Skin lesions have become a critical illness worldwide,and the earlier identification of skin lesions using dermoscopic images can raise the survival rate.Classification of the skin lesion from those dermoscopic images...Skin lesions have become a critical illness worldwide,and the earlier identification of skin lesions using dermoscopic images can raise the survival rate.Classification of the skin lesion from those dermoscopic images will be a tedious task.The accuracy of the classification of skin lesions is improved by the use of deep learning models.Recently,convolutional neural networks(CNN)have been established in this domain,and their techniques are extremely established for feature extraction,leading to enhanced classification.With this motivation,this study focuses on the design of artificial intelligence(AI)based solutions,particularly deep learning(DL)algorithms,to distinguish malignant skin lesions from benign lesions in dermoscopic images.This study presents an automated skin lesion detection and classification technique utilizing optimized stacked sparse autoen-coder(OSSAE)based feature extractor with backpropagation neural network(BPNN),named the OSSAE-BPNN technique.The proposed technique contains a multi-level thresholding based segmentation technique for detecting the affected lesion region.In addition,the OSSAE based feature extractor and BPNN based classifier are employed for skin lesion diagnosis.Moreover,the parameter tuning of the SSAE model is carried out by the use of sea gull optimization(SGO)algo-rithm.To showcase the enhanced outcomes of the OSSAE-BPNN model,a comprehensive experimental analysis is performed on the benchmark dataset.The experimentalfindings demonstrated that the OSSAE-BPNN approach outper-formed other current strategies in terms of several assessment metrics.展开更多
This paper explores and theoretically reports the effects of different magnet structures on the cogging torque and the total harmonic distortion of the output waveforms from a permanent magnet generator.The generator ...This paper explores and theoretically reports the effects of different magnet structures on the cogging torque and the total harmonic distortion of the output waveforms from a permanent magnet generator.The generator is a radial flux machine and four different structures are considered for the magnet arrangement in the rotor component and modelled in the Ansys/Maxwell electromagnetic simulation program.This three-phase machine exhibits different behaviours towards various magnet structures,i.e.rectangular,inclined slotted rectangular,skewed double rectangular and inclined slotted skewed double rectangular,respectively.It has been proven by finite element analysis and Fourier analysis that both the cogging and total harmonic distortion values vary significantly for all models.The cogging torque values change in the range of 89.95 to 436.75 mNm and the lowest cogging torque is measured for the inclined slotted skewed double rectangular magnet geometry,while the conventional rectangular magnet geometry yields the worst value with 436.75 mNm.Furthermore,the total harmonic distortion values varies between 1.63 and 3.55 for different magnetic orientations.While the worst total harmonic distortion value is obtained from the inclined slotted rectangular magnet,the best total harmonic distortion is acquired from the skewed double rectangular magnet.All these results will provide scientists and engineers with important information in order to obtain more efficient machines.展开更多
The development of skills and abilities in laparoscopy is directly related to the use of trainers. The trainer should model the patient with all its natural complexities as closely as possible. In this article we prop...The development of skills and abilities in laparoscopy is directly related to the use of trainers. The trainer should model the patient with all its natural complexities as closely as possible. In this article we propose a system for training the establishment of pneumoperitoneum executing the basic tasks to create the workspace in the trainer, the insertion of primary umbilical trocar and simulate some of the everyday problems in surgery. Materials and Methods. A group of electrical with biomedical engineers and laparoscopic surgeons developed a physical trainer that allows implementing the pneumoperitoneum. The system uses pneumatic electro valves that are controlled with a dedicated microprocessor. The user can program the system to set the parameters of the pneumoperitoneum. Results. This new trainer facilitated the programming of right values of parameters to distend the abdominal cavity according a specific clinical case. The model developed enables the trainee to consolidate his knowledge on establishing the parameters required within clinical practice, as well as the entry techniques. Conclusions. A new physical model for laparoscopic training was designed. The system enables the laparoscopic surgeon to set the parameters for establishing the workspace according to the clinical case. The trainer allows the surgeon to train in the Hasson technique for the introduction of the first trocar, as well as the placement of the rest of surgical instruments with video assistance. We think this new trainer system will help minimize entry-related injuries.展开更多
We demonstrate an indoor 5 m free-space optical wireless coherent communication in mid L-band（1606.7 nm）by employing a tunable self-seeded InAs/InGaAlAs/InP quantum-dash（Qdash） laser as a subcarrier generator for ...We demonstrate an indoor 5 m free-space optical wireless coherent communication in mid L-band（1606.7 nm）by employing a tunable self-seeded InAs/InGaAlAs/InP quantum-dash（Qdash） laser as a subcarrier generator for 128 Gb/s dual-polarization quadrature phase shift keying（DP-QPSK） modulation signal. The bare Qdash laser diode displays ~6 nm self-locked Fabry-Perot mode tunability with ~30 dB side mode suppression ratio（SMSR） and ~10 dBm mode power across the tuning range, thus encompassing ~10 modes with an achievable capacity of 1.28 Tb/s（10 × 128 Gb∕s） and potentially qualifying the source requirements for future access networks.展开更多
基金University Research Committee fund URC-UJ2019,awarded to Kingsley A.Ogudo.
