Breast Arterial Calcification(BAC)is a mammographic decision dissimilar to cancer and commonly observed in elderly women.Thus identifying BAC could provide an expense,and be inaccurate.Recently Deep Learning(DL)method...Breast Arterial Calcification(BAC)is a mammographic decision dissimilar to cancer and commonly observed in elderly women.Thus identifying BAC could provide an expense,and be inaccurate.Recently Deep Learning(DL)methods have been introduced for automatic BAC detection and quantification with increased accuracy.Previously,classification with deep learning had reached higher efficiency,but designing the structure of DL proved to be an extremely challenging task due to overfitting models.It also is not able to capture the patterns and irregularities presented in the images.To solve the overfitting problem,an optimal feature set has been formed by Enhanced Wolf Pack Algorithm(EWPA),and their irregularities are identified by Dense-kUNet segmentation.In this paper,Dense-kUNet for segmentation and optimal feature has been introduced for classification(severe,mild,light)that integrates DenseUNet and kU-Net.Longer bound links exist among adjacent modules,allowing relatively rough data to be sent to the following component and assisting the system in finding higher qualities.The major contribution of the work is to design the best features selected by Enhanced Wolf Pack Algorithm(EWPA),and Modified Support Vector Machine(MSVM)based learning for classification.k-Dense-UNet is introduced which combines the procedure of Dense-UNet and kU-Net for image segmentation.Longer bound associations occur among nearby sections,allowing relatively granular data to be sent to the next subsystem and benefiting the system in recognizing smaller characteristics.The proposed techniques and the performance are tested using several types of analysis techniques 826 filled digitized mammography.The proposed method achieved the highest precision,recall,F-measure,and accuracy of 84.4333%,84.5333%,84.4833%,and 86.8667%when compared to other methods on the Digital Database for Screening Mammography(DDSM).展开更多
In order to solve the problem that the global navigation satellite system（GNSS） receivers can hardly detect the GNSS spoofing when they are deceived by a spoofer,a model-based approach for the identification of the ...In order to solve the problem that the global navigation satellite system（GNSS） receivers can hardly detect the GNSS spoofing when they are deceived by a spoofer,a model-based approach for the identification of the GNSS spoofing is proposed.First,a Hammerstein model is applied to model the spoofer/GNSS transmitter and the wireless channel.Then,a novel method based on the uncultivated wolf pack algorithm（UWPA） is proposed to estimate the model parameters.Taking the estimated model parameters as a feature vector,the identification of the spoofing is realized by comparing the Euclidean distance between the feature vectors.Simulations verify the effectiveness and the robustness of the proposed method.The results show that,compared with the other identification algorithms,such as least square（LS）,the iterative method and the bat-inspired algorithm（BA）,although the UWPA has a little more time-eomplexity than the LS and the BA algorithm,it has better estimation precision of the model parameters and higher identification rate of the GNSS spoofing,even for relative low signal-to-noise ratios.展开更多
