Developing a Machine Vision System Equipped with UV Light to Predict Fish Freshness Based on Fish-Surface Color

This study assessed the feasibility of developing a machine vision system equipped with ultraviolet (UV) light, using changes in fish-surface color to predict aerobic plate count (APC, a standard freshness indicator) during storage. The APC values were tested and images of the fish surface were taken when fish were stored at room temperature. Then, images’ color-space conversion among RGB, HSV, and L*a*b* color spaces was carried out and analyzed. The results revealed that a* and b* values from the UV-light image decreased linearly during storage. A further regression analysis of these two parameters with APC value demonstrated a good exponential relationship between the a* value and the APC value (R2 = 0.97), followed by the b* (R2 = 0.85). Therefore, our results suggest that the change in color of the fish surface under UV light can be used to assess fish freshness during storage.

Machine Vision Based Fish Cutting Point Prediction for Target Weight

Food processing companies pursue the distribution of ingredientsthat were packaged according to a certain weight. Particularly, foods like fishare highly demanded and supplied. However, despite the high quantity offish to be supplied, most seafood processing companies have yet to installautomation equipment. Such absence of automation equipment for seafoodprocessing incurs a considerable cost regarding labor force, economy, andtime. Moreover, workers responsible for fish processing are exposed to risksbecause fish processing tasks require the use of dangerous tools, such aspower saws or knives. To solve these problems observed in the fish processingfield, this study proposed a fish cutting point prediction method based onAI machine vision and target weight. The proposed method performs threedimensional(3D) modeling of a fish’s form based on image processing techniquesand partitioned random sample consensus (RANSAC) and extracts 3Dfeature information. Then, it generates a neural network model for predictingfish cutting points according to the target weight by performing machinelearning of the extracted 3D feature information and measured weight information.This study allows for the direct cutting of fish based on cutting pointspredicted by the proposed method. Subsequently, we compared the measuredweight of the cut pieces with the target weight. The comparison result verifiedthat the proposed method showed a mean error rate of approximately 3%.

Identification of navigation characteristics of single otter trawl vessel using four machine learning models

Fishing logbook records the fishing behaviors and other information of fishing vessels.However,the accuracy of the recorded information is often difficult to guarantee due to the misreport and concealment.The fishing vessel monitoring system(VMS)can monitor and record the navigation information of fishing vessels in real time,and it may be used to improve the accuracy of identifying the state of fishing vessels.If the VMS data and fishing logbook are combined to establish their relationships,then the navigation characteristics and fishing behavior of fishing vessels can be more accurately identified.Therefore,first,a method for determining the state of VMS data points using fishing log data was proposed.Secondly,the relationship between VMS data and the different states of fishing vessels was further explored.Thirdly,the state of the fishing vessel was predicted using VMS data by building machine learning models.The speed,heading,longitude,latitude,and time as features from the VMS data were extracted by matching the VMS and logbook data of three single otter trawl vessels from September 2012 to January 2013,and four machine learning models were established,i.e.,Random Forest(RF),Adaptive Boosting(AdaBoost),K-Nearest Neighbor(KNN),and Gradient Boosting Decision Tree(GBDT)to predict the behavior of fishing vessels.The prediction performances of the models were evaluated by using normalized confusion matrix and receiver operator characteristic curve.Results show that the importance rankings of spatial(longitude and latitude)and time features were higher than those of speed and heading.The prediction performances of the RF and AdaBoost models were higher than those of the KNN and GBDT models.RF model showed the highest prediction performance for fishing state.Meanwhile,AdaBoost model exhibited the highest prediction performance for non-fishing state.This study offered a technical basis for judging the navigation characteristics of fishing vessels,which improved the algorithm for judging the behavior of fishing vessels based on VMS data,enhanced the prediction accuracy,and upgraded the fishery management being more scientific and efficient.

