microelectronics technology to ...
详细信息
ISBN:
(纸本)9798350333718
Numerous technologies are constantly being created due to the rapid rise in the standardization and automation of operational and management systems. It simplifies procedures and allows microelectronics technology to advance more often. It was managed by an Android app and controlled by sensor networks and parking systems. The wireless sensor network manages parking spot management, parking lot reservations, vehicle navigation, and other complex circumstances. This study suggests a wireless sensor network-based and android app-based intelligent parking system. Sensors installed beneath enable the cutting-edge parking system to function. The research suggests an intelligent parking system that uses wireless sensor networks and IR, magnetic, and light sensors. The ground-level sensors used by the advanced parking system function. The base station receives the node/slot information, and the base station delivers data to FTP. At the user's request, FTP transmits details about nodes and spaces to mobile devices. The idea came from using an IoT application to control the automobile parking system, which is crucial to our daily lives. For this purpose, a mobile application for Android called Smart Parker was developed. It provides information about a parking lot, such as available or reserved spaces. Sensors at the base station will send information about parking spaces to the FTP server. The user of the innovative payment system is required to pay to park the car. Cash is first collected using cash counters, but maintaining them is challenging. Later, different methods are employed to collect the payment. The payment is made by an Automated Vehicle Identification (AVI) tag using RFID technologies. Smart, debit, and credit cards are contact methods, whereas RFID technology and mobile devices are contactless alternatives. The smart parking system on FPGA (Finite State Machine Modeling) works on two main modules, i.e., the identification module and slot checking module. The
This paper presents a novel autonomous navigation system for grapevine cultivation robots operating in overhead trellis vineyards, a challenging environment characterized by irregular grape cluster distribution and co...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
This paper presents a novel autonomous navigation system for grapevine cultivation robots operating in overhead trellis vineyards, a challenging environment characterized by irregular grape cluster distribution and complex 3D structures. The system integrates two complementary navigation approaches: high-precision positioning under target grape bunches using YOLOv8-based object detection of QR codes, and large-scale vineyard navigation using global navigation satellite system (GNSS). Each QR code uniquely identifies a grape bunch and provides access to its associated cultivation data. Experimental evaluations in a simulated vineyard environment demonstrated an 83.3% success rate for object detection-based positioning beneath grape bunches and 90% accuracy for GNSS-based navigation within a 1.0 m radius of the target locations. These results validate the system's effectiveness in automating navigation tasks within overhead trellis vineyards, offering a promising solution to address labor shortages and improve the efficiency of grape cultivation practices.
Water distribution systems (WDS) are empowered by modern technologies to treat and distribute clean water more effectively. They improve automation, real-time monitoring and quality of water. Nonetheless, they may be ...
详细信息
ISBN:
(数字)9798331536381
ISBN:
(纸本)9798331536398
Water distribution systems (WDS) are empowered by modern technologies to treat and distribute clean water more effectively. They improve automation, real-time monitoring and quality of water. Nonetheless, they may be susceptible to various cyber-attacks. The attackers can alter the system's vital information and elements, resulting in disruption of the normal operation of the system. They can change the water pump's speed, ON/OFF status of valves or contaminate the water by altering water quality parameters etc. To detect and mitigate cyber-physical attacks (CPA) and improve WDS security, empirical Artificial Intelligence (AI)-based techniques must be developed and put into practice. Many methods were proposed to detect CPAs, but limitations such as scalability, false alarm rate, recognizing the location of the compromised components, time to detect the attacks, and overall robustness against data poisoning, etc. still need improvement. Deep learning models can improve system security and resilience and deliver early alerts of threats or malfunctions by continuously analyzing streaming data from sensors and control systems. This paper summarizes the design guidelines for a hybrid deep learning model and performance improvements and the scope of the supervised and unsupervised models in WDSs.
In the automotive industry, accurate and efficient vehicle damage detection is crucial for reducing the cost of claims and improving assessment procedures. This paper presents an automated method for vehicle damage de...
详细信息
ISBN:
(数字)9798350369175
ISBN:
(纸本)9798350369182
In the automotive industry, accurate and efficient vehicle damage detection is crucial for reducing the cost of claims and improving assessment procedures. This paper presents an automated method for vehicle damage detection using deep learning based You Only Look Once models, specifically YOLOv3, YOLOv5, and YOLOv8, in conjunction with two optimizers, AdamW and SGD. The COCOtoYOLO dataset contains pictures with six damage kinds. Gaussian Blur, Median Blur, Grayscale conversion, and Contrast Limited Adaptive Histogram Equalization (CLAHE) improved picture quality and feature visibility. The results reveal that YOLOv8, optimized with SGD over 200 epochs, achieved the highest mean Average Precision (mAP-50) of $72 \%$, surpassing other configurations. This study demonstrates the effectiveness of YOLOv8 and SGD in vehicle damage detection. The highest F1-score of ${9 3 \%}$ for glass shutter class claims the model’s robustness for different types of car damages.
This paper proposes a novel method for automatically inferring message flow specifications from the communication traces of a system-on-chip (SoC) design that captures messages exchanged among the components during a ...
详细信息
Focusing on cluster-based portable wireless sensor networks (CPWSN) may be a good idea for researchers. The sole reason CPWSN has been used in practical applications is due to the accessibility of low-cost Sensor node...
详细信息
暂无评论