Due to the shortcomings such as the premature convergence and the bad local optimal searching capability in traditional intelligence methods for pattern synthesis,a new type of wolf pack algorithm named Levy⁃Cultural ...Due to the shortcomings such as the premature convergence and the bad local optimal searching capability in traditional intelligence methods for pattern synthesis,a new type of wolf pack algorithm named Levy⁃Cultural Wolf Pack Algorithm(LCWPA)was designed on the basis of the Cultural Wolf Pack Algorithm(CWPA),which obeys the selective Levy flight.Because of the good overall management ability provided by the cultural algorithm in optimization process and the characteristics of excellent population diversity brought by Levy flight,the search efficiency of the new algorithm was greatly improved.When the algorithm was applied in the pattern synthesis of array antenna,the simulation results showed its high performance with multi⁃null and low side⁃lobe restrictions.In addition,the algorithm was superior to the Quantum Particle Swarm Optimization(QPSO),Particle Swarm Optimization(PSO),and Genetic Algorithm(GA)in optimization accuracy and operation speed,and is of very good generalization.展开更多
Binary wolf pack algorithm (BWPA) is a kind of intelligence algorithm which can solve combination optimization problems in discrete spaces.Based on BWPA, an improved binary wolf pack algorithm (AIBWPA) can be proposed...Binary wolf pack algorithm (BWPA) is a kind of intelligence algorithm which can solve combination optimization problems in discrete spaces.Based on BWPA, an improved binary wolf pack algorithm (AIBWPA) can be proposed by adopting adaptive step length and improved update strategy of wolf pack. AIBWPA is applied to 10 classic 0-1 knapsack problems and compared with BWPA, DPSO, which proves that AIBWPA has higher optimization accuracy and better computational robustness. AIBWPA makes the parameters simple, protects the population diversity and enhances the global convergence.展开更多
针对多目标狼群算法存在的搜索不充分、收敛性不足和多样性欠缺的问题,以及缺少对约束进行处理的问题,提出环境选择的双种群约束多目标狼群算法(multi-objective wolf pack algorithm for dual population constraints with environment...针对多目标狼群算法存在的搜索不充分、收敛性不足和多样性欠缺的问题,以及缺少对约束进行处理的问题,提出环境选择的双种群约束多目标狼群算法(multi-objective wolf pack algorithm for dual population constraints with environment selection,DCMOWPA-ES)。引入双种群约束处理方法给种群设置不同的搜索偏好,主种群运用可行性准则优先保留可行解,次种群通过ε约束探索不可行区域并将搜索结果传递给主种群,让算法能较好应对复杂的不可行区域,保障算法的可行性;提出维度选择的随机游走策略,使人工狼可自主选择游走方向,提高种群的全局搜索能力;设计精英学习的步长调整机制,人工狼通过向头狼学习的方式提升种群的局部搜索能力,确保算法的收敛性;采用环境选择的狼群更新策略,根据人工狼被支配的情况和所处位置的密度信息对其赋值,选择被支配数少且密度信息小的人工狼作为优秀个体,改善算法的多样性。为验证算法性能,将DCMOWPA-ES与六种新兴约束多目标优化算法在两组约束多目标测试集和汽车侧面碰撞设计问题上进行对比实验。实验结果表明,DCMOWPA-ES算法具备较好的可行性、收敛性和多样性。展开更多
文摘Breast Arterial Calcification(BAC)is a mammographic decision dissimilar to cancer and commonly observed in elderly women.Thus identifying BAC could provide an expense,and be inaccurate.Recently Deep Learning(DL)methods have been introduced for automatic BAC detection and quantification with increased accuracy.Previously,classification with deep learning had reached higher efficiency,but designing the structure of DL proved to be an extremely challenging task due to overfitting models.It also is not able to capture the patterns and irregularities presented in the images.To solve the overfitting problem,an optimal feature set has been formed by Enhanced Wolf Pack Algorithm(EWPA),and their irregularities are identified by Dense-kUNet segmentation.In this paper,Dense-kUNet for segmentation and optimal feature has been introduced for classification(severe,mild,light)that integrates DenseUNet and kU-Net.Longer bound links exist among adjacent modules,allowing relatively rough data to be sent to the following component and assisting the system in finding higher qualities.The major contribution of the work is to design the best features selected by Enhanced Wolf Pack Algorithm(EWPA),and Modified Support Vector Machine(MSVM)based learning for classification.k-Dense-UNet is introduced which combines the procedure of Dense-UNet and kU-Net for image segmentation.Longer bound associations occur among nearby sections,allowing relatively granular data to be sent to the next subsystem and benefiting the system in recognizing smaller characteristics.The proposed techniques and the performance are tested using several types of analysis techniques 826 filled digitized mammography.The proposed method achieved the highest precision,recall,F-measure,and accuracy of 84.4333%,84.5333%,84.4833%,and 86.8667%when compared to other methods on the Digital Database for Screening Mammography(DDSM).