Identification of Fishing State of Purse Seine Fishing Vessels Based on Multi-Indices

With the popularization of vessel satellite AIS(automatic identification system)equipment and the continuous improve-ment of the AIS data’s coverage,continuity and effectiveness,AIS has become an important data source to study the navigation char-acteristics of vessel groups.This study established an identification model to extract the fishing state and intensity information of fishing vessels,based on the AIS data of purse seine fishing vessels,combined with the variables of vessel position,speed and course.Expert experience,spatial statistics and data mining analysis methods were applied to establish the model,and the Western and Cen-tral Pacific Ocean areas were studied.The results showed that the overall accuracy of identification of the fishing state using Support Vector Machine method is higher,and the method has a good modeling effect.The spatial distribution characteristics of the vessels’fishing intensity based on AIS data showed a significant cluster distribution pattern.The obtained high-intensity fishing area can be used as a prediction of purse seine fishing grounds in the Western and Central Pacific areas.Through the processing and research of AIS data,this study provided important scientific support for the identification of fishing state of purse seine fishing vessels.The spatial fishing intensity of fishing vessels based on AIS data can also be used for the analysis of fishery resources and fishing grounds,and further serve the sustainable development of marine fisheries.

基于拉普拉斯算法和梯度边缘特征的鱼货去鳞机表面磨损检测方法

为了确保鱼货去鳞机的正常使用,需要检测其表面磨损情况。提出基于拉普拉斯算法和梯度边缘特征的鱼货去鳞机表面磨损检测方法。首先,采用布谷鸟搜索算法优化二维高斯函数,结合拉普拉斯算法与优化后的二维高斯函数对鱼货去鳞机表面图像展开卷积处理,以此增强磨损区域边缘细节信息,实现磨损区域边缘检测;其次,对磨损区域展开Gamma校正,在此基础上提取磨损区域的HOG特征与LSS特征,结合上述特征构成梯度边缘特征;最后,基于S-SVM建立鱼货去鳞机表面磨损检测模型,将梯度边缘特征输入模型内,实现鱼货去鳞机表面磨损检测。实验结果表明,所提方法可准确确定磨损边缘,高精度地完成磨损特征提取与检测。

机器学习算法在渔船数据挖掘技术中的应用

本文基于PCA_Word2Vec的渔船数据挖掘技术展开研究,构建了PCA_Word2Vec渔船数据挖掘模型并对渔船轨迹数据进行挖掘,在此基础之上通过将LightGBM模型与其他经典模型分类效果进行比较,以及对PCA_Word2Vec数据挖掘模型挖掘前后的数据展开对比,验证了渔船数据挖掘技术的有效性和实用性。

深度学习与机器视觉在鱼类加工与品质监测中的研究进展

在全球渔业产量不断增加和对鱼类品质保障需求提升的背景下,传统的鱼类加工和品质监测方法大多依赖人工操作,这不仅效率低下而且结果的一致性和准确性难以保证,逐渐无法满足现代需求。机器视觉和深度学习技术的结合,提供了一种高效、自动化的方法来提升鱼类加工与品质监测的准确性和效率。该综述概述了机器视觉系统和深度学习在鱼类加工中的应用,包括分类分拣、切割定位、重量估算等方面,并详细介绍了利用高光谱成像、近红外成像、比色传感器和传统成像等方法在品质监测中的最新研究进展,突出了深度学习在提升这些技术识别、分类精度和处理复杂图像数据能力方面的潜力。尽管机器学习技术在单一的加工问题中取得了成功,但面对复杂数据和环境变化时的适应性仍有限,这促使深度学习的相关研究日益受到重视。该文发现当前针对鱼类加工领域的深度学习研究还相对较少,且缺乏能够综合解决鱼类加工和品质监测多重任务的系统性研究。

基于AFSA-SVM动态光谱的血液识别研究

血液是一种受管制的特殊遗传生物资源。针对传统血液光谱检测中易氧化变质的问题,采用基于仿生血管的动态共聚焦拉曼荧光光谱,开展了猪、马、鸽、鸡、鸭、鹅等六种家禽家畜的血液物种鉴别研究。原始光谱的预处理过程包括去基线、平滑和归一化等。采用线性判别分析对光谱数据进行降维处理,继而用支持向量机建立识别模型,选用高斯核函数,通过人工鱼群算法优化支持向量机的参数C和γ,使其分类准确率最高,最优的C和γ分别为0.2和0.134。人工鱼群-支持向量机模型识别准确率达到97.2%,基于仿生血管的动态共聚焦拉曼荧光光谱可以满足血液安全高效的检测要求,用人工鱼群算法优化支持向量机参数的算法模型表现出较好的分类效果。