文摘Skin lesions have become a critical illness worldwide,and the earlier identification of skin lesions using dermoscopic images can raise the survival rate.Classification of the skin lesion from those dermoscopic images will be a tedious task.The accuracy of the classification of skin lesions is improved by the use of deep learning models.Recently,convolutional neural networks(CNN)have been established in this domain,and their techniques are extremely established for feature extraction,leading to enhanced classification.With this motivation,this study focuses on the design of artificial intelligence(AI)based solutions,particularly deep learning(DL)algorithms,to distinguish malignant skin lesions from benign lesions in dermoscopic images.This study presents an automated skin lesion detection and classification technique utilizing optimized stacked sparse autoen-coder(OSSAE)based feature extractor with backpropagation neural network(BPNN),named the OSSAE-BPNN technique.The proposed technique contains a multi-level thresholding based segmentation technique for detecting the affected lesion region.In addition,the OSSAE based feature extractor and BPNN based classifier are employed for skin lesion diagnosis.Moreover,the parameter tuning of the SSAE model is carried out by the use of sea gull optimization(SGO)algo-rithm.To showcase the enhanced outcomes of the OSSAE-BPNN model,a comprehensive experimental analysis is performed on the benchmark dataset.The experimentalfindings demonstrated that the OSSAE-BPNN approach outper-formed other current strategies in terms of several assessment metrics.
文摘This paper explores and theoretically reports the effects of different magnet structures on the cogging torque and the total harmonic distortion of the output waveforms from a permanent magnet generator.The generator is a radial flux machine and four different structures are considered for the magnet arrangement in the rotor component and modelled in the Ansys/Maxwell electromagnetic simulation program.This three-phase machine exhibits different behaviours towards various magnet structures,i.e.rectangular,inclined slotted rectangular,skewed double rectangular and inclined slotted skewed double rectangular,respectively.It has been proven by finite element analysis and Fourier analysis that both the cogging and total harmonic distortion values vary significantly for all models.The cogging torque values change in the range of 89.95 to 436.75 mNm and the lowest cogging torque is measured for the inclined slotted skewed double rectangular magnet geometry,while the conventional rectangular magnet geometry yields the worst value with 436.75 mNm.Furthermore,the total harmonic distortion values varies between 1.63 and 3.55 for different magnetic orientations.While the worst total harmonic distortion value is obtained from the inclined slotted rectangular magnet,the best total harmonic distortion is acquired from the skewed double rectangular magnet.All these results will provide scientists and engineers with important information in order to obtain more efficient machines.
文摘The development of skills and abilities in laparoscopy is directly related to the use of trainers. The trainer should model the patient with all its natural complexities as closely as possible. In this article we propose a system for training the establishment of pneumoperitoneum executing the basic tasks to create the workspace in the trainer, the insertion of primary umbilical trocar and simulate some of the everyday problems in surgery. Materials and Methods. A group of electrical with biomedical engineers and laparoscopic surgeons developed a physical trainer that allows implementing the pneumoperitoneum. The system uses pneumatic electro valves that are controlled with a dedicated microprocessor. The user can program the system to set the parameters of the pneumoperitoneum. Results. This new trainer facilitated the programming of right values of parameters to distend the abdominal cavity according a specific clinical case. The model developed enables the trainee to consolidate his knowledge on establishing the parameters required within clinical practice, as well as the entry techniques. Conclusions. A new physical model for laparoscopic training was designed. The system enables the laparoscopic surgeon to set the parameters for establishing the workspace according to the clinical case. The trainer allows the surgeon to train in the Hasson technique for the introduction of the first trocar, as well as the placement of the rest of surgical instruments with video assistance. We think this new trainer system will help minimize entry-related injuries.
基金supported in part by King Fahd University of Petroleum and Minerals through the KAUST004 grantin part by King Saud University,Deanship of Scientific Research through the RG-1438-092 grantin part by KACST-TIC in SSL
文摘We demonstrate an indoor 5 m free-space optical wireless coherent communication in mid L-band（1606.7 nm）by employing a tunable self-seeded InAs/InGaAlAs/InP quantum-dash（Qdash） laser as a subcarrier generator for 128 Gb/s dual-polarization quadrature phase shift keying（DP-QPSK） modulation signal. The bare Qdash laser diode displays ~6 nm self-locked Fabry-Perot mode tunability with ~30 dB side mode suppression ratio（SMSR） and ~10 dBm mode power across the tuning range, thus encompassing ~10 modes with an achievable capacity of 1.28 Tb/s（10 × 128 Gb∕s） and potentially qualifying the source requirements for future access networks.