基金The National Natural Science Foundation of China(No.61271214,61471152)the Postdoctoral Science Foundation of Jiangsu Province(No.1402023C)the Natural Science Foundation of Zhejiang Province(No.LZ14F010003)
文摘In order to solve the problem that the global navigation satellite system（GNSS） receivers can hardly detect the GNSS spoofing when they are deceived by a spoofer,a model-based approach for the identification of the GNSS spoofing is proposed.First,a Hammerstein model is applied to model the spoofer/GNSS transmitter and the wireless channel.Then,a novel method based on the uncultivated wolf pack algorithm（UWPA） is proposed to estimate the model parameters.Taking the estimated model parameters as a feature vector,the identification of the spoofing is realized by comparing the Euclidean distance between the feature vectors.Simulations verify the effectiveness and the robustness of the proposed method.The results show that,compared with the other identification algorithms,such as least square（LS）,the iterative method and the bat-inspired algorithm（BA）,although the UWPA has a little more time-eomplexity than the LS and the BA algorithm,it has better estimation precision of the model parameters and higher identification rate of the GNSS spoofing,even for relative low signal-to-noise ratios.
基金the Hebei Province Natural Science Foundation(Grant No.E2016202341)the Research Project of Science and Technology for Hebei Province Higher Education Institutions(Grant No.BJ2014013)。
文摘Due to the shortcomings such as the premature convergence and the bad local optimal searching capability in traditional intelligence methods for pattern synthesis,a new type of wolf pack algorithm named Levy⁃Cultural Wolf Pack Algorithm(LCWPA)was designed on the basis of the Cultural Wolf Pack Algorithm(CWPA),which obeys the selective Levy flight.Because of the good overall management ability provided by the cultural algorithm in optimization process and the characteristics of excellent population diversity brought by Levy flight,the search efficiency of the new algorithm was greatly improved.When the algorithm was applied in the pattern synthesis of array antenna,the simulation results showed its high performance with multi⁃null and low side⁃lobe restrictions.In addition,the algorithm was superior to the Quantum Particle Swarm Optimization(QPSO),Particle Swarm Optimization(PSO),and Genetic Algorithm(GA)in optimization accuracy and operation speed,and is of very good generalization.
文摘Binary wolf pack algorithm (BWPA) is a kind of intelligence algorithm which can solve combination optimization problems in discrete spaces.Based on BWPA, an improved binary wolf pack algorithm (AIBWPA) can be proposed by adopting adaptive step length and improved update strategy of wolf pack. AIBWPA is applied to 10 classic 0-1 knapsack problems and compared with BWPA, DPSO, which proves that AIBWPA has higher optimization accuracy and better computational robustness. AIBWPA makes the parameters simple, protects the population diversity and enhances the global convergence.
文摘针对多目标狼群算法存在的搜索不充分、收敛性不足和多样性欠缺的问题,以及缺少对约束进行处理的问题,提出环境选择的双种群约束多目标狼群算法(multi-objective wolf pack algorithm for dual population constraints with environment selection,DCMOWPA-ES)。引入双种群约束处理方法给种群设置不同的搜索偏好,主种群运用可行性准则优先保留可行解,次种群通过ε约束探索不可行区域并将搜索结果传递给主种群,让算法能较好应对复杂的不可行区域,保障算法的可行性;提出维度选择的随机游走策略,使人工狼可自主选择游走方向,提高种群的全局搜索能力;设计精英学习的步长调整机制,人工狼通过向头狼学习的方式提升种群的局部搜索能力,确保算法的收敛性;采用环境选择的狼群更新策略,根据人工狼被支配的情况和所处位置的密度信息对其赋值,选择被支配数少且密度信息小的人工狼作为优秀个体,改善算法的多样性。为验证算法性能,将DCMOWPA-ES与六种新兴约束多目标优化算法在两组约束多目标测试集和汽车侧面碰撞设计问题上进行对比实验。实验结果表明,DCMOWPA-ES算法具备较好的可行性、收敛性和多样性。