微磨料气射流加工结构化拓扑鱼鳞表面的实验研究

为了在脆性难加工材料上制备结构化鱼鳞表面,首先提取了鱼鳞表面的拓扑特征,建立了鱼鳞单元的表面模型,并基于鱼鳞模型进行搭接,得到结构化鱼鳞表面;然后根据微磨料气射流加工原理,分析了气射流加工拓扑鱼鳞实验的可行性与影响结构化鱼鳞表面形貌的重要工艺参数;最后采用单因素实验法对重要加工参数进行实验分析,得到了较好的拓扑鱼鳞表面单元,并以此进行排布得到结构化表面。研究结果表明,微磨料气射流加工结构化拓扑鱼鳞表面较为合理的工艺参数组合是加工时间为10 s、气射流加工压力为0.5 MPa、靶距离为10 mm以及射流角度为30°,在此工艺条件下,鱼鳞表面的形态和尺寸可能会受到一定的影响,但鱼鳞表面的拓扑属性保持不变。

基于电子鼻和机器视觉的鱼肉新鲜度检测研究

为了提升鱼肉新鲜度检测的准确率,该研究采用了电子鼻、机器视觉和多数据融合技术快速地检测冷藏鱼肉的新鲜度。挥发性盐基氮含量与新鲜度密切相关且易于测量,因此被选定作为鱼肉新鲜度的指标;用机器视觉和电子鼻获取样品的图像和气味信息。应用反向传播神经网络、卷积神经网络(convolutional neural network,CNN)和卷积神经网络-门控循环单元-注意力(CNN-GRU-Attention)3种模型对鱼肉新鲜度进行3分类和7分类预测。结果表明,3分类和7分类实验中,3种模型利用电子鼻数据进行分类的效果均优于机器视觉方法。此外,对原始数据进行融合后,3个模型的分类准确率均有提升。特别是基于CNN-GRU-Attention模型的多感官数据融合方法在本次研究中效果最优,其在测试集上的准确率分别达97.61%和90.48%。研究结果表明,采用多感知检测技术结合CNN-GRU-Attention预测模型能够有效地提高鱼肉新鲜度检测的准确性。

基于全局图推理与改进三维动态卷积的鱼类摄食行为分析

本研究提出一种基于时间动作检测的轻量化视频分类网络,旨在解决水产智能化养殖中饵料的投喂不均和水体污染等问题,提高投喂准确性和效率。该网络以ResNet 3D为基础,引入深度可分离卷积模块和三维动态卷积模块,以降低模型规模和参数量;同时采用图卷积全局推理模块和稠密卷积模块构建区域和全局关系,增强网络深层特征的表达,提高网络分类准确率。经试验验证,该模型检测准确率可达96.70%,相较变分自动编码器卷积网络和3D ResNet-GloRe网络,其准确率分别提高7.7个百分点和4.4个百分点;同时,该模型的参数量和计算量也明显降低,分别为1.10 M和3.87 G。研究结果表明,该基于时间动作检测的轻量化视频分类网络可以有效提高水产养殖中饵料的智能化投喂的准确性和效率,减少饵料投喂不均以及水体污染等问题,具有较高的应用价值。

面向虚拟人上肢的避障作业姿态规划算法

为了完成虚拟维修仿真环境下的虚拟人维修作业姿态规划问题,提出一种基于改进RRT-Connect算法的虚拟人上肢作业姿态求解方式。在该求解方式中,将人工鱼群算法(AFSA)的觅食行为法则作为导向性策略引入传统RRT-Connect算法,从而使得路径规划任务中初始点与目标点的扩展具有导向性;将路径点作为虚拟人上肢末端关节运动轨迹点。为获得虚拟人维修姿态,利用逆向运动学进行推导,以在每一个路径点中得到符合人体关节自由度的姿态集。另外,为了选择出姿态集中的最优路径,利用快速上肢评估法求取最优的虚拟人上肢维修作业姿态。最后,以无人艇虚拟维修操作仿真为例,验证了该方法在虚拟维修应用中的可行性。

