Developing a breast cancer screening method is very important to facilitate early breast cancer detection and treatment. Building a screening method using medical imaging modality that does not cause body tissue damage (non-invasive) and does not involve physical touch is challenging. Thermography, a non-invasive and non-contact cancer screening method, can detect tumors at an early stage even under precancerous conditions by observing temperature distribution in both breasts. The thermograms obtained on thermography can be interpreted using deep learning models such as convolutional neural networks (CNNs). CNNs can automatically classify breast thermograms into categories such as normal and abnormal. Despite their demostrated utility, CNNs have not been widely used in breast thermogram classification. In this study, we aimed to summarize the current work and progress in breast cancer detection based on thermography and CNNs. We first discuss of breast thermography potential in early breast cancer detection, providing an overview of the availability of breast thermal datasets together with publicly accessible. We also discuss characteristics of breast thermograms and the differences between healthy and cancerous thermographic patterns. Breast thermogram classification using a CNN model is described step by step including a simulation example illustrating feature learning. We cover most research related to the implementation of deep neural networks for breast thermogram classification and propose future research directions for developing representative datasets, feeding the segmented image, assigning a good kernel, and building a lightweight CNN model to improve CNN performance. INDEX TERMS breast cancer; convolutional neural network; deep learning; early detection; thermogram

No abstract

Clamshells are the waste of clams which are usually consumed by people. Clamshells contain 66.70% of CaO, the chemical compounds that have pozzolanic properties, which can be used as a substitute for cement. The purpose of this study was to determine the effect of the addition of clamshell ash to the index value of soil properties, soil classification, soil plastic properties, free compressive strength value, and CBR value. The test was carried out with Unconfined Compression Test (UCT) and California Bearing Ratio (CBR). The result showed that according to AASHTO this soil was classified as A-7-6 (9) and according to USCS it was classified as CL (Clay - Low Plasticity). The original soil sample had a moisture content of 34.43%; specific weight of 2.65%; liquid limit of 47.33%; plastic limit of 17.45%; and plasticity index of 29.88%. The values of unsoaked design CBR and UCT for the original soil were 6.29% and 1,42 kg/cm2. Meanwhile, among all the variations, the mixture of 12% clamshell ash reached the optimum value of soaked design California Bearing Ratio and free compressive strength in Unconfined Compression Test which were 8.13% and 2.39 kg/cm2.

Sistem kendali attitude hold pada multirotor adalah sebuah sistem kendali penjaga sikap untuk mempertahankan sikap stabil saat terbang. Sistem attitude hold pada penelitian ini diaplikasikan dalam bentuk seesaw atau pengungkit yang merupakan salah satu bentuk pesawat sederhana dari lengan kuasa. Penelitian ini merupakan sistem kendali penjaga sikap pada seesaw diatur di 1 derajat kebebasan (DOF) yang ditetapkan sebagai setpoint pada kemiringan 0°. Kestabilan pada seesaw dikendalikan dengan metode kendali PID, yang merupakan sistem pengendali yang berfungsi untuk mencari nilai kestabilan sehingga respon sistem yang diperoleh dapat mencapai setpoint dengan baik. Maka dari itu diperlukan sistem penyeimbang yang dapat membaca sudut kemiringan pada lengan seesaw. Pembacaan sudut tersebut menjadi acuan kecepatan putaran baling-baling motor brushless dc (BLDC). Sensor yang digunakan adalah gyroscope. Sensor tersebut terdapat dalam modul IMU MPU-6050. Baling-baling menggunakan akuator berupa dua motor BLDC 920 kv kontroler berupa Electronic Speed Control (ESC). Setpoint ditentukan pada kemiringan 0° terhadap gaya gerak 1 DOF lengan. Motor BLDC kanan dan kiri melakukan variasi kecepatan putaran ketika pembacaan sudut tidak sama dengan setpoint. Motor BLDC kiri akan melakukan putaran CW dan motor BLDC kanan melakukan putaran CCW untuk membuat gaya angkat sehingga mencapai kestabilan. Pengaruh besarnya variasi kecepatan baling-baling yang diberikan yaitu berdasarkan besarnya nilai eror yang terjadi antara setpoint dengan input. Penelitian ini telah menghasilkan prototipe alat yang dapat bekerja pada kemiringan -30 derajat hingga 30 derajat dengan setpoint stabil pada 0 derajat. Dari perhitungan penalaan konstanta PID Ziegler-Nichols kurva reaksi didapat nilai Kp = 2,94, Ki = 1,2 dan Kd = 0,33. Dari hasil nilai penalaan tersebut didapatkan hasil stabil sesuai terhadap setpoint dengan hasil pengujian PID dengan nilai rise time= 18 detik, setling time= 7,5 detik, overshoot= 3,1%, peak time= 18 detik.

Finite element (FE) techniques are used to analyse mechanical stress in optical fibre sensors embedded in acrylic. The models represent many features observed in real materials with embedded fibre optic for stress and strain sensor application such as for health monitoring of structures. Three thicknesses, namely 6 mm, 8 mm and 10 mm of acrylic were analyzed with the optical fibre embedded at the mid-plane of acrylic. The simulation was done by implementing Finite Element Method using ABAQUS software. Contact between acrylic and optical fibre was modelled as frictionless and with friction. The friction coefficient was varied for various values which are 0.3, and 0.5. This paper investigates the effect of friction coefficient and the effect of fibre optic’s depth embedded in acrylic to the their von Misses stress. Simulation result shows that the higher the friction coefficient the higher von Misses stress in fibre optic and the higher von Misses stress in acrylic. The higher the fibre’s depth the higher von Misses stress in fibre and the lower von Misses stress in acrylic. The maximum stress occurred for the coefficient of friction 0.5, with magnitude of 116.4 MPa and 58.72 MPa for acrylic and optical fibre respectively. The most significant effect of fibre’s depth to the von Misses stress was obtained for 1 mm depth for acrylic and 5 mm for optical fibre, with magnitude of 72.64 MPa and 57.65 MPa for acrylic and optical fibre respectively.