Yeong Min Jang

Syed Samiul Alam, Samiul Based Shuvo, Shams Nafisa Ali et al.

Ocular Toxoplasmosis (OT), is a common eye infection caused by T. gondii that can cause vision problems. Diagnosis is typically done through a clinical examination and imaging, but these methods can be complicated and costly, requiring trained personnel. To address this issue, we have created a benchmark study that evaluates the effectiveness of existing pre-trained networks using transfer learning techniques to detect OT from fundus images. Furthermore, we have also analysed the performance of transfer-learning based segmentation networks to segment lesions in the images. This research seeks to provide a guide for future researchers looking to utilise DL techniques and develop a cheap, automated, easy-to-use, and accurate diagnostic method. We have performed in-depth analysis of different feature extraction techniques in order to find the most optimal one for OT classification and segmentation of lesions. For classification tasks, we have evaluated pre-trained models such as VGG16, MobileNetV2, InceptionV3, ResNet50, and DenseNet121 models. Among them, MobileNetV2 outperformed all other models in terms of Accuracy (Acc), Recall, and F1 Score outperforming the second-best model, InceptionV3 by 0.7% higher Acc. However, DenseNet121 achieved the best result in terms of Precision, which was 0.1% higher than MobileNetv2. For the segmentation task, this work has exploited U-Net architecture. In order to utilize transfer learning the encoder block of the traditional U-Net was replaced by MobileNetV2, InceptionV3, ResNet34, and VGG16 to evaluate different architectures moreover two different two different loss functions (Dice loss and Jaccard loss) were exploited in order to find the most optimal one. The MobileNetV2/U-Net outperformed ResNet34 by 0.5% and 2.1% in terms of Acc and Dice Score, respectively when Jaccard loss function is employed during the training.

Mostafa Zaman Chowdhury, Mohammad Arif Hossain, Shakil Ahmed et al.

In the modern era, cellular communication consumers are exponentially increasing as they find the system more user-friendly. Due to enormous users and their numerous demands, it has become a mandate to make the best use of the limited radio resources that assures the highest standard of Quality of Service (QoS). To reach the guaranteed level of QoS for the maximum number of users, maximum utilization of bandwidth is not only the key issue to be considered, rather some other factors like interference, call blocking probability etc. are also needed to keep under deliberation. The lower performances of these factors may retrograde the overall cellular networks performances. Keeping these difficulties under consideration, we propose an effective dynamic channel borrowing model that safeguards better QoS, other factors as well. The proposed scheme reduces the excessive overall call blocking probability and does interference mitigation without sacrificing bandwidth utilization. The proposed scheme is modeled in such a way that the cells are bifurcated after the channel borrowing process if the borrowed channels have the same type of frequency band (i.e. reused frequency). We also propose that the unoccupied interfering channels of adjacent cells can also be inactivated, instead of cell bifurcation for interference mitigation. The simulation endings show satisfactory performances in terms of overall call blocking probability and bandwidth utilization that are compared to the conventional scheme without channel borrowing. Furthermore, signal to interference plus noise ratio (SINR) level, capacity, and outage probability are compared to the conventional scheme without interference mitigation after channel borrowing that may attract the considerable concentration to the operators.

Mostafa Zaman Chowdhury, Yeong Min Jang

Video broadcast/multicast over wireless access networks is an attractive research issue in the field of wireless communication. With the rapid improvement of various wireless network technologies, it is now possible to provide high quality video transmission over wireless networks. The high quality video streams need higher bandwidth. Hence, during the video transmission through wireless networks, it is very important to make the best utilization of the limited bandwidth. Therefore, when many broadcasting video sessions are active, the bandwidth per video session can be allocated based on popularity of the video sessions (programs). Instead of allocating equal bandwidth to each of them, our proposed scheme allocates bandwidth per broadcasting video session based on popularity of the video program. When the system bandwidth is not sufficient to allocate the demanded bandwidth for all the active video sessions, our proposed scheme efficiently allocates the total system bandwidth among all the scalable active video sessions in such a way that higher bandwidth is allocated to higher popularity one. Using the mathematical and simulation analyses, we show that the proposed scheme maximizes the average user satisfaction level and achieves the best utilization of bandwidth. The simulation results indicate that a large number of subscribers can receive a significantly improved quality of video. To improve the video quality for large number of subscribers, the only tradeoff is that a very few subscribers receive slightly degraded video quality.