非匀速条件下车辆底盘超近距成像测量方法

针对车辆非匀速条件下轴距视觉测量及轴型识别所面临的超近距、大幅面、低畸变成像及视觉测量问题,提出一种适用于非匀速条件下的车辆底盘结构超近距成像测量方法。利用鱼眼相机采集运动车辆底盘的超广角图像序列,通过一种改进的多采样点圆拟合方法实现图像感兴趣区域的提取。建立三维等距成像模型对鱼眼图像进行畸变校正。针对车辆非匀速行驶带来的视频帧重叠度差异,采用基于图像内容的重叠度分析技术,实现了多步分层的关键帧提取,有效避免了车速不稳定对车辆底盘结构测量的影响。现场实验结果表明:该方法可在非匀速条件下,以20~50 cm的成像距离获得清晰、低畸变的完整车辆底盘图像,车辆轴距测量误差均值约为5%。

基于优化TQWT及孪生SVM的有载分接开关机械故障诊断

为进一步提高有载分接开关(on-load tap changer,OLTC)机械状态监测的准确性,文中基于优化品质因数可调小波变换(tunable quality wavelet transform,TQWT)对OLTC切换过程中的振动信号进行了分析。即使用人工鱼群算法(artificial fish swarm algorithm,AFSA)基于分解余量与整体正交系数研究了TQWT的优化分解方法,计算得到了OLTC振动信号的多个子序列,构建了基于优化孪生支持向量机(twin support vector machine,TWSVM)的OLTC机械故障诊断模型。对某CM型OLTC正常与典型机械故障下振动信号的分析结果表明,所提优化TQWT分解方法有效提高了OLTC振动信号分解结果的准确性。相对于其他诊断模型,所构建AFSA-TWSVM的OLTC机械故障诊断模型分类效果好且收敛速度更快。

鱼类智能化加工技术研究应用现状与展望

随着全球对水产品需求的不断增长,水产品加工业正面临着提升效率、提高质量和实现绿色发展的重大挑战。鱼类智能化加工技术作为应对这些挑战的关键创新,融合了人工智能、机器学习、机器人技术、数据分析等前沿科技,为水产品加工行业带来了革命性的变革。本文综述了鱼类智能化加工技术的核心组成部分、当前应用情况以及未来发展方向,以期为行业内的科研和生产实践提供参考。首先,针对鱼类智能化加工的相关关键技术进行详细介绍,包括机器视觉、图像分析、机器人自动化、机器学习、深度学习以及大数据分析等,这些技术在提高加工效率、降低人力成本、提升产品质量稳定性方面发挥着至关重要的作用;其次,对鱼类智能化加工技术在实际应用中的多样化场景进行了探讨,如鱼类的自动分选和分级、宰杀和分割过程的自动化,以及智能包装系统的开发和应用等,这些应用不仅提高了生产效率,还增强了产品的市场竞争力;最后,展望了鱼类智能化加工技术的未来,强调了物联网、云计算、大数据分析和消费者个性化需求的重要性,这些趋势预示着水产品加工行业将朝着更智能、更自动化的方向发展。

不同诱鱼方式在黄登升鱼机鱼道的诱鱼效果比较研究

以澜沧裂腹鱼和光唇裂腹鱼为研究对象,通过在鱼道内安装黄色集鱼灯和饵料袋,鱼道进口处安装PIT监测设备,采用饵料诱鱼、灯光诱鱼和综合诱鱼(饵料+灯光)等3种诱鱼方式进行诱鱼,记录标记鱼类进入鱼道的时间、频次和数量,研究澜沧江云南流域黄登水电站的升鱼机系统鱼道的诱鱼方式。结果表明,使用饵料诱鱼触发PIT天线的频次最高;综合诱鱼方式标记鱼触发PIT设备5次以下共计12尾,高于其他诱鱼方式;综合诱鱼的总诱鱼效率最高,总诱鱼效率为60%,饵料诱鱼总诱鱼效率为50%,灯光诱鱼总诱鱼效率为35%。研究认为综合诱鱼方式适用于黄登升鱼机工程鱼道诱鱼措施。