Mostafa Zaman Chowdhury, Yeong Min Jang, Zygmunt J. Haas

Provisioning of Quality of Service (QoS) is a key issue in any multi-media system. However, in wireless systems, supporting QoS requirements of different traffic types is more challenging due to the need to minimize two performance metrics - the probability of dropping a handover call and the probability of blocking a new call. Since QoS requirements are not as stringent for non-real-time traffic types, as opposed to real-time traffic, more calls can be accommodated by releasing some bandwidth from the already admitted non-real-time traffic calls. If we require that such a released bandwidth to accept a handover call ought to be larger than the bandwidth to accept a new call, then the resulting probability of dropping a handover call will be smaller than the probability of blocking a new call. In this paper we propose an efficient Call Admission Control (CAC) that relies on adaptive multi-level bandwidth-allocation scheme for non-real-time calls. The scheme allows reduction of the call dropping probability along with increase of the bandwidth utilization. The numerical results show that the proposed scheme is capable of attaining negligible handover call dropping probability without sacrificing bandwidth utilization.

Mostafa Zaman Chowdhury, Tuan Nguyen, Young-Il Kim et al.

Good quality video services always require higher bandwidth. Hence, to provide the video services e.g., multicast/broadcast services (MBS) and unicast services along with the existing voice, internet, and other background traffic services over the wireless cellular networks, it is required to efficiently manage the wireless resources in order to reduce the overall forced call termination probability, to maximize the overall service quality, and to maximize the revenue. Fixed bandwidth allocation for the MBS sessions either reduces the quality of the MBS videos and bandwidth utilization or increases the overall forced call termination probability and of course the handover call dropping probability as well. Scalable Video Coding (SVC) technique allows the variable bit rate allocation for the video services. In this paper, we propose a bandwidth allocation scheme that efficiently allocates bandwidth among the MBS sessions and the non-MBS traffic calls (e.g., voice, unicast, internet, and other background traffic). The proposed scheme reduces the bandwidth allocation for the MBS sessions during the congested traffic condition only to accommodate more calls in the system. Instead of allocating fixed bandwidths for the BMS sessions and the non-MBS traffic, our scheme allocates variable bandwidths for them. However, the minimum quality of the videos is guaranteed by allocating minimum bandwidth for them. Using the mathematical and numerical analyses, we show that the proposed scheme maximizes the bandwidth utilization and significantly reduces the overall forced call termination probability as well as the handover call dropping probability.

Mostafa Zaman Chowdhury, Yeong Min Jang

Due to the fact that quality of service requirements are not very strict for all traffic types, more calls of higher priority can be accommodated by reducing some bandwidth allocation for the bandwidth adaptive calls. The bandwidth adaptation to accept a higher priority call is more than that of a lower priority call. Therefore, the multi-level bandwidth adaptation technique improves the overall forced call termination probability as well as provides priority of the traffic classes in terms of call blocking probability without reducing the bandwidth utilization. We propose a novel bandwidth adaptation model that releases multi-level of bandwidth from the existing multimedia traffic calls. The amount of released bandwidth is decided based on the priority of the requesting traffic calls and the number of existing bandwidth adaptive calls. This prioritization of traffic classes does not reduce the bandwidth utilization. Moreover, our scheme reduces the overall forced call termination probability significantly. The proposed scheme is modeled using the Markov Chain. The numerical results show that the proposed scheme is able to provide negligible handover call dropping probability as well as significantly reduced new call blocking probability of higher priority calls without increasing the overall forced call termination probability.