基于贝叶斯优化轻量级梯度提升机模型预测淡水鱼中恩诺沙星抽检结果

目的建立基于贝叶斯优化轻量级梯度提升机(Bayesian optimization light gradient boosting machine,BO-LGBM)的预测模型,对上海市市售淡水鱼中恩诺沙星的抽检结果进行预测。方法基于2020—2023年上海市市售淡水鱼中恩诺沙星的抽检数据,以抽样地区、抽样月份、抽样环节、抽样场所、检测机构、淡水鱼品种6个特征为输入变量,以淡水鱼中恩诺沙星的抽检结果是否合格为输出变量,采用十折交叉验证法从7种机器学习算法中筛选出的最佳模型作为初始模型,逐步构建BO-LGBM模型及其与5种数据重采样方法结合的预测模型。结果上海市市售11114件淡水鱼中恩诺沙星的不合格率为4.7%。其中,泥鳅中恩诺沙星的不合格率最高(27.1%),其次为鳝鱼(24.6%)和鳊鱼(18.8%)。相比较其他模型,采用自适应合成抽样(adaptive synthetic sampling,ADASYN)与BO-LGBM结合模型对测试集样品抽检结果预测的准确率(0.83)、召回率(0.86)、F1值(0.82)和AUC值(0.84)均为最高。结论ADASYN-BO-LGBM模型的预测性能好,能够较为准确地预测淡水鱼中恩诺沙星抽检结果,为基于问题导向的淡水鱼监督抽检方案制定及风险预警提供技术支撑。

基于改进支持向量机的公共建筑碳排放量估计研究

目前,进行公共建筑碳排放量估计时,存在估计精度低和模型稳定性差的问题,对此,提出基于改进支持向量机的公共建筑碳排放量估计研究方法。首先,分析公共建筑碳排放量的影响因素,并对采集到的公共建筑碳排放数据展开预处理;然后,建立支持向量机模型,并基于人工鱼群算法对支持向量机参数进行优化。最后将优化后的正则化参数和宽度参数代入支持向量机中,得到公共建筑碳排放量。实验结果表明,所提方法的PCC系数最高达到0.81,MAE最低值为0.08,MAPE最低值为19%,由此可见所提方法可精准的完成碳排放量估计,同时具有较高的稳定性。

基于机器视觉的工厂化鱼类养殖投料控制系统研制

为了实现工厂化循环水养殖中的鱼群数量估算和投料自动控制,以加州鲈鱼为研究对象,基于YOLOv8构建了一种鱼群数量估算模型,并结合投料设备研制了一套鱼类养殖投料控制系统。该系统首先通过DCP算子增强鱼群图像边界;然后使用YOLOv8深度学习模型识别鱼体轮廓并对鱼群数量进行分级,结合养殖户经验为各数量等级鱼群设定相应饲料投放量;最终系统通过PLC控制投料机投放给定重量饲料,实现饲料投喂的全自动化管理。测试证实:该系统能够实时估算鱼群数量,控制投料机完成饲料投放量合理的自动投喂工作。

基于多源异构数据融合分析技术的激光通信网络钓鱼检测

网络钓鱼对激光通信网络的应用带来较大危险,为保障激光通信网络应用安全,提出基于多源异构数据融合分析技术的激光通信网络钓鱼检测方法。首先采集激光通信网络钓鱼特征,采用D-S证据理论融合不同来源、不同结构的激光通信网络钓鱼特征数据,然后根据特下数,采用支持向量机检测设计激光通信网络钓鱼检测模型,最后进行了仿真实验,结果表明,该方法可有效提取并准确融合钓鱼特征数据,激光通信网络钓鱼检测激光通信网络钓鱼检测准确率超过95%,降低激光通信网络安全风险。